X-Git-Url: http://nv-tegra.nvidia.com/gitweb/?p=linux-2.6.git;a=blobdiff_plain;f=arch%2Fi386%2Fmm%2Ffault.c;h=bd6fe96cc16d1f5cf0814aae900425a7dc39fecc;hp=8e90339d6eaaa18c96a5292c53f6590235804764;hb=19964fecf25c17f865dec07ae242b1a40ea93f16;hpb=c7c5844526f55b93fc9a44170cb7568c9bc95c4a diff --git a/arch/i386/mm/fault.c b/arch/i386/mm/fault.c index 8e90339..bd6fe96 100644 --- a/arch/i386/mm/fault.c +++ b/arch/i386/mm/fault.c @@ -21,6 +21,7 @@ #include /* For unblank_screen() */ #include #include +#include #include #include @@ -76,12 +77,15 @@ static inline unsigned long get_segment_eip(struct pt_regs *regs, unsigned seg = regs->xcs & 0xffff; u32 seg_ar, seg_limit, base, *desc; + /* Unlikely, but must come before segment checks. */ + if (unlikely(regs->eflags & VM_MASK)) { + base = seg << 4; + *eip_limit = base + 0xffff; + return base + (eip & 0xffff); + } + /* The standard kernel/user address space limit. */ *eip_limit = (seg & 3) ? USER_DS.seg : KERNEL_DS.seg; - - /* Unlikely, but must come before segment checks. */ - if (unlikely((regs->eflags & VM_MASK) != 0)) - return eip + (seg << 4); /* By far the most common cases. */ if (likely(seg == __USER_CS || seg == __KERNEL_CS)) @@ -107,7 +111,7 @@ static inline unsigned long get_segment_eip(struct pt_regs *regs, desc = (void *)desc + (seg & ~7); } else { /* Must disable preemption while reading the GDT. */ - desc = (u32 *)&per_cpu(cpu_gdt_table, get_cpu()); + desc = (u32 *)get_cpu_gdt_table(get_cpu()); desc = (void *)desc + (seg & ~7); } @@ -199,8 +203,82 @@ static inline int is_prefetch(struct pt_regs *regs, unsigned long addr, return 0; } +static noinline void force_sig_info_fault(int si_signo, int si_code, + unsigned long address, struct task_struct *tsk) +{ + siginfo_t info; + + info.si_signo = si_signo; + info.si_errno = 0; + info.si_code = si_code; + info.si_addr = (void __user *)address; + force_sig_info(si_signo, &info, tsk); +} + fastcall void do_invalid_op(struct pt_regs *, unsigned long); +static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address) +{ + unsigned index = pgd_index(address); + pgd_t *pgd_k; + pud_t *pud, *pud_k; + pmd_t *pmd, *pmd_k; + + pgd += index; + pgd_k = init_mm.pgd + index; + + if (!pgd_present(*pgd_k)) + return NULL; + + /* + * set_pgd(pgd, *pgd_k); here would be useless on PAE + * and redundant with the set_pmd() on non-PAE. As would + * set_pud. + */ + + pud = pud_offset(pgd, address); + pud_k = pud_offset(pgd_k, address); + if (!pud_present(*pud_k)) + return NULL; + + pmd = pmd_offset(pud, address); + pmd_k = pmd_offset(pud_k, address); + if (!pmd_present(*pmd_k)) + return NULL; + if (!pmd_present(*pmd)) + set_pmd(pmd, *pmd_k); + else + BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k)); + return pmd_k; +} + +/* + * Handle a fault on the vmalloc or module mapping area + * + * This assumes no large pages in there. + */ +static inline int vmalloc_fault(unsigned long address) +{ + unsigned long pgd_paddr; + pmd_t *pmd_k; + pte_t *pte_k; + /* + * Synchronize this task's top level page-table + * with the 'reference' page table. + * + * Do _not_ use "current" here. We might be inside + * an interrupt in the middle of a task switch.. + */ + pgd_paddr = read_cr3(); + pmd_k = vmalloc_sync_one(__va(pgd_paddr), address); + if (!pmd_k) + return -1; + pte_k = pte_offset_kernel(pmd_k, address); + if (!pte_present(*pte_k)) + return -1; + return 0; +} + /* * This routine handles page faults. It determines the address, * and the problem, and then passes it off to one of the appropriate @@ -210,30 +288,25 @@ fastcall void do_invalid_op(struct pt_regs *, unsigned long); * bit 0 == 0 means no page found, 1 means protection fault * bit 1 == 0 means read, 1 means write * bit 2 == 0 means kernel, 1 means user-mode + * bit 3 == 1 means use of reserved bit detected + * bit 4 == 1 means fault was an instruction fetch */ -fastcall void do_page_fault(struct pt_regs *regs, unsigned long error_code) +fastcall void __kprobes do_page_fault(struct pt_regs *regs, + unsigned long error_code) { struct task_struct *tsk; struct mm_struct *mm; struct vm_area_struct * vma; unsigned long address; unsigned long page; - int write; - siginfo_t info; + int write, si_code; /* get the address */ - __asm__("movl %%cr2,%0":"=r" (address)); - - if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14, - SIGSEGV) == NOTIFY_STOP) - return; - /* It's safe to allow irq's after cr2 has been saved */ - if (regs->eflags & (X86_EFLAGS_IF|VM_MASK)) - local_irq_enable(); + address = read_cr2(); tsk = current; - info.si_code = SEGV_MAPERR; + si_code = SEGV_MAPERR; /* * We fault-in kernel-space virtual memory on-demand. The @@ -246,17 +319,29 @@ fastcall void do_page_fault(struct pt_regs *regs, unsigned long error_code) * * This verifies that the fault happens in kernel space * (error_code & 4) == 0, and that the fault was not a - * protection error (error_code & 1) == 0. + * protection error (error_code & 9) == 0. */ - if (unlikely(address >= TASK_SIZE)) { - if (!(error_code & 5)) - goto vmalloc_fault; - /* + if (unlikely(address >= TASK_SIZE)) { + if (!(error_code & 0x0000000d) && vmalloc_fault(address) >= 0) + return; + if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14, + SIGSEGV) == NOTIFY_STOP) + return; + /* * Don't take the mm semaphore here. If we fixup a prefetch * fault we could otherwise deadlock. */ goto bad_area_nosemaphore; - } + } + + if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14, + SIGSEGV) == NOTIFY_STOP) + return; + + /* It's safe to allow irq's after cr2 has been saved and the vmalloc + fault has been handled. */ + if (regs->eflags & (X86_EFLAGS_IF|VM_MASK)) + local_irq_enable(); mm = tsk->mm; @@ -298,12 +383,12 @@ fastcall void do_page_fault(struct pt_regs *regs, unsigned long error_code) goto bad_area; if (error_code & 4) { /* - * accessing the stack below %esp is always a bug. - * The "+ 32" is there due to some instructions (like - * pusha) doing post-decrement on the stack and that - * doesn't show up until later.. + * Accessing the stack below %esp is always a bug. + * The large cushion allows instructions like enter + * and pusha to work. ("enter $65535,$31" pushes + * 32 pointers and then decrements %esp by 65535.) */ - if (address + 32 < regs->esp) + if (address + 65536 + 32 * sizeof(unsigned long) < regs->esp) goto bad_area; } if (expand_stack(vma, address)) @@ -313,7 +398,7 @@ fastcall void do_page_fault(struct pt_regs *regs, unsigned long error_code) * we can handle it.. */ good_area: - info.si_code = SEGV_ACCERR; + si_code = SEGV_ACCERR; write = 0; switch (error_code & 3) { default: /* 3: write, present */ @@ -387,11 +472,7 @@ bad_area_nosemaphore: /* Kernel addresses are always protection faults */ tsk->thread.error_code = error_code | (address >= TASK_SIZE); tsk->thread.trap_no = 14; - info.si_signo = SIGSEGV; - info.si_errno = 0; - /* info.si_code has been set above */ - info.si_addr = (void __user *)address; - force_sig_info(SIGSEGV, &info, tsk); + force_sig_info_fault(SIGSEGV, si_code, address, tsk); return; } @@ -431,24 +512,31 @@ no_context: bust_spinlocks(1); -#ifdef CONFIG_X86_PAE - if (error_code & 16) { - pte_t *pte = lookup_address(address); + if (oops_may_print()) { + #ifdef CONFIG_X86_PAE + if (error_code & 16) { + pte_t *pte = lookup_address(address); - if (pte && pte_present(*pte) && !pte_exec_kernel(*pte)) - printk(KERN_CRIT "kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n", current->uid); + if (pte && pte_present(*pte) && !pte_exec_kernel(*pte)) + printk(KERN_CRIT "kernel tried to execute " + "NX-protected page - exploit attempt? " + "(uid: %d)\n", current->uid); + } + #endif + if (address < PAGE_SIZE) + printk(KERN_ALERT "BUG: unable to handle kernel NULL " + "pointer dereference"); + else + printk(KERN_ALERT "BUG: unable to handle kernel paging" + " request"); + printk(" at virtual address %08lx\n",address); + printk(KERN_ALERT " printing eip:\n"); + printk("%08lx\n", regs->eip); } -#endif - if (address < PAGE_SIZE) - printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference"); - else - printk(KERN_ALERT "Unable to handle kernel paging request"); - printk(" at virtual address %08lx\n",address); - printk(KERN_ALERT " printing eip:\n"); - printk("%08lx\n", regs->eip); - asm("movl %%cr3,%0":"=r" (page)); + page = read_cr3(); page = ((unsigned long *) __va(page))[address >> 22]; - printk(KERN_ALERT "*pde = %08lx\n", page); + if (oops_may_print()) + printk(KERN_ALERT "*pde = %08lx\n", page); /* * We must not directly access the pte in the highpte * case, the page table might be allocated in highmem. @@ -456,7 +544,7 @@ no_context: * it's allocated already. */ #ifndef CONFIG_HIGHPTE - if (page & 1) { + if ((page & 1) && oops_may_print()) { page &= PAGE_MASK; address &= 0x003ff000; page = ((unsigned long *) __va(page))[address >> PAGE_SHIFT]; @@ -500,56 +588,42 @@ do_sigbus: tsk->thread.cr2 = address; tsk->thread.error_code = error_code; tsk->thread.trap_no = 14; - info.si_signo = SIGBUS; - info.si_errno = 0; - info.si_code = BUS_ADRERR; - info.si_addr = (void __user *)address; - force_sig_info(SIGBUS, &info, tsk); - return; - -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 index = pgd_index(address); - unsigned long pgd_paddr; - pgd_t *pgd, *pgd_k; - pud_t *pud, *pud_k; - pmd_t *pmd, *pmd_k; - pte_t *pte_k; - - asm("movl %%cr3,%0":"=r" (pgd_paddr)); - pgd = index + (pgd_t *)__va(pgd_paddr); - pgd_k = init_mm.pgd + index; - - if (!pgd_present(*pgd_k)) - goto no_context; - - /* - * set_pgd(pgd, *pgd_k); here would be useless on PAE - * and redundant with the set_pmd() on non-PAE. As would - * set_pud. - */ + force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk); +} - 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); +#ifndef CONFIG_X86_PAE +void vmalloc_sync_all(void) +{ + /* + * 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 address; - pte_k = pte_offset_kernel(pmd_k, address); - if (!pte_present(*pte_k)) - goto no_context; - return; + 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); + } + if (address == start && test_bit(pgd_index(address), insync)) + start = address + PGDIR_SIZE; } } +#endif