OpenCloudOS-Kernel/arch/alpha/mm/fault.c

242 lines
5.9 KiB
C
Raw Normal View History

/*
* linux/arch/alpha/mm/fault.c
*
* Copyright (C) 1995 Linus Torvalds
*/
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <asm/io.h>
#define __EXTERN_INLINE inline
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>
#undef __EXTERN_INLINE
#include <linux/signal.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/smp.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <asm/system.h>
#include <asm/uaccess.h>
extern void die_if_kernel(char *,struct pt_regs *,long, unsigned long *);
/*
* Force a new ASN for a task.
*/
#ifndef CONFIG_SMP
unsigned long last_asn = ASN_FIRST_VERSION;
#endif
void
__load_new_mm_context(struct mm_struct *next_mm)
{
unsigned long mmc;
struct pcb_struct *pcb;
mmc = __get_new_mm_context(next_mm, smp_processor_id());
next_mm->context[smp_processor_id()] = mmc;
pcb = &current_thread_info()->pcb;
pcb->asn = mmc & HARDWARE_ASN_MASK;
pcb->ptbr = ((unsigned long) next_mm->pgd - IDENT_ADDR) >> PAGE_SHIFT;
__reload_thread(pcb);
}
/*
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to handle_mm_fault().
*
* mmcsr:
* 0 = translation not valid
* 1 = access violation
* 2 = fault-on-read
* 3 = fault-on-execute
* 4 = fault-on-write
*
* cause:
* -1 = instruction fetch
* 0 = load
* 1 = store
*
* Registers $9 through $15 are saved in a block just prior to `regs' and
* are saved and restored around the call to allow exception code to
* modify them.
*/
/* Macro for exception fixup code to access integer registers. */
#define dpf_reg(r) \
(((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-16 : \
(r) <= 18 ? (r)+8 : (r)-10])
asmlinkage void
do_page_fault(unsigned long address, unsigned long mmcsr,
long cause, struct pt_regs *regs)
{
struct vm_area_struct * vma;
struct mm_struct *mm = current->mm;
const struct exception_table_entry *fixup;
int fault, si_code = SEGV_MAPERR;
siginfo_t info;
/* As of EV6, a load into $31/$f31 is a prefetch, and never faults
(or is suppressed by the PALcode). Support that for older CPUs
by ignoring such an instruction. */
if (cause == 0) {
unsigned int insn;
__get_user(insn, (unsigned int __user *)regs->pc);
if ((insn >> 21 & 0x1f) == 0x1f &&
/* ldq ldl ldt lds ldg ldf ldwu ldbu */
(1ul << (insn >> 26) & 0x30f00001400ul)) {
regs->pc += 4;
return;
}
}
/* If we're in an interrupt context, or have no user context,
we must not take the fault. */
if (!mm || in_atomic())
goto no_context;
#ifdef CONFIG_ALPHA_LARGE_VMALLOC
if (address >= TASK_SIZE)
goto vmalloc_fault;
#endif
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
if (!vma)
goto bad_area;
if (vma->vm_start <= address)
goto good_area;
if (!(vma->vm_flags & VM_GROWSDOWN))
goto bad_area;
if (expand_stack(vma, address))
goto bad_area;
/* Ok, we have a good vm_area for this memory access, so
we can handle it. */
good_area:
si_code = SEGV_ACCERR;
if (cause < 0) {
if (!(vma->vm_flags & VM_EXEC))
goto bad_area;
} else if (!cause) {
/* Allow reads even for write-only mappings */
if (!(vma->vm_flags & (VM_READ | VM_WRITE)))
goto bad_area;
} else {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
}
survive:
/* 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(mm, vma, address, cause > 0 ? FAULT_FLAG_WRITE : 0);
up_read(&mm->mmap_sem);
mm: fault feedback #2 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>
2007-07-19 16:47:05 +08:00
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
}
mm: fault feedback #2 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>
2007-07-19 16:47:05 +08:00
if (fault & VM_FAULT_MAJOR)
current->maj_flt++;
else
current->min_flt++;
return;
/* Something tried to access memory that isn't in our memory map.
Fix it, but check if it's kernel or user first. */
bad_area:
up_read(&mm->mmap_sem);
if (user_mode(regs))
goto do_sigsegv;
no_context:
/* Are we prepared to handle this fault as an exception? */
if ((fixup = search_exception_tables(regs->pc)) != 0) {
unsigned long newpc;
newpc = fixup_exception(dpf_reg, fixup, regs->pc);
regs->pc = newpc;
return;
}
/* Oops. The kernel tried to access some bad page. We'll have to
terminate things with extreme prejudice. */
printk(KERN_ALERT "Unable to handle kernel paging request at "
"virtual address %016lx\n", address);
die_if_kernel("Oops", regs, cause, (unsigned long*)regs - 16);
do_exit(SIGKILL);
/* 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:
pid namespaces: define is_global_init() and is_container_init() is_init() is an ambiguous name for the pid==1 check. Split it into is_global_init() and is_container_init(). A cgroup init has it's tsk->pid == 1. A global init also has it's tsk->pid == 1 and it's active pid namespace is the init_pid_ns. But rather than check the active pid namespace, compare the task structure with 'init_pid_ns.child_reaper', which is initialized during boot to the /sbin/init process and never changes. Changelog: 2.6.22-rc4-mm2-pidns1: - Use 'init_pid_ns.child_reaper' to determine if a given task is the global init (/sbin/init) process. This would improve performance and remove dependence on the task_pid(). 2.6.21-mm2-pidns2: - [Sukadev Bhattiprolu] Changed is_container_init() calls in {powerpc, ppc,avr32}/traps.c for the _exception() call to is_global_init(). This way, we kill only the cgroup if the cgroup's init has a bug rather than force a kernel panic. [akpm@linux-foundation.org: fix comment] [sukadev@us.ibm.com: Use is_global_init() in arch/m32r/mm/fault.c] [bunk@stusta.de: kernel/pid.c: remove unused exports] [sukadev@us.ibm.com: Fix capability.c to work with threaded init] Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Signed-off-by: Sukadev Bhattiprolu <sukadev@us.ibm.com> Acked-by: Pavel Emelianov <xemul@openvz.org> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Cc: Dave Hansen <haveblue@us.ibm.com> Cc: Herbert Poetzel <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-19 14:39:52 +08:00
if (is_global_init(current)) {
yield();
down_read(&mm->mmap_sem);
goto survive;
}
printk(KERN_ALERT "VM: killing process %s(%d)\n",
current->comm, task_pid_nr(current));
if (!user_mode(regs))
goto no_context;
During VM oom condition, kill all threads in process group We have had complaints where a threaded application is left in a bad state after one of it's threads is killed when we hit a VM: out_of_memory condition. Killing just one of the process threads can leave the application in a bad state, whereas killing the entire process group would allow for the application to restart, or be otherwise handled, and makes it very obvious that something has gone wrong. This change allows the entire process group to be taken down, rather than just the one thread. Signed-off-by: Will Schmidt <will_schmidt@vnet.ibm.com> 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: Haavard Skinnemoen <hskinnemoen@atmel.com> Cc: Mikael Starvik <starvik@axis.com> Cc: David Howells <dhowells@redhat.com> Cc: Andi Kleen <ak@suse.de> 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: Ralf Baechle <ralf@linux-mips.org> Cc: Kyle McMartin <kyle@mcmartin.ca> 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: Chris Zankel <chris@zankel.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-16 16:24:18 +08:00
do_group_exit(SIGKILL);
do_sigbus:
/* Send a sigbus, regardless of whether we were in kernel
or user mode. */
info.si_signo = SIGBUS;
info.si_errno = 0;
info.si_code = BUS_ADRERR;
info.si_addr = (void __user *) address;
force_sig_info(SIGBUS, &info, current);
if (!user_mode(regs))
goto no_context;
return;
do_sigsegv:
info.si_signo = SIGSEGV;
info.si_errno = 0;
info.si_code = si_code;
info.si_addr = (void __user *) address;
force_sig_info(SIGSEGV, &info, current);
return;
#ifdef CONFIG_ALPHA_LARGE_VMALLOC
vmalloc_fault:
if (user_mode(regs))
goto do_sigsegv;
else {
/* Synchronize this task's top level page-table
with the "reference" page table from init. */
long index = pgd_index(address);
pgd_t *pgd, *pgd_k;
pgd = current->active_mm->pgd + index;
pgd_k = swapper_pg_dir + index;
if (!pgd_present(*pgd) && pgd_present(*pgd_k)) {
pgd_val(*pgd) = pgd_val(*pgd_k);
return;
}
goto no_context;
}
#endif
}