diff options
Diffstat (limited to 'arch/x86/mm')
27 files changed, 1236 insertions, 303 deletions
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 8e13b8cc6bed..27e9e90a8d35 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -10,7 +10,7 @@ CFLAGS_REMOVE_mem_encrypt.o = -pg endif obj-y := init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \ - pat.o pgtable.o physaddr.o setup_nx.o tlb.o + pat.o pgtable.o physaddr.o setup_nx.o tlb.o cpu_entry_area.o # Make sure __phys_addr has no stackprotector nostackp := $(call cc-option, -fno-stack-protector) @@ -41,9 +41,10 @@ obj-$(CONFIG_AMD_NUMA) += amdtopology.o obj-$(CONFIG_ACPI_NUMA) += srat.o obj-$(CONFIG_NUMA_EMU) += numa_emulation.o -obj-$(CONFIG_X86_INTEL_MPX) += mpx.o -obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o -obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o +obj-$(CONFIG_X86_INTEL_MPX) += mpx.o +obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o +obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o +obj-$(CONFIG_PAGE_TABLE_ISOLATION) += pti.o obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt.o obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_boot.o diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c new file mode 100644 index 000000000000..b9283cc27622 --- /dev/null +++ b/arch/x86/mm/cpu_entry_area.c @@ -0,0 +1,166 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/spinlock.h> +#include <linux/percpu.h> + +#include <asm/cpu_entry_area.h> +#include <asm/pgtable.h> +#include <asm/fixmap.h> +#include <asm/desc.h> + +static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage); + +#ifdef CONFIG_X86_64 +static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks + [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); +#endif + +struct cpu_entry_area *get_cpu_entry_area(int cpu) +{ + unsigned long va = CPU_ENTRY_AREA_PER_CPU + cpu * CPU_ENTRY_AREA_SIZE; + BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0); + + return (struct cpu_entry_area *) va; +} +EXPORT_SYMBOL(get_cpu_entry_area); + +void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags) +{ + unsigned long va = (unsigned long) cea_vaddr; + + set_pte_vaddr(va, pfn_pte(pa >> PAGE_SHIFT, flags)); +} + +static void __init +cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot) +{ + for ( ; pages; pages--, cea_vaddr+= PAGE_SIZE, ptr += PAGE_SIZE) + cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot); +} + +static void percpu_setup_debug_store(int cpu) +{ +#ifdef CONFIG_CPU_SUP_INTEL + int npages; + void *cea; + + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return; + + cea = &get_cpu_entry_area(cpu)->cpu_debug_store; + npages = sizeof(struct debug_store) / PAGE_SIZE; + BUILD_BUG_ON(sizeof(struct debug_store) % PAGE_SIZE != 0); + cea_map_percpu_pages(cea, &per_cpu(cpu_debug_store, cpu), npages, + PAGE_KERNEL); + + cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers; + /* + * Force the population of PMDs for not yet allocated per cpu + * memory like debug store buffers. + */ + npages = sizeof(struct debug_store_buffers) / PAGE_SIZE; + for (; npages; npages--, cea += PAGE_SIZE) + cea_set_pte(cea, 0, PAGE_NONE); +#endif +} + +/* Setup the fixmap mappings only once per-processor */ +static void __init setup_cpu_entry_area(int cpu) +{ +#ifdef CONFIG_X86_64 + extern char _entry_trampoline[]; + + /* On 64-bit systems, we use a read-only fixmap GDT and TSS. */ + pgprot_t gdt_prot = PAGE_KERNEL_RO; + pgprot_t tss_prot = PAGE_KERNEL_RO; +#else + /* + * On native 32-bit systems, the GDT cannot be read-only because + * our double fault handler uses a task gate, and entering through + * a task gate needs to change an available TSS to busy. If the + * GDT is read-only, that will triple fault. The TSS cannot be + * read-only because the CPU writes to it on task switches. + * + * On Xen PV, the GDT must be read-only because the hypervisor + * requires it. + */ + pgprot_t gdt_prot = boot_cpu_has(X86_FEATURE_XENPV) ? + PAGE_KERNEL_RO : PAGE_KERNEL; + pgprot_t tss_prot = PAGE_KERNEL; +#endif + + cea_set_pte(&get_cpu_entry_area(cpu)->gdt, get_cpu_gdt_paddr(cpu), + gdt_prot); + + cea_map_percpu_pages(&get_cpu_entry_area(cpu)->entry_stack_page, + per_cpu_ptr(&entry_stack_storage, cpu), 1, + PAGE_KERNEL); + + /* + * The Intel SDM says (Volume 3, 7.2.1): + * + * Avoid placing a page boundary in the part of the TSS that the + * processor reads during a task switch (the first 104 bytes). The + * processor may not correctly perform address translations if a + * boundary occurs in this area. During a task switch, the processor + * reads and writes into the first 104 bytes of each TSS (using + * contiguous physical addresses beginning with the physical address + * of the first byte of the TSS). So, after TSS access begins, if + * part of the 104 bytes is not physically contiguous, the processor + * will access incorrect information without generating a page-fault + * exception. + * + * There are also a lot of errata involving the TSS spanning a page + * boundary. Assert that we're not doing that. + */ + BUILD_BUG_ON((offsetof(struct tss_struct, x86_tss) ^ + offsetofend(struct tss_struct, x86_tss)) & PAGE_MASK); + BUILD_BUG_ON(sizeof(struct tss_struct) % PAGE_SIZE != 0); + cea_map_percpu_pages(&get_cpu_entry_area(cpu)->tss, + &per_cpu(cpu_tss_rw, cpu), + sizeof(struct tss_struct) / PAGE_SIZE, tss_prot); + +#ifdef CONFIG_X86_32 + per_cpu(cpu_entry_area, cpu) = get_cpu_entry_area(cpu); +#endif + +#ifdef CONFIG_X86_64 + BUILD_BUG_ON(sizeof(exception_stacks) % PAGE_SIZE != 0); + BUILD_BUG_ON(sizeof(exception_stacks) != + sizeof(((struct cpu_entry_area *)0)->exception_stacks)); + cea_map_percpu_pages(&get_cpu_entry_area(cpu)->exception_stacks, + &per_cpu(exception_stacks, cpu), + sizeof(exception_stacks) / PAGE_SIZE, PAGE_KERNEL); + + cea_set_pte(&get_cpu_entry_area(cpu)->entry_trampoline, + __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX); +#endif + percpu_setup_debug_store(cpu); +} + +static __init void setup_cpu_entry_area_ptes(void) +{ +#ifdef CONFIG_X86_32 + unsigned long start, end; + + BUILD_BUG_ON(CPU_ENTRY_AREA_PAGES * PAGE_SIZE < CPU_ENTRY_AREA_MAP_SIZE); + BUG_ON(CPU_ENTRY_AREA_BASE & ~PMD_MASK); + + start = CPU_ENTRY_AREA_BASE; + end = start + CPU_ENTRY_AREA_MAP_SIZE; + + /* Careful here: start + PMD_SIZE might wrap around */ + for (; start < end && start >= CPU_ENTRY_AREA_BASE; start += PMD_SIZE) + populate_extra_pte(start); +#endif +} + +void __init setup_cpu_entry_areas(void) +{ + unsigned int cpu; + + setup_cpu_entry_area_ptes(); + + for_each_possible_cpu(cpu) + setup_cpu_entry_area(cpu); +} diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c index bfcffdf6c577..421f2664ffa0 100644 --- a/arch/x86/mm/debug_pagetables.c +++ b/arch/x86/mm/debug_pagetables.c @@ -5,7 +5,7 @@ static int ptdump_show(struct seq_file *m, void *v) { - ptdump_walk_pgd_level(m, NULL); + ptdump_walk_pgd_level_debugfs(m, NULL, false); return 0; } @@ -22,21 +22,89 @@ static const struct file_operations ptdump_fops = { .release = single_release, }; -static struct dentry *pe; +static int ptdump_show_curknl(struct seq_file *m, void *v) +{ + if (current->mm->pgd) { + down_read(¤t->mm->mmap_sem); + ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, false); + up_read(¤t->mm->mmap_sem); + } + return 0; +} + +static int ptdump_open_curknl(struct inode *inode, struct file *filp) +{ + return single_open(filp, ptdump_show_curknl, NULL); +} + +static const struct file_operations ptdump_curknl_fops = { + .owner = THIS_MODULE, + .open = ptdump_open_curknl, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +#ifdef CONFIG_PAGE_TABLE_ISOLATION +static struct dentry *pe_curusr; + +static int ptdump_show_curusr(struct seq_file *m, void *v) +{ + if (current->mm->pgd) { + down_read(¤t->mm->mmap_sem); + ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, true); + up_read(¤t->mm->mmap_sem); + } + return 0; +} + +static int ptdump_open_curusr(struct inode *inode, struct file *filp) +{ + return single_open(filp, ptdump_show_curusr, NULL); +} + +static const struct file_operations ptdump_curusr_fops = { + .owner = THIS_MODULE, + .open = ptdump_open_curusr, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; +#endif + +static struct dentry *dir, *pe_knl, *pe_curknl; static int __init pt_dump_debug_init(void) { - pe = debugfs_create_file("kernel_page_tables", S_IRUSR, NULL, NULL, - &ptdump_fops); - if (!pe) + dir = debugfs_create_dir("page_tables", NULL); + if (!dir) return -ENOMEM; + pe_knl = debugfs_create_file("kernel", 0400, dir, NULL, + &ptdump_fops); + if (!pe_knl) + goto err; + + pe_curknl = debugfs_create_file("current_kernel", 0400, + dir, NULL, &ptdump_curknl_fops); + if (!pe_curknl) + goto err; + +#ifdef CONFIG_PAGE_TABLE_ISOLATION + pe_curusr = debugfs_create_file("current_user", 0400, + dir, NULL, &ptdump_curusr_fops); + if (!pe_curusr) + goto err; +#endif return 0; +err: + debugfs_remove_recursive(dir); + return -ENOMEM; } static void __exit pt_dump_debug_exit(void) { - debugfs_remove_recursive(pe); + debugfs_remove_recursive(dir); } module_init(pt_dump_debug_init); diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index 5e3ac6fe6c9e..2a4849e92831 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -44,68 +44,97 @@ struct addr_marker { unsigned long max_lines; }; -/* indices for address_markers; keep sync'd w/ address_markers below */ +/* Address space markers hints */ + +#ifdef CONFIG_X86_64 + enum address_markers_idx { USER_SPACE_NR = 0, -#ifdef CONFIG_X86_64 KERNEL_SPACE_NR, LOW_KERNEL_NR, +#if defined(CONFIG_MODIFY_LDT_SYSCALL) && defined(CONFIG_X86_5LEVEL) + LDT_NR, +#endif VMALLOC_START_NR, VMEMMAP_START_NR, #ifdef CONFIG_KASAN KASAN_SHADOW_START_NR, KASAN_SHADOW_END_NR, #endif -# ifdef CONFIG_X86_ESPFIX64 + CPU_ENTRY_AREA_NR, +#if defined(CONFIG_MODIFY_LDT_SYSCALL) && !defined(CONFIG_X86_5LEVEL) + LDT_NR, +#endif +#ifdef CONFIG_X86_ESPFIX64 ESPFIX_START_NR, -# endif +#endif +#ifdef CONFIG_EFI + EFI_END_NR, +#endif HIGH_KERNEL_NR, MODULES_VADDR_NR, MODULES_END_NR, -#else + FIXADDR_START_NR, + END_OF_SPACE_NR, +}; + +static struct addr_marker address_markers[] = { + [USER_SPACE_NR] = { 0, "User Space" }, + [KERNEL_SPACE_NR] = { (1UL << 63), "Kernel Space" }, + [LOW_KERNEL_NR] = { 0UL, "Low Kernel Mapping" }, + [VMALLOC_START_NR] = { 0UL, "vmalloc() Area" }, + [VMEMMAP_START_NR] = { 0UL, "Vmemmap" }, +#ifdef CONFIG_KASAN + [KASAN_SHADOW_START_NR] = { KASAN_SHADOW_START, "KASAN shadow" }, + [KASAN_SHADOW_END_NR] = { KASAN_SHADOW_END, "KASAN shadow end" }, +#endif +#ifdef CONFIG_MODIFY_LDT_SYSCALL + [LDT_NR] = { LDT_BASE_ADDR, "LDT remap" }, +#endif + [CPU_ENTRY_AREA_NR] = { CPU_ENTRY_AREA_BASE,"CPU entry Area" }, +#ifdef CONFIG_X86_ESPFIX64 + [ESPFIX_START_NR] = { ESPFIX_BASE_ADDR, "ESPfix Area", 16 }, +#endif +#ifdef CONFIG_EFI + [EFI_END_NR] = { EFI_VA_END, "EFI Runtime Services" }, +#endif + [HIGH_KERNEL_NR] = { __START_KERNEL_map, "High Kernel Mapping" }, + [MODULES_VADDR_NR] = { MODULES_VADDR, "Modules" }, + [MODULES_END_NR] = { MODULES_END, "End Modules" }, + [FIXADDR_START_NR] = { FIXADDR_START, "Fixmap Area" }, + [END_OF_SPACE_NR] = { -1, NULL } +}; + +#else /* CONFIG_X86_64 */ + +enum address_markers_idx { + USER_SPACE_NR = 0, KERNEL_SPACE_NR, VMALLOC_START_NR, VMALLOC_END_NR, -# ifdef CONFIG_HIGHMEM +#ifdef CONFIG_HIGHMEM PKMAP_BASE_NR, -# endif - FIXADDR_START_NR, #endif + CPU_ENTRY_AREA_NR, + FIXADDR_START_NR, + END_OF_SPACE_NR, }; -/* Address space markers hints */ static struct addr_marker address_markers[] = { - { 0, "User Space" }, -#ifdef CONFIG_X86_64 - { 0x8000000000000000UL, "Kernel Space" }, - { 0/* PAGE_OFFSET */, "Low Kernel Mapping" }, - { 0/* VMALLOC_START */, "vmalloc() Area" }, - { 0/* VMEMMAP_START */, "Vmemmap" }, -#ifdef CONFIG_KASAN - { KASAN_SHADOW_START, "KASAN shadow" }, - { KASAN_SHADOW_END, "KASAN shadow end" }, + [USER_SPACE_NR] = { 0, "User Space" }, + [KERNEL_SPACE_NR] = { PAGE_OFFSET, "Kernel Mapping" }, + [VMALLOC_START_NR] = { 0UL, "vmalloc() Area" }, + [VMALLOC_END_NR] = { 0UL, "vmalloc() End" }, +#ifdef CONFIG_HIGHMEM + [PKMAP_BASE_NR] = { 0UL, "Persistent kmap() Area" }, #endif -# ifdef CONFIG_X86_ESPFIX64 - { ESPFIX_BASE_ADDR, "ESPfix Area", 16 }, -# endif -# ifdef CONFIG_EFI - { EFI_VA_END, "EFI Runtime Services" }, -# endif - { __START_KERNEL_map, "High Kernel Mapping" }, - { MODULES_VADDR, "Modules" }, - { MODULES_END, "End Modules" }, -#else - { PAGE_OFFSET, "Kernel Mapping" }, - { 0/* VMALLOC_START */, "vmalloc() Area" }, - { 0/*VMALLOC_END*/, "vmalloc() End" }, -# ifdef CONFIG_HIGHMEM - { 0/*PKMAP_BASE*/, "Persistent kmap() Area" }, -# endif - { 0/*FIXADDR_START*/, "Fixmap Area" }, -#endif - { -1, NULL } /* End of list */ + [CPU_ENTRY_AREA_NR] = { 0UL, "CPU entry area" }, + [FIXADDR_START_NR] = { 0UL, "Fixmap area" }, + [END_OF_SPACE_NR] = { -1, NULL } }; +#endif /* !CONFIG_X86_64 */ + /* Multipliers for offsets within the PTEs */ #define PTE_LEVEL_MULT (PAGE_SIZE) #define PMD_LEVEL_MULT (PTRS_PER_PTE * PTE_LEVEL_MULT) @@ -140,7 +169,7 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg) static const char * const level_name[] = { "cr3", "pgd", "p4d", "pud", "pmd", "pte" }; - if (!pgprot_val(prot)) { + if (!(pr & _PAGE_PRESENT)) { /* Not present */ pt_dump_cont_printf(m, dmsg, " "); } else { @@ -447,7 +476,7 @@ static inline bool is_hypervisor_range(int idx) } static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, - bool checkwx) + bool checkwx, bool dmesg) { #ifdef CONFIG_X86_64 pgd_t *start = (pgd_t *) &init_top_pgt; @@ -460,7 +489,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, if (pgd) { start = pgd; - st.to_dmesg = true; + st.to_dmesg = dmesg; } st.check_wx = checkwx; @@ -498,13 +527,37 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd, void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd) { - ptdump_walk_pgd_level_core(m, pgd, false); + ptdump_walk_pgd_level_core(m, pgd, false, true); +} + +void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user) +{ +#ifdef CONFIG_PAGE_TABLE_ISOLATION + if (user && static_cpu_has(X86_FEATURE_PTI)) + pgd = kernel_to_user_pgdp(pgd); +#endif + ptdump_walk_pgd_level_core(m, pgd, false, false); +} +EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs); + +static void ptdump_walk_user_pgd_level_checkwx(void) +{ +#ifdef CONFIG_PAGE_TABLE_ISOLATION + pgd_t *pgd = (pgd_t *) &init_top_pgt; + + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + + pr_info("x86/mm: Checking user space page tables\n"); + pgd = kernel_to_user_pgdp(pgd); + ptdump_walk_pgd_level_core(NULL, pgd, true, false); +#endif } -EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level); void ptdump_walk_pgd_level_checkwx(void) { - ptdump_walk_pgd_level_core(NULL, NULL, true); + ptdump_walk_pgd_level_core(NULL, NULL, true, false); + ptdump_walk_user_pgd_level_checkwx(); } static int __init pt_dump_init(void) @@ -525,8 +578,8 @@ static int __init pt_dump_init(void) address_markers[PKMAP_BASE_NR].start_address = PKMAP_BASE; # endif address_markers[FIXADDR_START_NR].start_address = FIXADDR_START; + address_markers[CPU_ENTRY_AREA_NR].start_address = CPU_ENTRY_AREA_BASE; #endif - return 0; } __initcall(pt_dump_init); diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 3321b446b66c..9fe656c42aa5 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -1,6 +1,7 @@ #include <linux/extable.h> #include <linux/uaccess.h> #include <linux/sched/debug.h> +#include <xen/xen.h> #include <asm/fpu/internal.h> #include <asm/traps.h> @@ -82,7 +83,7 @@ bool ex_handler_refcount(const struct exception_table_entry *fixup, return true; } -EXPORT_SYMBOL_GPL(ex_handler_refcount); +EXPORT_SYMBOL(ex_handler_refcount); /* * Handler for when we fail to restore a task's FPU state. We should never get @@ -212,8 +213,9 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr) * Old CPUs leave the high bits of CS on the stack * undefined. I'm not sure which CPUs do this, but at least * the 486 DX works this way. + * Xen pv domains are not using the default __KERNEL_CS. */ - if (regs->cs != __KERNEL_CS) + if (!xen_pv_domain() && regs->cs != __KERNEL_CS) goto fail; /* diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 78ca9a8ee454..800de815519c 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -172,14 +172,15 @@ is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr) * 6. T1 : reaches here, sees vma_pkey(vma)=5, when we really * faulted on a pte with its pkey=4. */ -static void fill_sig_info_pkey(int si_code, siginfo_t *info, u32 *pkey) +static void fill_sig_info_pkey(int si_signo, int si_code, siginfo_t *info, + u32 *pkey) { /* This is effectively an #ifdef */ if (!boot_cpu_has(X86_FEATURE_OSPKE)) return; /* Fault not from Protection Keys: nothing to do */ - if (si_code != SEGV_PKUERR) + if ((si_code != SEGV_PKUERR) || (si_signo != SIGSEGV)) return; /* * force_sig_info_fault() is called from a number of @@ -218,7 +219,7 @@ force_sig_info_fault(int si_signo, int si_code, unsigned long address, lsb = PAGE_SHIFT; info.si_addr_lsb = lsb; - fill_sig_info_pkey(si_code, &info, pkey); + fill_sig_info_pkey(si_signo, si_code, &info, pkey); force_sig_info(si_signo, &info, tsk); } @@ -438,18 +439,13 @@ static noinline int vmalloc_fault(unsigned long address) if (pgd_none(*pgd_ref)) return -1; - if (pgd_none(*pgd)) { - set_pgd(pgd, *pgd_ref); - arch_flush_lazy_mmu_mode(); - } else if (CONFIG_PGTABLE_LEVELS > 4) { - /* - * With folded p4d, pgd_none() is always false, so the pgd may - * point to an empty page table entry and pgd_page_vaddr() - * will return garbage. - * - * We will do the correct sanity check on the p4d level. - */ - BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); + if (CONFIG_PGTABLE_LEVELS > 4) { + if (pgd_none(*pgd)) { + set_pgd(pgd, *pgd_ref); + arch_flush_lazy_mmu_mode(); + } else { + BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref)); + } } /* With 4-level paging, copying happens on the p4d level. */ @@ -458,7 +454,7 @@ static noinline int vmalloc_fault(unsigned long address) if (p4d_none(*p4d_ref)) return -1; - if (p4d_none(*p4d)) { + if (p4d_none(*p4d) && CONFIG_PGTABLE_LEVELS == 4) { set_p4d(p4d, *p4d_ref); arch_flush_lazy_mmu_mode(); } else { @@ -469,6 +465,7 @@ static noinline int vmalloc_fault(unsigned long address) * Below here mismatches are bugs because these lower tables * are shared: */ + BUILD_BUG_ON(CONFIG_PGTABLE_LEVELS < 4); pud = pud_offset(p4d, address); pud_ref = pud_offset(p4d_ref, address); @@ -701,7 +698,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, else printk(KERN_CONT "paging request"); - printk(KERN_CONT " at %p\n", (void *) address); + printk(KERN_CONT " at %px\n", (void *) address); printk(KERN_ALERT "IP: %pS\n", (void *)regs->ip); dump_pagetable(address); @@ -860,7 +857,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, if (!printk_ratelimit()) return; - printk("%s%s[%d]: segfault at %lx ip %p sp %p error %lx", + printk("%s%s[%d]: segfault at %lx ip %px sp %px error %lx", task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, task_pid_nr(tsk), address, (void *)regs->ip, (void *)regs->sp, error_code); diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 6fdf91ef130a..82f5252c723a 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -20,6 +20,7 @@ #include <asm/kaslr.h> #include <asm/hypervisor.h> #include <asm/cpufeature.h> +#include <asm/pti.h> /* * We need to define the tracepoints somewhere, and tlb.c @@ -160,6 +161,12 @@ struct map_range { static int page_size_mask; +static void enable_global_pages(void) +{ + if (!static_cpu_has(X86_FEATURE_PTI)) + __supported_pte_mask |= _PAGE_GLOBAL; +} + static void __init probe_page_size_mask(void) { /* @@ -177,11 +184,11 @@ static void __init probe_page_size_mask(void) cr4_set_bits_and_update_boot(X86_CR4_PSE); /* Enable PGE if available */ + __supported_pte_mask &= ~_PAGE_GLOBAL; if (boot_cpu_has(X86_FEATURE_PGE)) { cr4_set_bits_and_update_boot(X86_CR4_PGE); - __supported_pte_mask |= _PAGE_GLOBAL; - } else - __supported_pte_mask &= ~_PAGE_GLOBAL; + enable_global_pages(); + } /* Enable 1 GB linear kernel mappings if available: */ if (direct_gbpages && boot_cpu_has(X86_FEATURE_GBPAGES)) { @@ -194,34 +201,44 @@ static void __init probe_page_size_mask(void) static void setup_pcid(void) { -#ifdef CONFIG_X86_64 - if (boot_cpu_has(X86_FEATURE_PCID)) { - if (boot_cpu_has(X86_FEATURE_PGE)) { - /* - * This can't be cr4_set_bits_and_update_boot() -- - * the trampoline code can't handle CR4.PCIDE and - * it wouldn't do any good anyway. Despite the name, - * cr4_set_bits_and_update_boot() doesn't actually - * cause the bits in question to remain set all the - * way through the secondary boot asm. - * - * Instead, we brute-force it and set CR4.PCIDE - * manually in start_secondary(). - */ - cr4_set_bits(X86_CR4_PCIDE); - } else { - /* - * flush_tlb_all(), as currently implemented, won't - * work if PCID is on but PGE is not. Since that - * combination doesn't exist on real hardware, there's - * no reason to try to fully support it, but it's - * polite to avoid corrupting data if we're on - * an improperly configured VM. - */ - setup_clear_cpu_cap(X86_FEATURE_PCID); - } + if (!IS_ENABLED(CONFIG_X86_64)) + return; + + if (!boot_cpu_has(X86_FEATURE_PCID)) + return; + + if (boot_cpu_has(X86_FEATURE_PGE)) { + /* + * This can't be cr4_set_bits_and_update_boot() -- the + * trampoline code can't handle CR4.PCIDE and it wouldn't + * do any good anyway. Despite the name, + * cr4_set_bits_and_update_boot() doesn't actually cause + * the bits in question to remain set all the way through + * the secondary boot asm. + * + * Instead, we brute-force it and set CR4.PCIDE manually in + * start_secondary(). + */ + cr4_set_bits(X86_CR4_PCIDE); + + /* + * INVPCID's single-context modes (2/3) only work if we set + * X86_CR4_PCIDE, *and* we INVPCID support. It's unusable + * on systems that have X86_CR4_PCIDE clear, or that have + * no INVPCID support at all. + */ + if (boot_cpu_has(X86_FEATURE_INVPCID)) + setup_force_cpu_cap(X86_FEATURE_INVPCID_SINGLE); + } else { + /* + * flush_tlb_all(), as currently implemented, won't work if + * PCID is on but PGE is not. Since that combination + * doesn't exist on real hardware, there's no reason to try + * to fully support it, but it's polite to avoid corrupting + * data if we're on an improperly configured VM. + */ + setup_clear_cpu_cap(X86_FEATURE_PCID); } -#endif } #ifdef CONFIG_X86_32 @@ -622,6 +639,7 @@ void __init init_mem_mapping(void) { unsigned long end; + pti_check_boottime_disable(); probe_page_size_mask(); setup_pcid(); @@ -845,12 +863,12 @@ void __init zone_sizes_init(void) free_area_init_nodes(max_zone_pfns); } -DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = { +__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = { .loaded_mm = &init_mm, .next_asid = 1, .cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */ }; -EXPORT_SYMBOL_GPL(cpu_tlbstate); +EXPORT_PER_CPU_SYMBOL(cpu_tlbstate); void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache) { diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 8a64a6f2848d..135c9a7898c7 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -50,6 +50,7 @@ #include <asm/setup.h> #include <asm/set_memory.h> #include <asm/page_types.h> +#include <asm/cpu_entry_area.h> #include <asm/init.h> #include "mm_internal.h" @@ -766,6 +767,7 @@ void __init mem_init(void) mem_init_print_info(NULL); printk(KERN_INFO "virtual kernel memory layout:\n" " fixmap : 0x%08lx - 0x%08lx (%4ld kB)\n" + " cpu_entry : 0x%08lx - 0x%08lx (%4ld kB)\n" #ifdef CONFIG_HIGHMEM " pkmap : 0x%08lx - 0x%08lx (%4ld kB)\n" #endif @@ -777,6 +779,10 @@ void __init mem_init(void) FIXADDR_START, FIXADDR_TOP, (FIXADDR_TOP - FIXADDR_START) >> 10, + CPU_ENTRY_AREA_BASE, + CPU_ENTRY_AREA_BASE + CPU_ENTRY_AREA_MAP_SIZE, + CPU_ENTRY_AREA_MAP_SIZE >> 10, + #ifdef CONFIG_HIGHMEM PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE, (LAST_PKMAP*PAGE_SIZE) >> 10, diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 6e4573b1da34..c45b6ec5357b 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -404,11 +404,11 @@ void iounmap(volatile void __iomem *addr) return; } + mmiotrace_iounmap(addr); + addr = (volatile void __iomem *) (PAGE_MASK & (unsigned long __force)addr); - mmiotrace_iounmap(addr); - /* Use the vm area unlocked, assuming the caller ensures there isn't another iounmap for the same address in parallel. Reuse of the virtual address is prevented by diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 99dfed6dfef8..af6f2f9c6a26 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -15,15 +15,20 @@ #include <asm/tlbflush.h> #include <asm/sections.h> #include <asm/pgtable.h> +#include <asm/cpu_entry_area.h> extern struct range pfn_mapped[E820_MAX_ENTRIES]; static p4d_t tmp_p4d_table[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE); -static __init void *early_alloc(size_t size, int nid) +static __init void *early_alloc(size_t size, int nid, bool panic) { - return memblock_virt_alloc_try_nid_nopanic(size, size, - __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); + if (panic) + return memblock_virt_alloc_try_nid(size, size, + __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); + else + return memblock_virt_alloc_try_nid_nopanic(size, size, + __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); } static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, @@ -37,14 +42,14 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, if (boot_cpu_has(X86_FEATURE_PSE) && ((end - addr) == PMD_SIZE) && IS_ALIGNED(addr, PMD_SIZE)) { - p = early_alloc(PMD_SIZE, nid); + p = early_alloc(PMD_SIZE, nid, false); if (p && pmd_set_huge(pmd, __pa(p), PAGE_KERNEL)) return; else if (p) memblock_free(__pa(p), PMD_SIZE); } - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); pmd_populate_kernel(&init_mm, pmd, p); } @@ -56,7 +61,7 @@ static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, if (!pte_none(*pte)) continue; - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); entry = pfn_pte(PFN_DOWN(__pa(p)), PAGE_KERNEL); set_pte_at(&init_mm, addr, pte, entry); } while (pte++, addr += PAGE_SIZE, addr != end); @@ -74,14 +79,14 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr, if (boot_cpu_has(X86_FEATURE_GBPAGES) && ((end - addr) == PUD_SIZE) && IS_ALIGNED(addr, PUD_SIZE)) { - p = early_alloc(PUD_SIZE, nid); + p = early_alloc(PUD_SIZE, nid, false); if (p && pud_set_huge(pud, __pa(p), PAGE_KERNEL)) return; else if (p) memblock_free(__pa(p), PUD_SIZE); } - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); pud_populate(&init_mm, pud, p); } @@ -100,7 +105,7 @@ static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr, unsigned long next; if (p4d_none(*p4d)) { - void *p = early_alloc(PAGE_SIZE, nid); + void *p = early_alloc(PAGE_SIZE, nid, true); p4d_populate(&init_mm, p4d, p); } @@ -121,7 +126,7 @@ static void __init kasan_populate_pgd(pgd_t *pgd, unsigned long addr, unsigned long next; if (pgd_none(*pgd)) { - p = early_alloc(PAGE_SIZE, nid); + p = early_alloc(PAGE_SIZE, nid, true); pgd_populate(&init_mm, pgd, p); } @@ -277,6 +282,7 @@ void __init kasan_early_init(void) void __init kasan_init(void) { int i; + void *shadow_cpu_entry_begin, *shadow_cpu_entry_end; #ifdef CONFIG_KASAN_INLINE register_die_notifier(&kasan_die_notifier); @@ -321,16 +327,33 @@ void __init kasan_init(void) map_range(&pfn_mapped[i]); } + shadow_cpu_entry_begin = (void *)CPU_ENTRY_AREA_BASE; + shadow_cpu_entry_begin = kasan_mem_to_shadow(shadow_cpu_entry_begin); + shadow_cpu_entry_begin = (void *)round_down((unsigned long)shadow_cpu_entry_begin, + PAGE_SIZE); + + shadow_cpu_entry_end = (void *)(CPU_ENTRY_AREA_BASE + + CPU_ENTRY_AREA_MAP_SIZE); + shadow_cpu_entry_end = kasan_mem_to_shadow(shadow_cpu_entry_end); + shadow_cpu_entry_end = (void *)round_up((unsigned long)shadow_cpu_entry_end, + PAGE_SIZE); + kasan_populate_zero_shadow( kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM), - kasan_mem_to_shadow((void *)__START_KERNEL_map)); + shadow_cpu_entry_begin); + + kasan_populate_shadow((unsigned long)shadow_cpu_entry_begin, + (unsigned long)shadow_cpu_entry_end, 0); + + kasan_populate_zero_shadow(shadow_cpu_entry_end, + kasan_mem_to_shadow((void *)__START_KERNEL_map)); kasan_populate_shadow((unsigned long)kasan_mem_to_shadow(_stext), (unsigned long)kasan_mem_to_shadow(_end), early_pfn_to_nid(__pa(_stext))); kasan_populate_zero_shadow(kasan_mem_to_shadow((void *)MODULES_END), - (void *)KASAN_SHADOW_END); + (void *)KASAN_SHADOW_END); load_cr3(init_top_pgt); __flush_tlb_all(); diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 879ef930e2c2..aedebd2ebf1e 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -34,25 +34,14 @@ #define TB_SHIFT 40 /* - * Virtual address start and end range for randomization. The end changes base - * on configuration to have the highest amount of space for randomization. - * It increases the possible random position for each randomized region. + * Virtual address start and end range for randomization. * - * You need to add an if/def entry if you introduce a new memory region - * compatible with KASLR. Your entry must be in logical order with memory - * layout. For example, ESPFIX is before EFI because its virtual address is - * before. You also need to add a BUILD_BUG_ON() in kernel_randomize_memory() to - * ensure that this order is correct and won't be changed. + * The end address could depend on more configuration options to make the + * highest amount of space for randomization available, but that's too hard + * to keep straight and caused issues already. */ static const unsigned long vaddr_start = __PAGE_OFFSET_BASE; - -#if defined(CONFIG_X86_ESPFIX64) -static const unsigned long vaddr_end = ESPFIX_BASE_ADDR; -#elif defined(CONFIG_EFI) -static const unsigned long vaddr_end = EFI_VA_END; -#else -static const unsigned long vaddr_end = __START_KERNEL_map; -#endif +static const unsigned long vaddr_end = CPU_ENTRY_AREA_BASE; /* Default values */ unsigned long page_offset_base = __PAGE_OFFSET_BASE; @@ -101,15 +90,12 @@ void __init kernel_randomize_memory(void) unsigned long remain_entropy; /* - * All these BUILD_BUG_ON checks ensures the memory layout is - * consistent with the vaddr_start/vaddr_end variables. + * These BUILD_BUG_ON checks ensure the memory layout is consistent + * with the vaddr_start/vaddr_end variables. These checks are very + * limited.... */ BUILD_BUG_ON(vaddr_start >= vaddr_end); - BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_ESPFIX64) && - vaddr_end >= EFI_VA_END); - BUILD_BUG_ON((IS_ENABLED(CONFIG_X86_ESPFIX64) || - IS_ENABLED(CONFIG_EFI)) && - vaddr_end >= __START_KERNEL_map); + BUILD_BUG_ON(vaddr_end != CPU_ENTRY_AREA_BASE); BUILD_BUG_ON(vaddr_end > __START_KERNEL_map); if (!kaslr_memory_enabled()) diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c deleted file mode 100644 index cec594032515..000000000000 --- a/arch/x86/mm/kmemcheck/error.c +++ /dev/null @@ -1 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 diff --git a/arch/x86/mm/kmemcheck/error.h b/arch/x86/mm/kmemcheck/error.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/arch/x86/mm/kmemcheck/error.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmemcheck/opcode.c b/arch/x86/mm/kmemcheck/opcode.c deleted file mode 100644 index cec594032515..000000000000 --- a/arch/x86/mm/kmemcheck/opcode.c +++ /dev/null @@ -1 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 diff --git a/arch/x86/mm/kmemcheck/opcode.h b/arch/x86/mm/kmemcheck/opcode.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/arch/x86/mm/kmemcheck/opcode.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmemcheck/pte.c b/arch/x86/mm/kmemcheck/pte.c deleted file mode 100644 index cec594032515..000000000000 --- a/arch/x86/mm/kmemcheck/pte.c +++ /dev/null @@ -1 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 diff --git a/arch/x86/mm/kmemcheck/pte.h b/arch/x86/mm/kmemcheck/pte.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/arch/x86/mm/kmemcheck/pte.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmemcheck/selftest.c b/arch/x86/mm/kmemcheck/selftest.c deleted file mode 100644 index cec594032515..000000000000 --- a/arch/x86/mm/kmemcheck/selftest.c +++ /dev/null @@ -1 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 diff --git a/arch/x86/mm/kmemcheck/selftest.h b/arch/x86/mm/kmemcheck/selftest.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/arch/x86/mm/kmemcheck/selftest.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmemcheck/shadow.h b/arch/x86/mm/kmemcheck/shadow.h deleted file mode 100644 index ea32a7d3cf1b..000000000000 --- a/arch/x86/mm/kmemcheck/shadow.h +++ /dev/null @@ -1 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index c21c2ed04612..58477ec3d66d 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -435,17 +435,18 @@ int register_kmmio_probe(struct kmmio_probe *p) unsigned long flags; int ret = 0; unsigned long size = 0; + unsigned long addr = p->addr & PAGE_MASK; const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK); unsigned int l; pte_t *pte; spin_lock_irqsave(&kmmio_lock, flags); - if (get_kmmio_probe(p->addr)) { + if (get_kmmio_probe(addr)) { ret = -EEXIST; goto out; } - pte = lookup_address(p->addr, &l); + pte = lookup_address(addr, &l); if (!pte) { ret = -EINVAL; goto out; @@ -454,7 +455,7 @@ int register_kmmio_probe(struct kmmio_probe *p) kmmio_count++; list_add_rcu(&p->list, &kmmio_probes); while (size < size_lim) { - if (add_kmmio_fault_page(p->addr + size)) + if (add_kmmio_fault_page(addr + size)) pr_err("Unable to set page fault.\n"); size += page_level_size(l); } @@ -528,19 +529,20 @@ void unregister_kmmio_probe(struct kmmio_probe *p) { unsigned long flags; unsigned long size = 0; + unsigned long addr = p->addr & PAGE_MASK; const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK); struct kmmio_fault_page *release_list = NULL; struct kmmio_delayed_release *drelease; unsigned int l; pte_t *pte; - pte = lookup_address(p->addr, &l); + pte = lookup_address(addr, &l); if (!pte) return; spin_lock_irqsave(&kmmio_lock, flags); while (size < size_lim) { - release_kmmio_fault_page(p->addr + size, &release_list); + release_kmmio_fault_page(addr + size, &release_list); size += page_level_size(l); } list_del_rcu(&p->list); diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index d9a9e9fc75dd..e1d61e8500f9 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -405,13 +405,13 @@ bool sme_active(void) { return sme_me_mask && !sev_enabled; } -EXPORT_SYMBOL_GPL(sme_active); +EXPORT_SYMBOL(sme_active); bool sev_active(void) { return sme_me_mask && sev_enabled; } -EXPORT_SYMBOL_GPL(sev_active); +EXPORT_SYMBOL(sev_active); static const struct dma_map_ops sev_dma_ops = { .alloc = sev_alloc, @@ -464,37 +464,62 @@ void swiotlb_set_mem_attributes(void *vaddr, unsigned long size) set_memory_decrypted((unsigned long)vaddr, size >> PAGE_SHIFT); } -static void __init sme_clear_pgd(pgd_t *pgd_base, unsigned long start, - unsigned long end) +struct sme_populate_pgd_data { + void *pgtable_area; + pgd_t *pgd; + + pmdval_t pmd_flags; + pteval_t pte_flags; + unsigned long paddr; + + unsigned long vaddr; + unsigned long vaddr_end; +}; + +static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd) { unsigned long pgd_start, pgd_end, pgd_size; pgd_t *pgd_p; - pgd_start = start & PGDIR_MASK; - pgd_end = end & PGDIR_MASK; + pgd_start = ppd->vaddr & PGDIR_MASK; + pgd_end = ppd->vaddr_end & PGDIR_MASK; - pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1); - pgd_size *= sizeof(pgd_t); + pgd_size = (((pgd_end - pgd_start) / PGDIR_SIZE) + 1) * sizeof(pgd_t); - pgd_p = pgd_base + pgd_index(start); + pgd_p = ppd->pgd + pgd_index(ppd->vaddr); memset(pgd_p, 0, pgd_size); } -#define PGD_FLAGS _KERNPG_TABLE_NOENC -#define P4D_FLAGS _KERNPG_TABLE_NOENC -#define PUD_FLAGS _KERNPG_TABLE_NOENC -#define PMD_FLAGS (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL) +#define PGD_FLAGS _KERNPG_TABLE_NOENC +#define P4D_FLAGS _KERNPG_TABLE_NOENC +#define PUD_FLAGS _KERNPG_TABLE_NOENC +#define PMD_FLAGS _KERNPG_TABLE_NOENC + +#define PMD_FLAGS_LARGE (__PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL) + +#define PMD_FLAGS_DEC PMD_FLAGS_LARGE +#define PMD_FLAGS_DEC_WP ((PMD_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \ + (_PAGE_PAT | _PAGE_PWT)) + +#define PMD_FLAGS_ENC (PMD_FLAGS_LARGE | _PAGE_ENC) + +#define PTE_FLAGS (__PAGE_KERNEL_EXEC & ~_PAGE_GLOBAL) + +#define PTE_FLAGS_DEC PTE_FLAGS +#define PTE_FLAGS_DEC_WP ((PTE_FLAGS_DEC & ~_PAGE_CACHE_MASK) | \ + (_PAGE_PAT | _PAGE_PWT)) + +#define PTE_FLAGS_ENC (PTE_FLAGS | _PAGE_ENC) -static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area, - unsigned long vaddr, pmdval_t pmd_val) +static pmd_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) { pgd_t *pgd_p; p4d_t *p4d_p; pud_t *pud_p; pmd_t *pmd_p; - pgd_p = pgd_base + pgd_index(vaddr); + pgd_p = ppd->pgd + pgd_index(ppd->vaddr); if (native_pgd_val(*pgd_p)) { if (IS_ENABLED(CONFIG_X86_5LEVEL)) p4d_p = (p4d_t *)(native_pgd_val(*pgd_p) & ~PTE_FLAGS_MASK); @@ -504,15 +529,15 @@ static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area, pgd_t pgd; if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - p4d_p = pgtable_area; + p4d_p = ppd->pgtable_area; memset(p4d_p, 0, sizeof(*p4d_p) * PTRS_PER_P4D); - pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D; + ppd->pgtable_area += sizeof(*p4d_p) * PTRS_PER_P4D; pgd = native_make_pgd((pgdval_t)p4d_p + PGD_FLAGS); } else { - pud_p = pgtable_area; + pud_p = ppd->pgtable_area; memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); - pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; + ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; pgd = native_make_pgd((pgdval_t)pud_p + PGD_FLAGS); } @@ -520,58 +545,160 @@ static void __init *sme_populate_pgd(pgd_t *pgd_base, void *pgtable_area, } if (IS_ENABLED(CONFIG_X86_5LEVEL)) { - p4d_p += p4d_index(vaddr); + p4d_p += p4d_index(ppd->vaddr); if (native_p4d_val(*p4d_p)) { pud_p = (pud_t *)(native_p4d_val(*p4d_p) & ~PTE_FLAGS_MASK); } else { p4d_t p4d; - pud_p = pgtable_area; + pud_p = ppd->pgtable_area; memset(pud_p, 0, sizeof(*pud_p) * PTRS_PER_PUD); - pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; + ppd->pgtable_area += sizeof(*pud_p) * PTRS_PER_PUD; p4d = native_make_p4d((pudval_t)pud_p + P4D_FLAGS); native_set_p4d(p4d_p, p4d); } } - pud_p += pud_index(vaddr); + pud_p += pud_index(ppd->vaddr); if (native_pud_val(*pud_p)) { if (native_pud_val(*pud_p) & _PAGE_PSE) - goto out; + return NULL; pmd_p = (pmd_t *)(native_pud_val(*pud_p) & ~PTE_FLAGS_MASK); } else { pud_t pud; - pmd_p = pgtable_area; + pmd_p = ppd->pgtable_area; memset(pmd_p, 0, sizeof(*pmd_p) * PTRS_PER_PMD); - pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD; + ppd->pgtable_area += sizeof(*pmd_p) * PTRS_PER_PMD; pud = native_make_pud((pmdval_t)pmd_p + PUD_FLAGS); native_set_pud(pud_p, pud); } - pmd_p += pmd_index(vaddr); + return pmd_p; +} + +static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) +{ + pmd_t *pmd_p; + + pmd_p = sme_prepare_pgd(ppd); + if (!pmd_p) + return; + + pmd_p += pmd_index(ppd->vaddr); if (!native_pmd_val(*pmd_p) || !(native_pmd_val(*pmd_p) & _PAGE_PSE)) - native_set_pmd(pmd_p, native_make_pmd(pmd_val)); + native_set_pmd(pmd_p, native_make_pmd(ppd->paddr | ppd->pmd_flags)); +} -out: - return pgtable_area; +static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) +{ + pmd_t *pmd_p; + pte_t *pte_p; + + pmd_p = sme_prepare_pgd(ppd); + if (!pmd_p) + return; + + pmd_p += pmd_index(ppd->vaddr); + if (native_pmd_val(*pmd_p)) { + if (native_pmd_val(*pmd_p) & _PAGE_PSE) + return; + + pte_p = (pte_t *)(native_pmd_val(*pmd_p) & ~PTE_FLAGS_MASK); + } else { + pmd_t pmd; + + pte_p = ppd->pgtable_area; + memset(pte_p, 0, sizeof(*pte_p) * PTRS_PER_PTE); + ppd->pgtable_area += sizeof(*pte_p) * PTRS_PER_PTE; + + pmd = native_make_pmd((pteval_t)pte_p + PMD_FLAGS); + native_set_pmd(pmd_p, pmd); + } + + pte_p += pte_index(ppd->vaddr); + if (!native_pte_val(*pte_p)) + native_set_pte(pte_p, native_make_pte(ppd->paddr | ppd->pte_flags)); +} + +static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) +{ + while (ppd->vaddr < ppd->vaddr_end) { + sme_populate_pgd_large(ppd); + + ppd->vaddr += PMD_PAGE_SIZE; + ppd->paddr += PMD_PAGE_SIZE; + } +} + +static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd) +{ + while (ppd->vaddr < ppd->vaddr_end) { + sme_populate_pgd(ppd); + + ppd->vaddr += PAGE_SIZE; + ppd->paddr += PAGE_SIZE; + } +} + +static void __init __sme_map_range(struct sme_populate_pgd_data *ppd, + pmdval_t pmd_flags, pteval_t pte_flags) +{ + unsigned long vaddr_end; + + ppd->pmd_flags = pmd_flags; + ppd->pte_flags = pte_flags; + + /* Save original end value since we modify the struct value */ + vaddr_end = ppd->vaddr_end; + + /* If start is not 2MB aligned, create PTE entries */ + ppd->vaddr_end = ALIGN(ppd->vaddr, PMD_PAGE_SIZE); + __sme_map_range_pte(ppd); + + /* Create PMD entries */ + ppd->vaddr_end = vaddr_end & PMD_PAGE_MASK; + __sme_map_range_pmd(ppd); + + /* If end is not 2MB aligned, create PTE entries */ + ppd->vaddr_end = vaddr_end; + __sme_map_range_pte(ppd); +} + +static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC); +} + +static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC); +} + +static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd) +{ + __sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP); } static unsigned long __init sme_pgtable_calc(unsigned long len) { - unsigned long p4d_size, pud_size, pmd_size; + unsigned long p4d_size, pud_size, pmd_size, pte_size; unsigned long total; /* * Perform a relatively simplistic calculation of the pagetable - * entries that are needed. That mappings will be covered by 2MB - * PMD entries so we can conservatively calculate the required + * entries that are needed. Those mappings will be covered mostly + * by 2MB PMD entries so we can conservatively calculate the required * number of P4D, PUD and PMD structures needed to perform the - * mappings. Incrementing the count for each covers the case where - * the addresses cross entries. + * mappings. For mappings that are not 2MB aligned, PTE mappings + * would be needed for the start and end portion of the address range + * that fall outside of the 2MB alignment. This results in, at most, + * two extra pages to hold PTE entries for each range that is mapped. + * Incrementing the count for each covers the case where the addresses + * cross entries. */ if (IS_ENABLED(CONFIG_X86_5LEVEL)) { p4d_size = (ALIGN(len, PGDIR_SIZE) / PGDIR_SIZE) + 1; @@ -585,8 +712,9 @@ static unsigned long __init sme_pgtable_calc(unsigned long len) } pmd_size = (ALIGN(len, PUD_SIZE) / PUD_SIZE) + 1; pmd_size *= sizeof(pmd_t) * PTRS_PER_PMD; + pte_size = 2 * sizeof(pte_t) * PTRS_PER_PTE; - total = p4d_size + pud_size + pmd_size; + total = p4d_size + pud_size + pmd_size + pte_size; /* * Now calculate the added pagetable structures needed to populate @@ -610,29 +738,29 @@ static unsigned long __init sme_pgtable_calc(unsigned long len) return total; } -void __init sme_encrypt_kernel(void) +void __init __nostackprotector sme_encrypt_kernel(struct boot_params *bp) { unsigned long workarea_start, workarea_end, workarea_len; unsigned long execute_start, execute_end, execute_len; unsigned long kernel_start, kernel_end, kernel_len; + unsigned long initrd_start, initrd_end, initrd_len; + struct sme_populate_pgd_data ppd; unsigned long pgtable_area_len; - unsigned long paddr, pmd_flags; unsigned long decrypted_base; - void *pgtable_area; - pgd_t *pgd; if (!sme_active()) return; /* - * Prepare for encrypting the kernel by building new pagetables with - * the necessary attributes needed to encrypt the kernel in place. + * Prepare for encrypting the kernel and initrd by building new + * pagetables with the necessary attributes needed to encrypt the + * kernel in place. * * One range of virtual addresses will map the memory occupied - * by the kernel as encrypted. + * by the kernel and initrd as encrypted. * * Another range of virtual addresses will map the memory occupied - * by the kernel as decrypted and write-protected. + * by the kernel and initrd as decrypted and write-protected. * * The use of write-protect attribute will prevent any of the * memory from being cached. @@ -643,6 +771,20 @@ void __init sme_encrypt_kernel(void) kernel_end = ALIGN(__pa_symbol(_end), PMD_PAGE_SIZE); kernel_len = kernel_end - kernel_start; + initrd_start = 0; + initrd_end = 0; + initrd_len = 0; +#ifdef CONFIG_BLK_DEV_INITRD + initrd_len = (unsigned long)bp->hdr.ramdisk_size | + ((unsigned long)bp->ext_ramdisk_size << 32); + if (initrd_len) { + initrd_start = (unsigned long)bp->hdr.ramdisk_image | + ((unsigned long)bp->ext_ramdisk_image << 32); + initrd_end = PAGE_ALIGN(initrd_start + initrd_len); + initrd_len = initrd_end - initrd_start; + } +#endif + /* Set the encryption workarea to be immediately after the kernel */ workarea_start = kernel_end; @@ -665,16 +807,21 @@ void __init sme_encrypt_kernel(void) */ pgtable_area_len = sizeof(pgd_t) * PTRS_PER_PGD; pgtable_area_len += sme_pgtable_calc(execute_end - kernel_start) * 2; + if (initrd_len) + pgtable_area_len += sme_pgtable_calc(initrd_len) * 2; /* PUDs and PMDs needed in the current pagetables for the workarea */ pgtable_area_len += sme_pgtable_calc(execute_len + pgtable_area_len); /* * The total workarea includes the executable encryption area and - * the pagetable area. + * the pagetable area. The start of the workarea is already 2MB + * aligned, align the end of the workarea on a 2MB boundary so that + * we don't try to create/allocate PTE entries from the workarea + * before it is mapped. */ workarea_len = execute_len + pgtable_area_len; - workarea_end = workarea_start + workarea_len; + workarea_end = ALIGN(workarea_start + workarea_len, PMD_PAGE_SIZE); /* * Set the address to the start of where newly created pagetable @@ -683,45 +830,30 @@ void __init sme_encrypt_kernel(void) * pagetables and when the new encrypted and decrypted kernel * mappings are populated. */ - pgtable_area = (void *)execute_end; + ppd.pgtable_area = (void *)execute_end; /* * Make sure the current pagetable structure has entries for * addressing the workarea. */ - pgd = (pgd_t *)native_read_cr3_pa(); - paddr = workarea_start; - while (paddr < workarea_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr, - paddr + PMD_FLAGS); - - paddr += PMD_PAGE_SIZE; - } + ppd.pgd = (pgd_t *)native_read_cr3_pa(); + ppd.paddr = workarea_start; + ppd.vaddr = workarea_start; + ppd.vaddr_end = workarea_end; + sme_map_range_decrypted(&ppd); /* Flush the TLB - no globals so cr3 is enough */ native_write_cr3(__native_read_cr3()); /* * A new pagetable structure is being built to allow for the kernel - * to be encrypted. It starts with an empty PGD that will then be - * populated with new PUDs and PMDs as the encrypted and decrypted - * kernel mappings are created. + * and initrd to be encrypted. It starts with an empty PGD that will + * then be populated with new PUDs and PMDs as the encrypted and + * decrypted kernel mappings are created. */ - pgd = pgtable_area; - memset(pgd, 0, sizeof(*pgd) * PTRS_PER_PGD); - pgtable_area += sizeof(*pgd) * PTRS_PER_PGD; - - /* Add encrypted kernel (identity) mappings */ - pmd_flags = PMD_FLAGS | _PAGE_ENC; - paddr = kernel_start; - while (paddr < kernel_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr, - paddr + pmd_flags); - - paddr += PMD_PAGE_SIZE; - } + ppd.pgd = ppd.pgtable_area; + memset(ppd.pgd, 0, sizeof(pgd_t) * PTRS_PER_PGD); + ppd.pgtable_area += sizeof(pgd_t) * PTRS_PER_PGD; /* * A different PGD index/entry must be used to get different @@ -730,47 +862,79 @@ void __init sme_encrypt_kernel(void) * the base of the mapping. */ decrypted_base = (pgd_index(workarea_end) + 1) & (PTRS_PER_PGD - 1); + if (initrd_len) { + unsigned long check_base; + + check_base = (pgd_index(initrd_end) + 1) & (PTRS_PER_PGD - 1); + decrypted_base = max(decrypted_base, check_base); + } decrypted_base <<= PGDIR_SHIFT; + /* Add encrypted kernel (identity) mappings */ + ppd.paddr = kernel_start; + ppd.vaddr = kernel_start; + ppd.vaddr_end = kernel_end; + sme_map_range_encrypted(&ppd); + /* Add decrypted, write-protected kernel (non-identity) mappings */ - pmd_flags = (PMD_FLAGS & ~_PAGE_CACHE_MASK) | (_PAGE_PAT | _PAGE_PWT); - paddr = kernel_start; - while (paddr < kernel_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr + decrypted_base, - paddr + pmd_flags); - - paddr += PMD_PAGE_SIZE; + ppd.paddr = kernel_start; + ppd.vaddr = kernel_start + decrypted_base; + ppd.vaddr_end = kernel_end + decrypted_base; + sme_map_range_decrypted_wp(&ppd); + + if (initrd_len) { + /* Add encrypted initrd (identity) mappings */ + ppd.paddr = initrd_start; + ppd.vaddr = initrd_start; + ppd.vaddr_end = initrd_end; + sme_map_range_encrypted(&ppd); + /* + * Add decrypted, write-protected initrd (non-identity) mappings + */ + ppd.paddr = initrd_start; + ppd.vaddr = initrd_start + decrypted_base; + ppd.vaddr_end = initrd_end + decrypted_base; + sme_map_range_decrypted_wp(&ppd); } /* Add decrypted workarea mappings to both kernel mappings */ - paddr = workarea_start; - while (paddr < workarea_end) { - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr, - paddr + PMD_FLAGS); + ppd.paddr = workarea_start; + ppd.vaddr = workarea_start; + ppd.vaddr_end = workarea_end; + sme_map_range_decrypted(&ppd); - pgtable_area = sme_populate_pgd(pgd, pgtable_area, - paddr + decrypted_base, - paddr + PMD_FLAGS); - - paddr += PMD_PAGE_SIZE; - } + ppd.paddr = workarea_start; + ppd.vaddr = workarea_start + decrypted_base; + ppd.vaddr_end = workarea_end + decrypted_base; + sme_map_range_decrypted(&ppd); /* Perform the encryption */ sme_encrypt_execute(kernel_start, kernel_start + decrypted_base, - kernel_len, workarea_start, (unsigned long)pgd); + kernel_len, workarea_start, (unsigned long)ppd.pgd); + + if (initrd_len) + sme_encrypt_execute(initrd_start, initrd_start + decrypted_base, + initrd_len, workarea_start, + (unsigned long)ppd.pgd); /* * At this point we are running encrypted. Remove the mappings for * the decrypted areas - all that is needed for this is to remove * the PGD entry/entries. */ - sme_clear_pgd(pgd, kernel_start + decrypted_base, - kernel_end + decrypted_base); + ppd.vaddr = kernel_start + decrypted_base; + ppd.vaddr_end = kernel_end + decrypted_base; + sme_clear_pgd(&ppd); + + if (initrd_len) { + ppd.vaddr = initrd_start + decrypted_base; + ppd.vaddr_end = initrd_end + decrypted_base; + sme_clear_pgd(&ppd); + } - sme_clear_pgd(pgd, workarea_start + decrypted_base, - workarea_end + decrypted_base); + ppd.vaddr = workarea_start + decrypted_base; + ppd.vaddr_end = workarea_end + decrypted_base; + sme_clear_pgd(&ppd); /* Flush the TLB - no globals so cr3 is enough */ native_write_cr3(__native_read_cr3()); diff --git a/arch/x86/mm/mem_encrypt_boot.S b/arch/x86/mm/mem_encrypt_boot.S index 730e6d541df1..01f682cf77a8 100644 --- a/arch/x86/mm/mem_encrypt_boot.S +++ b/arch/x86/mm/mem_encrypt_boot.S @@ -22,9 +22,9 @@ ENTRY(sme_encrypt_execute) /* * Entry parameters: - * RDI - virtual address for the encrypted kernel mapping - * RSI - virtual address for the decrypted kernel mapping - * RDX - length of kernel + * RDI - virtual address for the encrypted mapping + * RSI - virtual address for the decrypted mapping + * RDX - length to encrypt * RCX - virtual address of the encryption workarea, including: * - stack page (PAGE_SIZE) * - encryption routine page (PAGE_SIZE) @@ -41,9 +41,9 @@ ENTRY(sme_encrypt_execute) addq $PAGE_SIZE, %rax /* Workarea encryption routine */ push %r12 - movq %rdi, %r10 /* Encrypted kernel */ - movq %rsi, %r11 /* Decrypted kernel */ - movq %rdx, %r12 /* Kernel length */ + movq %rdi, %r10 /* Encrypted area */ + movq %rsi, %r11 /* Decrypted area */ + movq %rdx, %r12 /* Area length */ /* Copy encryption routine into the workarea */ movq %rax, %rdi /* Workarea encryption routine */ @@ -52,10 +52,10 @@ ENTRY(sme_encrypt_execute) rep movsb /* Setup registers for call */ - movq %r10, %rdi /* Encrypted kernel */ - movq %r11, %rsi /* Decrypted kernel */ + movq %r10, %rdi /* Encrypted area */ + movq %r11, %rsi /* Decrypted area */ movq %r8, %rdx /* Pagetables used for encryption */ - movq %r12, %rcx /* Kernel length */ + movq %r12, %rcx /* Area length */ movq %rax, %r8 /* Workarea encryption routine */ addq $PAGE_SIZE, %r8 /* Workarea intermediate copy buffer */ @@ -71,7 +71,7 @@ ENDPROC(sme_encrypt_execute) ENTRY(__enc_copy) /* - * Routine used to encrypt kernel. + * Routine used to encrypt memory in place. * This routine must be run outside of the kernel proper since * the kernel will be encrypted during the process. So this * routine is defined here and then copied to an area outside @@ -79,19 +79,19 @@ ENTRY(__enc_copy) * during execution. * * On entry the registers must be: - * RDI - virtual address for the encrypted kernel mapping - * RSI - virtual address for the decrypted kernel mapping + * RDI - virtual address for the encrypted mapping + * RSI - virtual address for the decrypted mapping * RDX - address of the pagetables to use for encryption - * RCX - length of kernel + * RCX - length of area * R8 - intermediate copy buffer * * RAX - points to this routine * - * The kernel will be encrypted by copying from the non-encrypted - * kernel space to an intermediate buffer and then copying from the - * intermediate buffer back to the encrypted kernel space. The physical - * addresses of the two kernel space mappings are the same which - * results in the kernel being encrypted "in place". + * The area will be encrypted by copying from the non-encrypted + * memory space to an intermediate buffer and then copying from the + * intermediate buffer back to the encrypted memory space. The physical + * addresses of the two mappings are the same which results in the area + * being encrypted "in place". */ /* Enable the new page tables */ mov %rdx, %cr3 @@ -103,47 +103,55 @@ ENTRY(__enc_copy) orq $X86_CR4_PGE, %rdx mov %rdx, %cr4 + push %r15 + push %r12 + + movq %rcx, %r9 /* Save area length */ + movq %rdi, %r10 /* Save encrypted area address */ + movq %rsi, %r11 /* Save decrypted area address */ + /* Set the PAT register PA5 entry to write-protect */ - push %rcx movl $MSR_IA32_CR_PAT, %ecx rdmsr - push %rdx /* Save original PAT value */ + mov %rdx, %r15 /* Save original PAT value */ andl $0xffff00ff, %edx /* Clear PA5 */ orl $0x00000500, %edx /* Set PA5 to WP */ wrmsr - pop %rdx /* RDX contains original PAT value */ - pop %rcx - - movq %rcx, %r9 /* Save kernel length */ - movq %rdi, %r10 /* Save encrypted kernel address */ - movq %rsi, %r11 /* Save decrypted kernel address */ wbinvd /* Invalidate any cache entries */ - /* Copy/encrypt 2MB at a time */ + /* Copy/encrypt up to 2MB at a time */ + movq $PMD_PAGE_SIZE, %r12 1: - movq %r11, %rsi /* Source - decrypted kernel */ + cmpq %r12, %r9 + jnb 2f + movq %r9, %r12 + +2: + movq %r11, %rsi /* Source - decrypted area */ movq %r8, %rdi /* Dest - intermediate copy buffer */ - movq $PMD_PAGE_SIZE, %rcx /* 2MB length */ + movq %r12, %rcx rep movsb movq %r8, %rsi /* Source - intermediate copy buffer */ - movq %r10, %rdi /* Dest - encrypted kernel */ - movq $PMD_PAGE_SIZE, %rcx /* 2MB length */ + movq %r10, %rdi /* Dest - encrypted area */ + movq %r12, %rcx rep movsb - addq $PMD_PAGE_SIZE, %r11 - addq $PMD_PAGE_SIZE, %r10 - subq $PMD_PAGE_SIZE, %r9 /* Kernel length decrement */ + addq %r12, %r11 + addq %r12, %r10 + subq %r12, %r9 /* Kernel length decrement */ jnz 1b /* Kernel length not zero? */ /* Restore PAT register */ - push %rdx /* Save original PAT value */ movl $MSR_IA32_CR_PAT, %ecx rdmsr - pop %rdx /* Restore original PAT value */ + mov %r15, %rdx /* Restore original PAT value */ wrmsr + pop %r12 + pop %r15 + ret .L__enc_copy_end: ENDPROC(__enc_copy) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 96d456a94b03..004abf9ebf12 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -355,14 +355,15 @@ static inline void _pgd_free(pgd_t *pgd) kmem_cache_free(pgd_cache, pgd); } #else + static inline pgd_t *_pgd_alloc(void) { - return (pgd_t *)__get_free_page(PGALLOC_GFP); + return (pgd_t *)__get_free_pages(PGALLOC_GFP, PGD_ALLOCATION_ORDER); } static inline void _pgd_free(pgd_t *pgd) { - free_page((unsigned long)pgd); + free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER); } #endif /* CONFIG_X86_PAE */ diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 6b9bf023a700..c3c5274410a9 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -10,6 +10,7 @@ #include <linux/pagemap.h> #include <linux/spinlock.h> +#include <asm/cpu_entry_area.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/fixmap.h> diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c new file mode 100644 index 000000000000..ce38f165489b --- /dev/null +++ b/arch/x86/mm/pti.c @@ -0,0 +1,368 @@ +/* + * Copyright(c) 2017 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * This code is based in part on work published here: + * + * https://github.com/IAIK/KAISER + * + * The original work was written by and and signed off by for the Linux + * kernel by: + * + * Signed-off-by: Richard Fellner <richard.fellner@student.tugraz.at> + * Signed-off-by: Moritz Lipp <moritz.lipp@iaik.tugraz.at> + * Signed-off-by: Daniel Gruss <daniel.gruss@iaik.tugraz.at> + * Signed-off-by: Michael Schwarz <michael.schwarz@iaik.tugraz.at> + * + * Major changes to the original code by: Dave Hansen <dave.hansen@intel.com> + * Mostly rewritten by Thomas Gleixner <tglx@linutronix.de> and + * Andy Lutomirsky <luto@amacapital.net> + */ +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/bug.h> +#include <linux/init.h> +#include <linux/spinlock.h> +#include <linux/mm.h> +#include <linux/uaccess.h> + +#include <asm/cpufeature.h> +#include <asm/hypervisor.h> +#include <asm/vsyscall.h> +#include <asm/cmdline.h> +#include <asm/pti.h> +#include <asm/pgtable.h> +#include <asm/pgalloc.h> +#include <asm/tlbflush.h> +#include <asm/desc.h> + +#undef pr_fmt +#define pr_fmt(fmt) "Kernel/User page tables isolation: " fmt + +/* Backporting helper */ +#ifndef __GFP_NOTRACK +#define __GFP_NOTRACK 0 +#endif + +static void __init pti_print_if_insecure(const char *reason) +{ + if (boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + pr_info("%s\n", reason); +} + +static void __init pti_print_if_secure(const char *reason) +{ + if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + pr_info("%s\n", reason); +} + +void __init pti_check_boottime_disable(void) +{ + char arg[5]; + int ret; + + if (hypervisor_is_type(X86_HYPER_XEN_PV)) { + pti_print_if_insecure("disabled on XEN PV."); + return; + } + + ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg)); + if (ret > 0) { + if (ret == 3 && !strncmp(arg, "off", 3)) { + pti_print_if_insecure("disabled on command line."); + return; + } + if (ret == 2 && !strncmp(arg, "on", 2)) { + pti_print_if_secure("force enabled on command line."); + goto enable; + } + if (ret == 4 && !strncmp(arg, "auto", 4)) + goto autosel; + } + + if (cmdline_find_option_bool(boot_command_line, "nopti")) { + pti_print_if_insecure("disabled on command line."); + return; + } + +autosel: + if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + return; +enable: + setup_force_cpu_cap(X86_FEATURE_PTI); +} + +pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd) +{ + /* + * Changes to the high (kernel) portion of the kernelmode page + * tables are not automatically propagated to the usermode tables. + * + * Users should keep in mind that, unlike the kernelmode tables, + * there is no vmalloc_fault equivalent for the usermode tables. + * Top-level entries added to init_mm's usermode pgd after boot + * will not be automatically propagated to other mms. + */ + if (!pgdp_maps_userspace(pgdp)) + return pgd; + + /* + * The user page tables get the full PGD, accessible from + * userspace: + */ + kernel_to_user_pgdp(pgdp)->pgd = pgd.pgd; + + /* + * If this is normal user memory, make it NX in the kernel + * pagetables so that, if we somehow screw up and return to + * usermode with the kernel CR3 loaded, we'll get a page fault + * instead of allowing user code to execute with the wrong CR3. + * + * As exceptions, we don't set NX if: + * - _PAGE_USER is not set. This could be an executable + * EFI runtime mapping or something similar, and the kernel + * may execute from it + * - we don't have NX support + * - we're clearing the PGD (i.e. the new pgd is not present). + */ + if ((pgd.pgd & (_PAGE_USER|_PAGE_PRESENT)) == (_PAGE_USER|_PAGE_PRESENT) && + (__supported_pte_mask & _PAGE_NX)) + pgd.pgd |= _PAGE_NX; + + /* return the copy of the PGD we want the kernel to use: */ + return pgd; +} + +/* + * Walk the user copy of the page tables (optionally) trying to allocate + * page table pages on the way down. + * + * Returns a pointer to a P4D on success, or NULL on failure. + */ +static __init p4d_t *pti_user_pagetable_walk_p4d(unsigned long address) +{ + pgd_t *pgd = kernel_to_user_pgdp(pgd_offset_k(address)); + gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); + + if (address < PAGE_OFFSET) { + WARN_ONCE(1, "attempt to walk user address\n"); + return NULL; + } + + if (pgd_none(*pgd)) { + unsigned long new_p4d_page = __get_free_page(gfp); + if (!new_p4d_page) + return NULL; + + set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page))); + } + BUILD_BUG_ON(pgd_large(*pgd) != 0); + + return p4d_offset(pgd, address); +} + +/* + * Walk the user copy of the page tables (optionally) trying to allocate + * page table pages on the way down. + * + * Returns a pointer to a PMD on success, or NULL on failure. + */ +static __init pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) +{ + gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); + p4d_t *p4d = pti_user_pagetable_walk_p4d(address); + pud_t *pud; + + BUILD_BUG_ON(p4d_large(*p4d) != 0); + if (p4d_none(*p4d)) { + unsigned long new_pud_page = __get_free_page(gfp); + if (!new_pud_page) + return NULL; + + set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page))); + } + + pud = pud_offset(p4d, address); + /* The user page tables do not use large mappings: */ + if (pud_large(*pud)) { + WARN_ON(1); + return NULL; + } + if (pud_none(*pud)) { + unsigned long new_pmd_page = __get_free_page(gfp); + if (!new_pmd_page) + return NULL; + + set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page))); + } + + return pmd_offset(pud, address); +} + +#ifdef CONFIG_X86_VSYSCALL_EMULATION +/* + * Walk the shadow copy of the page tables (optionally) trying to allocate + * page table pages on the way down. Does not support large pages. + * + * Note: this is only used when mapping *new* kernel data into the + * user/shadow page tables. It is never used for userspace data. + * + * Returns a pointer to a PTE on success, or NULL on failure. + */ +static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address) +{ + gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); + pmd_t *pmd = pti_user_pagetable_walk_pmd(address); + pte_t *pte; + + /* We can't do anything sensible if we hit a large mapping. */ + if (pmd_large(*pmd)) { + WARN_ON(1); + return NULL; + } + + if (pmd_none(*pmd)) { + unsigned long new_pte_page = __get_free_page(gfp); + if (!new_pte_page) + return NULL; + + set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page))); + } + + pte = pte_offset_kernel(pmd, address); + if (pte_flags(*pte) & _PAGE_USER) { + WARN_ONCE(1, "attempt to walk to user pte\n"); + return NULL; + } + return pte; +} + +static void __init pti_setup_vsyscall(void) +{ + pte_t *pte, *target_pte; + unsigned int level; + + pte = lookup_address(VSYSCALL_ADDR, &level); + if (!pte || WARN_ON(level != PG_LEVEL_4K) || pte_none(*pte)) + return; + + target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR); + if (WARN_ON(!target_pte)) + return; + + *target_pte = *pte; + set_vsyscall_pgtable_user_bits(kernel_to_user_pgdp(swapper_pg_dir)); +} +#else +static void __init pti_setup_vsyscall(void) { } +#endif + +static void __init +pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear) +{ + unsigned long addr; + + /* + * Clone the populated PMDs which cover start to end. These PMD areas + * can have holes. + */ + for (addr = start; addr < end; addr += PMD_SIZE) { + pmd_t *pmd, *target_pmd; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + + pgd = pgd_offset_k(addr); + if (WARN_ON(pgd_none(*pgd))) + return; + p4d = p4d_offset(pgd, addr); + if (WARN_ON(p4d_none(*p4d))) + return; + pud = pud_offset(p4d, addr); + if (pud_none(*pud)) + continue; + pmd = pmd_offset(pud, addr); + if (pmd_none(*pmd)) + continue; + + target_pmd = pti_user_pagetable_walk_pmd(addr); + if (WARN_ON(!target_pmd)) + return; + + /* + * Copy the PMD. That is, the kernelmode and usermode + * tables will share the last-level page tables of this + * address range + */ + *target_pmd = pmd_clear_flags(*pmd, clear); + } +} + +/* + * Clone a single p4d (i.e. a top-level entry on 4-level systems and a + * next-level entry on 5-level systems. + */ +static void __init pti_clone_p4d(unsigned long addr) +{ + p4d_t *kernel_p4d, *user_p4d; + pgd_t *kernel_pgd; + + user_p4d = pti_user_pagetable_walk_p4d(addr); + kernel_pgd = pgd_offset_k(addr); + kernel_p4d = p4d_offset(kernel_pgd, addr); + *user_p4d = *kernel_p4d; +} + +/* + * Clone the CPU_ENTRY_AREA into the user space visible page table. + */ +static void __init pti_clone_user_shared(void) +{ + pti_clone_p4d(CPU_ENTRY_AREA_BASE); +} + +/* + * Clone the ESPFIX P4D into the user space visinble page table + */ +static void __init pti_setup_espfix64(void) +{ +#ifdef CONFIG_X86_ESPFIX64 + pti_clone_p4d(ESPFIX_BASE_ADDR); +#endif +} + +/* + * Clone the populated PMDs of the entry and irqentry text and force it RO. + */ +static void __init pti_clone_entry_text(void) +{ + pti_clone_pmds((unsigned long) __entry_text_start, + (unsigned long) __irqentry_text_end, + _PAGE_RW | _PAGE_GLOBAL); +} + +/* + * Initialize kernel page table isolation + */ +void __init pti_init(void) +{ + if (!static_cpu_has(X86_FEATURE_PTI)) + return; + + pr_info("enabled\n"); + + pti_clone_user_shared(); + pti_clone_entry_text(); + pti_setup_espfix64(); + pti_setup_vsyscall(); +} diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 3118392cdf75..5bfe61a5e8e3 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -28,6 +28,38 @@ * Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi */ +/* + * We get here when we do something requiring a TLB invalidation + * but could not go invalidate all of the contexts. We do the + * necessary invalidation by clearing out the 'ctx_id' which + * forces a TLB flush when the context is loaded. + */ +void clear_asid_other(void) +{ + u16 asid; + + /* + * This is only expected to be set if we have disabled + * kernel _PAGE_GLOBAL pages. + */ + if (!static_cpu_has(X86_FEATURE_PTI)) { + WARN_ON_ONCE(1); + return; + } + + for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) { + /* Do not need to flush the current asid */ + if (asid == this_cpu_read(cpu_tlbstate.loaded_mm_asid)) + continue; + /* + * Make sure the next time we go to switch to + * this asid, we do a flush: + */ + this_cpu_write(cpu_tlbstate.ctxs[asid].ctx_id, 0); + } + this_cpu_write(cpu_tlbstate.invalidate_other, false); +} + atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1); @@ -42,6 +74,9 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen, return; } + if (this_cpu_read(cpu_tlbstate.invalidate_other)) + clear_asid_other(); + for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) { if (this_cpu_read(cpu_tlbstate.ctxs[asid].ctx_id) != next->context.ctx_id) @@ -65,6 +100,25 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen, *need_flush = true; } +static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, bool need_flush) +{ + unsigned long new_mm_cr3; + + if (need_flush) { + invalidate_user_asid(new_asid); + new_mm_cr3 = build_cr3(pgdir, new_asid); + } else { + new_mm_cr3 = build_cr3_noflush(pgdir, new_asid); + } + + /* + * Caution: many callers of this function expect + * that load_cr3() is serializing and orders TLB + * fills with respect to the mm_cpumask writes. + */ + write_cr3(new_mm_cr3); +} + void leave_mm(int cpu) { struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm); @@ -97,6 +151,34 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next, local_irq_restore(flags); } +static void sync_current_stack_to_mm(struct mm_struct *mm) +{ + unsigned long sp = current_stack_pointer; + pgd_t *pgd = pgd_offset(mm, sp); + + if (CONFIG_PGTABLE_LEVELS > 4) { + if (unlikely(pgd_none(*pgd))) { + pgd_t *pgd_ref = pgd_offset_k(sp); + + set_pgd(pgd, *pgd_ref); + } + } else { + /* + * "pgd" is faked. The top level entries are "p4d"s, so sync + * the p4d. This compiles to approximately the same code as + * the 5-level case. + */ + p4d_t *p4d = p4d_offset(pgd, sp); + + if (unlikely(p4d_none(*p4d))) { + pgd_t *pgd_ref = pgd_offset_k(sp); + p4d_t *p4d_ref = p4d_offset(pgd_ref, sp); + + set_p4d(p4d, *p4d_ref); + } + } +} + void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { @@ -128,7 +210,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * isn't free. */ #ifdef CONFIG_DEBUG_VM - if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev, prev_asid))) { + if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid))) { /* * If we were to BUG here, we'd be very likely to kill * the system so hard that we don't see the call trace. @@ -172,11 +254,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * mapped in the new pgd, we'll double-fault. Forcibly * map it. */ - unsigned int index = pgd_index(current_stack_pointer); - pgd_t *pgd = next->pgd + index; - - if (unlikely(pgd_none(*pgd))) - set_pgd(pgd, init_mm.pgd[index]); + sync_current_stack_to_mm(next); } /* Stop remote flushes for the previous mm */ @@ -195,7 +273,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, if (need_flush) { this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); - write_cr3(build_cr3(next, new_asid)); + load_new_mm_cr3(next->pgd, new_asid, true); /* * NB: This gets called via leave_mm() in the idle path @@ -208,7 +286,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL); } else { /* The new ASID is already up to date. */ - write_cr3(build_cr3_noflush(next, new_asid)); + load_new_mm_cr3(next->pgd, new_asid, false); /* See above wrt _rcuidle. */ trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0); @@ -288,7 +366,7 @@ void initialize_tlbstate_and_flush(void) !(cr4_read_shadow() & X86_CR4_PCIDE)); /* Force ASID 0 and force a TLB flush. */ - write_cr3(build_cr3(mm, 0)); + write_cr3(build_cr3(mm->pgd, 0)); /* Reinitialize tlbstate. */ this_cpu_write(cpu_tlbstate.loaded_mm_asid, 0); @@ -551,7 +629,7 @@ static void do_kernel_range_flush(void *info) /* flush range by one by one 'invlpg' */ for (addr = f->start; addr < f->end; addr += PAGE_SIZE) - __flush_tlb_single(addr); + __flush_tlb_one(addr); } void flush_tlb_kernel_range(unsigned long start, unsigned long end) |