[mirror_ubuntu-artful-kernel.git] / arch / x86 / mm / fault.c

/*
 *  Copyright (C) 1995  Linus Torvalds
 *  Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs.
 *  Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar
 */
#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_event.h>           /* perf_sw_event                */
#include <linux/hugetlb.h>              /* hstate_index_to_shift        */
#include <linux/prefetch.h>             /* prefetchw                    */
#include <linux/context_tracking.h>     /* exception_enter(), ...       */

#include <asm/traps.h>                  /* dotraplinkage, ...           */
#include <asm/pgalloc.h>                /* pgd_*(), ...                 */
#include <asm/kmemcheck.h>              /* kmemcheck_*(), ...           */
#include <asm/fixmap.h>                 /* VSYSCALL_ADDR                */
#include <asm/vsyscall.h>               /* emulate_vsyscall             */

#define CREATE_TRACE_POINTS
#include <asm/trace/exceptions.h>

/*
 * Page fault error code bits:
 *
 *   bit 0 ==    0: no page found       1: protection fault
 *   bit 1 ==    0: read access         1: write access
 *   bit 2 ==    0: kernel-mode access  1: user-mode access
 *   bit 3 ==                           1: use of reserved bit detected
 *   bit 4 ==                           1: fault was an instruction fetch
 */
enum x86_pf_error_code {

        PF_PROT         =               1 << 0,
        PF_WRITE        =               1 << 1,
        PF_USER         =               1 << 2,
        PF_RSVD         =               1 << 3,
        PF_INSTR        =               1 << 4,
};

/*
 * Returns 0 if mmiotrace is disabled, or if the fault is not
 * handled by mmiotrace:
 */
static inline int __kprobes
kmmio_fault(struct pt_regs *regs, unsigned long addr)
{
        if (unlikely(is_kmmio_active()))
                if (kmmio_handler(regs, addr) == 1)
                        return -1;
        return 0;
}

static inline int __kprobes kprobes_fault(struct pt_regs *regs)
{
        int ret = 0;

        /* kprobe_running() needs smp_processor_id() */
        if (kprobes_built_in() && !user_mode_vm(regs)) {
                preempt_disable();
                if (kprobe_running() && kprobe_fault_handler(regs, 14))
                        ret = 1;
                preempt_enable();
        }

        return ret;
}

/*
 * Prefetch quirks:
 *
 * 32-bit mode:
 *
 *   Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch.
 *   Check that here and ignore it.
 *
 * 64-bit mode:
 *
 *   Sometimes the CPU reports invalid exceptions on prefetch.
 *   Check that here and ignore it.
 *
 * Opcode checker based on code by Richard Brunner.
 */
static inline int
check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr,
                      unsigned char opcode, int *prefetch)
{
        unsigned char instr_hi = opcode & 0xf0;
        unsigned char instr_lo = opcode & 0x0f;

        switch (instr_hi) {
        case 0x20:
        case 0x30:
                /*
                 * Values 0x26,0x2E,0x36,0x3E are valid x86 prefixes.
                 * In X86_64 long mode, the CPU will signal invalid
                 * opcode if some of these prefixes are present so
                 * X86_64 will never get here anyway
                 */
                return ((instr_lo & 7) == 0x6);
#ifdef CONFIG_X86_64
        case 0x40:
                /*
                 * In AMD64 long mode 0x40..0x4F are valid REX prefixes
                 * Need to figure out under what instruction mode the
                 * instruction was issued. Could check the LDT for lm,
                 * but for now it's good enough to assume that long
                 * mode only uses well known segments or kernel.
                 */
                return (!user_mode(regs) || user_64bit_mode(regs));
#endif
        case 0x60:
                /* 0x64 thru 0x67 are valid prefixes in all modes. */
                return (instr_lo & 0xC) == 0x4;
        case 0xF0:
                /* 0xF0, 0xF2, 0xF3 are valid prefixes in all modes. */
                return !instr_lo || (instr_lo>>1) == 1;
        case 0x00:
                /* Prefetch instruction is 0x0F0D or 0x0F18 */
                if (probe_kernel_address(instr, opcode))
                        return 0;

                *prefetch = (instr_lo == 0xF) &&
                        (opcode == 0x0D || opcode == 0x18);
                return 0;
        default:
                return 0;
        }
}

static int
is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
{
        unsigned char *max_instr;
        unsigned char *instr;
        int prefetch = 0;

        /*
         * If it was a exec (instruction fetch) fault on NX page, then
         * do not ignore the fault:
         */
        if (error_code & PF_INSTR)
                return 0;

        instr = (void *)convert_ip_to_linear(current, regs);
        max_instr = instr + 15;

        if (user_mode(regs) && instr >= (unsigned char *)TASK_SIZE)
                return 0;

        while (instr < max_instr) {
                unsigned char opcode;

                if (probe_kernel_address(instr, opcode))
                        break;

                instr++;

                if (!check_prefetch_opcode(regs, instr, opcode, &prefetch))
                        break;
        }
        return prefetch;
}

static void
force_sig_info_fault(int si_signo, int si_code, unsigned long address,
                     struct task_struct *tsk, int fault)
{
        unsigned lsb = 0;
        siginfo_t info;

        info.si_signo   = si_signo;
        info.si_errno   = 0;
        info.si_code    = si_code;
        info.si_addr    = (void __user *)address;
        if (fault & VM_FAULT_HWPOISON_LARGE)
                lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault)); 
        if (fault & VM_FAULT_HWPOISON)
                lsb = PAGE_SHIFT;
        info.si_addr_lsb = lsb;

        force_sig_info(si_signo, &info, tsk);
}

DEFINE_SPINLOCK(pgd_lock);
LIST_HEAD(pgd_list);

#ifdef CONFIG_X86_32
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;
}

void vmalloc_sync_all(void)
{
        unsigned long address;

        if (SHARED_KERNEL_PMD)
                return;

        for (address = VMALLOC_START & PMD_MASK;
             address >= TASK_SIZE && address < FIXADDR_TOP;
             address += PMD_SIZE) {
                struct page *page;

                spin_lock(&pgd_lock);
                list_for_each_entry(page, &pgd_list, lru) {
                        spinlock_t *pgt_lock;
                        pmd_t *ret;

                        /* the pgt_lock only for Xen */
                        pgt_lock = &pgd_page_get_mm(page)->page_table_lock;

                        spin_lock(pgt_lock);
                        ret = vmalloc_sync_one(page_address(page), address);
                        spin_unlock(pgt_lock);

                        if (!ret)
                                break;
                }
                spin_unlock(&pgd_lock);
        }
}

/*
 * 32-bit:
 *
 *   Handle a fault on the vmalloc or module mapping area
 */
static noinline __kprobes int vmalloc_fault(unsigned long address)
{
        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;

        WARN_ON_ONCE(in_nmi());

        /*
         * 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;
}

/*
 * Did it hit the DOS screen memory VA from vm86 mode?
 */
static inline void
check_v8086_mode(struct pt_regs *regs, unsigned long address,
                 struct task_struct *tsk)
{
        unsigned long bit;

        if (!v8086_mode(regs))
                return;

        bit = (address - 0xA0000) >> PAGE_SHIFT;
        if (bit < 32)
                tsk->thread.screen_bitmap |= 1 << bit;
}

static bool low_pfn(unsigned long pfn)
{
        return pfn < max_low_pfn;
}

static void dump_pagetable(unsigned long address)
{
        pgd_t *base = __va(read_cr3());
        pgd_t *pgd = &base[pgd_index(address)];
        pmd_t *pmd;
        pte_t *pte;

#ifdef CONFIG_X86_PAE
        printk("*pdpt = %016Lx ", pgd_val(*pgd));
        if (!low_pfn(pgd_val(*pgd) >> PAGE_SHIFT) || !pgd_present(*pgd))
                goto out;
#endif
        pmd = pmd_offset(pud_offset(pgd, address), address);
        printk(KERN_CONT "*pde = %0*Lx ", sizeof(*pmd) * 2, (u64)pmd_val(*pmd));

        /*
         * We must not directly access the pte in the highpte
         * case if the page table is located in highmem.
         * And let's rather not kmap-atomic the pte, just in case
         * it's allocated already:
         */
        if (!low_pfn(pmd_pfn(*pmd)) || !pmd_present(*pmd) || pmd_large(*pmd))
                goto out;

        pte = pte_offset_kernel(pmd, address);
        printk("*pte = %0*Lx ", sizeof(*pte) * 2, (u64)pte_val(*pte));
out:
        printk("\n");
}

#else /* CONFIG_X86_64: */

void vmalloc_sync_all(void)
{
        sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END);
}

/*
 * 64-bit:
 *
 *   Handle a fault on the vmalloc area
 *
 * This assumes no large pages in there.
 */
static noinline __kprobes 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;

        /* Make sure we are in vmalloc area: */
        if (!(address >= VMALLOC_START && address < VMALLOC_END))
                return -1;

        WARN_ON_ONCE(in_nmi());

        /*
         * 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->active_mm, address);
        pgd_ref = pgd_offset_k(address);
        if (pgd_none(*pgd_ref))
                return -1;

        if (pgd_none(*pgd)) {
                set_pgd(pgd, *pgd_ref);
                arch_flush_lazy_mmu_mode();
        } else {
                BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*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_vaddr(*pud) != pud_page_vaddr(*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);

        /*
         * Don't use pte_page here, because the mappings can point
         * outside mem_map, and the NUMA hash lookup cannot handle
         * that:
         */
        if (!pte_present(*pte) || pte_pfn(*pte) != pte_pfn(*pte_ref))
                BUG();

        return 0;
}

#ifdef CONFIG_CPU_SUP_AMD
static const char errata93_warning[] =
KERN_ERR 
"******* Your BIOS seems to not contain a fix for K8 errata #93\n"
"******* Working around it, but it may cause SEGVs or burn power.\n"
"******* Please consider a BIOS update.\n"
"******* Disabling USB legacy in the BIOS may also help.\n";
#endif

/*
 * No vm86 mode in 64-bit mode:
 */
static inline void
check_v8086_mode(struct pt_regs *regs, unsigned long address,
                 struct task_struct *tsk)
{
}

static int bad_address(void *p)
{
        unsigned long dummy;

        return probe_kernel_address((unsigned long *)p, dummy);
}

static void dump_pagetable(unsigned long address)
{
        pgd_t *base = __va(read_cr3() & PHYSICAL_PAGE_MASK);
        pgd_t *pgd = base + pgd_index(address);
        pud_t *pud;
        pmd_t *pmd;
        pte_t *pte;

        if (bad_address(pgd))
                goto bad;

        printk("PGD %lx ", pgd_val(*pgd));

        if (!pgd_present(*pgd))
                goto out;

        pud = pud_offset(pgd, address);
        if (bad_address(pud))
                goto bad;

        printk("PUD %lx ", pud_val(*pud));
        if (!pud_present(*pud) || pud_large(*pud))
                goto out;

        pmd = pmd_offset(pud, address);
        if (bad_address(pmd))
                goto bad;

        printk("PMD %lx ", pmd_val(*pmd));
        if (!pmd_present(*pmd) || pmd_large(*pmd))
                goto out;

        pte = pte_offset_kernel(pmd, address);
        if (bad_address(pte))
                goto bad;

        printk("PTE %lx", pte_val(*pte));
out:
        printk("\n");
        return;
bad:
        printk("BAD\n");
}

#endif /* CONFIG_X86_64 */

/*
 * Workaround for K8 erratum #93 & buggy BIOS.
 *
 * BIOS SMM functions are required to use a specific workaround
 * to avoid corruption of the 64bit RIP register on C stepping K8.
 *
 * A lot of BIOS that didn't get tested properly miss this.
 *
 * The OS sees this as a page fault with the upper 32bits of RIP cleared.
 * Try to work around it here.
 *
 * Note we only handle faults in kernel here.
 * Does nothing on 32-bit.
 */
static int is_errata93(struct pt_regs *regs, unsigned long address)
{
#if defined(CONFIG_X86_64) && defined(CONFIG_CPU_SUP_AMD)
        if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD
            || boot_cpu_data.x86 != 0xf)
                return 0;

        if (address != regs->ip)
                return 0;

        if ((address >> 32) != 0)
                return 0;

        address |= 0xffffffffUL << 32;
        if ((address >= (u64)_stext && address <= (u64)_etext) ||
            (address >= MODULES_VADDR && address <= MODULES_END)) {
                printk_once(errata93_warning);
                regs->ip = address;
                return 1;
        }
#endif
        return 0;
}

/*
 * Work around K8 erratum #100 K8 in compat mode occasionally jumps
 * to illegal addresses >4GB.
 *
 * We catch this in the page fault handler because these addresses
 * are not reachable. Just detect this case and return.  Any code
 * segment in LDT is compatibility mode.
 */
static int is_errata100(struct pt_regs *regs, unsigned long address)
{
#ifdef CONFIG_X86_64
        if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) && (address >> 32))
                return 1;
#endif
        return 0;
}

static int is_f00f_bug(struct pt_regs *regs, unsigned long address)
{
#ifdef CONFIG_X86_F00F_BUG
        unsigned long nr;

        /*
         * Pentium F0 0F C7 C8 bug workaround:
         */
        if (boot_cpu_has_bug(X86_BUG_F00F)) {
                nr = (address - idt_descr.address) >> 3;

                if (nr == 6) {
                        do_invalid_op(regs, 0);
                        return 1;
                }
        }
#endif
        return 0;
}

static const char nx_warning[] = KERN_CRIT
"kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n";

static void
show_fault_oops(struct pt_regs *regs, unsigned long error_code,
                unsigned long address)
{
        if (!oops_may_print())
                return;

        if (error_code & PF_INSTR) {
                unsigned int level;
                pgd_t *pgd;
                pte_t *pte;

                pgd = __va(read_cr3() & PHYSICAL_PAGE_MASK);
                pgd += pgd_index(address);

                pte = lookup_address_in_pgd(pgd, address, &level);

                if (pte && pte_present(*pte) && !pte_exec(*pte))
                        printk(nx_warning, from_kuid(&init_user_ns, current_uid()));
        }

        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 %p\n", (void *) address);
        printk(KERN_ALERT "IP:");
        printk_address(regs->ip);

        dump_pagetable(address);
}

static noinline void
pgtable_bad(struct pt_regs *regs, unsigned long error_code,
            unsigned long address)
{
        struct task_struct *tsk;
        unsigned long flags;
        int sig;

        flags = oops_begin();
        tsk = current;
        sig = SIGKILL;

        printk(KERN_ALERT "%s: Corrupted page table at address %lx\n",
               tsk->comm, address);
        dump_pagetable(address);

        tsk->thread.cr2         = address;
        tsk->thread.trap_nr     = X86_TRAP_PF;
        tsk->thread.error_code  = error_code;

        if (__die("Bad pagetable", regs, error_code))
                sig = 0;

        oops_end(flags, regs, sig);
}

static noinline void
no_context(struct pt_regs *regs, unsigned long error_code,
           unsigned long address, int signal, int si_code)
{
        struct task_struct *tsk = current;
        unsigned long *stackend;
        unsigned long flags;
        int sig;

        /* Are we prepared to handle this kernel fault? */
        if (fixup_exception(regs)) {
                /*
                 * Any interrupt that takes a fault gets the fixup. This makes
                 * the below recursive fault logic only apply to a faults from
                 * task context.
                 */
                if (in_interrupt())
                        return;

                /*
                 * Per the above we're !in_interrupt(), aka. task context.
                 *
                 * In this case we need to make sure we're not recursively
                 * faulting through the emulate_vsyscall() logic.
                 */
                if (current_thread_info()->sig_on_uaccess_error && signal) {
                        tsk->thread.trap_nr = X86_TRAP_PF;
                        tsk->thread.error_code = error_code | PF_USER;
                        tsk->thread.cr2 = address;

                        /* XXX: hwpoison faults will set the wrong code. */
                        force_sig_info_fault(signal, si_code, address, tsk, 0);
                }

                /*
                 * Barring that, we can do the fixup and be happy.
                 */
                return;
        }

        /*
         * 32-bit:
         *
         *   Valid to do another page fault here, because if this fault
         *   had been triggered by is_prefetch fixup_exception would have
         *   handled it.
         *
         * 64-bit:
         *
         *   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:
         */
        flags = oops_begin();

        show_fault_oops(regs, error_code, address);

        stackend = end_of_stack(tsk);
        if (tsk != &init_task && *stackend != STACK_END_MAGIC)
                printk(KERN_EMERG "Thread overran stack, or stack corrupted\n");

        tsk->thread.cr2         = address;
        tsk->thread.trap_nr     = X86_TRAP_PF;
        tsk->thread.error_code  = error_code;

        sig = SIGKILL;
        if (__die("Oops", regs, error_code))
                sig = 0;

        /* Executive summary in case the body of the oops scrolled away */
        printk(KERN_DEFAULT "CR2: %016lx\n", address);

        oops_end(flags, regs, sig);
}

/*
 * Print out info about fatal segfaults, if the show_unhandled_signals
 * sysctl is set:
 */
static inline void
show_signal_msg(struct pt_regs *regs, unsigned long error_code,
                unsigned long address, struct task_struct *tsk)
{
        if (!unhandled_signal(tsk, SIGSEGV))
                return;

        if (!printk_ratelimit())
                return;

        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(KERN_CONT " in ", regs->ip);

        printk(KERN_CONT "\n");
}

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;

#ifdef CONFIG_X86_64
                /*
                 * Instruction fetch faults in the vsyscall page might need
                 * emulation.
                 */
                if (unlikely((error_code & PF_INSTR) &&
                             ((address & ~0xfff) == VSYSCALL_ADDR))) {
                        if (emulate_vsyscall(regs, address))
                                return;
                }
#endif
                /* Kernel addresses are always protection faults: */
                if (address >= TASK_SIZE)
                        error_code |= PF_PROT;

                if (likely(show_unhandled_signals))
                        show_signal_msg(regs, error_code, address, tsk);

                tsk->thread.cr2         = address;
                tsk->thread.error_code  = error_code;
                tsk->thread.trap_nr     = X86_TRAP_PF;

                force_sig_info_fault(SIGSEGV, si_code, address, tsk, 0);

                return;
        }

        if (is_f00f_bug(regs, address))
                return;

        no_context(regs, error_code, address, SIGSEGV, si_code);
}

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);
}

static void
do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
          unsigned int fault)
{
        struct task_struct *tsk = current;
        struct mm_struct *mm = tsk->mm;
        int code = BUS_ADRERR;

        up_read(&mm->mmap_sem);

        /* Kernel mode? Handle exceptions or die: */
        if (!(error_code & PF_USER)) {
                no_context(regs, error_code, address, SIGBUS, BUS_ADRERR);
                return;
        }

        /* User-space => ok to do another page fault: */
        if (is_prefetch(regs, error_code, address))
                return;

        tsk->thread.cr2         = address;
        tsk->thread.error_code  = error_code;
        tsk->thread.trap_nr     = X86_TRAP_PF;

#ifdef CONFIG_MEMORY_FAILURE
        if (fault & (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
                printk(KERN_ERR
        "MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n",
                        tsk->comm, tsk->pid, address);
                code = BUS_MCEERR_AR;
        }
#endif
        force_sig_info_fault(SIGBUS, code, address, tsk, fault);
}

static noinline void
mm_fault_error(struct pt_regs *regs, unsigned long error_code,
               unsigned long address, unsigned int fault)
{
        if (fatal_signal_pending(current) && !(error_code & PF_USER)) {
                up_read(&current->mm->mmap_sem);
                no_context(regs, error_code, address, 0, 0);
                return;
        }

        if (fault & VM_FAULT_OOM) {
                /* Kernel mode? Handle exceptions or die: */
                if (!(error_code & PF_USER)) {
                        up_read(&current->mm->mmap_sem);
                        no_context(regs, error_code, address,
                                   SIGSEGV, SEGV_MAPERR);
                        return;
                }

                up_read(&current->mm->mmap_sem);

                /*
                 * 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):
                 */
                pagefault_out_of_memory();
        } else {
                if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
                             VM_FAULT_HWPOISON_LARGE))
                        do_sigbus(regs, error_code, address, fault);
                else
                        BUG();
        }
}

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 noinline __kprobes int
spurious_fault(unsigned long error_code, unsigned long address)
{
        pgd_t *pgd;
        pud_t *pud;
        pmd_t *pmd;
        pte_t *pte;
        int ret;

        /* 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;

        ret = spurious_fault_check(error_code, pte);
        if (!ret)
                return 0;

        /*
         * Make sure we have permissions in PMD.
         * If not, then there's a bug in the page tables:
         */
        ret = spurious_fault_check(error_code, (pte_t *) pmd);
        WARN_ONCE(!ret, "PMD has incorrect permission bits\n");

        return ret;
}

int show_unhandled_signals = 1;

static inline int
access_error(unsigned long error_code, struct vm_area_struct *vma)
{
        if (error_code & PF_WRITE) {
                /* write, present and write, not present: */
                if (unlikely(!(vma->vm_flags & VM_WRITE)))
                        return 1;
                return 0;
        }

        /* read, present: */
        if (unlikely(error_code & PF_PROT))
                return 1;

        /* read, not present: */
        if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))))
                return 1;

        return 0;
}

static int fault_in_kernel_space(unsigned long address)
{
        return address >= TASK_SIZE_MAX;
}

static inline bool smap_violation(int error_code, struct pt_regs *regs)
{
        if (!IS_ENABLED(CONFIG_X86_SMAP))
                return false;

        if (!static_cpu_has(X86_FEATURE_SMAP))
                return false;

        if (error_code & PF_USER)
                return false;

        if (!user_mode_vm(regs) && (regs->flags & X86_EFLAGS_AC))
                return false;

        return true;
}

/*
 * This routine handles page faults.  It determines the address,
 * and the problem, and then passes it off to one of the appropriate
 * routines.
 *
 * This function must have noinline because both callers
 * {,trace_}do_page_fault() have notrace on. Having this an actual function
 * guarantees there's a function trace entry.
 */
static void __kprobes noinline
__do_page_fault(struct pt_regs *regs, unsigned long error_code,
                unsigned long address)
{
        struct vm_area_struct *vma;
        struct task_struct *tsk;
        struct mm_struct *mm;
        int fault;
        unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

        tsk = current;
        mm = tsk->mm;

        /*
         * 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;

        /*
         * We fault-in kernel-space virtual memory on-demand. The
         * 'reference' page table is init_mm.pgd.
         *
         * NOTE! We MUST NOT take any locks for this case. We may
         * be in an interrupt or a critical region, and should
         * only copy the information from the master page table,
         * nothing more.
         *
         * This verifies that the fault happens in kernel space
         * (error_code & 4) == 0, and that the fault was not a
         * protection error (error_code & 9) == 0.
         */
        if (unlikely(fault_in_kernel_space(address))) {
                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))
                        return;

                /* kprobes don't want to hook the spurious faults: */
                if (kprobes_fault(regs))
                        return;
                /*
                 * Don't take the mm semaphore here. If we fixup a prefetch
                 * fault we could otherwise deadlock:
                 */
                bad_area_nosemaphore(regs, error_code, address);

                return;
        }

        /* kprobes don't want to hook the spurious faults: */
        if (unlikely(kprobes_fault(regs)))
                return;

        if (unlikely(error_code & PF_RSVD))
                pgtable_bad(regs, error_code, address);

        if (unlikely(smap_violation(error_code, regs))) {
                bad_area_nosemaphore(regs, error_code, address);
                return;
        }

        /*
         * 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)) {
                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.
         *
         * User-mode registers count as a user access even for any
         * potential system fault or CPU buglet:
         */
        if (user_mode_vm(regs)) {
                local_irq_enable();
                error_code |= PF_USER;
                flags |= FAULT_FLAG_USER;
        } else {
                if (regs->flags & X86_EFLAGS_IF)
                        local_irq_enable();
        }

        perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);

        if (error_code & PF_WRITE)
                flags |= FAULT_FLAG_WRITE;

        /*
         * When running in the kernel we expect faults to occur only to
         * addresses in user space.  All other faults represent errors in
         * the kernel and should generate an OOPS.  Unfortunately, in the
         * case of an erroneous fault occurring in a code path which already
         * holds mmap_sem we will deadlock attempting to validate the fault
         * against the address space.  Luckily the kernel only validly
         * references user space from well defined areas of code, which are
         * listed in the exceptions table.
         *
         * As the vast majority of faults will be valid we will only perform
         * the source reference check when there is a possibility of a
         * deadlock. Attempt to lock the address space, if we cannot we then
         * validate the source. If this is invalid we can skip the address
         * space check, thus avoiding the deadlock:
         */
        if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
                if ((error_code & PF_USER) == 0 &&
                    !search_exception_tables(regs->ip)) {
                        bad_area_nosemaphore(regs, error_code, address);
                        return;
                }
retry:
                down_read(&mm->mmap_sem);
        } else {
                /*
                 * The above down_read_trylock() might have succeeded in
                 * which case we'll have missed the might_sleep() from
                 * down_read():
                 */
                might_sleep();
        }

        vma = find_vma(mm, address);
        if (unlikely(!vma)) {
                bad_area(regs, error_code, address);
                return;
        }
        if (likely(vma->vm_start <= address))
                goto good_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.
                 * The large cushion allows instructions like enter
                 * and pusha to work. ("enter $65535, $31" pushes
                 * 32 pointers and then decrements %sp by 65535.)
                 */
                if (unlikely(address + 65536 + 32 * sizeof(unsigned long) < regs->sp)) {
                        bad_area(regs, error_code, address);
                        return;
                }
        }
        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:
        if (unlikely(access_error(error_code, vma))) {
                bad_area_access_error(regs, error_code, address);
                return;
        }

        /*
         * If for any reason at all we couldn't handle the fault,
         * make sure we exit gracefully rather than endlessly redo
         * the fault:
         */
        fault = handle_mm_fault(mm, vma, address, flags);

        /*
         * If we need to retry but a fatal signal is pending, handle the
         * signal first. We do not need to release the mmap_sem because it
         * would already be released in __lock_page_or_retry in mm/filemap.c.
         */
        if (unlikely((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)))
                return;

        if (unlikely(fault & VM_FAULT_ERROR)) {
                mm_fault_error(regs, error_code, address, fault);
                return;
        }

        /*
         * Major/minor page fault accounting is only done on the
         * initial attempt. If we go through a retry, it is extremely
         * likely that the page will be found in page cache at that point.
         */
        if (flags & FAULT_FLAG_ALLOW_RETRY) {
                if (fault & VM_FAULT_MAJOR) {
                        tsk->maj_flt++;
                        perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1,
                                      regs, address);
                } else {
                        tsk->min_flt++;
                        perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1,
                                      regs, address);
                }
                if (fault & VM_FAULT_RETRY) {
                        /* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
                         * of starvation. */
                        flags &= ~FAULT_FLAG_ALLOW_RETRY;
                        flags |= FAULT_FLAG_TRIED;
                        goto retry;
                }
        }

        check_v8086_mode(regs, address, tsk);

        up_read(&mm->mmap_sem);
}

dotraplinkage void __kprobes notrace
do_page_fault(struct pt_regs *regs, unsigned long error_code)
{
        unsigned long address = read_cr2(); /* Get the faulting address */
        enum ctx_state prev_state;

        /*
         * We must have this function tagged with __kprobes, notrace and call
         * read_cr2() before calling anything else. To avoid calling any kind
         * of tracing machinery before we've observed the CR2 value.
         *
         * exception_{enter,exit}() contain all sorts of tracepoints.
         */

        prev_state = exception_enter();
        __do_page_fault(regs, error_code, address);
        exception_exit(prev_state);
}

#ifdef CONFIG_TRACING
static void trace_page_fault_entries(unsigned long address, struct pt_regs *regs,
                                     unsigned long error_code)
{
        if (user_mode(regs))
                trace_page_fault_user(address, regs, error_code);
        else
                trace_page_fault_kernel(address, regs, error_code);
}

dotraplinkage void __kprobes notrace
trace_do_page_fault(struct pt_regs *regs, unsigned long error_code)
{
        /*
         * The exception_enter and tracepoint processing could
         * trigger another page faults (user space callchain
         * reading) and destroy the original cr2 value, so read
         * the faulting address now.
         */
        unsigned long address = read_cr2();
        enum ctx_state prev_state;

        prev_state = exception_enter();
        trace_page_fault_entries(address, regs, error_code);
        __do_page_fault(regs, error_code, address);
        exception_exit(prev_state);
}
#endif /* CONFIG_TRACING */