fault.c 7.2 KB
Newer Older
1 2
/*
 * Page fault handler for SH with an MMU.
L
Linus Torvalds 已提交
3 4
 *
 *  Copyright (C) 1999  Niibe Yutaka
P
Paul Mundt 已提交
5
 *  Copyright (C) 2003 - 2007  Paul Mundt
L
Linus Torvalds 已提交
6 7 8
 *
 *  Based on linux/arch/i386/mm/fault.c:
 *   Copyright (C) 1995  Linus Torvalds
9 10 11 12
 *
 * This file is subject to the terms and conditions of the GNU General Public
 * License.  See the file "COPYING" in the main directory of this archive
 * for more details.
L
Linus Torvalds 已提交
13 14 15
 */
#include <linux/kernel.h>
#include <linux/mm.h>
16 17
#include <linux/hardirq.h>
#include <linux/kprobes.h>
L
Linus Torvalds 已提交
18 19
#include <asm/system.h>
#include <asm/mmu_context.h>
20
#include <asm/tlbflush.h>
L
Linus Torvalds 已提交
21 22 23 24 25 26 27
#include <asm/kgdb.h>

/*
 * This routine handles page faults.  It determines the address,
 * and the problem, and then passes it off to one of the appropriate
 * routines.
 */
28 29 30
asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
					unsigned long writeaccess,
					unsigned long address)
L
Linus Torvalds 已提交
31 32 33 34
{
	struct task_struct *tsk;
	struct mm_struct *mm;
	struct vm_area_struct * vma;
35 36
	int si_code;
	siginfo_t info;
L
Linus Torvalds 已提交
37

38 39 40
	trace_hardirqs_on();
	local_irq_enable();

L
Linus Torvalds 已提交
41 42 43 44 45 46 47
#ifdef CONFIG_SH_KGDB
	if (kgdb_nofault && kgdb_bus_err_hook)
		kgdb_bus_err_hook();
#endif

	tsk = current;
	mm = tsk->mm;
48
	si_code = SEGV_MAPERR;
L
Linus Torvalds 已提交
49

S
Stuart Menefy 已提交
50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88
	if (unlikely(address >= TASK_SIZE)) {
		/*
		 * Synchronize this task's top level page-table
		 * with the 'reference' page table.
		 *
		 * Do _not_ use "tsk" here. We might be inside
		 * an interrupt in the middle of a task switch..
		 */
		int offset = pgd_index(address);
		pgd_t *pgd, *pgd_k;
		pud_t *pud, *pud_k;
		pmd_t *pmd, *pmd_k;

		pgd = get_TTB() + offset;
		pgd_k = swapper_pg_dir + offset;

		/* This will never happen with the folded page table. */
		if (!pgd_present(*pgd)) {
			if (!pgd_present(*pgd_k))
				goto bad_area_nosemaphore;
			set_pgd(pgd, *pgd_k);
			return;
		}

		pud = pud_offset(pgd, address);
		pud_k = pud_offset(pgd_k, address);
		if (pud_present(*pud) || !pud_present(*pud_k))
			goto bad_area_nosemaphore;
		set_pud(pud, *pud_k);

		pmd = pmd_offset(pud, address);
		pmd_k = pmd_offset(pud_k, address);
		if (pmd_present(*pmd) || !pmd_present(*pmd_k))
			goto bad_area_nosemaphore;
		set_pmd(pmd, *pmd_k);

		return;
	}

L
Linus Torvalds 已提交
89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111
	/*
	 * If we're in an interrupt or have no user
	 * context, we must not take the fault..
	 */
	if (in_atomic() || !mm)
		goto no_context;

	down_read(&mm->mmap_sem);

	vma = find_vma(mm, address);
	if (!vma)
		goto bad_area;
	if (vma->vm_start <= address)
		goto good_area;
	if (!(vma->vm_flags & VM_GROWSDOWN))
		goto bad_area;
	if (expand_stack(vma, address))
		goto bad_area;
/*
 * Ok, we have a good vm_area for this memory access, so
 * we can handle it..
 */
good_area:
112
	si_code = SEGV_ACCERR;
L
Linus Torvalds 已提交
113 114 115 116
	if (writeaccess) {
		if (!(vma->vm_flags & VM_WRITE))
			goto bad_area;
	} else {
117
		if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
L
Linus Torvalds 已提交
118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151
			goto bad_area;
	}

	/*
	 * If for any reason at all we couldn't handle the fault,
	 * make sure we exit gracefully rather than endlessly redo
	 * the fault.
	 */
survive:
	switch (handle_mm_fault(mm, vma, address, writeaccess)) {
		case VM_FAULT_MINOR:
			tsk->min_flt++;
			break;
		case VM_FAULT_MAJOR:
			tsk->maj_flt++;
			break;
		case VM_FAULT_SIGBUS:
			goto do_sigbus;
		case VM_FAULT_OOM:
			goto out_of_memory;
		default:
			BUG();
	}

	up_read(&mm->mmap_sem);
	return;

/*
 * Something tried to access memory that isn't in our memory map..
 * Fix it, but check if it's kernel or user first..
 */
bad_area:
	up_read(&mm->mmap_sem);

S
Stuart Menefy 已提交
152
bad_area_nosemaphore:
L
Linus Torvalds 已提交
153
	if (user_mode(regs)) {
154 155 156 157 158
		info.si_signo = SIGSEGV;
		info.si_errno = 0;
		info.si_code = si_code;
		info.si_addr = (void *) address;
		force_sig_info(SIGSEGV, &info, tsk);
L
Linus Torvalds 已提交
159 160 161 162 163 164 165 166 167 168 169 170 171
		return;
	}

no_context:
	/* Are we prepared to handle this kernel fault?  */
	if (fixup_exception(regs))
		return;

/*
 * Oops. The kernel tried to access some bad page. We'll have to
 * terminate things with extreme prejudice.
 *
 */
172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198

	bust_spinlocks(1);

	if (oops_may_print()) {
		__typeof__(pte_val(__pte(0))) page;

		if (address < PAGE_SIZE)
			printk(KERN_ALERT "Unable to handle kernel NULL "
					  "pointer dereference");
		else
			printk(KERN_ALERT "Unable to handle kernel paging "
					  "request");
		printk(" at virtual address %08lx\n", address);
		printk(KERN_ALERT "pc = %08lx\n", regs->pc);
		page = (unsigned long)get_TTB();
		if (page) {
			page = ((__typeof__(page) *) __va(page))[address >>
								 PGDIR_SHIFT];
			printk(KERN_ALERT "*pde = %08lx\n", page);
			if (page & _PAGE_PRESENT) {
				page &= PAGE_MASK;
				address &= 0x003ff000;
				page = ((__typeof__(page) *)
						__va(page))[address >>
							    PAGE_SHIFT];
				printk(KERN_ALERT "*pte = %08lx\n", page);
			}
L
Linus Torvalds 已提交
199 200
		}
	}
201

L
Linus Torvalds 已提交
202
	die("Oops", regs, writeaccess);
203
	bust_spinlocks(0);
L
Linus Torvalds 已提交
204 205 206 207 208 209 210 211
	do_exit(SIGKILL);

/*
 * We ran out of memory, or some other thing happened to us that made
 * us unable to handle the page fault gracefully.
 */
out_of_memory:
	up_read(&mm->mmap_sem);
212
	if (is_init(current)) {
L
Linus Torvalds 已提交
213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228
		yield();
		down_read(&mm->mmap_sem);
		goto survive;
	}
	printk("VM: killing process %s\n", tsk->comm);
	if (user_mode(regs))
		do_exit(SIGKILL);
	goto no_context;

do_sigbus:
	up_read(&mm->mmap_sem);

	/*
	 * Send a sigbus, regardless of whether we were in kernel
	 * or user mode.
	 */
229 230 231 232 233
	info.si_signo = SIGBUS;
	info.si_errno = 0;
	info.si_code = BUS_ADRERR;
	info.si_addr = (void *)address;
	force_sig_info(SIGBUS, &info, tsk);
L
Linus Torvalds 已提交
234 235 236 237 238

	/* Kernel mode? Handle exceptions or die */
	if (!user_mode(regs))
		goto no_context;
}
239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263

#ifdef CONFIG_SH_STORE_QUEUES
/*
 * This is a special case for the SH-4 store queues, as pages for this
 * space still need to be faulted in before it's possible to flush the
 * store queue cache for writeout to the remapped region.
 */
#define P3_ADDR_MAX		(P4SEG_STORE_QUE + 0x04000000)
#else
#define P3_ADDR_MAX		P4SEG
#endif

/*
 * Called with interrupts disabled.
 */
asmlinkage int __kprobes __do_page_fault(struct pt_regs *regs,
					 unsigned long writeaccess,
					 unsigned long address)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;
	pte_t entry;
	struct mm_struct *mm = current->mm;
264
	spinlock_t *ptl = NULL;
265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324
	int ret = 1;

#ifdef CONFIG_SH_KGDB
	if (kgdb_nofault && kgdb_bus_err_hook)
		kgdb_bus_err_hook();
#endif

	/*
	 * We don't take page faults for P1, P2, and parts of P4, these
	 * are always mapped, whether it be due to legacy behaviour in
	 * 29-bit mode, or due to PMB configuration in 32-bit mode.
	 */
	if (address >= P3SEG && address < P3_ADDR_MAX) {
		pgd = pgd_offset_k(address);
		mm = NULL;
	} else {
		if (unlikely(address >= TASK_SIZE || !mm))
			return 1;

		pgd = pgd_offset(mm, address);
	}

	pud = pud_offset(pgd, address);
	if (pud_none_or_clear_bad(pud))
		return 1;
	pmd = pmd_offset(pud, address);
	if (pmd_none_or_clear_bad(pmd))
		return 1;

	if (mm)
		pte = pte_offset_map_lock(mm, pmd, address, &ptl);
	else
		pte = pte_offset_kernel(pmd, address);

	entry = *pte;
	if (unlikely(pte_none(entry) || pte_not_present(entry)))
		goto unlock;
	if (unlikely(writeaccess && !pte_write(entry)))
		goto unlock;

	if (writeaccess)
		entry = pte_mkdirty(entry);
	entry = pte_mkyoung(entry);

#ifdef CONFIG_CPU_SH4
	/*
	 * ITLB is not affected by "ldtlb" instruction.
	 * So, we need to flush the entry by ourselves.
	 */
	local_flush_tlb_one(get_asid(), address & PAGE_MASK);
#endif

	set_pte(pte, entry);
	update_mmu_cache(NULL, address, entry);
	ret = 0;
unlock:
	if (mm)
		pte_unmap_unlock(pte, ptl);
	return ret;
}