diff options
Diffstat (limited to 'arch/x86/mm')
| -rw-r--r-- | arch/x86/mm/fault.c | 450 | ||||
| -rw-r--r-- | arch/x86/mm/pageattr.c | 10 | ||||
| -rw-r--r-- | arch/x86/mm/pat.c | 45 | ||||
| -rw-r--r-- | arch/x86/mm/tlb.c | 16 |
4 files changed, 287 insertions, 234 deletions
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 37242c405f1..65709a6aa6e 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -92,8 +92,8 @@ static inline int notify_page_fault(struct pt_regs *regs) * * Opcode checker based on code by Richard Brunner */ -static int is_prefetch(struct pt_regs *regs, unsigned long addr, - unsigned long error_code) +static int is_prefetch(struct pt_regs *regs, unsigned long error_code, + unsigned long addr) { unsigned char *instr; int scan_more = 1; @@ -410,15 +410,15 @@ static void show_fault_oops(struct pt_regs *regs, unsigned long error_code, } #ifdef CONFIG_X86_64 -static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs, - unsigned long error_code) +static noinline void pgtable_bad(struct pt_regs *regs, + unsigned long error_code, unsigned long address) { unsigned long flags = oops_begin(); int sig = SIGKILL; - struct task_struct *tsk; + struct task_struct *tsk = current; printk(KERN_ALERT "%s: Corrupted page table at address %lx\n", - current->comm, address); + tsk->comm, address); dump_pagetable(address); tsk = current; tsk->thread.cr2 = address; @@ -430,6 +430,196 @@ static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs, } #endif +static noinline void no_context(struct pt_regs *regs, + unsigned long error_code, unsigned long address) +{ + 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)) + return; + + /* + * X86_32 + * Valid to do another page fault here, because if this fault + * had been triggered by is_prefetch fixup_exception would have + * handled it. + * + * X86_64 + * Hall of shame of CPU/BIOS bugs. + */ + if (is_prefetch(regs, error_code, address)) + return; + + if (is_errata93(regs, address)) + return; + + /* + * 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); + + stackend = end_of_stack(tsk); + 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; + +#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; + /* Executive summary in case the body of the oops scrolled away */ + printk(KERN_EMERG "CR2: %016lx\n", address); + oops_end(flags, regs, sig); +#endif +} + +static void __bad_area_nosemaphore(struct pt_regs *regs, + unsigned long error_code, unsigned long address, + int si_code) +{ + struct task_struct *tsk = current; + + /* User mode accesses just cause a SIGSEGV */ + if (error_code & PF_USER) { + /* + * It's possible to have interrupts off here. + */ + local_irq_enable(); + + /* + * Valid to do another page fault here because this one came + * from user space. + */ + if (is_prefetch(regs, error_code, address)) + return; + + if (is_errata100(regs, address)) + return; + + if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && + printk_ratelimit()) { + printk( + "%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, + (void *) regs->ip, (void *) regs->sp, error_code); + print_vma_addr(" in ", regs->ip); + printk("\n"); + } + + tsk->thread.cr2 = address; + /* Kernel addresses are always protection faults */ + tsk->thread.error_code = error_code | (address >= TASK_SIZE); + tsk->thread.trap_no = 14; + force_sig_info_fault(SIGSEGV, si_code, address, tsk); + return; + } + + if (is_f00f_bug(regs, address)) + return; + + no_context(regs, error_code, address); +} + +static noinline void bad_area_nosemaphore(struct pt_regs *regs, + unsigned long error_code, unsigned long address) +{ + __bad_area_nosemaphore(regs, error_code, address, SEGV_MAPERR); +} + +static void __bad_area(struct pt_regs *regs, + unsigned long error_code, unsigned long address, + int si_code) +{ + struct mm_struct *mm = current->mm; + + /* + * Something tried to access memory that isn't in our memory map.. + * Fix it, but check if it's kernel or user first.. + */ + up_read(&mm->mmap_sem); + + __bad_area_nosemaphore(regs, error_code, address, si_code); +} + +static noinline void bad_area(struct pt_regs *regs, + unsigned long error_code, unsigned long address) +{ + __bad_area(regs, error_code, address, SEGV_MAPERR); +} + +static noinline void bad_area_access_error(struct pt_regs *regs, + unsigned long error_code, unsigned long address) +{ + __bad_area(regs, error_code, address, SEGV_ACCERR); +} + +/* TODO: fixup for "mm-invoke-oom-killer-from-page-fault.patch" */ +static void out_of_memory(struct pt_regs *regs, + unsigned long error_code, unsigned long address) +{ + /* + * 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(¤t->mm->mmap_sem); + pagefault_out_of_memory(); +} + +static void do_sigbus(struct pt_regs *regs, + unsigned long error_code, unsigned long address) +{ + struct task_struct *tsk = current; + struct mm_struct *mm = tsk->mm; + + up_read(&mm->mmap_sem); + + /* Kernel mode? Handle exceptions or die */ + if (!(error_code & PF_USER)) + no_context(regs, error_code, address); +#ifdef CONFIG_X86_32 + /* 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; + tsk->thread.trap_no = 14; + force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk); +} + +static noinline void mm_fault_error(struct pt_regs *regs, + unsigned long error_code, unsigned long address, unsigned int fault) +{ + if (fault & VM_FAULT_OOM) + out_of_memory(regs, error_code, address); + else if (fault & VM_FAULT_SIGBUS) + do_sigbus(regs, error_code, address); + else + BUG(); +} + static int spurious_fault_check(unsigned long error_code, pte_t *pte) { if ((error_code & PF_WRITE) && !pte_write(*pte)) @@ -449,8 +639,8 @@ static int spurious_fault_check(unsigned long error_code, pte_t *pte) * 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) +static noinline int spurious_fault(unsigned long error_code, + unsigned long address) { pgd_t *pgd; pud_t *pud; @@ -495,7 +685,7 @@ static int spurious_fault(unsigned long address, * * This assumes no large pages in there. */ -static int vmalloc_fault(unsigned long address) +static noinline int vmalloc_fault(unsigned long address) { #ifdef CONFIG_X86_32 unsigned long pgd_paddr; @@ -574,6 +764,25 @@ static int vmalloc_fault(unsigned long address) int show_unhandled_signals = 1; +static inline int access_error(unsigned long error_code, int write, + struct vm_area_struct *vma) +{ + if (write) { + /* write, present and write, not present */ + if (unlikely(!(vma->vm_flags & VM_WRITE))) + return 1; + } else if (unlikely(error_code & PF_PROT)) { + /* read, present */ + return 1; + } else { + /* read, not present */ + if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))) + 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 @@ -584,18 +793,12 @@ asmlinkage #endif void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) { + unsigned long address; struct task_struct *tsk; struct mm_struct *mm; struct vm_area_struct *vma; - unsigned long address; - int write, si_code; + int write; int fault; - unsigned long *stackend; - -#ifdef CONFIG_X86_64 - unsigned long flags; - int sig; -#endif tsk = current; mm = tsk->mm; @@ -604,9 +807,7 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) /* get the address */ address = read_cr2(); - si_code = SEGV_MAPERR; - - if (notify_page_fault(regs)) + if (unlikely(notify_page_fault(regs))) return; if (unlikely(kmmio_fault(regs, address))) return; @@ -634,17 +835,17 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) return; /* Can handle a stale RO->RW TLB */ - if (spurious_fault(address, error_code)) + if (spurious_fault(error_code, address)) return; /* * Don't take the mm semaphore here. If we fixup a prefetch * fault we could otherwise deadlock. */ - goto bad_area_nosemaphore; + bad_area_nosemaphore(regs, error_code, address); + return; } - /* * It's safe to allow irq's after cr2 has been saved and the * vmalloc fault has been handled. @@ -660,15 +861,17 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) #ifdef CONFIG_X86_64 if (unlikely(error_code & PF_RSVD)) - pgtable_bad(address, regs, error_code); + pgtable_bad(regs, error_code, address); #endif /* * If we're in an interrupt, have no user context or are running in an * atomic region then we must not take the fault. */ - if (unlikely(in_atomic() || !mm)) - goto bad_area_nosemaphore; + if (unlikely(in_atomic() || !mm)) { + bad_area_nosemaphore(regs, error_code, address); + return; + } /* * When running in the kernel we expect faults to occur only to @@ -686,20 +889,26 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) * source. If this is invalid we can skip the address space check, * thus avoiding the deadlock. */ - if (!down_read_trylock(&mm->mmap_sem)) { + if (unlikely(!down_read_trylock(&mm->mmap_sem))) { if ((error_code & PF_USER) == 0 && - !search_exception_tables(regs->ip)) - goto bad_area_nosemaphore; + !search_exception_tables(regs->ip)) { + bad_area_nosemaphore(regs, error_code, address); + return; + } down_read(&mm->mmap_sem); } vma = find_vma(mm, address); - if (!vma) - goto bad_area; - if (vma->vm_start <= address) + if (unlikely(!vma)) { + bad_area(regs, error_code, address); + return; + } + if (likely(vma->vm_start <= address)) goto good_area; - if (!(vma->vm_flags & VM_GROWSDOWN)) - goto bad_area; + if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) { + bad_area(regs, error_code, address); + return; + } if (error_code & PF_USER) { /* * Accessing the stack below %sp is always a bug. @@ -707,31 +916,25 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code) * and pusha to work. ("enter $65535,$31" pushes * 32 pointers and then decrements %sp by 65535.) */ - if (address + 65536 + 32 * sizeof(unsigned long) < regs->sp) - goto bad_area; + if (unlikely(address + 65536 + 32 * sizeof(unsigned long) < regs->sp)) { + bad_area(regs, error_code, address); + return; + } } - if (expand_stack(vma, address)) - goto bad_area; -/* - * Ok, we have a good vm_area for this memory access, so - * we can handle it.. - */ + if (unlikely(expand_stack(vma, address))) { + bad_area(regs, error_code, address); + return; + } + + /* + * Ok, we have a good vm_area for this memory access, so + * we can handle it.. + */ good_area: - si_code = SEGV_ACCERR; - write = 0; - switch (error_code & (PF_PROT|PF_WRITE)) { - default: /* 3: write, present */ - /* fall through */ - case PF_WRITE: /* write, not present */ - if (!(vma->vm_flags & VM_WRITE)) - goto bad_area; - write++; - break; - case PF_PROT: /* read, present */ - goto bad_area; - case 0: /* read, not present */ - if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))) - goto bad_area; + write = error_code & PF_WRITE; + if (unlikely(access_error(error_code, write, vma))) { + bad_area_access_error(regs, error_code, address); + return; } /* @@ -741,11 +944,8 @@ good_area: */ fault = handle_mm_fault(mm, vma, address, write); if (unlikely(fault & VM_FAULT_ERROR)) { - if (fault & VM_FAULT_OOM) - goto out_of_memory; - else if (fault & VM_FAULT_SIGBUS) - goto do_sigbus; - BUG(); + mm_fault_error(regs, error_code, address, fault); + return; } if (fault & VM_FAULT_MAJOR) tsk->maj_flt++; @@ -763,132 +963,6 @@ good_area: } #endif 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 (error_code & PF_USER) { - /* - * It's possible to have interrupts off here. - */ - local_irq_enable(); - - /* - * Valid to do another page fault here because this one came - * from user space. - */ - if (is_prefetch(regs, address, error_code)) - return; - - if (is_errata100(regs, address)) - return; - - if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) && - printk_ratelimit()) { - printk( - "%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, - (void *) regs->ip, (void *) regs->sp, error_code); - print_vma_addr(" in ", regs->ip); - printk("\n"); - } - - tsk->thread.cr2 = address; - /* Kernel addresses are always protection faults */ - tsk->thread.error_code = error_code | (address >= TASK_SIZE); - tsk->thread.trap_no = 14; - force_sig_info_fault(SIGSEGV, si_code, address, tsk); - return; - } - - if (is_f00f_bug(regs, address)) - return; - -no_context: - /* Are we prepared to handle this kernel fault? */ - if (fixup_exception(regs)) - return; - - /* - * X86_32 - * Valid to do another page fault here, because if this fault - * had been triggered by is_prefetch fixup_exception would have - * handled it. - * - * X86_64 - * Hall of shame of CPU/BIOS bugs. - */ - if (is_prefetch(regs, address, error_code)) - return; - - if (is_errata93(regs, address)) - return; - -/* - * 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); - - stackend = end_of_stack(tsk); - 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; - -#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; - /* Executive summary in case the body of the oops scrolled away */ - printk(KERN_EMERG "CR2: %016lx\n", address); - oops_end(flags, regs, sig); -#endif - -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); - pagefault_out_of_memory(); - return; - -do_sigbus: - up_read(&mm->mmap_sem); - - /* Kernel mode? Handle exceptions or die */ - if (!(error_code & PF_USER)) - goto no_context; -#ifdef CONFIG_X86_32 - /* User space => ok to do another page fault */ - if (is_prefetch(regs, address, error_code)) - return; -#endif - tsk->thread.cr2 = address; - tsk->thread.error_code = error_code; - tsk->thread.trap_no = 14; - force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk); } DEFINE_SPINLOCK(pgd_lock); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 4cf30dee816..e89d24815f2 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -555,12 +555,10 @@ repeat: if (!pte_val(old_pte)) { if (!primary) return 0; - - /* - * Special error value returned, indicating that the mapping - * did not exist at this address. - */ - return -EFAULT; + WARN(1, KERN_WARNING "CPA: called for zero pte. " + "vaddr = %lx cpa->vaddr = %lx\n", address, + *cpa->vaddr); + return -EINVAL; } if (level == PG_LEVEL_4K) { diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 3be399013de..c9488513fd7 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -522,35 +522,6 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size) } #endif /* CONFIG_STRICT_DEVMEM */ -/* - * Change the memory type for the physial address range in kernel identity - * mapping space if that range is a part of identity map. - */ -static int kernel_map_sync_memtype(u64 base, unsigned long size, - unsigned long flags) -{ - unsigned long id_sz; - int ret; - - if (!pat_enabled || base >= __pa(high_memory)) - return 0; - - id_sz = (__pa(high_memory) < base + size) ? - __pa(high_memory) - base : - size; - - ret = ioremap_change_attr((unsigned long)__va(base), id_sz, flags); - /* - * -EFAULT return means that the addr was not valid and did not have - * any identity mapping. That case is a success for - * kernel_map_sync_memtype. - */ - if (ret == -EFAULT) - ret = 0; - - return ret; -} - int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, unsigned long size, pgprot_t *vma_prot) { @@ -601,7 +572,9 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, if (retval < 0) return 0; - if (kernel_map_sync_memtype(offset, size, flags)) { + if (((pfn < max_low_pfn_mapped) || + (pfn >= (1UL<<(32 - PAGE_SHIFT)) && pfn < max_pfn_mapped)) && + ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) { free_memtype(offset, offset + size); printk(KERN_INFO "%s:%d /dev/mem ioremap_change_attr failed %s for %Lx-%Lx\n", @@ -649,7 +622,7 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, int strict_prot) { int is_ram = 0; - int ret; + int id_sz, ret; unsigned long flags; unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK); @@ -690,7 +663,15 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, flags); } - if (kernel_map_sync_memtype(paddr, size, flags)) { + /* Need to keep identity mapping in sync */ + if (paddr >= __pa(high_memory)) + return 0; + + id_sz = (__pa(high_memory) < paddr + size) ? + __pa(high_memory) - paddr : + size; + + if (ioremap_change_attr((unsigned long)__va(paddr), id_sz, flags) < 0) { free_memtype(paddr, paddr + size); printk(KERN_ERR "%s:%d reserve_pfn_range ioremap_change_attr failed %s " diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index b3ca1b94065..72a6d4ebe34 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -29,7 +29,7 @@ DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) * To avoid global state use 8 different call vectors. * Each CPU uses a specific vector to trigger flushes on other * CPUs. Depending on the received vector the target CPUs look into - * the right per cpu variable for the flush data. + * the right array slot for the flush data. * * With more than 8 CPUs they are hashed to the 8 available * vectors. The limited global vector space forces us to this right now. @@ -44,13 +44,13 @@ union smp_flush_state { spinlock_t tlbstate_lock; DECLARE_BITMAP(flush_cpumask, NR_CPUS); }; - char pad[SMP_CACHE_BYTES]; -} ____cacheline_aligned; + char pad[CONFIG_X86_INTERNODE_CACHE_BYTES]; +} ____cacheline_internodealigned_in_smp; /* State is put into the per CPU data section, but padded to a full cache line because other CPUs can access it and we don't want false sharing in the per cpu data segment. */ -static DEFINE_PER_CPU(union smp_flush_state, flush_state); +static union smp_flush_state flush_state[NUM_INVALIDATE_TLB_VECTORS]; /* * We cannot call mmdrop() because we are in interrupt context, @@ -135,7 +135,7 @@ void smp_invalidate_interrupt(struct pt_regs *regs) * Use that to determine where the sender put the data. */ sender = ~regs->orig_ax - INVALIDATE_TLB_VECTOR_START; - f = &per_cpu(flush_state, sender); + f = &flush_state[sender]; if (!cpumask_test_cpu(cpu, to_cpumask(f->flush_cpumask))) goto out; @@ -173,7 +173,7 @@ static void flush_tlb_others_ipi(const struct cpumask *cpumask, /* Caller has disabled preemption */ sender = smp_processor_id() % NUM_INVALIDATE_TLB_VECTORS; - f = &per_cpu(flush_state, sender); + f = &flush_state[sender]; /* * Could avoid this lock when @@ -227,8 +227,8 @@ static int __cpuinit init_smp_flush(void) { int i; - for_each_possible_cpu(i) - spin_lock_init(&per_cpu(flush_state, i).tlbstate_lock); + for (i = 0; i < ARRAY_SIZE(flush_state); i++) + spin_lock_init(&flush_state[i].tlbstate_lock); return 0; } |