![Nick Piggin](/assets/img/avatar_default.png)
This patch completes Linus's wish that the fault return codes be made into bit flags, which I agree makes everything nicer. This requires requires all handle_mm_fault callers to be modified (possibly the modifications should go further and do things like fault accounting in handle_mm_fault -- however that would be for another patch). [akpm@linux-foundation.org: fix alpha build] [akpm@linux-foundation.org: fix s390 build] [akpm@linux-foundation.org: fix sparc build] [akpm@linux-foundation.org: fix sparc64 build] [akpm@linux-foundation.org: fix ia64 build] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Richard Henderson <rth@twiddle.net> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Ian Molton <spyro@f2s.com> Cc: Bryan Wu <bryan.wu@analog.com> Cc: Mikael Starvik <starvik@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Greg Ungerer <gerg@uclinux.org> Cc: Matthew Wilcox <willy@debian.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Richard Curnow <rc@rc0.org.uk> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Jeff Dike <jdike@addtoit.com> Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it> Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp> Cc: Chris Zankel <chris@zankel.net> Acked-by: Kyle McMartin <kyle@mcmartin.ca> Acked-by: Haavard Skinnemoen <hskinnemoen@atmel.com> Acked-by: Ralf Baechle <ralf@linux-mips.org> Acked-by: Andi Kleen <ak@muc.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> [ Still apparently needs some ARM and PPC loving - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
266 lines
6.3 KiB
C
266 lines
6.3 KiB
C
/*
|
|
* Copyright (C) 2000, 2001 Jeff Dike (jdike@karaya.com)
|
|
* Licensed under the GPL
|
|
*/
|
|
|
|
#include "linux/kernel.h"
|
|
#include "asm/errno.h"
|
|
#include "linux/sched.h"
|
|
#include "linux/mm.h"
|
|
#include "linux/spinlock.h"
|
|
#include "linux/init.h"
|
|
#include "linux/ptrace.h"
|
|
#include "asm/semaphore.h"
|
|
#include "asm/pgtable.h"
|
|
#include "asm/pgalloc.h"
|
|
#include "asm/tlbflush.h"
|
|
#include "asm/a.out.h"
|
|
#include "asm/current.h"
|
|
#include "asm/irq.h"
|
|
#include "sysdep/sigcontext.h"
|
|
#include "kern_util.h"
|
|
#include "as-layout.h"
|
|
#include "arch.h"
|
|
#include "kern.h"
|
|
#include "chan_kern.h"
|
|
#include "mconsole_kern.h"
|
|
#include "mem.h"
|
|
#include "mem_kern.h"
|
|
#include "sysdep/sigcontext.h"
|
|
#include "sysdep/ptrace.h"
|
|
#include "os.h"
|
|
#ifdef CONFIG_MODE_SKAS
|
|
#include "skas.h"
|
|
#endif
|
|
#include "os.h"
|
|
|
|
/* Note this is constrained to return 0, -EFAULT, -EACCESS, -ENOMEM by segv(). */
|
|
int handle_page_fault(unsigned long address, unsigned long ip,
|
|
int is_write, int is_user, int *code_out)
|
|
{
|
|
struct mm_struct *mm = current->mm;
|
|
struct vm_area_struct *vma;
|
|
pgd_t *pgd;
|
|
pud_t *pud;
|
|
pmd_t *pmd;
|
|
pte_t *pte;
|
|
int err = -EFAULT;
|
|
|
|
*code_out = SEGV_MAPERR;
|
|
|
|
/* If the fault was during atomic operation, don't take the fault, just
|
|
* fail. */
|
|
if (in_atomic())
|
|
goto out_nosemaphore;
|
|
|
|
down_read(&mm->mmap_sem);
|
|
vma = find_vma(mm, address);
|
|
if(!vma)
|
|
goto out;
|
|
else if(vma->vm_start <= address)
|
|
goto good_area;
|
|
else if(!(vma->vm_flags & VM_GROWSDOWN))
|
|
goto out;
|
|
else if(is_user && !ARCH_IS_STACKGROW(address))
|
|
goto out;
|
|
else if(expand_stack(vma, address))
|
|
goto out;
|
|
|
|
good_area:
|
|
*code_out = SEGV_ACCERR;
|
|
if(is_write && !(vma->vm_flags & VM_WRITE))
|
|
goto out;
|
|
|
|
/* Don't require VM_READ|VM_EXEC for write faults! */
|
|
if(!is_write && !(vma->vm_flags & (VM_READ | VM_EXEC)))
|
|
goto out;
|
|
|
|
do {
|
|
int fault;
|
|
survive:
|
|
fault = handle_mm_fault(mm, vma, address, is_write);
|
|
if (unlikely(fault & VM_FAULT_ERROR)) {
|
|
if (fault & VM_FAULT_OOM) {
|
|
err = -ENOMEM;
|
|
goto out_of_memory;
|
|
} else if (fault & VM_FAULT_SIGBUS) {
|
|
err = -EACCES;
|
|
goto out;
|
|
}
|
|
BUG();
|
|
}
|
|
if (fault & VM_FAULT_MAJOR)
|
|
current->maj_flt++;
|
|
else
|
|
current->min_flt++;
|
|
|
|
pgd = pgd_offset(mm, address);
|
|
pud = pud_offset(pgd, address);
|
|
pmd = pmd_offset(pud, address);
|
|
pte = pte_offset_kernel(pmd, address);
|
|
} while(!pte_present(*pte));
|
|
err = 0;
|
|
/* The below warning was added in place of
|
|
* pte_mkyoung(); if (is_write) pte_mkdirty();
|
|
* If it's triggered, we'd see normally a hang here (a clean pte is
|
|
* marked read-only to emulate the dirty bit).
|
|
* However, the generic code can mark a PTE writable but clean on a
|
|
* concurrent read fault, triggering this harmlessly. So comment it out.
|
|
*/
|
|
#if 0
|
|
WARN_ON(!pte_young(*pte) || (is_write && !pte_dirty(*pte)));
|
|
#endif
|
|
flush_tlb_page(vma, address);
|
|
out:
|
|
up_read(&mm->mmap_sem);
|
|
out_nosemaphore:
|
|
return(err);
|
|
|
|
/*
|
|
* 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:
|
|
if (is_init(current)) {
|
|
up_read(&mm->mmap_sem);
|
|
yield();
|
|
down_read(&mm->mmap_sem);
|
|
goto survive;
|
|
}
|
|
goto out;
|
|
}
|
|
|
|
static void bad_segv(struct faultinfo fi, unsigned long ip)
|
|
{
|
|
struct siginfo si;
|
|
|
|
si.si_signo = SIGSEGV;
|
|
si.si_code = SEGV_ACCERR;
|
|
si.si_addr = (void __user *) FAULT_ADDRESS(fi);
|
|
current->thread.arch.faultinfo = fi;
|
|
force_sig_info(SIGSEGV, &si, current);
|
|
}
|
|
|
|
static void segv_handler(int sig, union uml_pt_regs *regs)
|
|
{
|
|
struct faultinfo * fi = UPT_FAULTINFO(regs);
|
|
|
|
if(UPT_IS_USER(regs) && !SEGV_IS_FIXABLE(fi)){
|
|
bad_segv(*fi, UPT_IP(regs));
|
|
return;
|
|
}
|
|
segv(*fi, UPT_IP(regs), UPT_IS_USER(regs), regs);
|
|
}
|
|
|
|
/*
|
|
* We give a *copy* of the faultinfo in the regs to segv.
|
|
* This must be done, since nesting SEGVs could overwrite
|
|
* the info in the regs. A pointer to the info then would
|
|
* give us bad data!
|
|
*/
|
|
unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
|
|
union uml_pt_regs *regs)
|
|
{
|
|
struct siginfo si;
|
|
void *catcher;
|
|
int err;
|
|
int is_write = FAULT_WRITE(fi);
|
|
unsigned long address = FAULT_ADDRESS(fi);
|
|
|
|
if(!is_user && (address >= start_vm) && (address < end_vm)){
|
|
flush_tlb_kernel_vm();
|
|
return 0;
|
|
}
|
|
else if(current->mm == NULL) {
|
|
show_regs(container_of(regs, struct pt_regs, regs));
|
|
panic("Segfault with no mm");
|
|
}
|
|
|
|
if (SEGV_IS_FIXABLE(&fi) || SEGV_MAYBE_FIXABLE(&fi))
|
|
err = handle_page_fault(address, ip, is_write, is_user, &si.si_code);
|
|
else {
|
|
err = -EFAULT;
|
|
/* A thread accessed NULL, we get a fault, but CR2 is invalid.
|
|
* This code is used in __do_copy_from_user() of TT mode. */
|
|
address = 0;
|
|
}
|
|
|
|
catcher = current->thread.fault_catcher;
|
|
if(!err)
|
|
return 0;
|
|
else if(catcher != NULL){
|
|
current->thread.fault_addr = (void *) address;
|
|
do_longjmp(catcher, 1);
|
|
}
|
|
else if(current->thread.fault_addr != NULL)
|
|
panic("fault_addr set but no fault catcher");
|
|
else if(!is_user && arch_fixup(ip, regs))
|
|
return 0;
|
|
|
|
if(!is_user) {
|
|
show_regs(container_of(regs, struct pt_regs, regs));
|
|
panic("Kernel mode fault at addr 0x%lx, ip 0x%lx",
|
|
address, ip);
|
|
}
|
|
|
|
if (err == -EACCES) {
|
|
si.si_signo = SIGBUS;
|
|
si.si_errno = 0;
|
|
si.si_code = BUS_ADRERR;
|
|
si.si_addr = (void __user *)address;
|
|
current->thread.arch.faultinfo = fi;
|
|
force_sig_info(SIGBUS, &si, current);
|
|
} else if (err == -ENOMEM) {
|
|
printk("VM: killing process %s\n", current->comm);
|
|
do_exit(SIGKILL);
|
|
} else {
|
|
BUG_ON(err != -EFAULT);
|
|
si.si_signo = SIGSEGV;
|
|
si.si_addr = (void __user *) address;
|
|
current->thread.arch.faultinfo = fi;
|
|
force_sig_info(SIGSEGV, &si, current);
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
void relay_signal(int sig, union uml_pt_regs *regs)
|
|
{
|
|
if(arch_handle_signal(sig, regs))
|
|
return;
|
|
|
|
if(!UPT_IS_USER(regs)){
|
|
if(sig == SIGBUS)
|
|
printk("Bus error - the host /dev/shm or /tmp mount "
|
|
"likely just ran out of space\n");
|
|
panic("Kernel mode signal %d", sig);
|
|
}
|
|
|
|
current->thread.arch.faultinfo = *UPT_FAULTINFO(regs);
|
|
force_sig(sig, current);
|
|
}
|
|
|
|
static void bus_handler(int sig, union uml_pt_regs *regs)
|
|
{
|
|
if(current->thread.fault_catcher != NULL)
|
|
do_longjmp(current->thread.fault_catcher, 1);
|
|
else relay_signal(sig, regs);
|
|
}
|
|
|
|
static void winch(int sig, union uml_pt_regs *regs)
|
|
{
|
|
do_IRQ(WINCH_IRQ, regs);
|
|
}
|
|
|
|
const struct kern_handlers handlinfo_kern = {
|
|
.relay_signal = relay_signal,
|
|
.winch = winch,
|
|
.bus_handler = bus_handler,
|
|
.page_fault = segv_handler,
|
|
.sigio_handler = sigio_handler,
|
|
.timer_handler = timer_handler
|
|
};
|
|
|
|
void trap_init(void)
|
|
{
|
|
}
|