Contributors: 20
| Author |
Tokens |
Token Proportion |
Commits |
Commit Proportion |
| Linus Torvalds (pre-git) |
337 |
28.88% |
14 |
28.57% |
| Ralf Baechle |
224 |
19.19% |
12 |
24.49% |
| Linus Torvalds |
116 |
9.94% |
3 |
6.12% |
| Markos Chandras |
115 |
9.85% |
1 |
2.04% |
| David Daney |
113 |
9.68% |
3 |
6.12% |
| Kautuk Consul |
50 |
4.28% |
1 |
2.04% |
| Nicholas Piggin |
45 |
3.86% |
1 |
2.04% |
| Deng-Cheng Zhu |
40 |
3.43% |
1 |
2.04% |
| Andrew Morton |
34 |
2.91% |
1 |
2.04% |
| Johannes Weiner |
26 |
2.23% |
2 |
4.08% |
| Atsushi Nemoto |
20 |
1.71% |
1 |
2.04% |
| Eric W. Biedermann |
11 |
0.94% |
1 |
2.04% |
| Matt Redfearn |
9 |
0.77% |
1 |
2.04% |
| Thiemo Seufer |
8 |
0.69% |
1 |
2.04% |
| Akinobu Mita |
8 |
0.69% |
1 |
2.04% |
| David Hildenbrand |
4 |
0.34% |
1 |
2.04% |
| Shaohua Li |
4 |
0.34% |
1 |
2.04% |
| Paul Burton |
1 |
0.09% |
1 |
2.04% |
| Souptick Joarder |
1 |
0.09% |
1 |
2.04% |
| Steven J. Hill |
1 |
0.09% |
1 |
2.04% |
| Total |
1167 |
|
49 |
|
/*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*
* Copyright (C) 1995 - 2000 by Ralf Baechle
*/
#include <linux/context_tracking.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/ratelimit.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/kprobes.h>
#include <linux/perf_event.h>
#include <linux/uaccess.h>
#include <asm/branch.h>
#include <asm/mmu_context.h>
#include <asm/ptrace.h>
#include <asm/highmem.h> /* For VMALLOC_END */
#include <linux/kdebug.h>
int show_unhandled_signals = 1;
/*
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to one of the appropriate
* routines.
*/
static void __kprobes __do_page_fault(struct pt_regs *regs, unsigned long write,
unsigned long address)
{
struct vm_area_struct * vma = NULL;
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
const int field = sizeof(unsigned long) * 2;
int si_code;
vm_fault_t fault;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10);
#if 0
printk("Cpu%d[%s:%d:%0*lx:%ld:%0*lx]\n", raw_smp_processor_id(),
current->comm, current->pid, field, address, write,
field, regs->cp0_epc);
#endif
#ifdef CONFIG_KPROBES
/*
* This is to notify the fault handler of the kprobes.
*/
if (notify_die(DIE_PAGE_FAULT, "page fault", regs, -1,
current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
return;
#endif
si_code = SEGV_MAPERR;
/*
* We 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.
*/
#ifdef CONFIG_64BIT
# define VMALLOC_FAULT_TARGET no_context
#else
# define VMALLOC_FAULT_TARGET vmalloc_fault
#endif
if (unlikely(address >= VMALLOC_START && address <= VMALLOC_END))
goto VMALLOC_FAULT_TARGET;
#ifdef MODULE_START
if (unlikely(address >= MODULE_START && address < MODULE_END))
goto VMALLOC_FAULT_TARGET;
#endif
/*
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
if (faulthandler_disabled() || !mm)
goto bad_area_nosemaphore;
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
retry:
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 (write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
flags |= FAULT_FLAG_WRITE;
} else {
if (cpu_has_rixi) {
if (address == regs->cp0_epc && !(vma->vm_flags & VM_EXEC)) {
#if 0
pr_notice("Cpu%d[%s:%d:%0*lx:%ld:%0*lx] XI violation\n",
raw_smp_processor_id(),
current->comm, current->pid,
field, address, write,
field, regs->cp0_epc);
#endif
goto bad_area;
}
if (!(vma->vm_flags & VM_READ) &&
exception_epc(regs) != address) {
#if 0
pr_notice("Cpu%d[%s:%d:%0*lx:%ld:%0*lx] RI violation\n",
raw_smp_processor_id(),
current->comm, current->pid,
field, address, write,
field, regs->cp0_epc);
#endif
goto bad_area;
}
} else {
if (!(vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)))
goto bad_area;
}
}
/*
* 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);
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
return;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
BUG();
}
if (flags & FAULT_FLAG_ALLOW_RETRY) {
if (fault & VM_FAULT_MAJOR) {
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
regs, address);
tsk->maj_flt++;
} else {
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
regs, address);
tsk->min_flt++;
}
if (fault & VM_FAULT_RETRY) {
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);
bad_area_nosemaphore:
/* User mode accesses just cause a SIGSEGV */
if (user_mode(regs)) {
tsk->thread.cp0_badvaddr = address;
tsk->thread.error_code = write;
if (show_unhandled_signals &&
unhandled_signal(tsk, SIGSEGV) &&
__ratelimit(&ratelimit_state)) {
pr_info("do_page_fault(): sending SIGSEGV to %s for invalid %s %0*lx\n",
tsk->comm,
write ? "write access to" : "read access from",
field, address);
pr_info("epc = %0*lx in", field,
(unsigned long) regs->cp0_epc);
print_vma_addr(KERN_CONT " ", regs->cp0_epc);
pr_cont("\n");
pr_info("ra = %0*lx in", field,
(unsigned long) regs->regs[31]);
print_vma_addr(KERN_CONT " ", regs->regs[31]);
pr_cont("\n");
}
current->thread.trap_nr = (regs->cp0_cause >> 2) & 0x1f;
force_sig_fault(SIGSEGV, si_code, (void __user *)address, tsk);
return;
}
no_context:
/* Are we prepared to handle this kernel fault? */
if (fixup_exception(regs)) {
current->thread.cp0_baduaddr = address;
return;
}
/*
* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice.
*/
bust_spinlocks(1);
printk(KERN_ALERT "CPU %d Unable to handle kernel paging request at "
"virtual address %0*lx, epc == %0*lx, ra == %0*lx\n",
raw_smp_processor_id(), field, address, field, regs->cp0_epc,
field, regs->regs[31]);
die("Oops", regs);
out_of_memory:
/*
* 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).
*/
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;
/*
* Send a sigbus, regardless of whether we were in kernel
* or user mode.
*/
#if 0
printk("do_page_fault() #3: sending SIGBUS to %s for "
"invalid %s\n%0*lx (epc == %0*lx, ra == %0*lx)\n",
tsk->comm,
write ? "write access to" : "read access from",
field, address,
field, (unsigned long) regs->cp0_epc,
field, (unsigned long) regs->regs[31]);
#endif
current->thread.trap_nr = (regs->cp0_cause >> 2) & 0x1f;
tsk->thread.cp0_badvaddr = address;
force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address, tsk);
return;
#ifndef CONFIG_64BIT
vmalloc_fault:
{
/*
* Synchronize this task's top level page-table
* with the 'reference' page table.
*
* Do _not_ use "tsk" here. We might be inside
* an interrupt in the middle of a task switch..
*/
int offset = __pgd_offset(address);
pgd_t *pgd, *pgd_k;
pud_t *pud, *pud_k;
pmd_t *pmd, *pmd_k;
pte_t *pte_k;
pgd = (pgd_t *) pgd_current[raw_smp_processor_id()] + offset;
pgd_k = init_mm.pgd + offset;
if (!pgd_present(*pgd_k))
goto no_context;
set_pgd(pgd, *pgd_k);
pud = pud_offset(pgd, address);
pud_k = pud_offset(pgd_k, address);
if (!pud_present(*pud_k))
goto no_context;
pmd = pmd_offset(pud, address);
pmd_k = pmd_offset(pud_k, address);
if (!pmd_present(*pmd_k))
goto no_context;
set_pmd(pmd, *pmd_k);
pte_k = pte_offset_kernel(pmd_k, address);
if (!pte_present(*pte_k))
goto no_context;
return;
}
#endif
}
asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
unsigned long write, unsigned long address)
{
enum ctx_state prev_state;
prev_state = exception_enter();
__do_page_fault(regs, write, address);
exception_exit(prev_state);
}