[GitHub/mt8127/android_kernel_alcatel_ttab.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/exception.h>
#include <asm/debug-monitors.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);
		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 (show_unhandled_signals && unhandled_signal(tsk, sig) &&
	    printk_ratelimit()) {
		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;
	si.si_signo = sig;
	si.si_errno = 0;
	si.si_code = code;
	si.si_addr = (void __user *)addr;
	force_sig_info(sig, &si, tsk);
}

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_WRITE		(1 << 6)
#define ESR_CM			(1 << 8)
#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;

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

	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 (in_atomic() || !mm)
		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;
			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 (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 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_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;
}

/*
 * Some section permission faults need to be handled gracefully.  They can
 * happen due to a __{get,put}_user during an oops.
 */
static int do_sect_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,	"input address range 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,		"reserved access flag fault"	},
	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 access flag fault"	},
	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 2 access flag fault"	},
	{ do_page_fault,	SIGSEGV, SEGV_ACCERR,	"level 3 access flag fault"	},
	{ do_bad,		SIGBUS,  0,		"reserved permission fault"	},
	{ do_bad,		SIGSEGV, SEGV_ACCERR,	"level 1 permission fault"	},
	{ do_sect_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,		"asynchronous external abort"	},
	{ 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,		"asynchronous parity error"	},
	{ 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_bad,		SIGBUS,  BUS_ADRALN,	"alignment fault"		},
	{ do_bad,		SIGBUS,  0,		"debug event"			},
	{ 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,		"unknown 48"			},
	{ 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,		"unknown 53"			},
	{ 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,		"implementation fault (coprocessor abort)" },
	{ do_bad,		SIGBUS,  0,		"unknown 59"			},
	{ do_bad,		SIGBUS,  0,		"unknown 60"			},
	{ do_bad,		SIGBUS,  0,		"unknown 61"			},
	{ do_bad,		SIGBUS,  0,		"unknown 62"			},
	{ 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;

	info.si_signo = SIGBUS;
	info.si_errno = 0;
	info.si_code  = BUS_ADRALN;
	info.si_addr  = (void __user *)addr;
	arm64_notify_die("", regs, &info, esr);
}

static struct fault_info 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"	},
	{ do_bad,	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;
}

#ifdef CONFIG_MEDIATEK_SOLUTION
void __init hook_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(fault_info));

	fault_info[nr].fn   = fn;
	fault_info[nr].sig  = sig;
	fault_info[nr].code = code;
	fault_info[nr].name = name;
}
#endif

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, esr);

	return 0;
}
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
	33	#include <asm/exception.h>
	34	#include <asm/debug-monitors.h>
	35	#include <asm/system_misc.h>
	36	#include <asm/pgtable.h>
	37	#include <asm/tlbflush.h>
	38
3495386b CM	39	static const char *fault_name(unsigned int esr);
3495386b CM	40
1d18c47c CM	41	/*
	42	* Dump out the page tables associated with 'addr' in mm 'mm'.
	43	*/
	44	void show_pte(struct mm_struct *mm, unsigned long addr)
	45	{
	46	pgd_t *pgd;
	47
	48	if (!mm)
	49	mm = &init_mm;
	50
	51	pr_alert("pgd = %p\n", mm->pgd);
	52	pgd = pgd_offset(mm, addr);
	53	pr_alert("[%08lx] pgd=%016llx", addr, pgd_val(pgd));
	54
	55	do {
	56	pud_t *pud;
	57	pmd_t *pmd;
	58	pte_t *pte;
	59
4339e3f3	60	if (pgd_none(pgd) \|\| pgd_bad(pgd))
1d18c47c CM	61	break;
	62
	63	pud = pud_offset(pgd, addr);
4339e3f3	64	if (pud_none(pud) \|\| pud_bad(pud))
1d18c47c CM	65	break;
	66
	67	pmd = pmd_offset(pud, addr);
	68	printk(", pmd=%016llx", pmd_val(pmd));
4339e3f3	69	if (pmd_none(pmd) \|\| pmd_bad(pmd))
1d18c47c CM	70	break;
	71
	72	pte = pte_offset_map(pmd, addr);
	73	printk(", pte=%016llx", pte_val(pte));
	74	pte_unmap(pte);
	75	} while(0);
	76
	77	printk("\n");
	78	}
	79
	80	/*
	81	* The kernel tried to access some page that wasn't present.
	82	*/
	83	static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
	84	unsigned int esr, struct pt_regs *regs)
	85	{
	86	/*
	87	* Are we prepared to handle this kernel fault?
	88	*/
	89	if (fixup_exception(regs))
	90	return;
	91
	92	/*
	93	* No handler, we'll have to terminate things with extreme prejudice.
	94	*/
	95	bust_spinlocks(1);
	96	pr_alert("Unable to handle kernel %s at virtual address %08lx\n",
	97	(addr < PAGE_SIZE) ? "NULL pointer dereference" :
	98	"paging request", addr);
	99
	100	show_pte(mm, addr);
	101	die("Oops", regs, esr);
	102	bust_spinlocks(0);
	103	do_exit(SIGKILL);
	104	}
	105
	106	/*
	107	* Something tried to access memory that isn't in our memory map. User mode
	108	* accesses just cause a SIGSEGV
	109	*/
	110	static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
	111	unsigned int esr, unsigned int sig, int code,
	112	struct pt_regs *regs)
	113	{
	114	struct siginfo si;
	115
953dbbed CM	116	if (show_unhandled_signals && unhandled_signal(tsk, sig) &&
953dbbed CM	117	printk_ratelimit()) {
3495386b CM	118	pr_info("%s[%d]: unhandled %s (%d) at 0x%08lx, esr 0x%03x\n",
	119	tsk->comm, task_pid_nr(tsk), fault_name(esr), sig,
	120	addr, esr);
1d18c47c CM	121	show_pte(tsk->mm, addr);
	122	show_regs(regs);
	123	}
	124
	125	tsk->thread.fault_address = addr;
	126	si.si_signo = sig;
	127	si.si_errno = 0;
	128	si.si_code = code;
	129	si.si_addr = (void __user *)addr;
	130	force_sig_info(sig, &si, tsk);
	131	}
	132
	133	void do_bad_area(unsigned long addr, unsigned int esr, struct pt_regs *regs)
	134	{
	135	struct task_struct *tsk = current;
	136	struct mm_struct *mm = tsk->active_mm;
	137
	138	/*
	139	* If we are in kernel mode at this point, we have no context to
	140	* handle this fault with.
	141	*/
	142	if (user_mode(regs))
	143	__do_user_fault(tsk, addr, esr, SIGSEGV, SEGV_MAPERR, regs);
	144	else
	145	__do_kernel_fault(mm, addr, esr, regs);
	146	}
	147
	148	#define VM_FAULT_BADMAP 0x010000
	149	#define VM_FAULT_BADACCESS 0x020000
	150
	151	#define ESR_WRITE (1 << 6)
0e7f7bcc	152	#define ESR_CM (1 << 8)
1d18c47c CM	153	#define ESR_LNX_EXEC (1 << 24)
1d18c47c CM	154
1d18c47c	155	static int __do_page_fault(struct mm_struct *mm, unsigned long addr,
88c0a794	156	unsigned int mm_flags, unsigned long vm_flags,
1d18c47c CM	157	struct task_struct *tsk)
	158	{
	159	struct vm_area_struct *vma;
	160	int fault;
	161
	162	vma = find_vma(mm, addr);
	163	fault = VM_FAULT_BADMAP;
	164	if (unlikely(!vma))
	165	goto out;
	166	if (unlikely(vma->vm_start > addr))
	167	goto check_stack;
	168
	169	/*
	170	* Ok, we have a good vm_area for this memory access, so we can handle
	171	* it.
	172	*/
	173	good_area:
88c0a794 WD	174	/*
	175	* Check that the permissions on the VMA allow for the fault which
	176	* occurred. If we encountered a write or exec fault, we must have
	177	* appropriate permissions, otherwise we allow any permission.
	178	*/
	179	if (!(vma->vm_flags & vm_flags)) {
1d18c47c CM	180	fault = VM_FAULT_BADACCESS;
	181	goto out;
	182	}
	183
88c0a794	184	return handle_mm_fault(mm, vma, addr & PAGE_MASK, mm_flags);
1d18c47c CM	185
	186	check_stack:
	187	if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
	188	goto good_area;
	189	out:
	190	return fault;
	191	}
	192
	193	static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
	194	struct pt_regs *regs)
	195	{
	196	struct task_struct *tsk;
	197	struct mm_struct *mm;
	198	int fault, sig, code;
88c0a794 WD	199	unsigned long vm_flags = VM_READ \| VM_WRITE \| VM_EXEC;
	200	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY \| FAULT_FLAG_KILLABLE;
	201
	202	if (esr & ESR_LNX_EXEC) {
	203	vm_flags = VM_EXEC;
	204	} else if ((esr & ESR_WRITE) && !(esr & ESR_CM)) {
	205	vm_flags = VM_WRITE;
	206	mm_flags \|= FAULT_FLAG_WRITE;
	207	}
1d18c47c CM	208
	209	tsk = current;
	210	mm = tsk->mm;
	211
	212	/* Enable interrupts if they were enabled in the parent context. */
	213	if (interrupts_enabled(regs))
	214	local_irq_enable();
	215
	216	/*
	217	* If we're in an interrupt or have no user context, we must not take
	218	* the fault.
	219	*/
	220	if (in_atomic() \|\| !mm)
	221	goto no_context;
	222
	223	/*
	224	* As per x86, we may deadlock here. However, since the kernel only
	225	* validly references user space from well defined areas of the code,
	226	* we can bug out early if this is from code which shouldn't.
	227	*/
	228	if (!down_read_trylock(&mm->mmap_sem)) {
	229	if (!user_mode(regs) && !search_exception_tables(regs->pc))
	230	goto no_context;
	231	retry:
	232	down_read(&mm->mmap_sem);
	233	} else {
	234	/*
	235	* The above down_read_trylock() might have succeeded in which
	236	* case, we'll have missed the might_sleep() from down_read().
	237	*/
	238	might_sleep();
	239	#ifdef CONFIG_DEBUG_VM
	240	if (!user_mode(regs) && !search_exception_tables(regs->pc))
	241	goto no_context;
	242	#endif
	243	}
	244
88c0a794	245	fault = __do_page_fault(mm, addr, mm_flags, vm_flags, tsk);
1d18c47c CM	246
	247	/*
	248	* If we need to retry but a fatal signal is pending, handle the
	249	* signal first. We do not need to release the mmap_sem because it
	250	* would already be released in __lock_page_or_retry in mm/filemap.c.
	251	*/
	252	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
	253	return 0;
	254
	255	/*
	256	* Major/minor page fault accounting is only done on the initial
	257	* attempt. If we go through a retry, it is extremely likely that the
	258	* page will be found in page cache at that point.
	259	*/
	260
	261	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);
88c0a794	262	if (mm_flags & FAULT_FLAG_ALLOW_RETRY) {
1d18c47c CM	263	if (fault & VM_FAULT_MAJOR) {
	264	tsk->maj_flt++;
	265	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
	266	addr);
	267	} else {
	268	tsk->min_flt++;
	269	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs,
	270	addr);
	271	}
	272	if (fault & VM_FAULT_RETRY) {
	273	/*
	274	* Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk of
	275	* starvation.
	276	*/
88c0a794	277	mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
1d18c47c CM	278	goto retry;
	279	}
	280	}
	281
	282	up_read(&mm->mmap_sem);
	283
	284	/*
	285	* Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR
	286	*/
	287	if (likely(!(fault & (VM_FAULT_ERROR \| VM_FAULT_BADMAP \|
	288	VM_FAULT_BADACCESS))))
	289	return 0;
	290
	291	if (fault & VM_FAULT_OOM) {
	292	/*
	293	* We ran out of memory, call the OOM killer, and return to
	294	* userspace (which will retry the fault, or kill us if we got
	295	* oom-killed).
	296	*/
	297	pagefault_out_of_memory();
	298	return 0;
	299	}
	300
	301	/*
	302	* If we are in kernel mode at this point, we have no context to
	303	* handle this fault with.
	304	*/
	305	if (!user_mode(regs))
	306	goto no_context;
	307
	308	if (fault & VM_FAULT_SIGBUS) {
	309	/*
	310	* We had some memory, but were unable to successfully fix up
	311	* this page fault.
	312	*/
	313	sig = SIGBUS;
	314	code = BUS_ADRERR;
	315	} else {
	316	/*
	317	* Something tried to access memory that isn't in our memory
	318	* map.
	319	*/
	320	sig = SIGSEGV;
	321	code = fault == VM_FAULT_BADACCESS ?
	322	SEGV_ACCERR : SEGV_MAPERR;
	323	}
	324
	325	__do_user_fault(tsk, addr, esr, sig, code, regs);
	326	return 0;
	327
	328	no_context:
	329	__do_kernel_fault(mm, addr, esr, regs);
	330	return 0;
	331	}
	332
	333	/*
	334	* First Level Translation Fault Handler
	335	*
	336	* We enter here because the first level page table doesn't contain a valid
	337	* entry for the address.
	338	*
	339	* If the address is in kernel space (>= TASK_SIZE), then we are probably
	340	* faulting in the vmalloc() area.
	341	*
342	* If the init_task's first level page tables contains the relevant entry, we
343	* copy the it to this task. If not, we send the process a signal, fixup the
344	* exception, or oops the kernel.
345	*
346	* NOTE! We MUST NOT take any locks for this case. We may be in an interrupt
347	* or a critical region, and should only copy the information from the master
348	* page table, nothing more.
349	*/
350	static int __kprobes do_translation_fault(unsigned long addr,
351	unsigned int esr,
352	struct pt_regs *regs)
353	{
354	if (addr < TASK_SIZE)
355	return do_page_fault(addr, esr, regs);
356
357	do_bad_area(addr, esr, regs);
358	return 0;
359	}
360
361	/*
362	* Some section permission faults need to be handled gracefully. They can
363	* happen due to a __{get,put}_user during an oops.
364	*/
365	static int do_sect_fault(unsigned long addr, unsigned int esr,
366	struct pt_regs *regs)
367	{
368	do_bad_area(addr, esr, regs);
369	return 0;
370	}
371
372	/*
373	* This abort handler always returns "fault".
374	*/
375	static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
376	{
377	return 1;
378	}
379
380	static struct fault_info {
381	int (fn)(unsigned long addr, unsigned int esr, struct pt_regs regs);
382	int sig;
383	int code;
384	const char *name;
385	} fault_info[] = {
386	{ do_bad, SIGBUS, 0, "ttbr address size fault" },
387	{ do_bad, SIGBUS, 0, "level 1 address size fault" },
388	{ do_bad, SIGBUS, 0, "level 2 address size fault" },
389	{ do_bad, SIGBUS, 0, "level 3 address size fault" },
390	{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "input address range fault" },
391	{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" },
392	{ do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" },
393	{ do_page_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" },
394	{ do_bad, SIGBUS, 0, "reserved access flag fault" },
395	{ do_bad, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" },
396	{ do_bad, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" },
397	{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" },
398	{ do_bad, SIGBUS, 0, "reserved permission fault" },
399	{ do_bad, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" },
400	{ do_sect_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" },
401	{ do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" },
402	{ do_bad, SIGBUS, 0, "synchronous external abort" },
403	{ do_bad, SIGBUS, 0, "asynchronous external abort" },
404	{ do_bad, SIGBUS, 0, "unknown 18" },
405	{ do_bad, SIGBUS, 0, "unknown 19" },
406	{ do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
407	{ do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
408	{ do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
409	{ do_bad, SIGBUS, 0, "synchronous abort (translation table walk)" },
410	{ do_bad, SIGBUS, 0, "synchronous parity error" },
411	{ do_bad, SIGBUS, 0, "asynchronous parity error" },
412	{ do_bad, SIGBUS, 0, "unknown 26" },
413	{ do_bad, SIGBUS, 0, "unknown 27" },
414	{ do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" },
415	{ do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" },
416	{ do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" },
417	{ do_bad, SIGBUS, 0, "synchronous parity error (translation table walk" },
418	{ do_bad, SIGBUS, 0, "unknown 32" },
419	{ do_bad, SIGBUS, BUS_ADRALN, "alignment fault" },
420	{ do_bad, SIGBUS, 0, "debug event" },
421	{ do_bad, SIGBUS, 0, "unknown 35" },
422	{ do_bad, SIGBUS, 0, "unknown 36" },
423	{ do_bad, SIGBUS, 0, "unknown 37" },
424	{ do_bad, SIGBUS, 0, "unknown 38" },
425	{ do_bad, SIGBUS, 0, "unknown 39" },
426	{ do_bad, SIGBUS, 0, "unknown 40" },
427	{ do_bad, SIGBUS, 0, "unknown 41" },
428	{ do_bad, SIGBUS, 0, "unknown 42" },
429	{ do_bad, SIGBUS, 0, "unknown 43" },
430	{ do_bad, SIGBUS, 0, "unknown 44" },
431	{ do_bad, SIGBUS, 0, "unknown 45" },
432	{ do_bad, SIGBUS, 0, "unknown 46" },
433	{ do_bad, SIGBUS, 0, "unknown 47" },
434	{ do_bad, SIGBUS, 0, "unknown 48" },
435	{ do_bad, SIGBUS, 0, "unknown 49" },
436	{ do_bad, SIGBUS, 0, "unknown 50" },
437	{ do_bad, SIGBUS, 0, "unknown 51" },
438	{ do_bad, SIGBUS, 0, "implementation fault (lockdown abort)" },
439	{ do_bad, SIGBUS, 0, "unknown 53" },
440	{ do_bad, SIGBUS, 0, "unknown 54" },
441	{ do_bad, SIGBUS, 0, "unknown 55" },
442	{ do_bad, SIGBUS, 0, "unknown 56" },
443	{ do_bad, SIGBUS, 0, "unknown 57" },
444	{ do_bad, SIGBUS, 0, "implementation fault (coprocessor abort)" },
445	{ do_bad, SIGBUS, 0, "unknown 59" },
446	{ do_bad, SIGBUS, 0, "unknown 60" },
447	{ do_bad, SIGBUS, 0, "unknown 61" },
448	{ do_bad, SIGBUS, 0, "unknown 62" },
449	{ do_bad, SIGBUS, 0, "unknown 63" },
450	};
451
3495386b CM	452	static const char *fault_name(unsigned int esr)
	453	{
	454	const struct fault_info *inf = fault_info + (esr & 63);
	455	return inf->name;
	456	}
	457
1d18c47c CM	458	/*
	459	* Dispatch a data abort to the relevant handler.
	460	*/
	461	asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
	462	struct pt_regs *regs)
	463	{
	464	const struct fault_info *inf = fault_info + (esr & 63);
	465	struct siginfo info;
	466
	467	if (!inf->fn(addr, esr, regs))
	468	return;
	469
	470	pr_alert("Unhandled fault: %s (0x%08x) at 0x%016lx\n",
	471	inf->name, esr, addr);
	472
	473	info.si_signo = inf->sig;
	474	info.si_errno = 0;
	475	info.si_code = inf->code;
	476	info.si_addr = (void __user *)addr;
	477	arm64_notify_die("", regs, &info, esr);
	478	}
	479
	480	/*
	481	* Handle stack alignment exceptions.
	482	*/
	483	asmlinkage void __exception do_sp_pc_abort(unsigned long addr,
	484	unsigned int esr,
	485	struct pt_regs *regs)
	486	{
	487	struct siginfo info;
	488
	489	info.si_signo = SIGBUS;
	490	info.si_errno = 0;
	491	info.si_code = BUS_ADRALN;
	492	info.si_addr = (void __user *)addr;
	493	arm64_notify_die("", regs, &info, esr);
	494	}
	495
	496	static struct fault_info debug_fault_info[] = {
	497	{ do_bad, SIGTRAP, TRAP_HWBKPT, "hardware breakpoint" },
	498	{ do_bad, SIGTRAP, TRAP_HWBKPT, "hardware single-step" },
	499	{ do_bad, SIGTRAP, TRAP_HWBKPT, "hardware watchpoint" },
	500	{ do_bad, SIGBUS, 0, "unknown 3" },
	501	{ do_bad, SIGTRAP, TRAP_BRKPT, "aarch32 BKPT" },
	502	{ do_bad, SIGTRAP, 0, "aarch32 vector catch" },
	503	{ do_bad, SIGTRAP, TRAP_BRKPT, "aarch64 BRK" },
	504	{ do_bad, SIGBUS, 0, "unknown 7" },
	505	};
	506
	507	void __init hook_debug_fault_code(int nr,
	508	int (fn)(unsigned long, unsigned int, struct pt_regs ),
	509	int sig, int code, const char *name)
	510	{
	511	BUG_ON(nr < 0 \|\| nr >= ARRAY_SIZE(debug_fault_info));
	512
	513	debug_fault_info[nr].fn = fn;
	514	debug_fault_info[nr].sig = sig;
	515	debug_fault_info[nr].code = code;
	516	debug_fault_info[nr].name = name;
	517	}
	518
6fa3eb70 S	519	#ifdef CONFIG_MEDIATEK_SOLUTION
	520	void __init hook_fault_code(int nr,
	521	int (fn)(unsigned long, unsigned int, struct pt_regs ),
	522	int sig, int code, const char *name)
	523	{
	524	BUG_ON(nr < 0 \|\| nr >= ARRAY_SIZE(fault_info));
	525
	526	fault_info[nr].fn = fn;
	527	fault_info[nr].sig = sig;
	528	fault_info[nr].code = code;
	529	fault_info[nr].name = name;
	530	}
	531	#endif
	532
1d18c47c CM	533	asmlinkage int __exception do_debug_exception(unsigned long addr,
	534	unsigned int esr,
	535	struct pt_regs *regs)
	536	{
	537	const struct fault_info *inf = debug_fault_info + DBG_ESR_EVT(esr);
	538	struct siginfo info;
	539
	540	if (!inf->fn(addr, esr, regs))
	541	return 1;
	542
	543	pr_alert("Unhandled debug exception: %s (0x%08x) at 0x%016lx\n",
	544	inf->name, esr, addr);
	545
	546	info.si_signo = inf->sig;
	547	info.si_errno = 0;
	548	info.si_code = inf->code;
	549	info.si_addr = (void __user *)addr;
	550	arm64_notify_die("", regs, &info, esr);
	551
	552	return 0;
	553	}