/*
* Copyright (C) 1995 Linus Torvalds
* Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs.
+ * Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar
*/
-#include <linux/interrupt.h>
-#include <linux/mmiotrace.h>
-#include <linux/bootmem.h>
-#include <linux/compiler.h>
-#include <linux/highmem.h>
-#include <linux/kprobes.h>
-#include <linux/uaccess.h>
-#include <linux/vmalloc.h>
-#include <linux/vt_kern.h>
-#include <linux/signal.h>
-#include <linux/kernel.h>
-#include <linux/ptrace.h>
-#include <linux/string.h>
-#include <linux/module.h>
-#include <linux/kdebug.h>
-#include <linux/errno.h>
-#include <linux/magic.h>
-#include <linux/sched.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/mman.h>
-#include <linux/tty.h>
-#include <linux/smp.h>
-#include <linux/mm.h>
-
-#include <asm-generic/sections.h>
-
-#include <asm/tlbflush.h>
-#include <asm/pgalloc.h>
-#include <asm/segment.h>
-#include <asm/system.h>
-#include <asm/proto.h>
-#include <asm/traps.h>
-#include <asm/desc.h>
+#include <linux/magic.h> /* STACK_END_MAGIC */
+#include <linux/sched.h> /* test_thread_flag(), ... */
+#include <linux/kdebug.h> /* oops_begin/end, ... */
+#include <linux/module.h> /* search_exception_table */
+#include <linux/bootmem.h> /* max_low_pfn */
+#include <linux/kprobes.h> /* __kprobes, ... */
+#include <linux/mmiotrace.h> /* kmmio_handler, ... */
+#include <linux/perf_counter.h> /* perf_swcounter_event */
+
+#include <asm/traps.h> /* dotraplinkage, ... */
+#include <asm/pgalloc.h> /* pgd_*(), ... */
+#include <asm/kmemcheck.h> /* kmemcheck_*(), ... */
/*
* Page fault error code bits:
};
/*
- * (returns 0 if mmiotrace is disabled)
+ * Returns 0 if mmiotrace is disabled, or if the fault is not
+ * handled by mmiotrace:
*/
static inline int kmmio_fault(struct pt_regs *regs, unsigned long addr)
{
if (!pmd_present(*pmd_k))
return NULL;
- if (!pmd_present(*pmd)) {
+ if (!pmd_present(*pmd))
set_pmd(pmd, *pmd_k);
- arch_flush_lazy_mmu_mode();
- } else {
+ else
BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
- }
return pmd_k;
}
static int is_errata93(struct pt_regs *regs, unsigned long address)
{
#ifdef CONFIG_X86_64
- static int once;
-
if (address != regs->ip)
return 0;
address |= 0xffffffffUL << 32;
if ((address >= (u64)_stext && address <= (u64)_etext) ||
(address >= MODULES_VADDR && address <= MODULES_END)) {
- if (!once) {
- printk(errata93_warning);
- once = 1;
- }
+ printk_once(errata93_warning);
regs->ip = address;
return 1;
}
{
struct task_struct *tsk = current;
unsigned long *stackend;
-
-#ifdef CONFIG_X86_64
unsigned long flags;
int sig;
-#endif
/* Are we prepared to handle this kernel fault? */
if (fixup_exception(regs))
* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice:
*/
-#ifdef CONFIG_X86_32
- bust_spinlocks(1);
-#else
flags = oops_begin();
-#endif
show_fault_oops(regs, error_code, address);
if (*stackend != STACK_END_MAGIC)
printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
- tsk->thread.cr2 = address;
- tsk->thread.trap_no = 14;
- tsk->thread.error_code = error_code;
+ tsk->thread.cr2 = address;
+ tsk->thread.trap_no = 14;
+ tsk->thread.error_code = error_code;
-#ifdef CONFIG_X86_32
- die("Oops", regs, error_code);
- bust_spinlocks(0);
- do_exit(SIGKILL);
-#else
sig = SIGKILL;
if (__die("Oops", regs, error_code))
sig = 0;
printk(KERN_EMERG "CR2: %016lx\n", address);
oops_end(flags, regs, sig);
-#endif
}
/*
if (!(error_code & PF_USER))
no_context(regs, error_code, address);
-#ifdef CONFIG_X86_32
- /* User space => ok to do another page fault: */
+ /* User-space => ok to do another page fault: */
if (is_prefetch(regs, error_code, address))
return;
-#endif
tsk->thread.cr2 = address;
tsk->thread.error_code = error_code;
static int fault_in_kernel_space(unsigned long address)
{
-#ifdef CONFIG_X86_32
- return address >= TASK_SIZE;
-#else
- return address >= TASK_SIZE64;
-#endif
+ return address >= TASK_SIZE_MAX;
}
/*
* and the problem, and then passes it off to one of the appropriate
* routines.
*/
-#ifdef CONFIG_X86_64
-asmlinkage
-#endif
-void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
+dotraplinkage void __kprobes
+do_page_fault(struct pt_regs *regs, unsigned long error_code)
{
struct vm_area_struct *vma;
struct task_struct *tsk;
tsk = current;
mm = tsk->mm;
- prefetchw(&mm->mmap_sem);
-
/* Get the faulting address: */
address = read_cr2();
+ /*
+ * Detect and handle instructions that would cause a page fault for
+ * both a tracked kernel page and a userspace page.
+ */
+ if (kmemcheck_active(regs))
+ kmemcheck_hide(regs);
+ prefetchw(&mm->mmap_sem);
+
if (unlikely(kmmio_fault(regs, address)))
return;
* protection error (error_code & 9) == 0.
*/
if (unlikely(fault_in_kernel_space(address))) {
- if (!(error_code & (PF_RSVD|PF_USER|PF_PROT)) &&
- vmalloc_fault(address) >= 0)
- return;
+ if (!(error_code & (PF_RSVD | PF_USER | PF_PROT))) {
+ if (vmalloc_fault(address) >= 0)
+ return;
+
+ if (kmemcheck_fault(regs, address, error_code))
+ return;
+ }
/* Can handle a stale RO->RW TLB: */
if (spurious_fault(error_code, address))
if (unlikely(error_code & PF_RSVD))
pgtable_bad(regs, error_code, address);
+ perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+
/*
* If we're in an interrupt, have no user context or are running
* in an atomic region then we must not take the fault:
* make sure we exit gracefully rather than endlessly redo
* the fault:
*/
- fault = handle_mm_fault(mm, vma, address, write);
+ fault = handle_mm_fault(mm, vma, address, write ? FAULT_FLAG_WRITE : 0);
if (unlikely(fault & VM_FAULT_ERROR)) {
mm_fault_error(regs, error_code, address, fault);
return;
}
- if (fault & VM_FAULT_MAJOR)
+ if (fault & VM_FAULT_MAJOR) {
tsk->maj_flt++;
- else
+ perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
+ regs, address);
+ } else {
tsk->min_flt++;
+ perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
+ regs, address);
+ }
check_v8086_mode(regs, address, tsk);