X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=arch%2Fx86_64%2Fmm%2Ffault.c;h=5724370475cc10816730aeb7375e4193206f36fc;hb=6a77f38946aaee1cd85eeec6cf4229b204c15071;hp=4e12a56c9321ca1775fad11556f897a4dab13a21;hpb=87fc8d1bb10cd459024a742c6a10961fefcef18f;p=linux-2.6.git diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c index 4e12a56c9..572437047 100644 --- a/arch/x86_64/mm/fault.c +++ b/arch/x86_64/mm/fault.c @@ -23,6 +23,7 @@ #include /* For unblank_screen() */ #include #include +#include #include #include @@ -32,6 +33,7 @@ #include #include #include +#include void bust_spinlocks(int yes) { @@ -141,25 +143,25 @@ static int bad_address(void *p) void dump_pagetable(unsigned long address) { - pml4_t *pml4; pgd_t *pgd; + pud_t *pud; pmd_t *pmd; pte_t *pte; - asm("movq %%cr3,%0" : "=r" (pml4)); - - pml4 = __va((unsigned long)pml4 & PHYSICAL_PAGE_MASK); - pml4 += pml4_index(address); - printk("PML4 %lx ", pml4_val(*pml4)); - if (bad_address(pml4)) goto bad; - if (!pml4_present(*pml4)) goto ret; + asm("movq %%cr3,%0" : "=r" (pgd)); - pgd = __pgd_offset_k((pgd_t *)pml4_page(*pml4), address); + pgd = __va((unsigned long)pgd & PHYSICAL_PAGE_MASK); + pgd += pgd_index(address); + printk("PGD %lx ", pgd_val(*pgd)); if (bad_address(pgd)) goto bad; - printk("PGD %lx ", pgd_val(*pgd)); - if (!pgd_present(*pgd)) goto ret; + if (!pgd_present(*pgd)) goto ret; - pmd = pmd_offset(pgd, address); + pud = __pud_offset_k((pud_t *)pgd_page(*pgd), address); + if (bad_address(pud)) goto bad; + printk("PUD %lx ", pud_val(*pud)); + if (!pud_present(*pud)) goto ret; + + pmd = pmd_offset(pud, address); if (bad_address(pmd)) goto bad; printk("PMD %lx ", pmd_val(*pmd)); if (!pmd_present(*pmd)) goto ret; @@ -210,6 +212,8 @@ static int is_errata93(struct pt_regs *regs, unsigned long address) int unhandled_signal(struct task_struct *tsk, int sig) { + if (tsk->pid == 1) + return 1; /* Warn for strace, but not for gdb */ if (!test_ti_thread_flag(tsk->thread_info, TIF_SYSCALL_TRACE) && (tsk->ptrace & PT_PTRACED)) @@ -230,7 +234,53 @@ static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs, do_exit(SIGKILL); } -int page_fault_trace; +/* + * Handle a fault on the vmalloc or module mapping area + */ +static int vmalloc_fault(unsigned long address) +{ + pgd_t *pgd, *pgd_ref; + pud_t *pud, *pud_ref; + pmd_t *pmd, *pmd_ref; + pte_t *pte, *pte_ref; + + /* Copy kernel mappings over when needed. This can also + happen within a race in page table update. In the later + case just flush. */ + + pgd = pgd_offset(current->mm ?: &init_mm, address); + pgd_ref = pgd_offset_k(address); + if (pgd_none(*pgd_ref)) + return -1; + if (pgd_none(*pgd)) + set_pgd(pgd, *pgd_ref); + + /* Below here mismatches are bugs because these lower tables + are shared */ + + pud = pud_offset(pgd, address); + pud_ref = pud_offset(pgd_ref, address); + if (pud_none(*pud_ref)) + return -1; + if (pud_none(*pud) || pud_page(*pud) != pud_page(*pud_ref)) + BUG(); + pmd = pmd_offset(pud, address); + pmd_ref = pmd_offset(pud_ref, address); + if (pmd_none(*pmd_ref)) + return -1; + if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref)) + BUG(); + pte_ref = pte_offset_kernel(pmd_ref, address); + if (!pte_present(*pte_ref)) + return -1; + pte = pte_offset_kernel(pmd, address); + if (!pte_present(*pte) || pte_page(*pte) != pte_page(*pte_ref)) + BUG(); + __flush_tlb_all(); + return 0; +} + +int page_fault_trace = 0; int exception_trace = 1; /* @@ -268,6 +318,9 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code) /* get the address */ __asm__("movq %%cr2,%0":"=r" (address)); + if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14, + SIGSEGV) == NOTIFY_STOP) + return; if (likely(regs->eflags & X86_EFLAGS_IF)) local_irq_enable(); @@ -295,8 +348,11 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code) * protection error (error_code & 1) == 0. */ if (unlikely(address >= TASK_SIZE)) { - if (!(error_code & 5)) - goto vmalloc_fault; + if (!(error_code & 5)) { + if (vmalloc_fault(address) < 0) + goto bad_area_nosemaphore; + return; + } /* * Don't take the mm semaphore here. If we fixup a prefetch * fault we could otherwise deadlock. @@ -305,7 +361,7 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code) } if (unlikely(error_code & (1 << 3))) - goto page_table_corruption; + pgtable_bad(address, regs, error_code); /* * If we're in an interrupt or have no user @@ -406,7 +462,7 @@ bad_area_nosemaphore: #ifdef CONFIG_IA32_EMULATION /* 32bit vsyscall. map on demand. */ if (test_thread_flag(TIF_IA32) && - address >= 0xffffe000 && address < 0xffffe000 + PAGE_SIZE) { + address >= VSYSCALL32_BASE && address < VSYSCALL32_END) { if (map_syscall32(mm, address) < 0) goto out_of_memory2; return; @@ -429,8 +485,9 @@ bad_area_nosemaphore: return; if (exception_trace && unhandled_signal(tsk, SIGSEGV)) { - printk(KERN_INFO - "%s[%d]: segfault at %016lx rip %016lx rsp %016lx error %lx\n", + printk( + "%s%s[%d]: segfault at %016lx rip %016lx rsp %016lx error %lx\n", + tsk->pid > 1 ? KERN_INFO : KERN_EMERG, tsk->comm, tsk->pid, address, regs->rip, regs->rsp, error_code); } @@ -519,34 +576,4 @@ do_sigbus: info.si_addr = (void __user *)address; force_sig_info(SIGBUS, &info, tsk); return; - -vmalloc_fault: - { - pgd_t *pgd; - pmd_t *pmd; - pte_t *pte; - - /* - * x86-64 has the same kernel 3rd level pages for all CPUs. - * But for vmalloc/modules the TLB synchronization works lazily, - * so it can happen that we get a page fault for something - * that is really already in the page table. Just check if it - * is really there and when yes flush the local TLB. - */ - pgd = pgd_offset_k(address); - if (!pgd_present(*pgd)) - goto bad_area_nosemaphore; - pmd = pmd_offset(pgd, address); - if (!pmd_present(*pmd)) - goto bad_area_nosemaphore; - pte = pte_offset_kernel(pmd, address); - if (!pte_present(*pte)) - goto bad_area_nosemaphore; - - __flush_tlb_all(); - return; - } - -page_table_corruption: - pgtable_bad(address, regs, error_code); }