forked from Minki/linux
e31cf2f4ca
Patch series "mm: consolidate definitions of page table accessors", v2. The low level page table accessors (pXY_index(), pXY_offset()) are duplicated across all architectures and sometimes more than once. For instance, we have 31 definition of pgd_offset() for 25 supported architectures. Most of these definitions are actually identical and typically it boils down to, e.g. static inline unsigned long pmd_index(unsigned long address) { return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1); } static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address) { return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address); } These definitions can be shared among 90% of the arches provided XYZ_SHIFT, PTRS_PER_XYZ and xyz_page_vaddr() are defined. For architectures that really need a custom version there is always possibility to override the generic version with the usual ifdefs magic. These patches introduce include/linux/pgtable.h that replaces include/asm-generic/pgtable.h and add the definitions of the page table accessors to the new header. This patch (of 12): The linux/mm.h header includes <asm/pgtable.h> to allow inlining of the functions involving page table manipulations, e.g. pte_alloc() and pmd_alloc(). So, there is no point to explicitly include <asm/pgtable.h> in the files that include <linux/mm.h>. The include statements in such cases are remove with a simple loop: for f in $(git grep -l "include <linux/mm.h>") ; do sed -i -e '/include <asm\/pgtable.h>/ d' $f done Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: "David S. Miller" <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Ungerer <gerg@linux-m68k.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: Mark Salter <msalter@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Mike Rapoport <rppt@kernel.org> Cc: Nick Hu <nickhu@andestech.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vincent Chen <deanbo422@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Will Deacon <will@kernel.org> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200514170327.31389-1-rppt@kernel.org Link: http://lkml.kernel.org/r/20200514170327.31389-2-rppt@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
252 lines
6.6 KiB
C
252 lines
6.6 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* handle transition of Linux booting another kernel
|
|
* Copyright (C) 2002-2005 Eric Biederman <ebiederm@xmission.com>
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/kexec.h>
|
|
#include <linux/delay.h>
|
|
#include <linux/numa.h>
|
|
#include <linux/ftrace.h>
|
|
#include <linux/suspend.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/io.h>
|
|
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/mmu_context.h>
|
|
#include <asm/apic.h>
|
|
#include <asm/io_apic.h>
|
|
#include <asm/cpufeature.h>
|
|
#include <asm/desc.h>
|
|
#include <asm/set_memory.h>
|
|
#include <asm/debugreg.h>
|
|
|
|
static void set_gdt(void *newgdt, __u16 limit)
|
|
{
|
|
struct desc_ptr curgdt;
|
|
|
|
/* ia32 supports unaligned loads & stores */
|
|
curgdt.size = limit;
|
|
curgdt.address = (unsigned long)newgdt;
|
|
|
|
load_gdt(&curgdt);
|
|
}
|
|
|
|
static void load_segments(void)
|
|
{
|
|
#define __STR(X) #X
|
|
#define STR(X) __STR(X)
|
|
|
|
__asm__ __volatile__ (
|
|
"\tljmp $"STR(__KERNEL_CS)",$1f\n"
|
|
"\t1:\n"
|
|
"\tmovl $"STR(__KERNEL_DS)",%%eax\n"
|
|
"\tmovl %%eax,%%ds\n"
|
|
"\tmovl %%eax,%%es\n"
|
|
"\tmovl %%eax,%%ss\n"
|
|
: : : "eax", "memory");
|
|
#undef STR
|
|
#undef __STR
|
|
}
|
|
|
|
static void machine_kexec_free_page_tables(struct kimage *image)
|
|
{
|
|
free_pages((unsigned long)image->arch.pgd, PGD_ALLOCATION_ORDER);
|
|
image->arch.pgd = NULL;
|
|
#ifdef CONFIG_X86_PAE
|
|
free_page((unsigned long)image->arch.pmd0);
|
|
image->arch.pmd0 = NULL;
|
|
free_page((unsigned long)image->arch.pmd1);
|
|
image->arch.pmd1 = NULL;
|
|
#endif
|
|
free_page((unsigned long)image->arch.pte0);
|
|
image->arch.pte0 = NULL;
|
|
free_page((unsigned long)image->arch.pte1);
|
|
image->arch.pte1 = NULL;
|
|
}
|
|
|
|
static int machine_kexec_alloc_page_tables(struct kimage *image)
|
|
{
|
|
image->arch.pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
|
|
PGD_ALLOCATION_ORDER);
|
|
#ifdef CONFIG_X86_PAE
|
|
image->arch.pmd0 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
|
|
image->arch.pmd1 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
|
|
#endif
|
|
image->arch.pte0 = (pte_t *)get_zeroed_page(GFP_KERNEL);
|
|
image->arch.pte1 = (pte_t *)get_zeroed_page(GFP_KERNEL);
|
|
if (!image->arch.pgd ||
|
|
#ifdef CONFIG_X86_PAE
|
|
!image->arch.pmd0 || !image->arch.pmd1 ||
|
|
#endif
|
|
!image->arch.pte0 || !image->arch.pte1) {
|
|
return -ENOMEM;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static void machine_kexec_page_table_set_one(
|
|
pgd_t *pgd, pmd_t *pmd, pte_t *pte,
|
|
unsigned long vaddr, unsigned long paddr)
|
|
{
|
|
p4d_t *p4d;
|
|
pud_t *pud;
|
|
|
|
pgd += pgd_index(vaddr);
|
|
#ifdef CONFIG_X86_PAE
|
|
if (!(pgd_val(*pgd) & _PAGE_PRESENT))
|
|
set_pgd(pgd, __pgd(__pa(pmd) | _PAGE_PRESENT));
|
|
#endif
|
|
p4d = p4d_offset(pgd, vaddr);
|
|
pud = pud_offset(p4d, vaddr);
|
|
pmd = pmd_offset(pud, vaddr);
|
|
if (!(pmd_val(*pmd) & _PAGE_PRESENT))
|
|
set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE));
|
|
pte = pte_offset_kernel(pmd, vaddr);
|
|
set_pte(pte, pfn_pte(paddr >> PAGE_SHIFT, PAGE_KERNEL_EXEC));
|
|
}
|
|
|
|
static void machine_kexec_prepare_page_tables(struct kimage *image)
|
|
{
|
|
void *control_page;
|
|
pmd_t *pmd = NULL;
|
|
|
|
control_page = page_address(image->control_code_page);
|
|
#ifdef CONFIG_X86_PAE
|
|
pmd = image->arch.pmd0;
|
|
#endif
|
|
machine_kexec_page_table_set_one(
|
|
image->arch.pgd, pmd, image->arch.pte0,
|
|
(unsigned long)control_page, __pa(control_page));
|
|
#ifdef CONFIG_X86_PAE
|
|
pmd = image->arch.pmd1;
|
|
#endif
|
|
machine_kexec_page_table_set_one(
|
|
image->arch.pgd, pmd, image->arch.pte1,
|
|
__pa(control_page), __pa(control_page));
|
|
}
|
|
|
|
/*
|
|
* A architecture hook called to validate the
|
|
* proposed image and prepare the control pages
|
|
* as needed. The pages for KEXEC_CONTROL_PAGE_SIZE
|
|
* have been allocated, but the segments have yet
|
|
* been copied into the kernel.
|
|
*
|
|
* Do what every setup is needed on image and the
|
|
* reboot code buffer to allow us to avoid allocations
|
|
* later.
|
|
*
|
|
* - Make control page executable.
|
|
* - Allocate page tables
|
|
* - Setup page tables
|
|
*/
|
|
int machine_kexec_prepare(struct kimage *image)
|
|
{
|
|
int error;
|
|
|
|
set_memory_x((unsigned long)page_address(image->control_code_page), 1);
|
|
error = machine_kexec_alloc_page_tables(image);
|
|
if (error)
|
|
return error;
|
|
machine_kexec_prepare_page_tables(image);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Undo anything leftover by machine_kexec_prepare
|
|
* when an image is freed.
|
|
*/
|
|
void machine_kexec_cleanup(struct kimage *image)
|
|
{
|
|
set_memory_nx((unsigned long)page_address(image->control_code_page), 1);
|
|
machine_kexec_free_page_tables(image);
|
|
}
|
|
|
|
/*
|
|
* Do not allocate memory (or fail in any way) in machine_kexec().
|
|
* We are past the point of no return, committed to rebooting now.
|
|
*/
|
|
void machine_kexec(struct kimage *image)
|
|
{
|
|
unsigned long page_list[PAGES_NR];
|
|
void *control_page;
|
|
int save_ftrace_enabled;
|
|
asmlinkage unsigned long
|
|
(*relocate_kernel_ptr)(unsigned long indirection_page,
|
|
unsigned long control_page,
|
|
unsigned long start_address,
|
|
unsigned int has_pae,
|
|
unsigned int preserve_context);
|
|
|
|
#ifdef CONFIG_KEXEC_JUMP
|
|
if (image->preserve_context)
|
|
save_processor_state();
|
|
#endif
|
|
|
|
save_ftrace_enabled = __ftrace_enabled_save();
|
|
|
|
/* Interrupts aren't acceptable while we reboot */
|
|
local_irq_disable();
|
|
hw_breakpoint_disable();
|
|
|
|
if (image->preserve_context) {
|
|
#ifdef CONFIG_X86_IO_APIC
|
|
/*
|
|
* We need to put APICs in legacy mode so that we can
|
|
* get timer interrupts in second kernel. kexec/kdump
|
|
* paths already have calls to restore_boot_irq_mode()
|
|
* in one form or other. kexec jump path also need one.
|
|
*/
|
|
clear_IO_APIC();
|
|
restore_boot_irq_mode();
|
|
#endif
|
|
}
|
|
|
|
control_page = page_address(image->control_code_page);
|
|
memcpy(control_page, relocate_kernel, KEXEC_CONTROL_CODE_MAX_SIZE);
|
|
|
|
relocate_kernel_ptr = control_page;
|
|
page_list[PA_CONTROL_PAGE] = __pa(control_page);
|
|
page_list[VA_CONTROL_PAGE] = (unsigned long)control_page;
|
|
page_list[PA_PGD] = __pa(image->arch.pgd);
|
|
|
|
if (image->type == KEXEC_TYPE_DEFAULT)
|
|
page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page)
|
|
<< PAGE_SHIFT);
|
|
|
|
/*
|
|
* The segment registers are funny things, they have both a
|
|
* visible and an invisible part. Whenever the visible part is
|
|
* set to a specific selector, the invisible part is loaded
|
|
* with from a table in memory. At no other time is the
|
|
* descriptor table in memory accessed.
|
|
*
|
|
* I take advantage of this here by force loading the
|
|
* segments, before I zap the gdt with an invalid value.
|
|
*/
|
|
load_segments();
|
|
/*
|
|
* The gdt & idt are now invalid.
|
|
* If you want to load them you must set up your own idt & gdt.
|
|
*/
|
|
idt_invalidate(phys_to_virt(0));
|
|
set_gdt(phys_to_virt(0), 0);
|
|
|
|
/* now call it */
|
|
image->start = relocate_kernel_ptr((unsigned long)image->head,
|
|
(unsigned long)page_list,
|
|
image->start,
|
|
boot_cpu_has(X86_FEATURE_PAE),
|
|
image->preserve_context);
|
|
|
|
#ifdef CONFIG_KEXEC_JUMP
|
|
if (image->preserve_context)
|
|
restore_processor_state();
|
|
#endif
|
|
|
|
__ftrace_enabled_restore(save_ftrace_enabled);
|
|
}
|