linux/arch/arc/mm/fault.c

227 lines
5.0 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/* Page Fault Handling for ARC (TLB Miss / ProtV)
*
* Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
*/
#include <linux/signal.h>
#include <linux/interrupt.h>
#include <linux/sched/signal.h>
#include <linux/errno.h>
#include <linux/ptrace.h>
#include <linux/uaccess.h>
#include <linux/kdebug.h>
#include <linux/perf_event.h>
mm: convert return type of handle_mm_fault() caller to vm_fault_t Use new return type vm_fault_t for fault handler. For now, this is just documenting that the function returns a VM_FAULT value rather than an errno. Once all instances are converted, vm_fault_t will become a distinct type. Ref-> commit 1c8f422059ae ("mm: change return type to vm_fault_t") In this patch all the caller of handle_mm_fault() are changed to return vm_fault_t type. Link: http://lkml.kernel.org/r/20180617084810.GA6730@jordon-HP-15-Notebook-PC Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Tony Luck <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Russell King <linux@armlinux.org.uk> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Michal Simek <monstr@monstr.eu> Cc: James Hogan <jhogan@kernel.org> Cc: Ley Foon Tan <lftan@altera.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Palmer Dabbelt <palmer@sifive.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: David S. Miller <davem@davemloft.net> Cc: Richard Weinberger <richard@nod.at> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Levin, Alexander (Sasha Levin)" <alexander.levin@verizon.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-17 22:44:47 +00:00
#include <linux/mm_types.h>
#include <asm/pgalloc.h>
#include <asm/mmu.h>
/*
* kernel virtual address is required to implement vmalloc/pkmap/fixmap
* Refer to asm/processor.h for System Memory Map
*
* It simply copies the PMD entry (pointer to 2nd level page table or hugepage)
* from swapper pgdir to task pgdir. The 2nd level table/page is thus shared
*/
noinline static int handle_kernel_vaddr_fault(unsigned long address)
{
/*
* Synchronize this task's top level page-table
* with the 'reference' page table.
*/
pgd_t *pgd, *pgd_k;
pud_t *pud, *pud_k;
pmd_t *pmd, *pmd_k;
pgd = pgd_offset_fast(current->active_mm, address);
pgd_k = pgd_offset_k(address);
if (!pgd_present(*pgd_k))
goto bad_area;
pud = pud_offset(pgd, address);
pud_k = pud_offset(pgd_k, address);
if (!pud_present(*pud_k))
goto bad_area;
pmd = pmd_offset(pud, address);
pmd_k = pmd_offset(pud_k, address);
if (!pmd_present(*pmd_k))
goto bad_area;
set_pmd(pmd, *pmd_k);
/* XXX: create the TLB entry here */
return 0;
bad_area:
return 1;
}
void do_page_fault(unsigned long address, struct pt_regs *regs)
{
struct vm_area_struct *vma = NULL;
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
int si_code = SEGV_MAPERR;
unsigned int write = 0, exec = 0, mask;
vm_fault_t fault; /* handle_mm_fault() output */
unsigned int flags; /* handle_mm_fault() input */
/*
* NOTE! We MUST NOT take any locks for this case. We may
* be in an interrupt or a critical region, and should
* only copy the information from the master page table,
* nothing more.
*/
if (address >= VMALLOC_START && !user_mode(regs)) {
if (unlikely(handle_kernel_vaddr_fault(address)))
goto no_context;
else
return;
}
/*
* 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 15:52:11 +00:00
if (faulthandler_disabled() || !mm)
goto no_context;
if (regs->ecr_cause & ECR_C_PROTV_STORE) /* ST/EX */
write = 1;
else if ((regs->ecr_vec == ECR_V_PROTV) &&
(regs->ecr_cause == ECR_C_PROTV_INST_FETCH))
exec = 1;
flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
if (write)
flags |= FAULT_FLAG_WRITE;
retry:
down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
if (!vma)
goto bad_area;
if (unlikely(address < vma->vm_start)) {
if (!(vma->vm_flags & VM_GROWSDOWN) || expand_stack(vma, address))
goto bad_area;
}
/*
* vm_area is good, now check permissions for this memory access
*/
mask = VM_READ;
if (write)
mask = VM_WRITE;
if (exec)
mask = VM_EXEC;
if (!(vma->vm_flags & mask)) {
si_code = SEGV_ACCERR;
goto bad_area;
}
fault = handle_mm_fault(vma, address, flags);
/*
* Fault retry nuances
*/
if (unlikely(fault & VM_FAULT_RETRY)) {
ARC: mm: do_page_fault fixes #1: relinquish mmap_sem if signal arrives while handle_mm_fault do_page_fault() forgot to relinquish mmap_sem if a signal came while handling handle_mm_fault() - due to say a ctl+c or oom etc. This would later cause a deadlock by acquiring it twice. This came to light when running libc testsuite tst-tls3-malloc test but is likely also the cause for prior seen LTP failures. Using lockdep clearly showed what the issue was. | # while true; do ./tst-tls3-malloc ; done | Didn't expect signal from child: got `Segmentation fault' | ^C | ============================================ | WARNING: possible recursive locking detected | 4.17.0+ #25 Not tainted | -------------------------------------------- | tst-tls3-malloc/510 is trying to acquire lock: | 606c7728 (&mm->mmap_sem){++++}, at: __might_fault+0x28/0x5c | |but task is already holding lock: |606c7728 (&mm->mmap_sem){++++}, at: do_page_fault+0x9c/0x2a0 | | other info that might help us debug this: | Possible unsafe locking scenario: | | CPU0 | ---- | lock(&mm->mmap_sem); | lock(&mm->mmap_sem); | | *** DEADLOCK *** | ------------------------------------------------------------ What the change does is not obvious (note to myself) prior code was | do_page_fault | | down_read() <-- lock taken | handle_mm_fault <-- signal pending as this runs | if fatal_signal_pending | if VM_FAULT_ERROR | up_read | if user_mode | return <-- lock still held, this was the BUG New code | do_page_fault | | down_read() <-- lock taken | handle_mm_fault <-- signal pending as this runs | if fatal_signal_pending | if VM_FAULT_RETRY | return <-- not same case as above, but still OK since | core mm already relinq lock for FAULT_RETRY | ... | | < Now falls through for bug case above > | | up_read() <-- lock relinquished Cc: stable@vger.kernel.org Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
2018-12-11 00:56:45 +00:00
/*
* If fault needs to be retried, handle any pending signals
* first (by returning to user mode).
* mmap_sem already relinquished by core mm for RETRY case
ARC: mm: do_page_fault fixes #1: relinquish mmap_sem if signal arrives while handle_mm_fault do_page_fault() forgot to relinquish mmap_sem if a signal came while handling handle_mm_fault() - due to say a ctl+c or oom etc. This would later cause a deadlock by acquiring it twice. This came to light when running libc testsuite tst-tls3-malloc test but is likely also the cause for prior seen LTP failures. Using lockdep clearly showed what the issue was. | # while true; do ./tst-tls3-malloc ; done | Didn't expect signal from child: got `Segmentation fault' | ^C | ============================================ | WARNING: possible recursive locking detected | 4.17.0+ #25 Not tainted | -------------------------------------------- | tst-tls3-malloc/510 is trying to acquire lock: | 606c7728 (&mm->mmap_sem){++++}, at: __might_fault+0x28/0x5c | |but task is already holding lock: |606c7728 (&mm->mmap_sem){++++}, at: do_page_fault+0x9c/0x2a0 | | other info that might help us debug this: | Possible unsafe locking scenario: | | CPU0 | ---- | lock(&mm->mmap_sem); | lock(&mm->mmap_sem); | | *** DEADLOCK *** | ------------------------------------------------------------ What the change does is not obvious (note to myself) prior code was | do_page_fault | | down_read() <-- lock taken | handle_mm_fault <-- signal pending as this runs | if fatal_signal_pending | if VM_FAULT_ERROR | up_read | if user_mode | return <-- lock still held, this was the BUG New code | do_page_fault | | down_read() <-- lock taken | handle_mm_fault <-- signal pending as this runs | if fatal_signal_pending | if VM_FAULT_RETRY | return <-- not same case as above, but still OK since | core mm already relinq lock for FAULT_RETRY | ... | | < Now falls through for bug case above > | | up_read() <-- lock relinquished Cc: stable@vger.kernel.org Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
2018-12-11 00:56:45 +00:00
*/
if (fatal_signal_pending(current)) {
ARC: mm: do_page_fault fixes #1: relinquish mmap_sem if signal arrives while handle_mm_fault do_page_fault() forgot to relinquish mmap_sem if a signal came while handling handle_mm_fault() - due to say a ctl+c or oom etc. This would later cause a deadlock by acquiring it twice. This came to light when running libc testsuite tst-tls3-malloc test but is likely also the cause for prior seen LTP failures. Using lockdep clearly showed what the issue was. | # while true; do ./tst-tls3-malloc ; done | Didn't expect signal from child: got `Segmentation fault' | ^C | ============================================ | WARNING: possible recursive locking detected | 4.17.0+ #25 Not tainted | -------------------------------------------- | tst-tls3-malloc/510 is trying to acquire lock: | 606c7728 (&mm->mmap_sem){++++}, at: __might_fault+0x28/0x5c | |but task is already holding lock: |606c7728 (&mm->mmap_sem){++++}, at: do_page_fault+0x9c/0x2a0 | | other info that might help us debug this: | Possible unsafe locking scenario: | | CPU0 | ---- | lock(&mm->mmap_sem); | lock(&mm->mmap_sem); | | *** DEADLOCK *** | ------------------------------------------------------------ What the change does is not obvious (note to myself) prior code was | do_page_fault | | down_read() <-- lock taken | handle_mm_fault <-- signal pending as this runs | if fatal_signal_pending | if VM_FAULT_ERROR | up_read | if user_mode | return <-- lock still held, this was the BUG New code | do_page_fault | | down_read() <-- lock taken | handle_mm_fault <-- signal pending as this runs | if fatal_signal_pending | if VM_FAULT_RETRY | return <-- not same case as above, but still OK since | core mm already relinq lock for FAULT_RETRY | ... | | < Now falls through for bug case above > | | up_read() <-- lock relinquished Cc: stable@vger.kernel.org Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
2018-12-11 00:56:45 +00:00
if (!user_mode(regs))
goto no_context;
return;
ARC: mm: do_page_fault fixes #1: relinquish mmap_sem if signal arrives while handle_mm_fault do_page_fault() forgot to relinquish mmap_sem if a signal came while handling handle_mm_fault() - due to say a ctl+c or oom etc. This would later cause a deadlock by acquiring it twice. This came to light when running libc testsuite tst-tls3-malloc test but is likely also the cause for prior seen LTP failures. Using lockdep clearly showed what the issue was. | # while true; do ./tst-tls3-malloc ; done | Didn't expect signal from child: got `Segmentation fault' | ^C | ============================================ | WARNING: possible recursive locking detected | 4.17.0+ #25 Not tainted | -------------------------------------------- | tst-tls3-malloc/510 is trying to acquire lock: | 606c7728 (&mm->mmap_sem){++++}, at: __might_fault+0x28/0x5c | |but task is already holding lock: |606c7728 (&mm->mmap_sem){++++}, at: do_page_fault+0x9c/0x2a0 | | other info that might help us debug this: | Possible unsafe locking scenario: | | CPU0 | ---- | lock(&mm->mmap_sem); | lock(&mm->mmap_sem); | | *** DEADLOCK *** | ------------------------------------------------------------ What the change does is not obvious (note to myself) prior code was | do_page_fault | | down_read() <-- lock taken | handle_mm_fault <-- signal pending as this runs | if fatal_signal_pending | if VM_FAULT_ERROR | up_read | if user_mode | return <-- lock still held, this was the BUG New code | do_page_fault | | down_read() <-- lock taken | handle_mm_fault <-- signal pending as this runs | if fatal_signal_pending | if VM_FAULT_RETRY | return <-- not same case as above, but still OK since | core mm already relinq lock for FAULT_RETRY | ... | | < Now falls through for bug case above > | | up_read() <-- lock relinquished Cc: stable@vger.kernel.org Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
2018-12-11 00:56:45 +00:00
}
/*
* retry state machine
*/
if (flags & FAULT_FLAG_ALLOW_RETRY) {
flags &= ~FAULT_FLAG_ALLOW_RETRY;
flags |= FAULT_FLAG_TRIED;
goto retry;
}
}
/*
* Major/minor page fault accounting
* (in case of retry we only land here once)
*/
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
if (likely(!(fault & VM_FAULT_ERROR))) {
if (fault & VM_FAULT_MAJOR) {
tsk->maj_flt++;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
regs, address);
} else {
tsk->min_flt++;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
regs, address);
}
/* Normal return path: fault Handled Gracefully */
up_read(&mm->mmap_sem);
return;
}
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
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>
2015-01-29 18:51:32 +00:00
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
/* no man's land */
BUG();
/*
* 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);
/* User mode accesses just cause a SIGSEGV */
if (user_mode(regs)) {
tsk->thread.fault_address = address;
force_sig_fault(SIGSEGV, si_code, (void __user *)address, tsk);
return;
}
out_of_memory:
up_read(&mm->mmap_sem);
if (user_mode(regs)) {
pagefault_out_of_memory();
return;
}
goto no_context;
do_sigbus:
up_read(&mm->mmap_sem);
if (!user_mode(regs))
goto no_context;
tsk->thread.fault_address = address;
force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address, tsk);
return;
no_context:
if (fixup_exception(regs))
return;
die("Oops", regs, address);
}