271 lines
6.5 KiB
C
271 lines
6.5 KiB
C
// SPDX-License-Identifier: GPL-2.0-or-later
|
|
/*
|
|
* Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
|
|
* Lennox Wu <lennox.wu@sunplusct.com>
|
|
* Chen Liqin <liqin.chen@sunplusct.com>
|
|
* Copyright (C) 2012 Regents of the University of California
|
|
*/
|
|
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/perf_event.h>
|
|
#include <linux/signal.h>
|
|
#include <linux/uaccess.h>
|
|
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/ptrace.h>
|
|
|
|
/*
|
|
* This routine handles page faults. It determines the address and the
|
|
* problem, and then passes it off to one of the appropriate routines.
|
|
*/
|
|
asmlinkage void do_page_fault(struct pt_regs *regs)
|
|
{
|
|
struct task_struct *tsk;
|
|
struct vm_area_struct *vma;
|
|
struct mm_struct *mm;
|
|
unsigned long addr, cause;
|
|
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
|
|
int code = SEGV_MAPERR;
|
|
vm_fault_t fault;
|
|
|
|
cause = regs->scause;
|
|
addr = regs->sbadaddr;
|
|
|
|
tsk = current;
|
|
mm = tsk->mm;
|
|
|
|
/*
|
|
* Fault-in kernel-space virtual memory on-demand.
|
|
* The 'reference' page table is init_mm.pgd.
|
|
*
|
|
* 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 (unlikely((addr >= VMALLOC_START) && (addr <= VMALLOC_END)))
|
|
goto vmalloc_fault;
|
|
|
|
/* Enable interrupts if they were enabled in the parent context. */
|
|
if (likely(regs->sstatus & SR_SPIE))
|
|
local_irq_enable();
|
|
|
|
/*
|
|
* If we're in an interrupt, have no user context, or are running
|
|
* in an atomic region, then we must not take the fault.
|
|
*/
|
|
if (unlikely(faulthandler_disabled() || !mm))
|
|
goto no_context;
|
|
|
|
if (user_mode(regs))
|
|
flags |= FAULT_FLAG_USER;
|
|
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
|
|
|
|
retry:
|
|
down_read(&mm->mmap_sem);
|
|
vma = find_vma(mm, addr);
|
|
if (unlikely(!vma))
|
|
goto bad_area;
|
|
if (likely(vma->vm_start <= addr))
|
|
goto good_area;
|
|
if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
|
|
goto bad_area;
|
|
if (unlikely(expand_stack(vma, addr)))
|
|
goto bad_area;
|
|
|
|
/*
|
|
* Ok, we have a good vm_area for this memory access, so
|
|
* we can handle it.
|
|
*/
|
|
good_area:
|
|
code = SEGV_ACCERR;
|
|
|
|
switch (cause) {
|
|
case EXC_INST_PAGE_FAULT:
|
|
if (!(vma->vm_flags & VM_EXEC))
|
|
goto bad_area;
|
|
break;
|
|
case EXC_LOAD_PAGE_FAULT:
|
|
if (!(vma->vm_flags & VM_READ))
|
|
goto bad_area;
|
|
break;
|
|
case EXC_STORE_PAGE_FAULT:
|
|
if (!(vma->vm_flags & VM_WRITE))
|
|
goto bad_area;
|
|
flags |= FAULT_FLAG_WRITE;
|
|
break;
|
|
default:
|
|
panic("%s: unhandled cause %lu", __func__, cause);
|
|
}
|
|
|
|
/*
|
|
* If for any reason at all we could not handle the fault,
|
|
* make sure we exit gracefully rather than endlessly redo
|
|
* the fault.
|
|
*/
|
|
fault = handle_mm_fault(vma, addr, flags);
|
|
|
|
/*
|
|
* If we need to retry but a fatal signal is pending, handle the
|
|
* signal first. We do not need to release the mmap_sem because it
|
|
* would already be released in __lock_page_or_retry in mm/filemap.c.
|
|
*/
|
|
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(tsk))
|
|
return;
|
|
|
|
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();
|
|
}
|
|
|
|
/*
|
|
* 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) {
|
|
tsk->maj_flt++;
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
|
|
1, regs, addr);
|
|
} else {
|
|
tsk->min_flt++;
|
|
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
|
|
1, regs, addr);
|
|
}
|
|
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;
|
|
|
|
/*
|
|
* 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)) {
|
|
do_trap(regs, SIGSEGV, code, addr, tsk);
|
|
return;
|
|
}
|
|
|
|
no_context:
|
|
/* Are we prepared to handle this kernel fault? */
|
|
if (fixup_exception(regs))
|
|
return;
|
|
|
|
/*
|
|
* Oops. The kernel tried to access some bad page. We'll have to
|
|
* terminate things with extreme prejudice.
|
|
*/
|
|
bust_spinlocks(1);
|
|
pr_alert("Unable to handle kernel %s at virtual address " REG_FMT "\n",
|
|
(addr < PAGE_SIZE) ? "NULL pointer dereference" :
|
|
"paging request", addr);
|
|
die(regs, "Oops");
|
|
do_exit(SIGKILL);
|
|
|
|
/*
|
|
* We ran out of memory, call the OOM killer, and return the userspace
|
|
* (which will retry the fault, or kill us if we got oom-killed).
|
|
*/
|
|
out_of_memory:
|
|
up_read(&mm->mmap_sem);
|
|
if (!user_mode(regs))
|
|
goto no_context;
|
|
pagefault_out_of_memory();
|
|
return;
|
|
|
|
do_sigbus:
|
|
up_read(&mm->mmap_sem);
|
|
/* Kernel mode? Handle exceptions or die */
|
|
if (!user_mode(regs))
|
|
goto no_context;
|
|
do_trap(regs, SIGBUS, BUS_ADRERR, addr, tsk);
|
|
return;
|
|
|
|
vmalloc_fault:
|
|
{
|
|
pgd_t *pgd, *pgd_k;
|
|
pud_t *pud, *pud_k;
|
|
p4d_t *p4d, *p4d_k;
|
|
pmd_t *pmd, *pmd_k;
|
|
pte_t *pte_k;
|
|
int index;
|
|
|
|
/* User mode accesses just cause a SIGSEGV */
|
|
if (user_mode(regs))
|
|
return do_trap(regs, SIGSEGV, code, addr, tsk);
|
|
|
|
/*
|
|
* Synchronize this task's top level page-table
|
|
* with the 'reference' page table.
|
|
*
|
|
* Do _not_ use "tsk->active_mm->pgd" here.
|
|
* We might be inside an interrupt in the middle
|
|
* of a task switch.
|
|
*/
|
|
index = pgd_index(addr);
|
|
pgd = (pgd_t *)pfn_to_virt(csr_read(CSR_SATP)) + index;
|
|
pgd_k = init_mm.pgd + index;
|
|
|
|
if (!pgd_present(*pgd_k))
|
|
goto no_context;
|
|
set_pgd(pgd, *pgd_k);
|
|
|
|
p4d = p4d_offset(pgd, addr);
|
|
p4d_k = p4d_offset(pgd_k, addr);
|
|
if (!p4d_present(*p4d_k))
|
|
goto no_context;
|
|
|
|
pud = pud_offset(p4d, addr);
|
|
pud_k = pud_offset(p4d_k, addr);
|
|
if (!pud_present(*pud_k))
|
|
goto no_context;
|
|
|
|
/*
|
|
* Since the vmalloc area is global, it is unnecessary
|
|
* to copy individual PTEs
|
|
*/
|
|
pmd = pmd_offset(pud, addr);
|
|
pmd_k = pmd_offset(pud_k, addr);
|
|
if (!pmd_present(*pmd_k))
|
|
goto no_context;
|
|
set_pmd(pmd, *pmd_k);
|
|
|
|
/*
|
|
* Make sure the actual PTE exists as well to
|
|
* catch kernel vmalloc-area accesses to non-mapped
|
|
* addresses. If we don't do this, this will just
|
|
* silently loop forever.
|
|
*/
|
|
pte_k = pte_offset_kernel(pmd_k, addr);
|
|
if (!pte_present(*pte_k))
|
|
goto no_context;
|
|
return;
|
|
}
|
|
}
|