tlb-radix.c 10.3 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14
/*
 * TLB flush routines for radix kernels.
 *
 * Copyright 2015-2016, Aneesh Kumar K.V, IBM Corporation.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 */

#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/memblock.h>
15
#include <asm/ppc-opcode.h>
16 17 18 19 20 21

#include <asm/tlb.h>
#include <asm/tlbflush.h>

static DEFINE_RAW_SPINLOCK(native_tlbie_lock);

22 23 24 25 26 27
#define RIC_FLUSH_TLB 0
#define RIC_FLUSH_PWC 1
#define RIC_FLUSH_ALL 2

static inline void __tlbiel_pid(unsigned long pid, int set,
				unsigned long ric)
28
{
29
	unsigned long rb,rs,prs,r;
30 31 32 33 34 35 36 37

	rb = PPC_BIT(53); /* IS = 1 */
	rb |= set << PPC_BITLSHIFT(51);
	rs = ((unsigned long)pid) << PPC_BITLSHIFT(31);
	prs = 1; /* process scoped */
	r = 1;   /* raidx format */

	asm volatile("ptesync": : :"memory");
38
	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
39 40 41 42 43 44 45
		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
	asm volatile("ptesync": : :"memory");
}

/*
 * We use 128 set in radix mode and 256 set in hpt mode.
 */
46
static inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
47 48 49 50
{
	int set;

	for (set = 0; set < POWER9_TLB_SETS_RADIX ; set++) {
51
		__tlbiel_pid(pid, set, ric);
52 53 54 55
	}
	return;
}

56
static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
57
{
58
	unsigned long rb,rs,prs,r;
59 60 61 62 63 64 65

	rb = PPC_BIT(53); /* IS = 1 */
	rs = pid << PPC_BITLSHIFT(31);
	prs = 1; /* process scoped */
	r = 1;   /* raidx format */

	asm volatile("ptesync": : :"memory");
66
	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
67 68 69 70 71
		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
	asm volatile("eieio; tlbsync; ptesync": : :"memory");
}

static inline void _tlbiel_va(unsigned long va, unsigned long pid,
72
			      unsigned long ap, unsigned long ric)
73
{
74
	unsigned long rb,rs,prs,r;
75 76 77 78 79 80 81 82

	rb = va & ~(PPC_BITMASK(52, 63));
	rb |= ap << PPC_BITLSHIFT(58);
	rs = pid << PPC_BITLSHIFT(31);
	prs = 1; /* process scoped */
	r = 1;   /* raidx format */

	asm volatile("ptesync": : :"memory");
83
	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
84 85 86 87 88
		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
	asm volatile("ptesync": : :"memory");
}

static inline void _tlbie_va(unsigned long va, unsigned long pid,
89
			     unsigned long ap, unsigned long ric)
90
{
91
	unsigned long rb,rs,prs,r;
92 93 94 95 96 97 98 99

	rb = va & ~(PPC_BITMASK(52, 63));
	rb |= ap << PPC_BITLSHIFT(58);
	rs = pid << PPC_BITLSHIFT(31);
	prs = 1; /* process scoped */
	r = 1;   /* raidx format */

	asm volatile("ptesync": : :"memory");
100
	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117
		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
	asm volatile("eieio; tlbsync; ptesync": : :"memory");
}

/*
 * Base TLB flushing operations:
 *
 *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
 *  - flush_tlb_page(vma, vmaddr) flushes one page
 *  - flush_tlb_range(vma, start, end) flushes a range of pages
 *  - flush_tlb_kernel_range(start, end) flushes kernel pages
 *
 *  - local_* variants of page and mm only apply to the current
 *    processor
 */
void radix__local_flush_tlb_mm(struct mm_struct *mm)
{
118
	unsigned long pid;
119 120 121 122

	preempt_disable();
	pid = mm->context.id;
	if (pid != MMU_NO_CONTEXT)
123
		_tlbiel_pid(pid, RIC_FLUSH_ALL);
124 125 126 127
	preempt_enable();
}
EXPORT_SYMBOL(radix__local_flush_tlb_mm);

128 129 130 131 132 133 134 135 136 137 138 139 140 141 142
void radix__local_flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
{
	unsigned long pid;
	struct mm_struct *mm = tlb->mm;

	preempt_disable();

	pid = mm->context.id;
	if (pid != MMU_NO_CONTEXT)
		_tlbiel_pid(pid, RIC_FLUSH_PWC);

	preempt_enable();
}
EXPORT_SYMBOL(radix__local_flush_tlb_pwc);

143 144
void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
				       unsigned long ap)
145
{
146
	unsigned long pid;
147 148 149 150

	preempt_disable();
	pid = mm ? mm->context.id : 0;
	if (pid != MMU_NO_CONTEXT)
151
		_tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
152 153 154 155 156
	preempt_enable();
}

void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
{
157 158 159 160 161
#ifdef CONFIG_HUGETLB_PAGE
	/* need the return fix for nohash.c */
	if (vma && is_vm_hugetlb_page(vma))
		return __local_flush_hugetlb_page(vma, vmaddr);
#endif
162 163
	radix__local_flush_tlb_page_psize(vma ? vma->vm_mm : NULL, vmaddr,
					  mmu_get_ap(mmu_virtual_psize));
164 165 166 167 168 169
}
EXPORT_SYMBOL(radix__local_flush_tlb_page);

#ifdef CONFIG_SMP
void radix__flush_tlb_mm(struct mm_struct *mm)
{
170
	unsigned long pid;
171 172 173 174 175 176 177 178 179 180 181

	preempt_disable();
	pid = mm->context.id;
	if (unlikely(pid == MMU_NO_CONTEXT))
		goto no_context;

	if (!mm_is_core_local(mm)) {
		int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);

		if (lock_tlbie)
			raw_spin_lock(&native_tlbie_lock);
182
		_tlbie_pid(pid, RIC_FLUSH_ALL);
183 184 185
		if (lock_tlbie)
			raw_spin_unlock(&native_tlbie_lock);
	} else
186
		_tlbiel_pid(pid, RIC_FLUSH_ALL);
187 188 189 190 191
no_context:
	preempt_enable();
}
EXPORT_SYMBOL(radix__flush_tlb_mm);

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
void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
{
	unsigned long pid;
	struct mm_struct *mm = tlb->mm;

	preempt_disable();

	pid = mm->context.id;
	if (unlikely(pid == MMU_NO_CONTEXT))
		goto no_context;

	if (!mm_is_core_local(mm)) {
		int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);

		if (lock_tlbie)
			raw_spin_lock(&native_tlbie_lock);
		_tlbie_pid(pid, RIC_FLUSH_PWC);
		if (lock_tlbie)
			raw_spin_unlock(&native_tlbie_lock);
	} else
		_tlbiel_pid(pid, RIC_FLUSH_PWC);
no_context:
	preempt_enable();
}
EXPORT_SYMBOL(radix__flush_tlb_pwc);

218 219
void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
				 unsigned long ap)
220
{
221
	unsigned long pid;
222 223 224 225 226 227 228 229 230 231

	preempt_disable();
	pid = mm ? mm->context.id : 0;
	if (unlikely(pid == MMU_NO_CONTEXT))
		goto bail;
	if (!mm_is_core_local(mm)) {
		int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);

		if (lock_tlbie)
			raw_spin_lock(&native_tlbie_lock);
232
		_tlbie_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
233 234 235
		if (lock_tlbie)
			raw_spin_unlock(&native_tlbie_lock);
	} else
236
		_tlbiel_va(vmaddr, pid, ap, RIC_FLUSH_TLB);
237 238 239 240 241 242
bail:
	preempt_enable();
}

void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
{
243 244 245 246
#ifdef CONFIG_HUGETLB_PAGE
	if (vma && is_vm_hugetlb_page(vma))
		return flush_hugetlb_page(vma, vmaddr);
#endif
247 248
	radix__flush_tlb_page_psize(vma ? vma->vm_mm : NULL, vmaddr,
				    mmu_get_ap(mmu_virtual_psize));
249 250 251 252 253 254 255 256 257 258 259
}
EXPORT_SYMBOL(radix__flush_tlb_page);

#endif /* CONFIG_SMP */

void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);

	if (lock_tlbie)
		raw_spin_lock(&native_tlbie_lock);
260
	_tlbie_pid(0, RIC_FLUSH_ALL);
261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278
	if (lock_tlbie)
		raw_spin_unlock(&native_tlbie_lock);
}
EXPORT_SYMBOL(radix__flush_tlb_kernel_range);

/*
 * Currently, for range flushing, we just do a full mm flush. Because
 * we use this in code path where we don' track the page size.
 */
void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
		     unsigned long end)

{
	struct mm_struct *mm = vma->vm_mm;
	radix__flush_tlb_mm(mm);
}
EXPORT_SYMBOL(radix__flush_tlb_range);

279 280 281 282 283 284 285 286 287 288 289 290 291 292
static int radix_get_mmu_psize(int page_size)
{
	int psize;

	if (page_size == (1UL << mmu_psize_defs[mmu_virtual_psize].shift))
		psize = mmu_virtual_psize;
	else if (page_size == (1UL << mmu_psize_defs[MMU_PAGE_2M].shift))
		psize = MMU_PAGE_2M;
	else if (page_size == (1UL << mmu_psize_defs[MMU_PAGE_1G].shift))
		psize = MMU_PAGE_1G;
	else
		return -1;
	return psize;
}
293 294 295

void radix__tlb_flush(struct mmu_gather *tlb)
{
296
	int psize = 0;
297
	struct mm_struct *mm = tlb->mm;
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
	int page_size = tlb->page_size;

	psize = radix_get_mmu_psize(page_size);
	/*
	 * if page size is not something we understand, do a full mm flush
	 */
	if (psize != -1 && !tlb->fullmm && !tlb->need_flush_all)
		radix__flush_tlb_range_psize(mm, tlb->start, tlb->end, psize);
	else
		radix__flush_tlb_mm(mm);
}

#define TLB_FLUSH_ALL -1UL
/*
 * Number of pages above which we will do a bcast tlbie. Just a
 * number at this point copied from x86
 */
static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;

void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
				  unsigned long end, int psize)
{
	unsigned long pid;
	unsigned long addr;
	int local = mm_is_core_local(mm);
	unsigned long ap = mmu_get_ap(psize);
	int lock_tlbie = !mmu_has_feature(MMU_FTR_LOCKLESS_TLBIE);
	unsigned long page_size = 1UL << mmu_psize_defs[psize].shift;


	preempt_disable();
	pid = mm ? mm->context.id : 0;
	if (unlikely(pid == MMU_NO_CONTEXT))
		goto err_out;

	if (end == TLB_FLUSH_ALL ||
	    (end - start) > tlb_single_page_flush_ceiling * page_size) {
		if (local)
			_tlbiel_pid(pid, RIC_FLUSH_TLB);
		else
			_tlbie_pid(pid, RIC_FLUSH_TLB);
		goto err_out;
	}
	for (addr = start; addr < end; addr += page_size) {

		if (local)
			_tlbiel_va(addr, pid, ap, RIC_FLUSH_TLB);
		else {
			if (lock_tlbie)
				raw_spin_lock(&native_tlbie_lock);
			_tlbie_va(addr, pid, ap, RIC_FLUSH_TLB);
			if (lock_tlbie)
				raw_spin_unlock(&native_tlbie_lock);
		}
	}
err_out:
	preempt_enable();
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

void radix__flush_tlb_lpid_va(unsigned long lpid, unsigned long gpa,
			      unsigned long page_size)
{
	unsigned long rb,rs,prs,r;
	unsigned long ap;
	unsigned long ric = RIC_FLUSH_TLB;

	ap = mmu_get_ap(radix_get_mmu_psize(page_size));
	rb = gpa & ~(PPC_BITMASK(52, 63));
	rb |= ap << PPC_BITLSHIFT(58);
	rs = lpid & ((1UL << 32) - 1);
	prs = 0; /* process scoped */
	r = 1;   /* raidx format */

	asm volatile("ptesync": : :"memory");
	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
	asm volatile("eieio; tlbsync; ptesync": : :"memory");
}
EXPORT_SYMBOL(radix__flush_tlb_lpid_va);

void radix__flush_tlb_lpid(unsigned long lpid)
{
	unsigned long rb,rs,prs,r;
	unsigned long ric = RIC_FLUSH_ALL;

	rb = 0x2 << PPC_BITLSHIFT(53); /* IS = 2 */
	rs = lpid & ((1UL << 32) - 1);
	prs = 0; /* partition scoped */
	r = 1;   /* raidx format */

	asm volatile("ptesync": : :"memory");
	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
	asm volatile("eieio; tlbsync; ptesync": : :"memory");
}
EXPORT_SYMBOL(radix__flush_tlb_lpid);
394 395 396 397 398 399 400

void radix__flush_pmd_tlb_range(struct vm_area_struct *vma,
				unsigned long start, unsigned long end)
{
	radix__flush_tlb_range_psize(vma->vm_mm, start, end, MMU_PAGE_2M);
}
EXPORT_SYMBOL(radix__flush_pmd_tlb_range);