linux/arch/ia64/mm/fault.c

287 lines
7.3 KiB
C
Raw Normal View History

/*
* MMU fault handling support.
*
* Copyright (C) 1998-2002 Hewlett-Packard Co
* David Mosberger-Tang <davidm@hpl.hp.com>
*/
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/kprobes.h>
#include <linux/kdebug.h>
#include <asm/pgtable.h>
#include <asm/processor.h>
#include <asm/system.h>
#include <asm/uaccess.h>
extern void die (char *, struct pt_regs *, long);
#ifdef CONFIG_KPROBES
static inline int notify_page_fault(struct pt_regs *regs, int trap)
{
int ret = 0;
if (!user_mode(regs)) {
/* kprobe_running() needs smp_processor_id() */
preempt_disable();
if (kprobe_running() && kprobes_fault_handler(regs, trap))
ret = 1;
preempt_enable();
}
return ret;
}
#else
static inline int notify_page_fault(struct pt_regs *regs, int trap)
{
return 0;
}
#endif
/*
* Return TRUE if ADDRESS points at a page in the kernel's mapped segment
* (inside region 5, on ia64) and that page is present.
*/
static int
mapped_kernel_page_is_present (unsigned long address)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *ptep, pte;
pgd = pgd_offset_k(address);
if (pgd_none(*pgd) || pgd_bad(*pgd))
return 0;
pud = pud_offset(pgd, address);
if (pud_none(*pud) || pud_bad(*pud))
return 0;
pmd = pmd_offset(pud, address);
if (pmd_none(*pmd) || pmd_bad(*pmd))
return 0;
ptep = pte_offset_kernel(pmd, address);
if (!ptep)
return 0;
pte = *ptep;
return pte_present(pte);
}
void __kprobes
ia64_do_page_fault (unsigned long address, unsigned long isr, struct pt_regs *regs)
{
int signal = SIGSEGV, code = SEGV_MAPERR;
struct vm_area_struct *vma, *prev_vma;
struct mm_struct *mm = current->mm;
struct siginfo si;
unsigned long mask;
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
int fault;
/* mmap_sem is performance critical.... */
prefetchw(&mm->mmap_sem);
/*
* If we're in an interrupt or have no user context, we must not take the fault..
*/
if (in_atomic() || !mm)
goto no_context;
#ifdef CONFIG_VIRTUAL_MEM_MAP
/*
* If fault is in region 5 and we are in the kernel, we may already
* have the mmap_sem (pfn_valid macro is called during mmap). There
* is no vma for region 5 addr's anyway, so skip getting the semaphore
* and go directly to the exception handling code.
*/
if ((REGION_NUMBER(address) == 5) && !user_mode(regs))
goto bad_area_no_up;
#endif
[PATCH] Kprobes/IA64: kdebug die notification mechanism As many of you know that kprobes exist in the main line kernel for various architecture including i386, x86_64, ppc64 and sparc64. Attached patches following this mail are a port of Kprobes and Jprobes for IA64. I have tesed this patches for kprobes and Jprobes and this seems to work fine. I have tested this patch by inserting kprobes on various slots and various templates including various types of branch instructions. I have also tested this patch using the tool http://marc.theaimsgroup.com/?l=linux-kernel&m=111657358022586&w=2 and the kprobes for IA64 works great. Here is list of TODO things and pathes for the same will appear soon. 1) Support kprobes on "mov r1=ip" type of instruction 2) Support Kprobes and Jprobes to exist on the same address 3) Support Return probes 3) Architecture independent cleanup of kprobes This patch adds the kdebug die notification mechanism needed by Kprobes. For break instruction on Branch type slot, imm21 is ignored and value zero is placed in IIM register, hence we need to handle kprobes for switch case zero. Signed-off-by: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> Signed-off-by: Rusty Lynch <Rusty.lynch@intel.com> From: Rusty Lynch <rusty.lynch@intel.com> At the point in traps.c where we recieve a break with a zero value, we can not say if the break was a result of a kprobe or some other debug facility. This simple patch changes the informational string to a more correct "break 0" value, and applies to the 2.6.12-rc2-mm2 tree with all the kprobes patches that were just recently included for the next mm cut. Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:09:27 +08:00
/*
* This is to handle the kprobes on user space access instructions
*/
if (notify_page_fault(regs, TRAP_BRKPT))
[PATCH] Kprobes/IA64: kdebug die notification mechanism As many of you know that kprobes exist in the main line kernel for various architecture including i386, x86_64, ppc64 and sparc64. Attached patches following this mail are a port of Kprobes and Jprobes for IA64. I have tesed this patches for kprobes and Jprobes and this seems to work fine. I have tested this patch by inserting kprobes on various slots and various templates including various types of branch instructions. I have also tested this patch using the tool http://marc.theaimsgroup.com/?l=linux-kernel&m=111657358022586&w=2 and the kprobes for IA64 works great. Here is list of TODO things and pathes for the same will appear soon. 1) Support kprobes on "mov r1=ip" type of instruction 2) Support Kprobes and Jprobes to exist on the same address 3) Support Return probes 3) Architecture independent cleanup of kprobes This patch adds the kdebug die notification mechanism needed by Kprobes. For break instruction on Branch type slot, imm21 is ignored and value zero is placed in IIM register, hence we need to handle kprobes for switch case zero. Signed-off-by: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com> Signed-off-by: Rusty Lynch <Rusty.lynch@intel.com> From: Rusty Lynch <rusty.lynch@intel.com> At the point in traps.c where we recieve a break with a zero value, we can not say if the break was a result of a kprobe or some other debug facility. This simple patch changes the informational string to a more correct "break 0" value, and applies to the 2.6.12-rc2-mm2 tree with all the kprobes patches that were just recently included for the next mm cut. Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-06-23 15:09:27 +08:00
return;
down_read(&mm->mmap_sem);
vma = find_vma_prev(mm, address, &prev_vma);
if (!vma && !prev_vma )
goto bad_area;
/*
* find_vma_prev() returns vma such that address < vma->vm_end or NULL
*
* May find no vma, but could be that the last vm area is the
* register backing store that needs to expand upwards, in
* this case vma will be null, but prev_vma will ne non-null
*/
if (( !vma && prev_vma ) || (address < vma->vm_start) )
goto check_expansion;
good_area:
code = SEGV_ACCERR;
/* OK, we've got a good vm_area for this memory area. Check the access permissions: */
# define VM_READ_BIT 0
# define VM_WRITE_BIT 1
# define VM_EXEC_BIT 2
# if (((1 << VM_READ_BIT) != VM_READ || (1 << VM_WRITE_BIT) != VM_WRITE) \
|| (1 << VM_EXEC_BIT) != VM_EXEC)
# error File is out of sync with <linux/mm.h>. Please update.
# endif
[PATCH] make PROT_WRITE imply PROT_READ Make PROT_WRITE imply PROT_READ for a number of architectures which don't support write only in hardware. While looking at this, I noticed that some architectures which do not support write only mappings already take the exact same approach. For example, in arch/alpha/mm/fault.c: " 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; } " Thus, this patch brings other architectures which do not support write only mappings in-line and consistent with the rest. I've verified the patch on ia64, x86_64 and x86. Additional discussion: Several architectures, including x86, can not support write-only mappings. The pte for x86 reserves a single bit for protection and its two states are read only or read/write. Thus, write only is not supported in h/w. Currently, if i 'mmap' a page write-only, the first read attempt on that page creates a page fault and will SEGV. That check is enforced in arch/blah/mm/fault.c. However, if i first write that page it will fault in and the pte will be set to read/write. Thus, any subsequent reads to the page will succeed. It is this inconsistency in behavior that this patch is attempting to address. Furthermore, if the page is swapped out, and then brought back the first read will also cause a SEGV. Thus, any arbitrary read on a page can potentially result in a SEGV. According to the SuSv3 spec, "if the application requests only PROT_WRITE, the implementation may also allow read access." Also as mentioned, some archtectures, such as alpha, shown above already take the approach that i am suggesting. The counter-argument to this raised by Arjan, is that the kernel is enforcing the write only mapping the best it can given the h/w limitations. This is true, however Alan Cox, and myself would argue that the inconsitency in behavior, that is applications can sometimes work/sometimes fails is highly undesireable. If you read through the thread, i think people, came to an agreement on the last patch i posted, as nobody has objected to it... Signed-off-by: Jason Baron <jbaron@redhat.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Acked-by: Andi Kleen <ak@muc.de> Acked-by: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Arjan van de Ven <arjan@linux.intel.com> Acked-by: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Ian Molton <spyro@f2s.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-29 16:58:58 +08:00
if (((isr >> IA64_ISR_R_BIT) & 1UL) && (!(vma->vm_flags & (VM_READ | VM_WRITE))))
goto bad_area;
mask = ( (((isr >> IA64_ISR_X_BIT) & 1UL) << VM_EXEC_BIT)
[PATCH] make PROT_WRITE imply PROT_READ Make PROT_WRITE imply PROT_READ for a number of architectures which don't support write only in hardware. While looking at this, I noticed that some architectures which do not support write only mappings already take the exact same approach. For example, in arch/alpha/mm/fault.c: " 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; } " Thus, this patch brings other architectures which do not support write only mappings in-line and consistent with the rest. I've verified the patch on ia64, x86_64 and x86. Additional discussion: Several architectures, including x86, can not support write-only mappings. The pte for x86 reserves a single bit for protection and its two states are read only or read/write. Thus, write only is not supported in h/w. Currently, if i 'mmap' a page write-only, the first read attempt on that page creates a page fault and will SEGV. That check is enforced in arch/blah/mm/fault.c. However, if i first write that page it will fault in and the pte will be set to read/write. Thus, any subsequent reads to the page will succeed. It is this inconsistency in behavior that this patch is attempting to address. Furthermore, if the page is swapped out, and then brought back the first read will also cause a SEGV. Thus, any arbitrary read on a page can potentially result in a SEGV. According to the SuSv3 spec, "if the application requests only PROT_WRITE, the implementation may also allow read access." Also as mentioned, some archtectures, such as alpha, shown above already take the approach that i am suggesting. The counter-argument to this raised by Arjan, is that the kernel is enforcing the write only mapping the best it can given the h/w limitations. This is true, however Alan Cox, and myself would argue that the inconsitency in behavior, that is applications can sometimes work/sometimes fails is highly undesireable. If you read through the thread, i think people, came to an agreement on the last patch i posted, as nobody has objected to it... Signed-off-by: Jason Baron <jbaron@redhat.com> Cc: Russell King <rmk@arm.linux.org.uk> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Roman Zippel <zippel@linux-m68k.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Acked-by: Andi Kleen <ak@muc.de> Acked-by: Alan Cox <alan@lxorguk.ukuu.org.uk> Cc: Arjan van de Ven <arjan@linux.intel.com> Acked-by: Paul Mundt <lethal@linux-sh.org> Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp> Cc: Ian Molton <spyro@f2s.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-29 16:58:58 +08:00
| (((isr >> IA64_ISR_W_BIT) & 1UL) << VM_WRITE_BIT));
if ((vma->vm_flags & mask) != mask)
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.
*/
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
fault = handle_mm_fault(mm, vma, address, (mask & VM_WRITE) != 0);
if (unlikely(fault & VM_FAULT_ERROR)) {
/*
* We ran out of memory, or some other thing happened
* to us that made us unable to handle the page fault
* gracefully.
*/
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_OOM) {
goto out_of_memory;
} else if (fault & VM_FAULT_SIGBUS) {
signal = SIGBUS;
goto bad_area;
}
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++;
up_read(&mm->mmap_sem);
return;
check_expansion:
if (!(prev_vma && (prev_vma->vm_flags & VM_GROWSUP) && (address == prev_vma->vm_end))) {
if (!vma)
goto bad_area;
if (!(vma->vm_flags & VM_GROWSDOWN))
goto bad_area;
if (REGION_NUMBER(address) != REGION_NUMBER(vma->vm_start)
|| REGION_OFFSET(address) >= RGN_MAP_LIMIT)
goto bad_area;
if (expand_stack(vma, address))
goto bad_area;
} else {
vma = prev_vma;
if (REGION_NUMBER(address) != REGION_NUMBER(vma->vm_start)
|| REGION_OFFSET(address) >= RGN_MAP_LIMIT)
goto bad_area;
/*
* Since the register backing store is accessed sequentially,
* we disallow growing it by more than a page at a time.
*/
if (address > vma->vm_end + PAGE_SIZE - sizeof(long))
goto bad_area;
if (expand_upwards(vma, address))
goto bad_area;
}
goto good_area;
bad_area:
up_read(&mm->mmap_sem);
#ifdef CONFIG_VIRTUAL_MEM_MAP
bad_area_no_up:
#endif
if ((isr & IA64_ISR_SP)
|| ((isr & IA64_ISR_NA) && (isr & IA64_ISR_CODE_MASK) == IA64_ISR_CODE_LFETCH))
{
/*
* This fault was due to a speculative load or lfetch.fault, set the "ed"
* bit in the psr to ensure forward progress. (Target register will get a
* NaT for ld.s, lfetch will be canceled.)
*/
ia64_psr(regs)->ed = 1;
return;
}
if (user_mode(regs)) {
si.si_signo = signal;
si.si_errno = 0;
si.si_code = code;
si.si_addr = (void __user *) address;
si.si_isr = isr;
si.si_flags = __ISR_VALID;
force_sig_info(signal, &si, current);
return;
}
no_context:
if ((isr & IA64_ISR_SP)
|| ((isr & IA64_ISR_NA) && (isr & IA64_ISR_CODE_MASK) == IA64_ISR_CODE_LFETCH))
{
/*
* This fault was due to a speculative load or lfetch.fault, set the "ed"
* bit in the psr to ensure forward progress. (Target register will get a
* NaT for ld.s, lfetch will be canceled.)
*/
ia64_psr(regs)->ed = 1;
return;
}
/*
* Since we have no vma's for region 5, we might get here even if the address is
* valid, due to the VHPT walker inserting a non present translation that becomes
* stale. If that happens, the non present fault handler already purged the stale
* translation, which fixed the problem. So, we check to see if the translation is
* valid, and return if it is.
*/
if (REGION_NUMBER(address) == 5 && mapped_kernel_page_is_present(address))
return;
if (ia64_done_with_exception(regs))
return;
/*
* Oops. The kernel tried to access some bad page. We'll have to terminate things
* with extreme prejudice.
*/
bust_spinlocks(1);
if (address < PAGE_SIZE)
printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference (address %016lx)\n", address);
else
printk(KERN_ALERT "Unable to handle kernel paging request at "
"virtual address %016lx\n", address);
die("Oops", regs, isr);
bust_spinlocks(0);
do_exit(SIGKILL);
return;
out_of_memory:
up_read(&mm->mmap_sem);
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_CRIT "VM: killing process %s\n", current->comm);
if (user_mode(regs))
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);
goto no_context;
}