linux_dsm_epyc7002/arch/microblaze/mm/fault.c
Mike Rapoport e31cf2f4ca mm: don't include asm/pgtable.h if linux/mm.h is already included
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>
2020-06-09 09:39:13 -07:00

295 lines
7.7 KiB
C

/*
* arch/microblaze/mm/fault.c
*
* Copyright (C) 2007 Xilinx, Inc. All rights reserved.
*
* Derived from "arch/ppc/mm/fault.c"
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
*
* Derived from "arch/i386/mm/fault.c"
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
*
* Modified by Cort Dougan and Paul Mackerras.
*
* This file is subject to the terms and conditions of the GNU General
* Public License. See the file COPYING in the main directory of this
* archive for more details.
*
*/
#include <linux/extable.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <asm/page.h>
#include <asm/mmu.h>
#include <linux/mmu_context.h>
#include <linux/uaccess.h>
#include <asm/exceptions.h>
static unsigned long pte_misses; /* updated by do_page_fault() */
static unsigned long pte_errors; /* updated by do_page_fault() */
/*
* Check whether the instruction at regs->pc is a store using
* an update addressing form which will update r1.
*/
static int store_updates_sp(struct pt_regs *regs)
{
unsigned int inst;
if (get_user(inst, (unsigned int __user *)regs->pc))
return 0;
/* check for 1 in the rD field */
if (((inst >> 21) & 0x1f) != 1)
return 0;
/* check for store opcodes */
if ((inst & 0xd0000000) == 0xd0000000)
return 1;
return 0;
}
/*
* bad_page_fault is called when we have a bad access from the kernel.
* It is called from do_page_fault above and from some of the procedures
* in traps.c.
*/
void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
{
const struct exception_table_entry *fixup;
/* MS: no context */
/* Are we prepared to handle this fault? */
fixup = search_exception_tables(regs->pc);
if (fixup) {
regs->pc = fixup->fixup;
return;
}
/* kernel has accessed a bad area */
die("kernel access of bad area", regs, sig);
}
/*
* The error_code parameter is ESR for a data fault,
* 0 for an instruction fault.
*/
void do_page_fault(struct pt_regs *regs, unsigned long address,
unsigned long error_code)
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
int code = SEGV_MAPERR;
int is_write = error_code & ESR_S;
vm_fault_t fault;
unsigned int flags = FAULT_FLAG_DEFAULT;
regs->ear = address;
regs->esr = error_code;
/* On a kernel SLB miss we can only check for a valid exception entry */
if (unlikely(kernel_mode(regs) && (address >= TASK_SIZE))) {
pr_warn("kernel task_size exceed");
_exception(SIGSEGV, regs, code, address);
}
/* for instr TLB miss and instr storage exception ESR_S is undefined */
if ((error_code & 0x13) == 0x13 || (error_code & 0x11) == 0x11)
is_write = 0;
if (unlikely(faulthandler_disabled() || !mm)) {
if (kernel_mode(regs))
goto bad_area_nosemaphore;
/* faulthandler_disabled() in user mode is really bad,
as is current->mm == NULL. */
pr_emerg("Page fault in user mode with faulthandler_disabled(), mm = %p\n",
mm);
pr_emerg("r15 = %lx MSR = %lx\n",
regs->r15, regs->msr);
die("Weird page fault", regs, SIGSEGV);
}
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
/* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in the
* kernel and should generate an OOPS. Unfortunately, in the case of an
* erroneous fault occurring in a code path which already holds mmap_sem
* we will deadlock attempting to validate the fault against the
* address space. Luckily the kernel only validly references user
* space from well defined areas of code, which are listed in the
* exceptions table.
*
* As the vast majority of faults will be valid we will only perform
* the source reference check when there is a possibility of a deadlock.
* Attempt to lock the address space, if we cannot we then validate the
* source. If this is invalid we can skip the address space check,
* thus avoiding the deadlock.
*/
if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
if (kernel_mode(regs) && !search_exception_tables(regs->pc))
goto bad_area_nosemaphore;
retry:
down_read(&mm->mmap_sem);
}
vma = find_vma(mm, address);
if (unlikely(!vma))
goto bad_area;
if (vma->vm_start <= address)
goto good_area;
if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
goto bad_area;
if (unlikely(!is_write))
goto bad_area;
/*
* N.B. The ABI allows programs to access up to
* a few hundred bytes below the stack pointer (TBD).
* The kernel signal delivery code writes up to about 1.5kB
* below the stack pointer (r1) before decrementing it.
* The exec code can write slightly over 640kB to the stack
* before setting the user r1. Thus we allow the stack to
* expand to 1MB without further checks.
*/
if (unlikely(address + 0x100000 < vma->vm_end)) {
/* get user regs even if this fault is in kernel mode */
struct pt_regs *uregs = current->thread.regs;
if (uregs == NULL)
goto bad_area;
/*
* A user-mode access to an address a long way below
* the stack pointer is only valid if the instruction
* is one which would update the stack pointer to the
* address accessed if the instruction completed,
* i.e. either stwu rs,n(r1) or stwux rs,r1,rb
* (or the byte, halfword, float or double forms).
*
* If we don't check this then any write to the area
* between the last mapped region and the stack will
* expand the stack rather than segfaulting.
*/
if (address + 2048 < uregs->r1
&& (kernel_mode(regs) || !store_updates_sp(regs)))
goto bad_area;
}
if (expand_stack(vma, address))
goto bad_area;
good_area:
code = SEGV_ACCERR;
/* a write */
if (unlikely(is_write)) {
if (unlikely(!(vma->vm_flags & VM_WRITE)))
goto bad_area;
flags |= FAULT_FLAG_WRITE;
/* a read */
} else {
/* protection fault */
if (unlikely(error_code & 0x08000000))
goto bad_area;
if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC))))
goto bad_area;
}
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
fault = handle_mm_fault(vma, address, flags);
if (fault_signal_pending(fault, regs))
return;
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
}
if (flags & FAULT_FLAG_ALLOW_RETRY) {
if (unlikely(fault & VM_FAULT_MAJOR))
current->maj_flt++;
else
current->min_flt++;
if (fault & VM_FAULT_RETRY) {
flags |= FAULT_FLAG_TRIED;
/*
* No need to up_read(&mm->mmap_sem) as we would
* have already released it in __lock_page_or_retry
* in mm/filemap.c.
*/
goto retry;
}
}
up_read(&mm->mmap_sem);
/*
* keep track of tlb+htab misses that are good addrs but
* just need pte's created via handle_mm_fault()
* -- Cort
*/
pte_misses++;
return;
bad_area:
up_read(&mm->mmap_sem);
bad_area_nosemaphore:
pte_errors++;
/* User mode accesses cause a SIGSEGV */
if (user_mode(regs)) {
_exception(SIGSEGV, regs, code, address);
return;
}
bad_page_fault(regs, address, SIGSEGV);
return;
/*
* We ran out of memory, or some other thing happened to us that made
* us unable to handle the page fault gracefully.
*/
out_of_memory:
up_read(&mm->mmap_sem);
if (!user_mode(regs))
bad_page_fault(regs, address, SIGKILL);
else
pagefault_out_of_memory();
return;
do_sigbus:
up_read(&mm->mmap_sem);
if (user_mode(regs)) {
force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address);
return;
}
bad_page_fault(regs, address, SIGBUS);
}