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>
136 lines
3.5 KiB
C
136 lines
3.5 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
#include <linux/mm.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/sched/debug.h>
|
|
#include <linux/init_task.h>
|
|
#include <linux/fs.h>
|
|
|
|
#include <linux/uaccess.h>
|
|
#include <asm/processor.h>
|
|
#include <asm/desc.h>
|
|
#include <asm/traps.h>
|
|
|
|
extern void double_fault(void);
|
|
#define ptr_ok(x) ((x) > PAGE_OFFSET && (x) < PAGE_OFFSET + MAXMEM)
|
|
|
|
#define TSS(x) this_cpu_read(cpu_tss_rw.x86_tss.x)
|
|
|
|
static void set_df_gdt_entry(unsigned int cpu);
|
|
|
|
/*
|
|
* Called by double_fault with CR0.TS and EFLAGS.NT cleared. The CPU thinks
|
|
* we're running the doublefault task. Cannot return.
|
|
*/
|
|
asmlinkage notrace void __noreturn doublefault_shim(void)
|
|
{
|
|
unsigned long cr2;
|
|
struct pt_regs regs;
|
|
|
|
BUILD_BUG_ON(sizeof(struct doublefault_stack) != PAGE_SIZE);
|
|
|
|
cr2 = native_read_cr2();
|
|
|
|
/* Reset back to the normal kernel task. */
|
|
force_reload_TR();
|
|
set_df_gdt_entry(smp_processor_id());
|
|
|
|
trace_hardirqs_off();
|
|
|
|
/*
|
|
* Fill in pt_regs. A downside of doing this in C is that the unwinder
|
|
* won't see it (no ENCODE_FRAME_POINTER), so a nested stack dump
|
|
* won't successfully unwind to the source of the double fault.
|
|
* The main dump from do_double_fault() is fine, though, since it
|
|
* uses these regs directly.
|
|
*
|
|
* If anyone ever cares, this could be moved to asm.
|
|
*/
|
|
regs.ss = TSS(ss);
|
|
regs.__ssh = 0;
|
|
regs.sp = TSS(sp);
|
|
regs.flags = TSS(flags);
|
|
regs.cs = TSS(cs);
|
|
/* We won't go through the entry asm, so we can leave __csh as 0. */
|
|
regs.__csh = 0;
|
|
regs.ip = TSS(ip);
|
|
regs.orig_ax = 0;
|
|
regs.gs = TSS(gs);
|
|
regs.__gsh = 0;
|
|
regs.fs = TSS(fs);
|
|
regs.__fsh = 0;
|
|
regs.es = TSS(es);
|
|
regs.__esh = 0;
|
|
regs.ds = TSS(ds);
|
|
regs.__dsh = 0;
|
|
regs.ax = TSS(ax);
|
|
regs.bp = TSS(bp);
|
|
regs.di = TSS(di);
|
|
regs.si = TSS(si);
|
|
regs.dx = TSS(dx);
|
|
regs.cx = TSS(cx);
|
|
regs.bx = TSS(bx);
|
|
|
|
do_double_fault(®s, 0, cr2);
|
|
|
|
/*
|
|
* x86_32 does not save the original CR3 anywhere on a task switch.
|
|
* This means that, even if we wanted to return, we would need to find
|
|
* some way to reconstruct CR3. We could make a credible guess based
|
|
* on cpu_tlbstate, but that would be racy and would not account for
|
|
* PTI.
|
|
*
|
|
* Instead, don't bother. We can return through
|
|
* rewind_stack_do_exit() instead.
|
|
*/
|
|
panic("cannot return from double fault\n");
|
|
}
|
|
NOKPROBE_SYMBOL(doublefault_shim);
|
|
|
|
DEFINE_PER_CPU_PAGE_ALIGNED(struct doublefault_stack, doublefault_stack) = {
|
|
.tss = {
|
|
/*
|
|
* No sp0 or ss0 -- we never run CPL != 0 with this TSS
|
|
* active. sp is filled in later.
|
|
*/
|
|
.ldt = 0,
|
|
.io_bitmap_base = IO_BITMAP_OFFSET_INVALID,
|
|
|
|
.ip = (unsigned long) double_fault,
|
|
.flags = X86_EFLAGS_FIXED,
|
|
.es = __USER_DS,
|
|
.cs = __KERNEL_CS,
|
|
.ss = __KERNEL_DS,
|
|
.ds = __USER_DS,
|
|
.fs = __KERNEL_PERCPU,
|
|
#ifndef CONFIG_X86_32_LAZY_GS
|
|
.gs = __KERNEL_STACK_CANARY,
|
|
#endif
|
|
|
|
.__cr3 = __pa_nodebug(swapper_pg_dir),
|
|
},
|
|
};
|
|
|
|
static void set_df_gdt_entry(unsigned int cpu)
|
|
{
|
|
/* Set up doublefault TSS pointer in the GDT */
|
|
__set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS,
|
|
&get_cpu_entry_area(cpu)->doublefault_stack.tss);
|
|
|
|
}
|
|
|
|
void doublefault_init_cpu_tss(void)
|
|
{
|
|
unsigned int cpu = smp_processor_id();
|
|
struct cpu_entry_area *cea = get_cpu_entry_area(cpu);
|
|
|
|
/*
|
|
* The linker isn't smart enough to initialize percpu variables that
|
|
* point to other places in percpu space.
|
|
*/
|
|
this_cpu_write(doublefault_stack.tss.sp,
|
|
(unsigned long)&cea->doublefault_stack.stack +
|
|
sizeof(doublefault_stack.stack));
|
|
|
|
set_df_gdt_entry(cpu);
|
|
}
|