linux_dsm_epyc7002/arch/m68k/mm/fault.c

221 lines
5.3 KiB
C
Raw Normal View History

/*
* linux/arch/m68k/mm/fault.c
*
* Copyright (C) 1995 Hamish Macdonald
*/
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/kernel.h>
#include <linux/ptrace.h>
#include <linux/interrupt.h>
#include <linux/module.h>
mm/fault, arch: Use pagefault_disable() to check for disabled pagefaults in the handler Introduce faulthandler_disabled() and use it to check for irq context and disabled pagefaults (via pagefault_disable()) in the pagefault handlers. Please note that we keep the in_atomic() checks in place - to detect whether in irq context (in which case preemption is always properly disabled). In contrast, preempt_disable() should never be used to disable pagefaults. With !CONFIG_PREEMPT_COUNT, preempt_disable() doesn't modify the preempt counter, and therefore the result of in_atomic() differs. We validate that condition by using might_fault() checks when calling might_sleep(). Therefore, add a comment to faulthandler_disabled(), describing why this is needed. faulthandler_disabled() and pagefault_disable() are defined in linux/uaccess.h, so let's properly add that include to all relevant files. This patch is based on a patch from Thomas Gleixner. Reviewed-and-tested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: David.Laight@ACULAB.COM Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: airlied@linux.ie Cc: akpm@linux-foundation.org Cc: benh@kernel.crashing.org Cc: bigeasy@linutronix.de Cc: borntraeger@de.ibm.com Cc: daniel.vetter@intel.com Cc: heiko.carstens@de.ibm.com Cc: herbert@gondor.apana.org.au Cc: hocko@suse.cz Cc: hughd@google.com Cc: mst@redhat.com Cc: paulus@samba.org Cc: ralf@linux-mips.org Cc: schwidefsky@de.ibm.com Cc: yang.shi@windriver.com Link: http://lkml.kernel.org/r/1431359540-32227-7-git-send-email-dahi@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-11 22:52:11 +07:00
#include <linux/uaccess.h>
#include <asm/setup.h>
#include <asm/traps.h>
#include <asm/pgalloc.h>
extern void die_if_kernel(char *, struct pt_regs *, long);
int send_fault_sig(struct pt_regs *regs)
{
siginfo_t siginfo = { 0, 0, 0, };
siginfo.si_signo = current->thread.signo;
siginfo.si_code = current->thread.code;
siginfo.si_addr = (void *)current->thread.faddr;
pr_debug("send_fault_sig: %p,%d,%d\n", siginfo.si_addr,
siginfo.si_signo, siginfo.si_code);
if (user_mode(regs)) {
force_sig_info(siginfo.si_signo,
&siginfo, current);
} else {
if (handle_kernel_fault(regs))
return -1;
//if (siginfo.si_signo == SIGBUS)
// force_sig_info(siginfo.si_signo,
// &siginfo, current);
/*
* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice.
*/
if ((unsigned long)siginfo.si_addr < PAGE_SIZE)
pr_alert("Unable to handle kernel NULL pointer dereference");
else
pr_alert("Unable to handle kernel access");
pr_cont(" at virtual address %p\n", siginfo.si_addr);
die_if_kernel("Oops", regs, 0 /*error_code*/);
do_exit(SIGKILL);
}
return 1;
}
/*
* This routine handles page faults. It determines the problem, and
* then passes it off to one of the appropriate routines.
*
* error_code:
* bit 0 == 0 means no page found, 1 means protection fault
* bit 1 == 0 means read, 1 means write
*
* If this routine detects a bad access, it returns 1, otherwise it
* returns 0.
*/
int do_page_fault(struct pt_regs *regs, unsigned long address,
unsigned long error_code)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct * vma;
int fault;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
pr_debug("do page fault:\nregs->sr=%#x, regs->pc=%#lx, address=%#lx, %ld, %p\n",
regs->sr, regs->pc, address, error_code, mm ? mm->pgd : NULL);
/*
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
mm/fault, arch: Use pagefault_disable() to check for disabled pagefaults in the handler Introduce faulthandler_disabled() and use it to check for irq context and disabled pagefaults (via pagefault_disable()) in the pagefault handlers. Please note that we keep the in_atomic() checks in place - to detect whether in irq context (in which case preemption is always properly disabled). In contrast, preempt_disable() should never be used to disable pagefaults. With !CONFIG_PREEMPT_COUNT, preempt_disable() doesn't modify the preempt counter, and therefore the result of in_atomic() differs. We validate that condition by using might_fault() checks when calling might_sleep(). Therefore, add a comment to faulthandler_disabled(), describing why this is needed. faulthandler_disabled() and pagefault_disable() are defined in linux/uaccess.h, so let's properly add that include to all relevant files. This patch is based on a patch from Thomas Gleixner. Reviewed-and-tested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: David.Laight@ACULAB.COM Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: airlied@linux.ie Cc: akpm@linux-foundation.org Cc: benh@kernel.crashing.org Cc: bigeasy@linutronix.de Cc: borntraeger@de.ibm.com Cc: daniel.vetter@intel.com Cc: heiko.carstens@de.ibm.com Cc: herbert@gondor.apana.org.au Cc: hocko@suse.cz Cc: hughd@google.com Cc: mst@redhat.com Cc: paulus@samba.org Cc: ralf@linux-mips.org Cc: schwidefsky@de.ibm.com Cc: yang.shi@windriver.com Link: http://lkml.kernel.org/r/1431359540-32227-7-git-send-email-dahi@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-05-11 22:52:11 +07:00
if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
if (!vma)
goto map_err;
if (vma->vm_flags & VM_IO)
goto acc_err;
if (vma->vm_start <= address)
goto good_area;
if (!(vma->vm_flags & VM_GROWSDOWN))
goto map_err;
if (user_mode(regs)) {
/* Accessing the stack below usp is always a bug. The
"+ 256" is there due to some instructions doing
pre-decrement on the stack and that doesn't show up
until later. */
if (address + 256 < rdusp())
goto map_err;
}
if (expand_stack(vma, address))
goto map_err;
/*
* Ok, we have a good vm_area for this memory access, so
* we can handle it..
*/
good_area:
pr_debug("do_page_fault: good_area\n");
switch (error_code & 3) {
default: /* 3: write, present */
/* fall through */
case 2: /* write, not present */
if (!(vma->vm_flags & VM_WRITE))
goto acc_err;
flags |= FAULT_FLAG_WRITE;
break;
case 1: /* read, present */
goto acc_err;
case 0: /* read, not present */
[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 15:58:58 +07:00
if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
goto acc_err;
}
/*
* 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);
pr_debug("handle_mm_fault returns %d\n", fault);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return 0;
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 15:47:05 +07:00
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
vm: add VM_FAULT_SIGSEGV handling support The core VM already knows about VM_FAULT_SIGBUS, but cannot return a "you should SIGSEGV" error, because the SIGSEGV case was generally handled by the caller - usually the architecture fault handler. That results in lots of duplication - all the architecture fault handlers end up doing very similar "look up vma, check permissions, do retries etc" - but it generally works. However, there are cases where the VM actually wants to SIGSEGV, and applications _expect_ SIGSEGV. In particular, when accessing the stack guard page, libsigsegv expects a SIGSEGV. And it usually got one, because the stack growth is handled by that duplicated architecture fault handler. However, when the generic VM layer started propagating the error return from the stack expansion in commit fee7e49d4514 ("mm: propagate error from stack expansion even for guard page"), that now exposed the existing VM_FAULT_SIGBUS result to user space. And user space really expected SIGSEGV, not SIGBUS. To fix that case, we need to add a VM_FAULT_SIGSEGV, and teach all those duplicate architecture fault handlers about it. They all already have the code to handle SIGSEGV, so it's about just tying that new return value to the existing code, but it's all a bit annoying. This is the mindless minimal patch to do this. A more extensive patch would be to try to gather up the mostly shared fault handling logic into one generic helper routine, and long-term we really should do that cleanup. Just from this patch, you can generally see that most architectures just copied (directly or indirectly) the old x86 way of doing things, but in the meantime that original x86 model has been improved to hold the VM semaphore for shorter times etc and to handle VM_FAULT_RETRY and other "newer" things, so it would be a good idea to bring all those improvements to the generic case and teach other architectures about them too. Reported-and-tested-by: Takashi Iwai <tiwai@suse.de> Tested-by: Jan Engelhardt <jengelh@inai.de> Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # "s390 still compiles and boots" Cc: linux-arch@vger.kernel.org Cc: stable@vger.kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-01-30 01:51:32 +07:00
else if (fault & VM_FAULT_SIGSEGV)
goto map_err;
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 15:47:05 +07:00
else if (fault & VM_FAULT_SIGBUS)
goto bus_err;
BUG();
}
/*
* Major/minor page fault accounting is only done on the
* initial attempt. If we go through a retry, it is extremely
* likely that the page will be found in page cache at that point.
*/
if (flags & FAULT_FLAG_ALLOW_RETRY) {
if (fault & VM_FAULT_MAJOR)
current->maj_flt++;
else
current->min_flt++;
if (fault & VM_FAULT_RETRY) {
/* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
* of starvation. */
flags &= ~FAULT_FLAG_ALLOW_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);
return 0;
/*
* 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))
goto no_context;
pagefault_out_of_memory();
return 0;
no_context:
current->thread.signo = SIGBUS;
current->thread.faddr = address;
return send_fault_sig(regs);
bus_err:
current->thread.signo = SIGBUS;
current->thread.code = BUS_ADRERR;
current->thread.faddr = address;
goto send_sig;
map_err:
current->thread.signo = SIGSEGV;
current->thread.code = SEGV_MAPERR;
current->thread.faddr = address;
goto send_sig;
acc_err:
current->thread.signo = SIGSEGV;
current->thread.code = SEGV_ACCERR;
current->thread.faddr = address;
send_sig:
up_read(&mm->mmap_sem);
return send_fault_sig(regs);
}