vmem.c 10.1 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 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 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441
// SPDX-License-Identifier: GPL-2.0
/*
 *    Copyright IBM Corp. 2006
 *    Author(s): Heiko Carstens <heiko.carstens@de.ibm.com>
 */

#include <linux/bootmem.h>
#include <linux/pfn.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/hugetlb.h>
#include <linux/slab.h>
#include <linux/memblock.h>
#include <asm/cacheflush.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
#include <asm/setup.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <asm/set_memory.h>

static DEFINE_MUTEX(vmem_mutex);

struct memory_segment {
	struct list_head list;
	unsigned long start;
	unsigned long size;
};

static LIST_HEAD(mem_segs);

static void __ref *vmem_alloc_pages(unsigned int order)
{
	unsigned long size = PAGE_SIZE << order;

	if (slab_is_available())
		return (void *)__get_free_pages(GFP_KERNEL, order);
	return (void *) memblock_alloc(size, size);
}

void *vmem_crst_alloc(unsigned long val)
{
	unsigned long *table;

	table = vmem_alloc_pages(CRST_ALLOC_ORDER);
	if (table)
		crst_table_init(table, val);
	return table;
}

pte_t __ref *vmem_pte_alloc(void)
{
	unsigned long size = PTRS_PER_PTE * sizeof(pte_t);
	pte_t *pte;

	if (slab_is_available())
		pte = (pte_t *) page_table_alloc(&init_mm);
	else
		pte = (pte_t *) memblock_alloc(size, size);
	if (!pte)
		return NULL;
	clear_table((unsigned long *) pte, _PAGE_INVALID, size);
	return pte;
}

/*
 * Add a physical memory range to the 1:1 mapping.
 */
static int vmem_add_mem(unsigned long start, unsigned long size)
{
	unsigned long pgt_prot, sgt_prot, r3_prot;
	unsigned long pages4k, pages1m, pages2g;
	unsigned long end = start + size;
	unsigned long address = start;
	pgd_t *pg_dir;
	p4d_t *p4_dir;
	pud_t *pu_dir;
	pmd_t *pm_dir;
	pte_t *pt_dir;
	int ret = -ENOMEM;

	pgt_prot = pgprot_val(PAGE_KERNEL);
	sgt_prot = pgprot_val(SEGMENT_KERNEL);
	r3_prot = pgprot_val(REGION3_KERNEL);
	if (!MACHINE_HAS_NX) {
		pgt_prot &= ~_PAGE_NOEXEC;
		sgt_prot &= ~_SEGMENT_ENTRY_NOEXEC;
		r3_prot &= ~_REGION_ENTRY_NOEXEC;
	}
	pages4k = pages1m = pages2g = 0;
	while (address < end) {
		pg_dir = pgd_offset_k(address);
		if (pgd_none(*pg_dir)) {
			p4_dir = vmem_crst_alloc(_REGION2_ENTRY_EMPTY);
			if (!p4_dir)
				goto out;
			pgd_populate(&init_mm, pg_dir, p4_dir);
		}
		p4_dir = p4d_offset(pg_dir, address);
		if (p4d_none(*p4_dir)) {
			pu_dir = vmem_crst_alloc(_REGION3_ENTRY_EMPTY);
			if (!pu_dir)
				goto out;
			p4d_populate(&init_mm, p4_dir, pu_dir);
		}
		pu_dir = pud_offset(p4_dir, address);
		if (MACHINE_HAS_EDAT2 && pud_none(*pu_dir) && address &&
		    !(address & ~PUD_MASK) && (address + PUD_SIZE <= end) &&
		     !debug_pagealloc_enabled()) {
			pud_val(*pu_dir) = address | r3_prot;
			address += PUD_SIZE;
			pages2g++;
			continue;
		}
		if (pud_none(*pu_dir)) {
			pm_dir = vmem_crst_alloc(_SEGMENT_ENTRY_EMPTY);
			if (!pm_dir)
				goto out;
			pud_populate(&init_mm, pu_dir, pm_dir);
		}
		pm_dir = pmd_offset(pu_dir, address);
		if (MACHINE_HAS_EDAT1 && pmd_none(*pm_dir) && address &&
		    !(address & ~PMD_MASK) && (address + PMD_SIZE <= end) &&
		    !debug_pagealloc_enabled()) {
			pmd_val(*pm_dir) = address | sgt_prot;
			address += PMD_SIZE;
			pages1m++;
			continue;
		}
		if (pmd_none(*pm_dir)) {
			pt_dir = vmem_pte_alloc();
			if (!pt_dir)
				goto out;
			pmd_populate(&init_mm, pm_dir, pt_dir);
		}

		pt_dir = pte_offset_kernel(pm_dir, address);
		pte_val(*pt_dir) = address | pgt_prot;
		address += PAGE_SIZE;
		pages4k++;
	}
	ret = 0;
out:
	update_page_count(PG_DIRECT_MAP_4K, pages4k);
	update_page_count(PG_DIRECT_MAP_1M, pages1m);
	update_page_count(PG_DIRECT_MAP_2G, pages2g);
	return ret;
}

/*
 * Remove a physical memory range from the 1:1 mapping.
 * Currently only invalidates page table entries.
 */
static void vmem_remove_range(unsigned long start, unsigned long size)
{
	unsigned long pages4k, pages1m, pages2g;
	unsigned long end = start + size;
	unsigned long address = start;
	pgd_t *pg_dir;
	p4d_t *p4_dir;
	pud_t *pu_dir;
	pmd_t *pm_dir;
	pte_t *pt_dir;

	pages4k = pages1m = pages2g = 0;
	while (address < end) {
		pg_dir = pgd_offset_k(address);
		if (pgd_none(*pg_dir)) {
			address += PGDIR_SIZE;
			continue;
		}
		p4_dir = p4d_offset(pg_dir, address);
		if (p4d_none(*p4_dir)) {
			address += P4D_SIZE;
			continue;
		}
		pu_dir = pud_offset(p4_dir, address);
		if (pud_none(*pu_dir)) {
			address += PUD_SIZE;
			continue;
		}
		if (pud_large(*pu_dir)) {
			pud_clear(pu_dir);
			address += PUD_SIZE;
			pages2g++;
			continue;
		}
		pm_dir = pmd_offset(pu_dir, address);
		if (pmd_none(*pm_dir)) {
			address += PMD_SIZE;
			continue;
		}
		if (pmd_large(*pm_dir)) {
			pmd_clear(pm_dir);
			address += PMD_SIZE;
			pages1m++;
			continue;
		}
		pt_dir = pte_offset_kernel(pm_dir, address);
		pte_clear(&init_mm, address, pt_dir);
		address += PAGE_SIZE;
		pages4k++;
	}
	flush_tlb_kernel_range(start, end);
	update_page_count(PG_DIRECT_MAP_4K, -pages4k);
	update_page_count(PG_DIRECT_MAP_1M, -pages1m);
	update_page_count(PG_DIRECT_MAP_2G, -pages2g);
}

/*
 * Add a backed mem_map array to the virtual mem_map array.
 */
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
{
	unsigned long pgt_prot, sgt_prot;
	unsigned long address = start;
	pgd_t *pg_dir;
	p4d_t *p4_dir;
	pud_t *pu_dir;
	pmd_t *pm_dir;
	pte_t *pt_dir;
	int ret = -ENOMEM;

	pgt_prot = pgprot_val(PAGE_KERNEL);
	sgt_prot = pgprot_val(SEGMENT_KERNEL);
	if (!MACHINE_HAS_NX) {
		pgt_prot &= ~_PAGE_NOEXEC;
		sgt_prot &= ~_SEGMENT_ENTRY_NOEXEC;
	}
	for (address = start; address < end;) {
		pg_dir = pgd_offset_k(address);
		if (pgd_none(*pg_dir)) {
			p4_dir = vmem_crst_alloc(_REGION2_ENTRY_EMPTY);
			if (!p4_dir)
				goto out;
			pgd_populate(&init_mm, pg_dir, p4_dir);
		}

		p4_dir = p4d_offset(pg_dir, address);
		if (p4d_none(*p4_dir)) {
			pu_dir = vmem_crst_alloc(_REGION3_ENTRY_EMPTY);
			if (!pu_dir)
				goto out;
			p4d_populate(&init_mm, p4_dir, pu_dir);
		}

		pu_dir = pud_offset(p4_dir, address);
		if (pud_none(*pu_dir)) {
			pm_dir = vmem_crst_alloc(_SEGMENT_ENTRY_EMPTY);
			if (!pm_dir)
				goto out;
			pud_populate(&init_mm, pu_dir, pm_dir);
		}

		pm_dir = pmd_offset(pu_dir, address);
		if (pmd_none(*pm_dir)) {
			/* Use 1MB frames for vmemmap if available. We always
			 * use large frames even if they are only partially
			 * used.
			 * Otherwise we would have also page tables since
			 * vmemmap_populate gets called for each section
			 * separately. */
			if (MACHINE_HAS_EDAT1) {
				void *new_page;

				new_page = vmemmap_alloc_block(PMD_SIZE, node);
				if (!new_page)
					goto out;
				pmd_val(*pm_dir) = __pa(new_page) | sgt_prot;
				address = (address + PMD_SIZE) & PMD_MASK;
				continue;
			}
			pt_dir = vmem_pte_alloc();
			if (!pt_dir)
				goto out;
			pmd_populate(&init_mm, pm_dir, pt_dir);
		} else if (pmd_large(*pm_dir)) {
			address = (address + PMD_SIZE) & PMD_MASK;
			continue;
		}

		pt_dir = pte_offset_kernel(pm_dir, address);
		if (pte_none(*pt_dir)) {
			void *new_page;

			new_page = vmemmap_alloc_block(PAGE_SIZE, node);
			if (!new_page)
				goto out;
			pte_val(*pt_dir) = __pa(new_page) | pgt_prot;
		}
		address += PAGE_SIZE;
	}
	ret = 0;
out:
	return ret;
}

void vmemmap_free(unsigned long start, unsigned long end)
{
}

/*
 * Add memory segment to the segment list if it doesn't overlap with
 * an already present segment.
 */
static int insert_memory_segment(struct memory_segment *seg)
{
	struct memory_segment *tmp;

	if (seg->start + seg->size > VMEM_MAX_PHYS ||
	    seg->start + seg->size < seg->start)
		return -ERANGE;

	list_for_each_entry(tmp, &mem_segs, list) {
		if (seg->start >= tmp->start + tmp->size)
			continue;
		if (seg->start + seg->size <= tmp->start)
			continue;
		return -ENOSPC;
	}
	list_add(&seg->list, &mem_segs);
	return 0;
}

/*
 * Remove memory segment from the segment list.
 */
static void remove_memory_segment(struct memory_segment *seg)
{
	list_del(&seg->list);
}

static void __remove_shared_memory(struct memory_segment *seg)
{
	remove_memory_segment(seg);
	vmem_remove_range(seg->start, seg->size);
}

int vmem_remove_mapping(unsigned long start, unsigned long size)
{
	struct memory_segment *seg;
	int ret;

	mutex_lock(&vmem_mutex);

	ret = -ENOENT;
	list_for_each_entry(seg, &mem_segs, list) {
		if (seg->start == start && seg->size == size)
			break;
	}

	if (seg->start != start || seg->size != size)
		goto out;

	ret = 0;
	__remove_shared_memory(seg);
	kfree(seg);
out:
	mutex_unlock(&vmem_mutex);
	return ret;
}

int vmem_add_mapping(unsigned long start, unsigned long size)
{
	struct memory_segment *seg;
	int ret;

	mutex_lock(&vmem_mutex);
	ret = -ENOMEM;
	seg = kzalloc(sizeof(*seg), GFP_KERNEL);
	if (!seg)
		goto out;
	seg->start = start;
	seg->size = size;

	ret = insert_memory_segment(seg);
	if (ret)
		goto out_free;

	ret = vmem_add_mem(start, size);
	if (ret)
		goto out_remove;
	goto out;

out_remove:
	__remove_shared_memory(seg);
out_free:
	kfree(seg);
out:
	mutex_unlock(&vmem_mutex);
	return ret;
}

/*
 * map whole physical memory to virtual memory (identity mapping)
 * we reserve enough space in the vmalloc area for vmemmap to hotplug
 * additional memory segments.
 */
void __init vmem_map_init(void)
{
	struct memblock_region *reg;

	for_each_memblock(memory, reg)
		vmem_add_mem(reg->base, reg->size);
	__set_memory((unsigned long) _stext,
		     (_etext - _stext) >> PAGE_SHIFT,
		     SET_MEMORY_RO | SET_MEMORY_X);
	__set_memory((unsigned long) _etext,
		     (_eshared - _etext) >> PAGE_SHIFT,
		     SET_MEMORY_RO);
	__set_memory((unsigned long) _sinittext,
		     (_einittext - _sinittext) >> PAGE_SHIFT,
		     SET_MEMORY_RO | SET_MEMORY_X);
	pr_info("Write protected kernel read-only data: %luk\n",
		(_eshared - _stext) >> 10);
}

/*
 * Convert memblock.memory  to a memory segment list so there is a single
 * list that contains all memory segments.
 */
static int __init vmem_convert_memory_chunk(void)
{
	struct memblock_region *reg;
	struct memory_segment *seg;

	mutex_lock(&vmem_mutex);
	for_each_memblock(memory, reg) {
		seg = kzalloc(sizeof(*seg), GFP_KERNEL);
		if (!seg)
			panic("Out of memory...\n");
		seg->start = reg->base;
		seg->size = reg->size;
		insert_memory_segment(seg);
	}
	mutex_unlock(&vmem_mutex);
	return 0;
}

core_initcall(vmem_convert_memory_chunk);