This is a note to let you know that I've just added the patch titled
x86/cpu_entry_area: Move it to a separate unit
to the 4.14-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git%3Ba=su...
The filename of the patch is: x86-cpu_entry_area-move-it-to-a-separate-unit.patch and it can be found in the queue-4.14 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree, please let stable@vger.kernel.org know about it.
From ed1bbc40a0d10e0c5c74fe7bdc6298295cf40255 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner tglx@linutronix.de Date: Wed, 20 Dec 2017 18:28:54 +0100 Subject: x86/cpu_entry_area: Move it to a separate unit
From: Thomas Gleixner tglx@linutronix.de
commit ed1bbc40a0d10e0c5c74fe7bdc6298295cf40255 upstream.
Separate the cpu_entry_area code out of cpu/common.c and the fixmap.
Signed-off-by: Thomas Gleixner tglx@linutronix.de Cc: Andy Lutomirski luto@kernel.org Cc: Borislav Petkov bp@alien8.de Cc: Dave Hansen dave.hansen@linux.intel.com Cc: H. Peter Anvin hpa@zytor.com Cc: Josh Poimboeuf jpoimboe@redhat.com Cc: Juergen Gross jgross@suse.com Cc: Linus Torvalds torvalds@linux-foundation.org Cc: Peter Zijlstra peterz@infradead.org Signed-off-by: Ingo Molnar mingo@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org
--- arch/x86/include/asm/cpu_entry_area.h | 52 +++++++++++++++++ arch/x86/include/asm/fixmap.h | 41 ------------- arch/x86/kernel/cpu/common.c | 94 ------------------------------ arch/x86/kernel/traps.c | 1 arch/x86/mm/Makefile | 2 arch/x86/mm/cpu_entry_area.c | 104 ++++++++++++++++++++++++++++++++++ 6 files changed, 159 insertions(+), 135 deletions(-)
--- /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 <linux/percpu-defs.h> +#include <asm/processor.h> + +/* + * 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 --- a/arch/x86/include/asm/fixmap.h +++ b/arch/x86/include/asm/fixmap.h @@ -25,6 +25,7 @@ #else #include <uapi/asm/vsyscall.h> #endif +#include <asm/cpu_entry_area.h>
/* * We can't declare FIXADDR_TOP as variable for x86_64 because vsyscall @@ -45,46 +46,6 @@ extern unsigned long __FIXADDR_TOP; #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 * compile time, but to set the physical address only --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -482,102 +482,8 @@ static const unsigned int exception_stac [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) { --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -52,6 +52,7 @@ #include <asm/traps.h> #include <asm/desc.h> #include <asm/fpu/internal.h> +#include <asm/cpu_entry_area.h> #include <asm/mce.h> #include <asm/fixmap.h> #include <asm/mach_traps.h> --- 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) --- /dev/null +++ b/arch/x86/mm/cpu_entry_area.c @@ -0,0 +1,104 @@ +// 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 + +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); +}
Patches currently in stable-queue which might be from tglx@linutronix.de are
queue-4.14/x86-entry-rename-sysenter_stack-to-cpu_entry_area_entry_stack.patch queue-4.14/x86-mm-put-mmu-to-hardware-asid-translation-in-one-place.patch queue-4.14/x86-vsyscall-64-explicitly-set-_page_user-in-the-pagetable-hierarchy.patch queue-4.14/x86-uv-use-the-right-tlb-flush-api.patch queue-4.14/x86-decoder-fix-and-update-the-opcodes-map.patch queue-4.14/x86-mm-dump_pagetables-check-page_present-for-real.patch queue-4.14/x86-ldt-prevent-ldt-inheritance-on-exec.patch queue-4.14/x86-microcode-dont-abuse-the-tlb-flush-interface.patch queue-4.14/x86-doc-remove-obvious-weirdnesses-from-the-x86-mm-layout-documentation.patch queue-4.14/init-invoke-init_espfix_bsp-from-mm_init.patch queue-4.14/x86-cpu_entry_area-move-it-to-a-separate-unit.patch queue-4.14/x86-vsyscall-64-warn-and-fail-vsyscall-emulation-in-native-mode.patch queue-4.14/x86-mm-create-asm-invpcid.h.patch queue-4.14/x86-cpu_entry_area-prevent-wraparound-in-setup_cpu_entry_area_ptes-on-32bit.patch queue-4.14/x86-mm-remove-superfluous-barriers.patch queue-4.14/x86-ldt-rework-locking.patch queue-4.14/pci-pm-force-devices-to-d0-in-pci_pm_thaw_noirq.patch queue-4.14/arch-mm-allow-arch_dup_mmap-to-fail.patch queue-4.14/x86-cpu_entry_area-move-it-out-of-the-fixmap.patch queue-4.14/tools-headers-sync-objtool-uapi-header.patch queue-4.14/x86-mm-remove-hard-coded-asid-limit-checks.patch queue-4.14/x86-kconfig-limit-nr_cpus-on-32-bit-to-a-sane-amount.patch queue-4.14/objtool-fix-64-bit-build-on-32-bit-host.patch queue-4.14/x86-mm-add-comments-to-clarify-which-tlb-flush-functions-are-supposed-to-flush-what.patch queue-4.14/x86-mm-move-the-cr3-construction-functions-to-tlbflush.h.patch queue-4.14/x86-mm-dump_pagetables-make-the-address-hints-correct-and-readable.patch queue-4.14/x86-insn-eval-add-utility-functions-to-get-segment-selector.patch queue-4.14/objtool-move-synced-files-to-their-original-relative-locations.patch queue-4.14/x86-mm-use-__flush_tlb_one-for-kernel-memory.patch queue-4.14/objtool-move-kernel-headers-code-sync-check-to-a-script.patch queue-4.14/x86-mm-64-improve-the-memory-map-documentation.patch queue-4.14/objtool-fix-cross-build.patch