[mirror_ubuntu-artful-kernel.git] / arch / arm64 / mm / fault.c

/*
 * Based on arch/arm/mm/fault.c
 *
 * Copyright (C) 1995  Linus Torvalds
 * Copyright (C) 1995-2004 Russell King
 * Copyright (C) 2012 ARM Ltd.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

#include <linux/module.h>
#include <linux/signal.h>
#include <linux/mm.h>
#include <linux/hardirq.h>
#include <linux/init.h>
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/page-flags.h>
#include <linux/sched.h>
#include <linux/highmem.h>
#include <linux/perf_event.h>

#include <asm/cpufeature.h>
#include <asm/exception.h>
#include <asm/debug-monitors.h>
#include <asm/esr.h>
#include <asm/sysreg.h>
#include <asm/system_misc.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>

static const char *fault_name(unsigned int esr);

/*
 * Dump out the page tables associated with 'addr' in mm 'mm'.
 */
void show_pte(struct mm_struct *mm, unsigned long addr)
{
	pgd_t *pgd;

	if (!mm)
		mm = &init_mm;

	pr_alert("pgd = %p\n", mm->pgd);
	pgd = pgd_offset(mm, addr);
	pr_alert("[%08lx] *pgd=%016llx", addr, pgd_val(*pgd));

	do {
		pud_t *pud;
		pmd_t *pmd;
		pte_t *pte;

		if (pgd_none(*pgd) || pgd_bad(*pgd))
			break;

		pud = pud_offset(pgd, addr);
		printk(", *pud=%016llx", pud_val(*pud));
		if (pud_none(*pud) || pud_bad(*pud))
			break;

		pmd = pmd_offset(pud, addr);
		printk(", *pmd=%016llx", pmd_val(*pmd));
		if (pmd_none(*pmd) || pmd_bad(*pmd))
			break;

		pte = pte_offset_map(pmd, addr);
		printk(", *pte=%016llx", pte_val(*pte));
		pte_unmap(pte);
	} while(0);

	printk("\n");
}

/*
 * The kernel tried to access some page that wasn't present.
 */
static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
			      unsigned int esr, struct pt_regs *regs)
{
	/*
	 * Are we prepared to handle this kernel fault?
	 */
	if (fixup_exception(regs))
		return;

	/*
	 * No handler, we'll have to terminate things with extreme prejudice.
	 */
	bust_spinlocks(1);
	pr_alert("Unable to handle kernel %s at virtual address %08lx\n",
		 (addr < PAGE_SIZE) ? "NULL pointer dereference" :
		 "paging request", addr);

	show_pte(mm, addr);
	die("Oops", regs, esr);
	bust_spinlocks(0);
	do_exit(SIGKILL);
}

/*
 * Something tried to access memory that isn't in our memory map. User mode
 * accesses just cause a SIGSEGV
 */
static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
			    unsigned int esr, unsigned int sig, int code,
			    struct pt_regs *regs)
{
	struct siginfo si;

	if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) {
		pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
			tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
			addr, esr);
		show_pte(tsk->mm, addr);
		show_regs(regs);
	}

	tsk->thread.fault_address = addr;
	tsk->thread.fault_code = esr;
	si.si_signo = sig;
	si.si_errno = 0;
	si.si_code = code;
	si.si_addr = (void __user *)addr;
	force_sig_info(sig, &si, tsk);
}

static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs)
{
	struct task_struct *tsk = current;
	struct mm_struct *mm = tsk->active_mm;

	/*
	 * If we are in kernel mode at this point, we have no context to
	 * handle this fault with.
	 */
	if (user_mode(regs))
		__do_user_fault(tsk, addr, esr, SIGSEGV, SEGV_MAPERR, regs);
	else
		__do_kernel_fault(mm, addr, esr, regs);
}

#define VM_FAULT_BADMAP		0x010000
#define VM_FAULT_BADACCESS	0x020000

#define ESR_LNX_EXEC		(1 << 24)

static int __do_page_fault(struct mm_struct *mm, unsigned long addr,
			   unsigned int mm_flags, unsigned long vm_flags,
			   struct task_struct *tsk)
{
	struct vm_area_struct *vma;
	int fault;

	vma = find_vma(mm, addr);
	fault = VM_FAULT_BADMAP;
	if (unlikely(!vma))
		goto out;
	if (unlikely(vma->vm_start > addr))
		goto check_stack;

	/*
	 * Ok, we have a good vm_area for this memory access, so we can handle
	 * it.
	 */
good_area:
	/*
	 * Check that the permissions on the VMA allow for the fault which
	 * occurred. If we encountered a write or exec fault, we must have
	 * appropriate permissions, otherwise we allow any permission.
	 */
	if (!(vma->vm_flags & vm_flags)) {
		fault = VM_FAULT_BADACCESS;
		goto out;
	}

	return handle_mm_fault(mm, vma, addr & PAGE_MASK, mm_flags);

check_stack:
	if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
		goto good_area;
out:
	return fault;
}

static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
				   struct pt_regs *regs)
{
	struct task_struct *tsk;
	struct mm_struct *mm;
	int fault, sig, code;
	unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;

	tsk = current;
	mm  = tsk->mm;

	/* Enable interrupts if they were enabled in the parent context. */
	if (interrupts_enabled(regs))
		local_irq_enable();

	/*
	 * If we're in an interrupt or have no user context, we must not take
	 * the fault.
	 */
	if (faulthandler_disabled() || !mm)
		goto no_context;

	if (user_mode(regs))
		mm_flags |= FAULT_FLAG_USER;

	if (esr & ESR_LNX_EXEC) {
		vm_flags = VM_EXEC;
	} else if ((esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM)) {
		vm_flags = VM_WRITE;
		mm_flags |= FAULT_FLAG_WRITE;
	}

	/*
	 * PAN bit set implies the fault happened in kernel space, but not
	 * in the arch's user access functions.
	 */
	if (IS_ENABLED(CONFIG_ARM64_PAN) && (regs->pstate & PSR_PAN_BIT))
		goto no_context;

	/*
	 * As per x86, we may deadlock here. However, since the kernel only
	 * validly references user space from well defined areas of the code,
	 * we can bug out early if this is from code which shouldn't.
	 */
	if (!down_read_trylock(&mm->mmap_sem)) {
		if (!user_mode(regs) && !search_exception_tables(regs->pc))
			goto no_context;
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();
#ifdef CONFIG_DEBUG_VM
		if (!user_mode(regs) && !search_exception_tables(regs->pc))
			goto no_context;
#endif
	}

	fault = __do_page_fault(mm, addr, mm_flags, vm_flags, tsk);

	/*
	 * 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 ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
		return 0;

	/*
	 * 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.
	 */

	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
	if (mm_flags & FAULT_FLAG_ALLOW_RETRY) {
		if (fault & VM_FAULT_MAJOR) {
			tsk->maj_flt++;
			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
				      addr);
		} else {
			tsk->min_flt++;
			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs,
				      addr);
		}
		if (fault & VM_FAULT_RETRY) {
			/*
			 * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of
			 * starvation.
			 */
			mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
			mm_flags |= FAULT_FLAG_TRIED;
			goto retry;
		}
	}

	up_read(&mm->mmap_sem);

	/*
	 * Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR
	 */
	if (likely(!(fault & (VM_FAULT_ERROR | VM_FAULT_BADMAP |
			      VM_FAULT_BADACCESS))))
		return 0;

	/*
	 * If we are in kernel mode at this point, we have no context to
	 * handle this fault with.
	 */
	if (!user_mode(regs))
		goto no_context;

	if (fault & VM_FAULT_OOM) {
		/*
		 * We ran out of memory, call the OOM killer, and return to
		 * userspace (which will retry the fault, or kill us if we got
		 * oom-killed).
		 */
		pagefault_out_of_memory();
		return 0;
	}

	if (fault & VM_FAULT_SIGBUS) {
		/*
		 * We had some memory, but were unable to successfully fix up
		 * this page fault.
		 */
		sig = SIGBUS;
		code = BUS_ADRERR;
	} else {
		/*
		 * Something tried to access memory that isn't in our memory
		 * map.
		 */
		sig = SIGSEGV;
		code = fault == VM_FAULT_BADACCESS ?
			SEGV_ACCERR : SEGV_MAPERR;
	}

	__do_user_fault(tsk, addr, esr, sig, code, regs);
	return 0;

no_context:
	__do_kernel_fault(mm, addr, esr, regs);
	return 0;
}

/*
 * First Level Translation Fault Handler
 *
 * We enter here because the first level page table doesn't contain a valid
 * entry for the address.
 *
 * If the address is in kernel space (>= TASK_SIZE), then we are probably
 * faulting in the vmalloc() area.
 *
 * If the init_task's first level page tables contains the relevant entry, we
 * copy the it to this task.  If not, we send the process a signal, fixup the
 * exception, or oops the kernel.
 *
 * 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.
 */
static int __kprobes do_translation_fault(unsigned long addr,
					  unsigned int esr,
					  struct pt_regs *regs)
{
	if (addr < TASK_SIZE)
		return do_page_fault(addr, esr, regs);

	do_bad_area(addr, esr, regs);
	return 0;
}

static int do_alignment_fault(unsigned long addr, unsigned int esr,
			      struct pt_regs *regs)
{
	do_bad_area(addr, esr, regs);
	return 0;
}

/*
 * This abort handler always returns "fault".
 */
static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
{
	return 1;
}

static struct fault_info {
	int	(*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs);
	int	sig;
	int	code;
	const char *name;
} fault_info[] = {
	{ do_bad,		SIGBUS,  0,		"ttbr address size fault"	},
	{ do_bad,		SIGBUS,  0,		"level 1 address size fault"	},
	{ do_bad,		SIGBUS,  0,		"level 2 address size fault"	},
	{ do_bad,		SIGBUS,  0,		"level 3 address size fault"	},
	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 0 translation fault"	},
	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 1 translation fault"	},
	{ do_translation_fault,	SIGSEGV, SEGV_MAPERR,	"level 2 translation fault"	},
	{ do_page_fault,	SIGSEGV, SEGV_MAPERR,	"level 3 translation fault"	},
	{ do_bad,		SIGBUS,  0,		"unknown 8"			},
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 access flag fault"	},
	{ do_bad,		SIGBUS,  0,		"unknown 12"			},
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 2 permission fault"	},
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 permission fault"	},
	{ do_bad,		SIGBUS,  0,		"synchronous external abort"	},
	{ do_bad,		SIGBUS,  0,		"unknown 17"			},
	{ do_bad,		SIGBUS,  0,		"unknown 18"			},
	{ do_bad,		SIGBUS,  0,		"unknown 19"			},
	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
	{ do_bad,		SIGBUS,  0,		"synchronous parity error"	},
	{ do_bad,		SIGBUS,  0,		"unknown 25"			},
	{ do_bad,		SIGBUS,  0,		"unknown 26"			},
	{ do_bad,		SIGBUS,  0,		"unknown 27"			},
	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
	{ do_bad,		SIGBUS,  0,		"synchronous parity error (translation table walk)" },
	{ do_bad,		SIGBUS,  0,		"unknown 32"			},
	{ do_alignment_fault,	SIGBUS,  BUS_ADRALN,	"alignment fault"		},
	{ do_bad,		SIGBUS,  0,		"unknown 34"			},
	{ do_bad,		SIGBUS,  0,		"unknown 35"			},
	{ do_bad,		SIGBUS,  0,		"unknown 36"			},
	{ do_bad,		SIGBUS,  0,		"unknown 37"			},
	{ do_bad,		SIGBUS,  0,		"unknown 38"			},
	{ do_bad,		SIGBUS,  0,		"unknown 39"			},
	{ do_bad,		SIGBUS,  0,		"unknown 40"			},
	{ do_bad,		SIGBUS,  0,		"unknown 41"			},
	{ do_bad,		SIGBUS,  0,		"unknown 42"			},
	{ do_bad,		SIGBUS,  0,		"unknown 43"			},
	{ do_bad,		SIGBUS,  0,		"unknown 44"			},
	{ do_bad,		SIGBUS,  0,		"unknown 45"			},
	{ do_bad,		SIGBUS,  0,		"unknown 46"			},
	{ do_bad,		SIGBUS,  0,		"unknown 47"			},
	{ do_bad,		SIGBUS,  0,		"TLB conflict abort"		},
	{ do_bad,		SIGBUS,  0,		"unknown 49"			},
	{ do_bad,		SIGBUS,  0,		"unknown 50"			},
	{ do_bad,		SIGBUS,  0,		"unknown 51"			},
	{ do_bad,		SIGBUS,  0,		"implementation fault (lockdown abort)" },
	{ do_bad,		SIGBUS,  0,		"implementation fault (unsupported exclusive)" },
	{ do_bad,		SIGBUS,  0,		"unknown 54"			},
	{ do_bad,		SIGBUS,  0,		"unknown 55"			},
	{ do_bad,		SIGBUS,  0,		"unknown 56"			},
	{ do_bad,		SIGBUS,  0,		"unknown 57"			},
	{ do_bad,		SIGBUS,  0,		"unknown 58" 			},
	{ do_bad,		SIGBUS,  0,		"unknown 59"			},
	{ do_bad,		SIGBUS,  0,		"unknown 60"			},
	{ do_bad,		SIGBUS,  0,		"section domain fault"		},
	{ do_bad,		SIGBUS,  0,		"page domain fault"		},
	{ do_bad,		SIGBUS,  0,		"unknown 63"			},
};

static const char *fault_name(unsigned int esr)
{
	const struct fault_info *inf = fault_info + (esr & 63);
	return inf->name;
}

/*
 * Dispatch a data abort to the relevant handler.
 */
asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
					 struct pt_regs *regs)
{
	const struct fault_info *inf = fault_info + (esr & 63);
	struct siginfo info;

	if (!inf->fn(addr, esr, regs))
		return;

	pr_alert("Unhandled fault: %s (0x%08x) at 0x%016lx\n",
		 inf->name, esr, addr);

	info.si_signo = inf->sig;
	info.si_errno = 0;
	info.si_code  = inf->code;
	info.si_addr  = (void __user *)addr;
	arm64_notify_die("", regs, &info, esr);
}

/*
 * Handle stack alignment exceptions.
 */
asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
					   unsigned int esr,
					   struct pt_regs *regs)
{
	struct siginfo info;
	struct task_struct *tsk = current;

	if (show_unhandled_signals && unhandled_signal(tsk, SIGBUS))
		pr_info_ratelimited("%s[%d]: %s exception: pc=%p sp=%p\n",
				    tsk->comm, task_pid_nr(tsk),
				    esr_get_class_string(esr), (void *)regs->pc,
				    (void *)regs->sp);

	info.si_signo = SIGBUS;
	info.si_errno = 0;
	info.si_code  = BUS_ADRALN;
	info.si_addr  = (void __user *)addr;
	arm64_notify_die("Oops - SP/PC alignment exception", regs, &info, esr);
}

int __init early_brk64(unsigned long addr, unsigned int esr,
		       struct pt_regs *regs);

/*
 * __refdata because early_brk64 is __init, but the reference to it is
 * clobbered at arch_initcall time.
 * See traps.c and debug-monitors.c:debug_traps_init().
 */
static struct fault_info __refdata debug_fault_info[] = {
	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware breakpoint"	},
	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware single-step"	},
	{ do_bad,	SIGTRAP,	TRAP_HWBKPT,	"hardware watchpoint"	},
	{ do_bad,	SIGBUS,		0,		"unknown 3"		},
	{ do_bad,	SIGTRAP,	TRAP_BRKPT,	"aarch32 BKPT"		},
	{ do_bad,	SIGTRAP,	0,		"aarch32 vector catch"	},
	{ early_brk64,	SIGTRAP,	TRAP_BRKPT,	"aarch64 BRK"		},
	{ do_bad,	SIGBUS,		0,		"unknown 7"		},
};

void __init hook_debug_fault_code(int nr,
				  int (*fn)(unsigned long, unsigned int, struct pt_regs *),
				  int sig, int code, const char *name)
{
	BUG_ON(nr < 0 || nr >= ARRAY_SIZE(debug_fault_info));

	debug_fault_info[nr].fn		= fn;
	debug_fault_info[nr].sig	= sig;
	debug_fault_info[nr].code	= code;
	debug_fault_info[nr].name	= name;
}

asmlinkage int __exception do_debug_exception(unsigned long addr,
					      unsigned int esr,
					      struct pt_regs *regs)
{
	const struct fault_info *inf = debug_fault_info + DBG_ESR_EVT(esr);
	struct siginfo info;

	if (!inf->fn(addr, esr, regs))
		return 1;

	pr_alert("Unhandled debug exception: %s (0x%08x) at 0x%016lx\n",
		 inf->name, esr, addr);

	info.si_signo = inf->sig;
	info.si_errno = 0;
	info.si_code  = inf->code;
	info.si_addr  = (void __user *)addr;
	arm64_notify_die("", regs, &info, 0);

	return 0;
}

#ifdef CONFIG_ARM64_PAN
void cpu_enable_pan(void *__unused)
{
	config_sctlr_el1(SCTLR_EL1_SPAN, 0);
}
#endif /* CONFIG_ARM64_PAN */
Commit	Line	Data
1d18c47c CM	1	/*
	2	* Based on arch/arm/mm/fault.c
	3	*
	4	* Copyright (C) 1995 Linus Torvalds
	5	* Copyright (C) 1995-2004 Russell King
	6	* Copyright (C) 2012 ARM Ltd.
	7	*
	8	* This program is free software; you can redistribute it and/or modify
	9	* it under the terms of the GNU General Public License version 2 as
	10	* published by the Free Software Foundation.
	11	*
	12	* This program is distributed in the hope that it will be useful,
	13	* but WITHOUT ANY WARRANTY; without even the implied warranty of
	14	* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
	15	* GNU General Public License for more details.
	16	*
	17	* You should have received a copy of the GNU General Public License
	18	* along with this program. If not, see <http://www.gnu.org/licenses/>.
	19	*/
	20
	21	#include <linux/module.h>
	22	#include <linux/signal.h>
	23	#include <linux/mm.h>
	24	#include <linux/hardirq.h>
	25	#include <linux/init.h>
	26	#include <linux/kprobes.h>
	27	#include <linux/uaccess.h>
	28	#include <linux/page-flags.h>
	29	#include <linux/sched.h>
	30	#include <linux/highmem.h>
	31	#include <linux/perf_event.h>
	32
338d4f49	33	#include <asm/cpufeature.h>
1d18c47c CM	34	#include <asm/exception.h>
1d18c47c CM	35	#include <asm/debug-monitors.h>
9141300a	36	#include <asm/esr.h>
338d4f49	37	#include <asm/sysreg.h>
1d18c47c CM	38	#include <asm/system_misc.h>
	39	#include <asm/pgtable.h>
	40	#include <asm/tlbflush.h>
	41
3495386b CM	42	static const char *fault_name(unsigned int esr);
3495386b CM	43
1d18c47c CM	44	/*
	45	* Dump out the page tables associated with 'addr' in mm 'mm'.
	46	*/
	47	void show_pte(struct mm_struct *mm, unsigned long addr)
	48	{
	49	pgd_t *pgd;
	50
	51	if (!mm)
	52	mm = &init_mm;
	53
	54	pr_alert("pgd = %p\n", mm->pgd);
	55	pgd = pgd_offset(mm, addr);
	56	pr_alert("[%08lx] pgd=%016llx", addr, pgd_val(pgd));
	57
	58	do {
	59	pud_t *pud;
	60	pmd_t *pmd;
	61	pte_t *pte;
	62
4339e3f3	63	if (pgd_none(pgd) \|\| pgd_bad(pgd))
1d18c47c CM	64	break;
	65
	66	pud = pud_offset(pgd, addr);
c79b954b	67	printk(", pud=%016llx", pud_val(pud));
4339e3f3	68	if (pud_none(pud) \|\| pud_bad(pud))
1d18c47c CM	69	break;
	70
	71	pmd = pmd_offset(pud, addr);
	72	printk(", pmd=%016llx", pmd_val(pmd));
4339e3f3	73	if (pmd_none(pmd) \|\| pmd_bad(pmd))
1d18c47c CM	74	break;
	75
	76	pte = pte_offset_map(pmd, addr);
	77	printk(", pte=%016llx", pte_val(pte));
	78	pte_unmap(pte);
	79	} while(0);
	80
	81	printk("\n");
	82	}
	83
	84	/*
	85	* The kernel tried to access some page that wasn't present.
	86	*/
	87	static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
	88	unsigned int esr, struct pt_regs *regs)
	89	{
	90	/*
	91	* Are we prepared to handle this kernel fault?
	92	*/
	93	if (fixup_exception(regs))
	94	return;
	95
	96	/*
	97	* No handler, we'll have to terminate things with extreme prejudice.
	98	*/
	99	bust_spinlocks(1);
	100	pr_alert("Unable to handle kernel %s at virtual address %08lx\n",
	101	(addr < PAGE_SIZE) ? "NULL pointer dereference" :
	102	"paging request", addr);
	103
	104	show_pte(mm, addr);
	105	die("Oops", regs, esr);
	106	bust_spinlocks(0);
	107	do_exit(SIGKILL);
	108	}
	109
	110	/*
	111	* Something tried to access memory that isn't in our memory map. User mode
	112	* accesses just cause a SIGSEGV
	113	*/
	114	static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
	115	unsigned int esr, unsigned int sig, int code,
	116	struct pt_regs *regs)
	117	{
	118	struct siginfo si;
	119
f871d268	120	if (unhandled_signal(tsk, sig) && show_unhandled_signals_ratelimited()) {
3495386b CM	121	pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
	122	tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
	123	addr, esr);
1d18c47c CM	124	show_pte(tsk->mm, addr);
	125	show_regs(regs);
	126	}
	127
	128	tsk->thread.fault_address = addr;
9141300a	129	tsk->thread.fault_code = esr;
1d18c47c CM	130	si.si_signo = sig;
	131	si.si_errno = 0;
	132	si.si_code = code;
	133	si.si_addr = (void __user *)addr;
	134	force_sig_info(sig, &si, tsk);
	135	}
	136
59f67e16	137	static void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs)
1d18c47c CM	138	{
	139	struct task_struct *tsk = current;
	140	struct mm_struct *mm = tsk->active_mm;
	141
	142	/*
	143	* If we are in kernel mode at this point, we have no context to
	144	* handle this fault with.
	145	*/
	146	if (user_mode(regs))
	147	__do_user_fault(tsk, addr, esr, SIGSEGV, SEGV_MAPERR, regs);
	148	else
	149	__do_kernel_fault(mm, addr, esr, regs);
	150	}
	151
	152	#define VM_FAULT_BADMAP 0x010000
	153	#define VM_FAULT_BADACCESS 0x020000
	154
1d18c47c CM	155	#define ESR_LNX_EXEC (1 << 24)
1d18c47c CM	156
1d18c47c	157	static int __do_page_fault(struct mm_struct *mm, unsigned long addr,
db6f4106	158	unsigned int mm_flags, unsigned long vm_flags,
1d18c47c CM	159	struct task_struct *tsk)
	160	{
	161	struct vm_area_struct *vma;
	162	int fault;
	163
	164	vma = find_vma(mm, addr);
	165	fault = VM_FAULT_BADMAP;
	166	if (unlikely(!vma))
	167	goto out;
	168	if (unlikely(vma->vm_start > addr))
	169	goto check_stack;
	170
	171	/*
	172	* Ok, we have a good vm_area for this memory access, so we can handle
	173	* it.
	174	*/
	175	good_area:
db6f4106 WD	176	/*
db6f4106 WD	177	* Check that the permissions on the VMA allow for the fault which
5a0fdfad CM	178	* occurred. If we encountered a write or exec fault, we must have
5a0fdfad CM	179	* appropriate permissions, otherwise we allow any permission.
db6f4106 WD	180	*/
db6f4106 WD	181	if (!(vma->vm_flags & vm_flags)) {
1d18c47c CM	182	fault = VM_FAULT_BADACCESS;
	183	goto out;
	184	}
	185
db6f4106	186	return handle_mm_fault(mm, vma, addr & PAGE_MASK, mm_flags);
1d18c47c CM	187
	188	check_stack:
	189	if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
	190	goto good_area;
	191	out:
	192	return fault;
	193	}
	194
	195	static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
	196	struct pt_regs *regs)
	197	{
	198	struct task_struct *tsk;
	199	struct mm_struct *mm;
	200	int fault, sig, code;
5a0fdfad	201	unsigned long vm_flags = VM_READ \| VM_WRITE \| VM_EXEC;
db6f4106 WD	202	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY \| FAULT_FLAG_KILLABLE;
db6f4106 WD	203
1d18c47c CM	204	tsk = current;
	205	mm = tsk->mm;
	206
	207	/* Enable interrupts if they were enabled in the parent context. */
	208	if (interrupts_enabled(regs))
	209	local_irq_enable();
	210
	211	/*
	212	* If we're in an interrupt or have no user context, we must not take
	213	* the fault.
	214	*/
70ffdb93	215	if (faulthandler_disabled() \|\| !mm)
1d18c47c CM	216	goto no_context;
1d18c47c CM	217
759496ba JW	218	if (user_mode(regs))
	219	mm_flags \|= FAULT_FLAG_USER;
	220
	221	if (esr & ESR_LNX_EXEC) {
	222	vm_flags = VM_EXEC;
aed40e01	223	} else if ((esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM)) {
759496ba JW	224	vm_flags = VM_WRITE;
	225	mm_flags \|= FAULT_FLAG_WRITE;
	226	}
	227
338d4f49 JM	228	/*
	229	* PAN bit set implies the fault happened in kernel space, but not
	230	* in the arch's user access functions.
	231	*/
	232	if (IS_ENABLED(CONFIG_ARM64_PAN) && (regs->pstate & PSR_PAN_BIT))
	233	goto no_context;
	234
1d18c47c CM	235	/*
	236	* As per x86, we may deadlock here. However, since the kernel only
	237	* validly references user space from well defined areas of the code,
	238	* we can bug out early if this is from code which shouldn't.
	239	*/
	240	if (!down_read_trylock(&mm->mmap_sem)) {
	241	if (!user_mode(regs) && !search_exception_tables(regs->pc))
	242	goto no_context;
	243	retry:
	244	down_read(&mm->mmap_sem);
	245	} else {
	246	/*
	247	* The above down_read_trylock() might have succeeded in which
	248	* case, we'll have missed the might_sleep() from down_read().
	249	*/
	250	might_sleep();
	251	#ifdef CONFIG_DEBUG_VM
	252	if (!user_mode(regs) && !search_exception_tables(regs->pc))
	253	goto no_context;
	254	#endif
	255	}
	256
db6f4106	257	fault = __do_page_fault(mm, addr, mm_flags, vm_flags, tsk);
1d18c47c CM	258
	259	/*
	260	* If we need to retry but a fatal signal is pending, handle the
	261	* signal first. We do not need to release the mmap_sem because it
	262	* would already be released in __lock_page_or_retry in mm/filemap.c.
	263	*/
	264	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
	265	return 0;
	266
	267	/*
	268	* Major/minor page fault accounting is only done on the initial
	269	* attempt. If we go through a retry, it is extremely likely that the
	270	* page will be found in page cache at that point.
	271	*/
	272
	273	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
db6f4106	274	if (mm_flags & FAULT_FLAG_ALLOW_RETRY) {
1d18c47c CM	275	if (fault & VM_FAULT_MAJOR) {
	276	tsk->maj_flt++;
	277	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
	278	addr);
	279	} else {
	280	tsk->min_flt++;
	281	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs,
	282	addr);
	283	}
	284	if (fault & VM_FAULT_RETRY) {
	285	/*
	286	* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of
	287	* starvation.
	288	*/
db6f4106	289	mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
569ba74a	290	mm_flags \|= FAULT_FLAG_TRIED;
1d18c47c CM	291	goto retry;
	292	}
	293	}
	294
	295	up_read(&mm->mmap_sem);
	296
	297	/*
	298	* Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR
	299	*/
	300	if (likely(!(fault & (VM_FAULT_ERROR \| VM_FAULT_BADMAP \|
	301	VM_FAULT_BADACCESS))))
	302	return 0;
	303
87134102 JW	304	/*
	305	* If we are in kernel mode at this point, we have no context to
	306	* handle this fault with.
	307	*/
	308	if (!user_mode(regs))
	309	goto no_context;
	310
1d18c47c CM	311	if (fault & VM_FAULT_OOM) {
	312	/*
	313	* We ran out of memory, call the OOM killer, and return to
	314	* userspace (which will retry the fault, or kill us if we got
	315	* oom-killed).
	316	*/
	317	pagefault_out_of_memory();
	318	return 0;
	319	}
	320
1d18c47c CM	321	if (fault & VM_FAULT_SIGBUS) {
	322	/*
	323	* We had some memory, but were unable to successfully fix up
	324	* this page fault.
	325	*/
	326	sig = SIGBUS;
	327	code = BUS_ADRERR;
	328	} else {
	329	/*
	330	* Something tried to access memory that isn't in our memory
	331	* map.
	332	*/
	333	sig = SIGSEGV;
	334	code = fault == VM_FAULT_BADACCESS ?
	335	SEGV_ACCERR : SEGV_MAPERR;
	336	}
	337
	338	__do_user_fault(tsk, addr, esr, sig, code, regs);
	339	return 0;
	340
	341	no_context:
	342	__do_kernel_fault(mm, addr, esr, regs);
	343	return 0;
	344	}
	345
	346	/*
	347	* First Level Translation Fault Handler
	348	*
	349	* We enter here because the first level page table doesn't contain a valid
	350	* entry for the address.
	351	*
	352	* If the address is in kernel space (>= TASK_SIZE), then we are probably
	353	* faulting in the vmalloc() area.
	354	*
	355	* If the init_task's first level page tables contains the relevant entry, we
	356	* copy the it to this task. If not, we send the process a signal, fixup the
	357	* exception, or oops the kernel.
	358	*
	359	* NOTE! We MUST NOT take any locks for this case. We may be in an interrupt
	360	* or a critical region, and should only copy the information from the master
	361	* page table, nothing more.
	362	*/
	363	static int __kprobes do_translation_fault(unsigned long addr,
	364	unsigned int esr,
	365	struct pt_regs *regs)
	366	{
	367	if (addr < TASK_SIZE)
	368	return do_page_fault(addr, esr, regs);
	369
	370	do_bad_area(addr, esr, regs);
	371	return 0;
	372	}
	373
52d7523d EL	374	static int do_alignment_fault(unsigned long addr, unsigned int esr,
	375	struct pt_regs *regs)
	376	{
	377	do_bad_area(addr, esr, regs);
	378	return 0;
	379	}
	380
1d18c47c CM	381	/*
	382	* This abort handler always returns "fault".
	383	*/
	384	static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
	385	{
	386	return 1;
	387	}
	388
	389	static struct fault_info {
	390	int (fn)(unsigned long addr, unsigned int esr, struct pt_regs regs);
	391	int sig;
	392	int code;
	393	const char *name;
	394	} fault_info[] = {
	395	{ do_bad, SIGBUS, 0, "ttbr address size fault" },
	396	{ do_bad, SIGBUS, 0, "level 1 address size fault" },
	397	{ do_bad, SIGBUS, 0, "level 2 address size fault" },
	398	{ do_bad, SIGBUS, 0, "level 3 address size fault" },
7f73f7ae	399	{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 0 translation fault" },
1d18c47c CM	400	{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" },
	401	{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" },
	402	{ do_page_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" },
c03784ee	403	{ do_bad, SIGBUS, 0, "unknown 8" },
084bd298 SC	404	{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" },
084bd298 SC	405	{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" },
1d18c47c	406	{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" },
c03784ee	407	{ do_bad, SIGBUS, 0, "unknown 12" },
084bd298 SC	408	{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" },
084bd298 SC	409	{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" },
1d18c47c CM	410	{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" },
1d18c47c CM	411	{ do_bad, SIGBUS, 0, "synchronous external abort" },
c03784ee	412	{ do_bad, SIGBUS, 0, "unknown 17" },
1d18c47c CM	413	{ do_bad, SIGBUS, 0, "unknown 18" },
	414	{ do_bad, SIGBUS, 0, "unknown 19" },
	415	{ do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
	416	{ do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
	417	{ do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
	418	{ do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
	419	{ do_bad, SIGBUS, 0, "synchronous parity error" },
c03784ee	420	{ do_bad, SIGBUS, 0, "unknown 25" },
1d18c47c CM	421	{ do_bad, SIGBUS, 0, "unknown 26" },
1d18c47c CM	422	{ do_bad, SIGBUS, 0, "unknown 27" },
c03784ee MR	423	{ do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" },
	424	{ do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" },
	425	{ do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" },
	426	{ do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" },
1d18c47c	427	{ do_bad, SIGBUS, 0, "unknown 32" },
52d7523d	428	{ do_alignment_fault, SIGBUS, BUS_ADRALN, "alignment fault" },
c03784ee	429	{ do_bad, SIGBUS, 0, "unknown 34" },
1d18c47c CM	430	{ do_bad, SIGBUS, 0, "unknown 35" },
	431	{ do_bad, SIGBUS, 0, "unknown 36" },
	432	{ do_bad, SIGBUS, 0, "unknown 37" },
	433	{ do_bad, SIGBUS, 0, "unknown 38" },
	434	{ do_bad, SIGBUS, 0, "unknown 39" },
	435	{ do_bad, SIGBUS, 0, "unknown 40" },
	436	{ do_bad, SIGBUS, 0, "unknown 41" },
	437	{ do_bad, SIGBUS, 0, "unknown 42" },
	438	{ do_bad, SIGBUS, 0, "unknown 43" },
	439	{ do_bad, SIGBUS, 0, "unknown 44" },
	440	{ do_bad, SIGBUS, 0, "unknown 45" },
	441	{ do_bad, SIGBUS, 0, "unknown 46" },
	442	{ do_bad, SIGBUS, 0, "unknown 47" },
c03784ee	443	{ do_bad, SIGBUS, 0, "TLB conflict abort" },
1d18c47c CM	444	{ do_bad, SIGBUS, 0, "unknown 49" },
	445	{ do_bad, SIGBUS, 0, "unknown 50" },
	446	{ do_bad, SIGBUS, 0, "unknown 51" },
	447	{ do_bad, SIGBUS, 0, "implementation fault (lockdown abort)" },
c03784ee	448	{ do_bad, SIGBUS, 0, "implementation fault (unsupported exclusive)" },
1d18c47c CM	449	{ do_bad, SIGBUS, 0, "unknown 54" },
	450	{ do_bad, SIGBUS, 0, "unknown 55" },
	451	{ do_bad, SIGBUS, 0, "unknown 56" },
	452	{ do_bad, SIGBUS, 0, "unknown 57" },
c03784ee	453	{ do_bad, SIGBUS, 0, "unknown 58" },
1d18c47c CM	454	{ do_bad, SIGBUS, 0, "unknown 59" },
1d18c47c CM	455	{ do_bad, SIGBUS, 0, "unknown 60" },
c03784ee MR	456	{ do_bad, SIGBUS, 0, "section domain fault" },
c03784ee MR	457	{ do_bad, SIGBUS, 0, "page domain fault" },
1d18c47c CM	458	{ do_bad, SIGBUS, 0, "unknown 63" },
	459	};
	460
3495386b CM	461	static const char *fault_name(unsigned int esr)
	462	{
	463	const struct fault_info *inf = fault_info + (esr & 63);
	464	return inf->name;
	465	}
	466
1d18c47c CM	467	/*
	468	* Dispatch a data abort to the relevant handler.
	469	*/
	470	asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
	471	struct pt_regs *regs)
	472	{
	473	const struct fault_info *inf = fault_info + (esr & 63);
	474	struct siginfo info;
	475
	476	if (!inf->fn(addr, esr, regs))
	477	return;
	478
	479	pr_alert("Unhandled fault: %s (0x%08x) at 0x%016lx\n",
	480	inf->name, esr, addr);
	481
	482	info.si_signo = inf->sig;
	483	info.si_errno = 0;
	484	info.si_code = inf->code;
	485	info.si_addr = (void __user *)addr;
	486	arm64_notify_die("", regs, &info, esr);
	487	}
	488
	489	/*
	490	* Handle stack alignment exceptions.
	491	*/
	492	asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
	493	unsigned int esr,
	494	struct pt_regs *regs)
	495	{
	496	struct siginfo info;
9e793ab8 VM	497	struct task_struct *tsk = current;
	498
	499	if (show_unhandled_signals && unhandled_signal(tsk, SIGBUS))
	500	pr_info_ratelimited("%s[%d]: %s exception: pc=%p sp=%p\n",
	501	tsk->comm, task_pid_nr(tsk),
	502	esr_get_class_string(esr), (void *)regs->pc,
	503	(void *)regs->sp);
1d18c47c CM	504
	505	info.si_signo = SIGBUS;
	506	info.si_errno = 0;
	507	info.si_code = BUS_ADRALN;
	508	info.si_addr = (void __user *)addr;
9e793ab8	509	arm64_notify_die("Oops - SP/PC alignment exception", regs, &info, esr);
1d18c47c CM	510	}
1d18c47c CM	511
9fb7410f DM	512	int __init early_brk64(unsigned long addr, unsigned int esr,
	513	struct pt_regs *regs);
	514
	515	/*
	516	* __refdata because early_brk64 is __init, but the reference to it is
	517	* clobbered at arch_initcall time.
	518	* See traps.c and debug-monitors.c:debug_traps_init().
	519	*/
	520	static struct fault_info __refdata debug_fault_info[] = {
1d18c47c CM	521	{ do_bad, SIGTRAP, TRAP_HWBKPT, "hardware breakpoint" },
	522	{ do_bad, SIGTRAP, TRAP_HWBKPT, "hardware single-step" },
	523	{ do_bad, SIGTRAP, TRAP_HWBKPT, "hardware watchpoint" },
	524	{ do_bad, SIGBUS, 0, "unknown 3" },
	525	{ do_bad, SIGTRAP, TRAP_BRKPT, "aarch32 BKPT" },
	526	{ do_bad, SIGTRAP, 0, "aarch32 vector catch" },
9fb7410f	527	{ early_brk64, SIGTRAP, TRAP_BRKPT, "aarch64 BRK" },
1d18c47c CM	528	{ do_bad, SIGBUS, 0, "unknown 7" },
	529	};
	530
	531	void __init hook_debug_fault_code(int nr,
	532	int (fn)(unsigned long, unsigned int, struct pt_regs ),
	533	int sig, int code, const char *name)
	534	{
	535	BUG_ON(nr < 0 \|\| nr >= ARRAY_SIZE(debug_fault_info));
	536
	537	debug_fault_info[nr].fn = fn;
	538	debug_fault_info[nr].sig = sig;
	539	debug_fault_info[nr].code = code;
	540	debug_fault_info[nr].name = name;
	541	}
	542
	543	asmlinkage int __exception do_debug_exception(unsigned long addr,
	544	unsigned int esr,
	545	struct pt_regs *regs)
	546	{
	547	const struct fault_info *inf = debug_fault_info + DBG_ESR_EVT(esr);
	548	struct siginfo info;
	549
	550	if (!inf->fn(addr, esr, regs))
	551	return 1;
	552
	553	pr_alert("Unhandled debug exception: %s (0x%08x) at 0x%016lx\n",
	554	inf->name, esr, addr);
	555
	556	info.si_signo = inf->sig;
	557	info.si_errno = 0;
	558	info.si_code = inf->code;
	559	info.si_addr = (void __user *)addr;
9141300a	560	arm64_notify_die("", regs, &info, 0);
1d18c47c CM	561
	562	return 0;
	563	}
338d4f49 JM	564
338d4f49 JM	565	#ifdef CONFIG_ARM64_PAN
dbb4e152	566	void cpu_enable_pan(void *__unused)
338d4f49 JM	567	{
	568	config_sctlr_el1(SCTLR_EL1_SPAN, 0);
	569	}
	570	#endif /* CONFIG_ARM64_PAN */