diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h new file mode 100644 index 000000000000..5471826803af --- /dev/null +++ b/arch/x86/include/asm/cpu_entry_area.h @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 + +#ifndef _ASM_X86_CPU_ENTRY_AREA_H +#define _ASM_X86_CPU_ENTRY_AREA_H + +#include +#include + +/* + * cpu_entry_area is a percpu region that contains things needed by the CPU + * and early entry/exit code. Real types aren't used for all fields here + * to avoid circular header dependencies. + * + * Every field is a virtual alias of some other allocated backing store. + * There is no direct allocation of a struct cpu_entry_area. + */ +struct cpu_entry_area { + char gdt[PAGE_SIZE]; + + /* + * The GDT is just below entry_stack and thus serves (on x86_64) as + * a a read-only guard page. + */ + struct entry_stack_page entry_stack_page; + + /* + * On x86_64, the TSS is mapped RO. On x86_32, it's mapped RW because + * we need task switches to work, and task switches write to the TSS. + */ + struct tss_struct tss; + + char entry_trampoline[PAGE_SIZE]; + +#ifdef CONFIG_X86_64 + /* + * Exception stacks used for IST entries. + * + * In the future, this should have a separate slot for each stack + * with guard pages between them. + */ + char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]; +#endif +}; + +#define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area)) +#define CPU_ENTRY_AREA_PAGES (CPU_ENTRY_AREA_SIZE / PAGE_SIZE) + +DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); + +extern void setup_cpu_entry_areas(void); + +#endif diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h index 8153b8d86a3c..fb801662a230 100644 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -25,6 +25,7 @@ #else #include #endif +#include /* * We can't declare FIXADDR_TOP as variable for x86_64 because vsyscall @@ -44,46 +45,6 @@ extern unsigned long __FIXADDR_TOP; PAGE_SIZE) #endif -/* - * cpu_entry_area is a percpu region in the fixmap that contains things - * needed by the CPU and early entry/exit code. Real types aren't used - * for all fields here to avoid circular header dependencies. - * - * Every field is a virtual alias of some other allocated backing store. - * There is no direct allocation of a struct cpu_entry_area. - */ -struct cpu_entry_area { - char gdt[PAGE_SIZE]; - - /* - * The GDT is just below entry_stack and thus serves (on x86_64) as - * a a read-only guard page. - */ - struct entry_stack_page entry_stack_page; - - /* - * On x86_64, the TSS is mapped RO. On x86_32, it's mapped RW because - * we need task switches to work, and task switches write to the TSS. - */ - struct tss_struct tss; - - char entry_trampoline[PAGE_SIZE]; - -#ifdef CONFIG_X86_64 - /* - * Exception stacks used for IST entries. - * - * In the future, this should have a separate slot for each stack - * with guard pages between them. - */ - char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]; -#endif -}; - -#define CPU_ENTRY_AREA_PAGES (sizeof(struct cpu_entry_area) / PAGE_SIZE) - -extern void setup_cpu_entry_areas(void); - /* * Here we define all the compile-time 'special' virtual * addresses. The point is to have a constant address at diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index ed4acbce37a8..8ddcfa4d4165 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -482,102 +482,8 @@ static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = { [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STKSZ, [DEBUG_STACK - 1] = DEBUG_STKSZ }; - -static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks - [(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]); #endif -static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, - entry_stack_storage); - -static void __init -set_percpu_fixmap_pages(int idx, void *ptr, int pages, pgprot_t prot) -{ - for ( ; pages; pages--, idx--, ptr += PAGE_SIZE) - __set_fixmap(idx, per_cpu_ptr_to_phys(ptr), prot); -} - -/* 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 - - __set_fixmap(get_cpu_entry_area_index(cpu, gdt), get_cpu_gdt_paddr(cpu), gdt_prot); - set_percpu_fixmap_pages(get_cpu_entry_area_index(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); - set_percpu_fixmap_pages(get_cpu_entry_area_index(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)); - set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, exception_stacks), - &per_cpu(exception_stacks, cpu), - sizeof(exception_stacks) / PAGE_SIZE, - PAGE_KERNEL); - - __set_fixmap(get_cpu_entry_area_index(cpu, entry_trampoline), - __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX); -#endif -} - -void __init setup_cpu_entry_areas(void) -{ - unsigned int cpu; - - for_each_possible_cpu(cpu) - setup_cpu_entry_area(cpu); -} - /* Load the original GDT from the per-cpu structure */ void load_direct_gdt(int cpu) { diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 74136fd16f49..464daed6894f 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -52,6 +52,7 @@ #include #include #include +#include #include #include #include diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 7ba7f3d7f477..2e0017af8f9b 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) diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c new file mode 100644 index 000000000000..235ff9cfaaf4 --- /dev/null +++ b/arch/x86/mm/cpu_entry_area.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +#include +#include +#include +#include + +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 + +static void __init +set_percpu_fixmap_pages(int idx, void *ptr, int pages, pgprot_t prot) +{ + for ( ; pages; pages--, idx--, ptr += PAGE_SIZE) + __set_fixmap(idx, per_cpu_ptr_to_phys(ptr), prot); +} + +/* 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 + + __set_fixmap(get_cpu_entry_area_index(cpu, gdt), get_cpu_gdt_paddr(cpu), gdt_prot); + set_percpu_fixmap_pages(get_cpu_entry_area_index(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); + set_percpu_fixmap_pages(get_cpu_entry_area_index(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)); + set_percpu_fixmap_pages(get_cpu_entry_area_index(cpu, exception_stacks), + &per_cpu(exception_stacks, cpu), + sizeof(exception_stacks) / PAGE_SIZE, + PAGE_KERNEL); + + __set_fixmap(get_cpu_entry_area_index(cpu, entry_trampoline), + __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX); +#endif +} + +void __init setup_cpu_entry_areas(void) +{ + unsigned int cpu; + + for_each_possible_cpu(cpu) + setup_cpu_entry_area(cpu); +}