#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
+#include <linux/mmiotrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/smp.h>
#define PF_RSVD (1<<3)
#define PF_INSTR (1<<4)
+static inline int kmmio_fault(struct pt_regs *regs, unsigned long addr)
+{
+#ifdef CONFIG_MMIOTRACE_HOOKS
+ if (unlikely(is_kmmio_active()))
+ if (kmmio_handler(regs, addr) == 1)
+ return -1;
+#endif
+ return 0;
+}
+
static inline int notify_page_fault(struct pt_regs *regs)
{
#ifdef CONFIG_KPROBES
int ret = 0;
/* kprobe_running() needs smp_processor_id() */
-#ifdef CONFIG_X86_32
if (!user_mode_vm(regs)) {
-#else
- if (!user_mode(regs)) {
-#endif
preempt_disable();
if (kprobe_running() && kprobe_fault_handler(regs, 14))
ret = 1;
int prefetch = 0;
unsigned char *max_instr;
-#ifdef CONFIG_X86_32
- if (!(__supported_pte_mask & _PAGE_NX))
- return 0;
-#endif
-
- /* If it was a exec fault on NX page, ignore */
+ /*
+ * If it was a exec (instruction fetch) fault on NX page, then
+ * do not ignore the fault:
+ */
if (error_code & PF_INSTR)
return 0;
}
#endif
-void dump_pagetable(unsigned long address)
+static void dump_pagetable(unsigned long address)
{
#ifdef CONFIG_X86_32
__typeof__(pte_val(__pte(0))) page;
pud = pud_offset(pgd, address);
if (bad_address(pud)) goto bad;
printk("PUD %lx ", pud_val(*pud));
- if (!pud_present(*pud)) goto ret;
+ if (!pud_present(*pud) || pud_large(*pud))
+ goto ret;
pmd = pmd_offset(pud, address);
if (bad_address(pmd)) goto bad;
#ifdef CONFIG_X86_32
if (!oops_may_print())
return;
+#endif
#ifdef CONFIG_X86_PAE
if (error_code & PF_INSTR) {
- int level;
+ unsigned int level;
pte_t *pte = lookup_address(address, &level);
if (pte && pte_present(*pte) && !pte_exec(*pte))
"(uid: %d)\n", current->uid);
}
#endif
- printk(KERN_ALERT "BUG: unable to handle kernel ");
- if (address < PAGE_SIZE)
- printk(KERN_CONT "NULL pointer dereference");
- else
- printk(KERN_CONT "paging request");
- printk(KERN_CONT " at %08lx\n", address);
- printk(KERN_ALERT "IP:");
- printk_address(regs->ip, 1);
- dump_pagetable(address);
-#else /* CONFIG_X86_64 */
printk(KERN_ALERT "BUG: unable to handle kernel ");
if (address < PAGE_SIZE)
printk(KERN_CONT "NULL pointer dereference");
else
printk(KERN_CONT "paging request");
- printk(KERN_CONT " at %016lx\n", address);
-
+ printk(KERN_CONT " at %p\n", (void *) address);
printk(KERN_ALERT "IP:");
printk_address(regs->ip, 1);
dump_pagetable(address);
-#endif
}
#ifdef CONFIG_X86_64
}
#endif
+static int spurious_fault_check(unsigned long error_code, pte_t *pte)
+{
+ if ((error_code & PF_WRITE) && !pte_write(*pte))
+ return 0;
+ if ((error_code & PF_INSTR) && !pte_exec(*pte))
+ return 0;
+
+ return 1;
+}
+
+/*
+ * Handle a spurious fault caused by a stale TLB entry. This allows
+ * us to lazily refresh the TLB when increasing the permissions of a
+ * kernel page (RO -> RW or NX -> X). Doing it eagerly is very
+ * expensive since that implies doing a full cross-processor TLB
+ * flush, even if no stale TLB entries exist on other processors.
+ * There are no security implications to leaving a stale TLB when
+ * increasing the permissions on a page.
+ */
+static int spurious_fault(unsigned long address,
+ unsigned long error_code)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ /* Reserved-bit violation or user access to kernel space? */
+ if (error_code & (PF_USER | PF_RSVD))
+ return 0;
+
+ pgd = init_mm.pgd + pgd_index(address);
+ if (!pgd_present(*pgd))
+ return 0;
+
+ pud = pud_offset(pgd, address);
+ if (!pud_present(*pud))
+ return 0;
+
+ if (pud_large(*pud))
+ return spurious_fault_check(error_code, (pte_t *) pud);
+
+ pmd = pmd_offset(pud, address);
+ if (!pmd_present(*pmd))
+ return 0;
+
+ if (pmd_large(*pmd))
+ return spurious_fault_check(error_code, (pte_t *) pmd);
+
+ pte = pte_offset_kernel(pmd, address);
+ if (!pte_present(*pte))
+ return 0;
+
+ return spurious_fault_check(error_code, pte);
+}
+
/*
* X86_32
* Handle a fault on the vmalloc or module mapping area
unsigned long pgd_paddr;
pmd_t *pmd_k;
pte_t *pte_k;
+
+ /* Make sure we are in vmalloc area */
+ if (!(address >= VMALLOC_START && address < VMALLOC_END))
+ return -1;
+
/*
* Synchronize this task's top level page-table
* with the 'reference' page table.
pmd_t *pmd, *pmd_ref;
pte_t *pte, *pte_ref;
+ /* Make sure we are in vmalloc area */
+ if (!(address >= VMALLOC_START && address < VMALLOC_END))
+ return -1;
+
/* Copy kernel mappings over when needed. This can also
happen within a race in page table update. In the later
case just flush. */
if (notify_page_fault(regs))
return;
+ if (unlikely(kmmio_fault(regs, address)))
+ return;
/*
* We fault-in kernel-space virtual memory on-demand. The
*/
#ifdef CONFIG_X86_32
if (unlikely(address >= TASK_SIZE)) {
+#else
+ if (unlikely(address >= TASK_SIZE64)) {
+#endif
if (!(error_code & (PF_RSVD|PF_USER|PF_PROT)) &&
vmalloc_fault(address) >= 0)
return;
+
+ /* Can handle a stale RO->RW TLB */
+ if (spurious_fault(address, error_code))
+ return;
+
/*
* Don't take the mm semaphore here. If we fixup a prefetch
* fault we could otherwise deadlock.
goto bad_area_nosemaphore;
}
+
+#ifdef CONFIG_X86_32
/* It's safe to allow irq's after cr2 has been saved and the vmalloc
fault has been handled. */
- if (regs->flags & (X86_EFLAGS_IF|VM_MASK))
+ if (regs->flags & (X86_EFLAGS_IF | X86_VM_MASK))
local_irq_enable();
/*
if (in_atomic() || !mm)
goto bad_area_nosemaphore;
#else /* CONFIG_X86_64 */
- if (unlikely(address >= TASK_SIZE64)) {
- /*
- * Don't check for the module range here: its PML4
- * is always initialized because it's shared with the main
- * kernel text. Only vmalloc may need PML4 syncups.
- */
- if (!(error_code & (PF_RSVD|PF_USER|PF_PROT)) &&
- ((address >= VMALLOC_START && address < VMALLOC_END))) {
- if (vmalloc_fault(address) >= 0)
- return;
- }
- /*
- * Don't take the mm semaphore here. If we fixup a prefetch
- * fault we could otherwise deadlock.
- */
- goto bad_area_nosemaphore;
- }
if (likely(regs->flags & X86_EFLAGS_IF))
local_irq_enable();
vma = find_vma(mm, address);
if (!vma)
goto bad_area;
-#ifdef CONFIG_X86_32
if (vma->vm_start <= address)
-#else
- if (likely(vma->vm_start <= address))
-#endif
goto good_area;
if (!(vma->vm_flags & VM_GROWSDOWN))
goto bad_area;
if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
printk_ratelimit()) {
printk(
-#ifdef CONFIG_X86_32
- "%s%s[%d]: segfault at %lx ip %08lx sp %08lx error %lx",
-#else
- "%s%s[%d]: segfault at %lx ip %lx sp %lx error %lx",
-#endif
+ "%s%s[%d]: segfault at %lx ip %p sp %p error %lx",
task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
- tsk->comm, task_pid_nr(tsk), address, regs->ip,
- regs->sp, error_code);
+ tsk->comm, task_pid_nr(tsk), address,
+ (void *) regs->ip, (void *) regs->sp, error_code);
print_vma_addr(" in ", regs->ip);
printk("\n");
}
*/
#ifdef CONFIG_X86_32
bust_spinlocks(1);
+#else
+ flags = oops_begin();
+#endif
show_fault_oops(regs, error_code, address);
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 /* CONFIG_X86_64 */
- flags = oops_begin();
-
- show_fault_oops(regs, error_code, address);
-
- tsk->thread.cr2 = address;
- tsk->thread.trap_no = 14;
- tsk->thread.error_code = error_code;
+#else
if (__die("Oops", regs, error_code))
regs = NULL;
/* Executive summary in case the body of the oops scrolled away */
*/
out_of_memory:
up_read(&mm->mmap_sem);
-#ifdef CONFIG_X86_32
if (is_global_init(tsk)) {
yield();
+#ifdef CONFIG_X86_32
down_read(&mm->mmap_sem);
goto survive;
- }
#else
- if (is_global_init(current)) {
- yield();
goto again;
- }
#endif
+ }
+
printk("VM: killing process %s\n", tsk->comm);
if (error_code & PF_USER)
do_group_exit(SIGKILL);
force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);
}
-#ifdef CONFIG_X86_64
DEFINE_SPINLOCK(pgd_lock);
LIST_HEAD(pgd_list);
-#endif
void vmalloc_sync_all(void)
{
#ifdef CONFIG_X86_32
- /*
- * Note that races in the updates of insync and start aren't
- * problematic: insync can only get set bits added, and updates to
- * start are only improving performance (without affecting correctness
- * if undone).
- */
- static DECLARE_BITMAP(insync, PTRS_PER_PGD);
- static unsigned long start = TASK_SIZE;
+ unsigned long start = VMALLOC_START & PGDIR_MASK;
unsigned long address;
if (SHARED_KERNEL_PMD)
BUILD_BUG_ON(TASK_SIZE & ~PGDIR_MASK);
for (address = start; address >= TASK_SIZE; address += PGDIR_SIZE) {
- if (!test_bit(pgd_index(address), insync)) {
- unsigned long flags;
- struct page *page;
-
- spin_lock_irqsave(&pgd_lock, flags);
- for (page = pgd_list; page; page =
- (struct page *)page->index)
- if (!vmalloc_sync_one(page_address(page),
- address)) {
- BUG_ON(page != pgd_list);
- break;
- }
- spin_unlock_irqrestore(&pgd_lock, flags);
- if (!page)
- set_bit(pgd_index(address), insync);
+ unsigned long flags;
+ struct page *page;
+
+ spin_lock_irqsave(&pgd_lock, flags);
+ list_for_each_entry(page, &pgd_list, lru) {
+ if (!vmalloc_sync_one(page_address(page),
+ address))
+ break;
}
- if (address == start && test_bit(pgd_index(address), insync))
- start = address + PGDIR_SIZE;
+ spin_unlock_irqrestore(&pgd_lock, flags);
}
#else /* CONFIG_X86_64 */
- /*
- * Note that races in the updates of insync and start aren't
- * problematic: insync can only get set bits added, and updates to
- * start are only improving performance (without affecting correctness
- * if undone).
- */
- static DECLARE_BITMAP(insync, PTRS_PER_PGD);
- static unsigned long start = VMALLOC_START & PGDIR_MASK;
+ unsigned long start = VMALLOC_START & PGDIR_MASK;
unsigned long address;
for (address = start; address <= VMALLOC_END; address += PGDIR_SIZE) {
- if (!test_bit(pgd_index(address), insync)) {
- const pgd_t *pgd_ref = pgd_offset_k(address);
- struct page *page;
-
- if (pgd_none(*pgd_ref))
- continue;
- spin_lock(&pgd_lock);
- list_for_each_entry(page, &pgd_list, lru) {
- pgd_t *pgd;
- pgd = (pgd_t *)page_address(page) + pgd_index(address);
- if (pgd_none(*pgd))
- set_pgd(pgd, *pgd_ref);
- else
- BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
- }
- spin_unlock(&pgd_lock);
- set_bit(pgd_index(address), insync);
+ const pgd_t *pgd_ref = pgd_offset_k(address);
+ unsigned long flags;
+ struct page *page;
+
+ if (pgd_none(*pgd_ref))
+ continue;
+ spin_lock_irqsave(&pgd_lock, flags);
+ list_for_each_entry(page, &pgd_list, lru) {
+ pgd_t *pgd;
+ pgd = (pgd_t *)page_address(page) + pgd_index(address);
+ if (pgd_none(*pgd))
+ set_pgd(pgd, *pgd_ref);
+ else
+ BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
}
- if (address == start)
- start = address + PGDIR_SIZE;
+ spin_unlock_irqrestore(&pgd_lock, flags);
}
- /* Check that there is no need to do the same for the modules area. */
- BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL));
- BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) ==
- (__START_KERNEL & PGDIR_MASK)));
#endif
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff