Release 4.14 arch/um/kernel/trap.c

/*
 * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
 * Licensed under the GPL
 */

#include <linux/mm.h>
#include <linux/sched/signal.h>
#include <linux/hardirq.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/sched/debug.h>
#include <asm/current.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
#include <arch.h>
#include <as-layout.h>
#include <kern_util.h>
#include <os.h>
#include <skas.h>

/*
 * Note this is constrained to return 0, -EFAULT, -EACCESS, -ENOMEM by
 * segv().
 */


int handle_page_fault(unsigned long address, unsigned long ip,
		      int is_write, int is_user, int *code_out)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;
	int err = -EFAULT;
	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

	*code_out = SEGV_MAPERR;

	/*
         * If the fault was with pagefaults disabled, don't take the fault, just
         * fail.
         */
	if (faulthandler_disabled())
		goto out_nosemaphore;

	if (is_user)
		flags |= FAULT_FLAG_USER;
retry:
	down_read(&mm->mmap_sem);
	vma = find_vma(mm, address);
	if (!vma)
		goto out;
	else if (vma->vm_start <= address)
		goto good_area;
	else if (!(vma->vm_flags & VM_GROWSDOWN))
		goto out;
	else if (is_user && !ARCH_IS_STACKGROW(address))
		goto out;
	else if (expand_stack(vma, address))
		goto out;

good_area:
	*code_out = SEGV_ACCERR;
	if (is_write) {
		if (!(vma->vm_flags & VM_WRITE))
			goto out;
		flags |= FAULT_FLAG_WRITE;
	} else {
		/* Don't require VM_READ|VM_EXEC for write faults! */
		if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
			goto out;
	}

	do {
		int fault;

		fault = handle_mm_fault(vma, address, flags);

		if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
			goto out_nosemaphore;

		if (unlikely(fault & VM_FAULT_ERROR)) {
			if (fault & VM_FAULT_OOM) {
				goto out_of_memory;
			} else if (fault & VM_FAULT_SIGSEGV) {
				goto out;
			} else if (fault & VM_FAULT_SIGBUS) {
				err = -EACCES;
				goto out;
			}
			BUG();
		}
		if (flags & FAULT_FLAG_ALLOW_RETRY) {
			if (fault & VM_FAULT_MAJOR)
				current->maj_flt++;
			else
				current->min_flt++;
			if (fault & VM_FAULT_RETRY) {
				flags &= ~FAULT_FLAG_ALLOW_RETRY;
				flags |= FAULT_FLAG_TRIED;

				goto retry;
			}
		}

		pgd = pgd_offset(mm, address);
		pud = pud_offset(pgd, address);
		pmd = pmd_offset(pud, address);
		pte = pte_offset_kernel(pmd, address);
	} while (!pte_present(*pte));
	err = 0;
	/*
         * The below warning was added in place of
         *      pte_mkyoung(); if (is_write) pte_mkdirty();
         * If it's triggered, we'd see normally a hang here (a clean pte is
         * marked read-only to emulate the dirty bit).
         * However, the generic code can mark a PTE writable but clean on a
         * concurrent read fault, triggering this harmlessly. So comment it out.
         */
#if 0
	WARN_ON(!pte_young(*pte) || (is_write && !pte_dirty(*pte)));
#endif
	flush_tlb_page(vma, address);
out:
	up_read(&mm->mmap_sem);
out_nosemaphore:
	return err;

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);
	if (!is_user)
		goto out_nosemaphore;
	pagefault_out_of_memory();
	return 0;
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Jeff Dike
268
58.39%
7
31.82%
Nicholas Piggin
56
12.20%
2
9.09%
Kautuk Consul
51
11.11%
1
4.55%
Johannes Weiner
28
6.10%
2
9.09%
Paolo 'Blaisorblade' Giarrusso
26
5.66%
6
27.27%
Bodo Stroesser
12
2.61%
1
4.55%
Linus Torvalds
12
2.61%
1
4.55%
Shaohua Li
4
0.87%
1
4.55%
David Hildenbrand
2
0.44%
1
4.55%
Total
459
100.00%
22
100.00%


EXPORT_SYMBOL(handle_page_fault);



static void show_segv_info(struct uml_pt_regs *regs)
{
	struct task_struct *tsk = current;
	struct faultinfo *fi = UPT_FAULTINFO(regs);

	if (!unhandled_signal(tsk, SIGSEGV))
		return;

	if (!printk_ratelimit())
		return;

	printk("%s%s[%d]: segfault at %lx ip %p sp %p error %x",
		task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
		tsk->comm, task_pid_nr(tsk), FAULT_ADDRESS(*fi),
		(void *)UPT_IP(regs), (void *)UPT_SP(regs),
		fi->error_code);

	print_vma_addr(KERN_CONT " in ", UPT_IP(regs));
	printk(KERN_CONT "\n");
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Richard Weinberger
116
100.00%
1
100.00%
Total
116
100.00%
1
100.00%



static void bad_segv(struct faultinfo fi, unsigned long ip)
{
	struct siginfo si;

	si.si_signo = SIGSEGV;
	si.si_code = SEGV_ACCERR;
	si.si_addr = (void __user *) FAULT_ADDRESS(fi);
	current->thread.arch.faultinfo = fi;
	force_sig_info(SIGSEGV, &si, current);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jeff Dike
64
100.00%
1
100.00%
Total
64
100.00%
1
100.00%



void fatal_sigsegv(void)
{
	force_sigsegv(SIGSEGV, current);
	do_signal(&current->thread.regs);
	/*
         * This is to tell gcc that we're not returning - do_signal
         * can, in general, return, but in this case, it's not, since
         * we just got a fatal SIGSEGV queued.
         */
	os_dump_core();
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jeff Dike
20
71.43%
1
50.00%
Ingo Molnar
8
28.57%
1
50.00%
Total
28
100.00%
2
100.00%

/**
 * segv_handler() - the SIGSEGV handler
 * @sig:        the signal number
 * @unused_si:  the signal info struct; unused in this handler
 * @regs:       the ptrace register information
 *
 * The handler first extracts the faultinfo from the UML ptrace regs struct.
 * If the userfault did not happen in an UML userspace process, bad_segv is called.
 * Otherwise the signal did happen in a cloned userspace process, handle it.
 */


void segv_handler(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
{
	struct faultinfo * fi = UPT_FAULTINFO(regs);

	if (UPT_IS_USER(regs) && !SEGV_IS_FIXABLE(fi)) {
		show_segv_info(regs);
		bad_segv(*fi, UPT_IP(regs));
		return;
	}
	segv(*fi, UPT_IP(regs), UPT_IS_USER(regs), regs);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Gennady Sharapov
67
85.90%
1
25.00%
Richard Weinberger
5
6.41%
1
25.00%
Martin Pärtel
5
6.41%
1
25.00%
Jeff Dike
1
1.28%
1
25.00%
Total
78
100.00%
4
100.00%

/*
 * We give a *copy* of the faultinfo in the regs to segv.
 * This must be done, since nesting SEGVs could overwrite
 * the info in the regs. A pointer to the info then would
 * give us bad data!
 */


unsigned long segv(struct faultinfo fi, unsigned long ip, int is_user,
		   struct uml_pt_regs *regs)
{
	struct siginfo si;
	jmp_buf *catcher;
	int err;
	int is_write = FAULT_WRITE(fi);
	unsigned long address = FAULT_ADDRESS(fi);

	if (!is_user && regs)
		current->thread.segv_regs = container_of(regs, struct pt_regs, regs);

	if (!is_user && (address >= start_vm) && (address < end_vm)) {
		flush_tlb_kernel_vm();
		goto out;
	}
	else if (current->mm == NULL) {
		show_regs(container_of(regs, struct pt_regs, regs));
		panic("Segfault with no mm");
	}
	else if (!is_user && address > PAGE_SIZE && address < TASK_SIZE) {
		show_regs(container_of(regs, struct pt_regs, regs));
		panic("Kernel tried to access user memory at addr 0x%lx, ip 0x%lx",
		       address, ip);
	}

	if (SEGV_IS_FIXABLE(&fi))
		err = handle_page_fault(address, ip, is_write, is_user,
					&si.si_code);
	else {
		err = -EFAULT;
		/*
                 * A thread accessed NULL, we get a fault, but CR2 is invalid.
                 * This code is used in __do_copy_from_user() of TT mode.
                 * XXX tt mode is gone, so maybe this isn't needed any more
                 */
		address = 0;
	}

	catcher = current->thread.fault_catcher;
	if (!err)
		goto out;
	else if (catcher != NULL) {
		current->thread.fault_addr = (void *) address;
		UML_LONGJMP(catcher, 1);
	}
	else if (current->thread.fault_addr != NULL)
		panic("fault_addr set but no fault catcher");
	else if (!is_user && arch_fixup(ip, regs))
		goto out;

	if (!is_user) {
		show_regs(container_of(regs, struct pt_regs, regs));
		panic("Kernel mode fault at addr 0x%lx, ip 0x%lx",
		      address, ip);
	}

	show_segv_info(regs);

	if (err == -EACCES) {
		si.si_signo = SIGBUS;
		si.si_errno = 0;
		si.si_code = BUS_ADRERR;
		si.si_addr = (void __user *)address;
		current->thread.arch.faultinfo = fi;
		force_sig_info(SIGBUS, &si, current);
	} else {
		BUG_ON(err != -EFAULT);
		si.si_signo = SIGSEGV;
		si.si_addr = (void __user *) address;
		current->thread.arch.faultinfo = fi;
		force_sig_info(SIGSEGV, &si, current);
	}

out:
	if (regs)
		current->thread.segv_regs = NULL;

	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jeff Dike
279
63.84%
8
44.44%
Richard Weinberger
89
20.37%
5
27.78%
Bodo Stroesser
36
8.24%
1
5.56%
Paolo 'Blaisorblade' Giarrusso
31
7.09%
3
16.67%
Al Viro
2
0.46%
1
5.56%
Total
437
100.00%
18
100.00%



void relay_signal(int sig, struct siginfo *si, struct uml_pt_regs *regs)
{
	struct faultinfo *fi;
	struct siginfo clean_si;

	if (!UPT_IS_USER(regs)) {
		if (sig == SIGBUS)
			printk(KERN_ERR "Bus error - the host /dev/shm or /tmp "
			       "mount likely just ran out of space\n");
		panic("Kernel mode signal %d", sig);
	}

	arch_examine_signal(sig, regs);

	memset(&clean_si, 0, sizeof(clean_si));
	clean_si.si_signo = si->si_signo;
	clean_si.si_errno = si->si_errno;
	clean_si.si_code = si->si_code;
	switch (sig) {
	case SIGILL:
	case SIGFPE:
	case SIGSEGV:
	case SIGBUS:
	case SIGTRAP:
		fi = UPT_FAULTINFO(regs);
		clean_si.si_addr = (void __user *) FAULT_ADDRESS(*fi);
		current->thread.arch.faultinfo = *fi;
#ifdef __ARCH_SI_TRAPNO
		clean_si.si_trapno = si->si_trapno;
#endif
		break;
	default:
		printk(KERN_ERR "Attempted to relay unknown signal %d (si_code = %d)\n",
			sig, si->si_code);
	}

	force_sig_info(sig, &clean_si, current);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Martin Pärtel
124
64.58%
1
12.50%
Jeff Dike
56
29.17%
6
75.00%
Bodo Stroesser
12
6.25%
1
12.50%
Total
192
100.00%
8
100.00%



void bus_handler(int sig, struct siginfo *si, struct uml_pt_regs *regs)
{
	if (current->thread.fault_catcher != NULL)
		UML_LONGJMP(current->thread.fault_catcher, 1);
	else
		relay_signal(sig, si, regs);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Jeff Dike
42
85.71%
4
80.00%
Martin Pärtel
7
14.29%
1
20.00%
Total
49
100.00%
5
100.00%



void winch(int sig, struct siginfo *unused_si, struct uml_pt_regs *regs)
{
	do_IRQ(WINCH_IRQ, regs);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Paolo 'Blaisorblade' Giarrusso
19
76.00%
1
33.33%
Martin Pärtel
5
20.00%
1
33.33%
Jeff Dike
1
4.00%
1
33.33%
Total
25
100.00%
3
100.00%



void trap_init(void)
{
}
Contributors
Person
Tokens
Prop
Commits
CommitProp
Jeff Dike
6
100.00%
1
100.00%
Total
6
100.00%
1
100.00%

Overall Contributors
Person
Tokens
Prop
Commits
CommitProp
Jeff Dike
760
50.50%
19
36.54%
Richard Weinberger
210
13.95%
5
9.62%
Martin Pärtel
141
9.37%
1
1.92%
Paolo 'Blaisorblade' Giarrusso
78
5.18%
8
15.38%
Gennady Sharapov
71
4.72%
1
1.92%
Bodo Stroesser
61
4.05%
2
3.85%
Nicholas Piggin
56
3.72%
2
3.85%
Kautuk Consul
51
3.39%
1
1.92%
Johannes Weiner
28
1.86%
2
3.85%
Al Viro
15
1.00%
3
5.77%
Ingo Molnar
12
0.80%
3
5.77%
Linus Torvalds
12
0.80%
1
1.92%
Shaohua Li
4
0.27%
1
1.92%
Peter Zijlstra
3
0.20%
1
1.92%
David Hildenbrand
2
0.13%
1
1.92%
Thomas Meyer
1
0.07%
1
1.92%
Total
1505
100.00%
52
100.00%
Directory: arch/um/kernel

Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.