1/* SPDX-License-Identifier: GPL-2.0-or-later */
2#ifndef _ASM_POWERPC_BOOK3S_64_MMU_HASH_H_
3#define _ASM_POWERPC_BOOK3S_64_MMU_HASH_H_
4/*
5 * PowerPC64 memory management structures
6 *
7 * Dave Engebretsen & Mike Corrigan <{engebret|mikejc}@us.ibm.com>
8 *   PPC64 rework.
9 */
10
11#include <asm/page.h>
12#include <asm/bug.h>
13#include <asm/asm-const.h>
14
15/*
16 * This is necessary to get the definition of PGTABLE_RANGE which we
17 * need for various slices related matters. Note that this isn't the
18 * complete pgtable.h but only a portion of it.
19 */
20#include <asm/book3s/64/pgtable.h>
21#include <asm/bug.h>
22#include <asm/task_size_64.h>
23#include <asm/cpu_has_feature.h>
24
25/*
26 * SLB
27 */
28
29#define SLB_NUM_BOLTED		2
30#define SLB_CACHE_ENTRIES	8
31#define SLB_MIN_SIZE		32
32
33/* Bits in the SLB ESID word */
34#define SLB_ESID_V		ASM_CONST(0x0000000008000000) /* valid */
35
36/* Bits in the SLB VSID word */
37#define SLB_VSID_SHIFT		12
38#define SLB_VSID_SHIFT_256M	SLB_VSID_SHIFT
39#define SLB_VSID_SHIFT_1T	24
40#define SLB_VSID_SSIZE_SHIFT	62
41#define SLB_VSID_B		ASM_CONST(0xc000000000000000)
42#define SLB_VSID_B_256M		ASM_CONST(0x0000000000000000)
43#define SLB_VSID_B_1T		ASM_CONST(0x4000000000000000)
44#define SLB_VSID_KS		ASM_CONST(0x0000000000000800)
45#define SLB_VSID_KP		ASM_CONST(0x0000000000000400)
46#define SLB_VSID_N		ASM_CONST(0x0000000000000200) /* no-execute */
47#define SLB_VSID_L		ASM_CONST(0x0000000000000100)
48#define SLB_VSID_C		ASM_CONST(0x0000000000000080) /* class */
49#define SLB_VSID_LP		ASM_CONST(0x0000000000000030)
50#define SLB_VSID_LP_00		ASM_CONST(0x0000000000000000)
51#define SLB_VSID_LP_01		ASM_CONST(0x0000000000000010)
52#define SLB_VSID_LP_10		ASM_CONST(0x0000000000000020)
53#define SLB_VSID_LP_11		ASM_CONST(0x0000000000000030)
54#define SLB_VSID_LLP		(SLB_VSID_L|SLB_VSID_LP)
55
56#define SLB_VSID_KERNEL		(SLB_VSID_KP)
57#define SLB_VSID_USER		(SLB_VSID_KP|SLB_VSID_KS|SLB_VSID_C)
58
59#define SLBIE_C			(0x08000000)
60#define SLBIE_SSIZE_SHIFT	25
61
62/*
63 * Hash table
64 */
65
66#define HPTES_PER_GROUP 8
67
68#define HPTE_V_SSIZE_SHIFT	62
69#define HPTE_V_AVPN_SHIFT	7
70#define HPTE_V_COMMON_BITS	ASM_CONST(0x000fffffffffffff)
71#define HPTE_V_AVPN		ASM_CONST(0x3fffffffffffff80)
72#define HPTE_V_AVPN_3_0		ASM_CONST(0x000fffffffffff80)
73#define HPTE_V_AVPN_VAL(x)	(((x) & HPTE_V_AVPN) >> HPTE_V_AVPN_SHIFT)
74#define HPTE_V_COMPARE(x,y)	(!(((x) ^ (y)) & 0xffffffffffffff80UL))
75#define HPTE_V_BOLTED		ASM_CONST(0x0000000000000010)
76#define HPTE_V_LOCK		ASM_CONST(0x0000000000000008)
77#define HPTE_V_LARGE		ASM_CONST(0x0000000000000004)
78#define HPTE_V_SECONDARY	ASM_CONST(0x0000000000000002)
79#define HPTE_V_VALID		ASM_CONST(0x0000000000000001)
80
81/*
82 * ISA 3.0 has a different HPTE format.
83 */
84#define HPTE_R_3_0_SSIZE_SHIFT	58
85#define HPTE_R_3_0_SSIZE_MASK	(3ull << HPTE_R_3_0_SSIZE_SHIFT)
86#define HPTE_R_PP0		ASM_CONST(0x8000000000000000)
87#define HPTE_R_TS		ASM_CONST(0x4000000000000000)
88#define HPTE_R_KEY_HI		ASM_CONST(0x3000000000000000)
89#define HPTE_R_KEY_BIT4		ASM_CONST(0x2000000000000000)
90#define HPTE_R_KEY_BIT3		ASM_CONST(0x1000000000000000)
91#define HPTE_R_RPN_SHIFT	12
92#define HPTE_R_RPN		ASM_CONST(0x0ffffffffffff000)
93#define HPTE_R_RPN_3_0		ASM_CONST(0x01fffffffffff000)
94#define HPTE_R_PP		ASM_CONST(0x0000000000000003)
95#define HPTE_R_PPP		ASM_CONST(0x8000000000000003)
96#define HPTE_R_N		ASM_CONST(0x0000000000000004)
97#define HPTE_R_G		ASM_CONST(0x0000000000000008)
98#define HPTE_R_M		ASM_CONST(0x0000000000000010)
99#define HPTE_R_I		ASM_CONST(0x0000000000000020)
100#define HPTE_R_W		ASM_CONST(0x0000000000000040)
101#define HPTE_R_WIMG		ASM_CONST(0x0000000000000078)
102#define HPTE_R_C		ASM_CONST(0x0000000000000080)
103#define HPTE_R_R		ASM_CONST(0x0000000000000100)
104#define HPTE_R_KEY_LO		ASM_CONST(0x0000000000000e00)
105#define HPTE_R_KEY_BIT2		ASM_CONST(0x0000000000000800)
106#define HPTE_R_KEY_BIT1		ASM_CONST(0x0000000000000400)
107#define HPTE_R_KEY_BIT0		ASM_CONST(0x0000000000000200)
108#define HPTE_R_KEY		(HPTE_R_KEY_LO | HPTE_R_KEY_HI)
109
110#define HPTE_V_1TB_SEG		ASM_CONST(0x4000000000000000)
111#define HPTE_V_VRMA_MASK	ASM_CONST(0x4001ffffff000000)
112
113/* Values for PP (assumes Ks=0, Kp=1) */
114#define PP_RWXX	0	/* Supervisor read/write, User none */
115#define PP_RWRX 1	/* Supervisor read/write, User read */
116#define PP_RWRW 2	/* Supervisor read/write, User read/write */
117#define PP_RXRX 3	/* Supervisor read,       User read */
118#define PP_RXXX	(HPTE_R_PP0 | 2)	/* Supervisor read, user none */
119
120/* Fields for tlbiel instruction in architecture 2.06 */
121#define TLBIEL_INVAL_SEL_MASK	0xc00	/* invalidation selector */
122#define  TLBIEL_INVAL_PAGE	0x000	/* invalidate a single page */
123#define  TLBIEL_INVAL_SET_LPID	0x800	/* invalidate a set for current LPID */
124#define  TLBIEL_INVAL_SET	0xc00	/* invalidate a set for all LPIDs */
125#define TLBIEL_INVAL_SET_MASK	0xfff000	/* set number to inval. */
126#define TLBIEL_INVAL_SET_SHIFT	12
127
128#define POWER7_TLB_SETS		128	/* # sets in POWER7 TLB */
129#define POWER8_TLB_SETS		512	/* # sets in POWER8 TLB */
130#define POWER9_TLB_SETS_HASH	256	/* # sets in POWER9 TLB Hash mode */
131#define POWER9_TLB_SETS_RADIX	128	/* # sets in POWER9 TLB Radix mode */
132
133#ifndef __ASSEMBLY__
134
135struct mmu_hash_ops {
136	void            (*hpte_invalidate)(unsigned long slot,
137					   unsigned long vpn,
138					   int bpsize, int apsize,
139					   int ssize, int local);
140	long		(*hpte_updatepp)(unsigned long slot,
141					 unsigned long newpp,
142					 unsigned long vpn,
143					 int bpsize, int apsize,
144					 int ssize, unsigned long flags);
145	void            (*hpte_updateboltedpp)(unsigned long newpp,
146					       unsigned long ea,
147					       int psize, int ssize);
148	long		(*hpte_insert)(unsigned long hpte_group,
149				       unsigned long vpn,
150				       unsigned long prpn,
151				       unsigned long rflags,
152				       unsigned long vflags,
153				       int psize, int apsize,
154				       int ssize);
155	long		(*hpte_remove)(unsigned long hpte_group);
156	int             (*hpte_removebolted)(unsigned long ea,
157					     int psize, int ssize);
158	void		(*flush_hash_range)(unsigned long number, int local);
159	void		(*hugepage_invalidate)(unsigned long vsid,
160					       unsigned long addr,
161					       unsigned char *hpte_slot_array,
162					       int psize, int ssize, int local);
163	int		(*resize_hpt)(unsigned long shift);
164	/*
165	 * Special for kexec.
166	 * To be called in real mode with interrupts disabled. No locks are
167	 * taken as such, concurrent access on pre POWER5 hardware could result
168	 * in a deadlock.
169	 * The linear mapping is destroyed as well.
170	 */
171	void		(*hpte_clear_all)(void);
172};
173extern struct mmu_hash_ops mmu_hash_ops;
174
175struct hash_pte {
176	__be64 v;
177	__be64 r;
178};
179
180extern struct hash_pte *htab_address;
181extern unsigned long htab_size_bytes;
182extern unsigned long htab_hash_mask;
183
184
185static inline int shift_to_mmu_psize(unsigned int shift)
186{
187	int psize;
188
189	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize)
190		if (mmu_psize_defs[psize].shift == shift)
191			return psize;
192	return -1;
193}
194
195static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
196{
197	if (mmu_psize_defs[mmu_psize].shift)
198		return mmu_psize_defs[mmu_psize].shift;
199	BUG();
200}
201
202static inline unsigned int ap_to_shift(unsigned long ap)
203{
204	int psize;
205
206	for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
207		if (mmu_psize_defs[psize].ap == ap)
208			return mmu_psize_defs[psize].shift;
209	}
210
211	return -1;
212}
213
214static inline unsigned long get_sllp_encoding(int psize)
215{
216	unsigned long sllp;
217
218	sllp = ((mmu_psize_defs[psize].sllp & SLB_VSID_L) >> 6) |
219		((mmu_psize_defs[psize].sllp & SLB_VSID_LP) >> 4);
220	return sllp;
221}
222
223#endif /* __ASSEMBLY__ */
224
225/*
226 * Segment sizes.
227 * These are the values used by hardware in the B field of
228 * SLB entries and the first dword of MMU hashtable entries.
229 * The B field is 2 bits; the values 2 and 3 are unused and reserved.
230 */
231#define MMU_SEGSIZE_256M	0
232#define MMU_SEGSIZE_1T		1
233
234/*
235 * encode page number shift.
236 * in order to fit the 78 bit va in a 64 bit variable we shift the va by
237 * 12 bits. This enable us to address upto 76 bit va.
238 * For hpt hash from a va we can ignore the page size bits of va and for
239 * hpte encoding we ignore up to 23 bits of va. So ignoring lower 12 bits ensure
240 * we work in all cases including 4k page size.
241 */
242#define VPN_SHIFT	12
243
244/*
245 * HPTE Large Page (LP) details
246 */
247#define LP_SHIFT	12
248#define LP_BITS		8
249#define LP_MASK(i)	((0xFF >> (i)) << LP_SHIFT)
250
251#ifndef __ASSEMBLY__
252
253static inline int slb_vsid_shift(int ssize)
254{
255	if (ssize == MMU_SEGSIZE_256M)
256		return SLB_VSID_SHIFT;
257	return SLB_VSID_SHIFT_1T;
258}
259
260static inline int segment_shift(int ssize)
261{
262	if (ssize == MMU_SEGSIZE_256M)
263		return SID_SHIFT;
264	return SID_SHIFT_1T;
265}
266
267/*
268 * This array is indexed by the LP field of the HPTE second dword.
269 * Since this field may contain some RPN bits, some entries are
270 * replicated so that we get the same value irrespective of RPN.
271 * The top 4 bits are the page size index (MMU_PAGE_*) for the
272 * actual page size, the bottom 4 bits are the base page size.
273 */
274extern u8 hpte_page_sizes[1 << LP_BITS];
275
276static inline unsigned long __hpte_page_size(unsigned long h, unsigned long l,
277					     bool is_base_size)
278{
279	unsigned int i, lp;
280
281	if (!(h & HPTE_V_LARGE))
282		return 1ul << 12;
283
284	/* Look at the 8 bit LP value */
285	lp = (l >> LP_SHIFT) & ((1 << LP_BITS) - 1);
286	i = hpte_page_sizes[lp];
287	if (!i)
288		return 0;
289	if (!is_base_size)
290		i >>= 4;
291	return 1ul << mmu_psize_defs[i & 0xf].shift;
292}
293
294static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
295{
296	return __hpte_page_size(h, l, 0);
297}
298
299static inline unsigned long hpte_base_page_size(unsigned long h, unsigned long l)
300{
301	return __hpte_page_size(h, l, 1);
302}
303
304/*
305 * The current system page and segment sizes
306 */
307extern int mmu_kernel_ssize;
308extern int mmu_highuser_ssize;
309extern u16 mmu_slb_size;
310extern unsigned long tce_alloc_start, tce_alloc_end;
311
312/*
313 * If the processor supports 64k normal pages but not 64k cache
314 * inhibited pages, we have to be prepared to switch processes
315 * to use 4k pages when they create cache-inhibited mappings.
316 * If this is the case, mmu_ci_restrictions will be set to 1.
317 */
318extern int mmu_ci_restrictions;
319
320/*
321 * This computes the AVPN and B fields of the first dword of a HPTE,
322 * for use when we want to match an existing PTE.  The bottom 7 bits
323 * of the returned value are zero.
324 */
325static inline unsigned long hpte_encode_avpn(unsigned long vpn, int psize,
326					     int ssize)
327{
328	unsigned long v;
329	/*
330	 * The AVA field omits the low-order 23 bits of the 78 bits VA.
331	 * These bits are not needed in the PTE, because the
332	 * low-order b of these bits are part of the byte offset
333	 * into the virtual page and, if b < 23, the high-order
334	 * 23-b of these bits are always used in selecting the
335	 * PTEGs to be searched
336	 */
337	v = (vpn >> (23 - VPN_SHIFT)) & ~(mmu_psize_defs[psize].avpnm);
338	v <<= HPTE_V_AVPN_SHIFT;
339	v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT;
340	return v;
341}
342
343/*
344 * ISA v3.0 defines a new HPTE format, which differs from the old
345 * format in having smaller AVPN and ARPN fields, and the B field
346 * in the second dword instead of the first.
347 */
348static inline unsigned long hpte_old_to_new_v(unsigned long v)
349{
350	/* trim AVPN, drop B */
351	return v & HPTE_V_COMMON_BITS;
352}
353
354static inline unsigned long hpte_old_to_new_r(unsigned long v, unsigned long r)
355{
356	/* move B field from 1st to 2nd dword, trim ARPN */
357	return (r & ~HPTE_R_3_0_SSIZE_MASK) |
358		(((v) >> HPTE_V_SSIZE_SHIFT) << HPTE_R_3_0_SSIZE_SHIFT);
359}
360
361static inline unsigned long hpte_new_to_old_v(unsigned long v, unsigned long r)
362{
363	/* insert B field */
364	return (v & HPTE_V_COMMON_BITS) |
365		((r & HPTE_R_3_0_SSIZE_MASK) <<
366		 (HPTE_V_SSIZE_SHIFT - HPTE_R_3_0_SSIZE_SHIFT));
367}
368
369static inline unsigned long hpte_new_to_old_r(unsigned long r)
370{
371	/* clear out B field */
372	return r & ~HPTE_R_3_0_SSIZE_MASK;
373}
374
375static inline unsigned long hpte_get_old_v(struct hash_pte *hptep)
376{
377	unsigned long hpte_v;
378
379	hpte_v = be64_to_cpu(hptep->v);
380	if (cpu_has_feature(CPU_FTR_ARCH_300))
381		hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r));
382	return hpte_v;
383}
384
385/*
386 * This function sets the AVPN and L fields of the HPTE  appropriately
387 * using the base page size and actual page size.
388 */
389static inline unsigned long hpte_encode_v(unsigned long vpn, int base_psize,
390					  int actual_psize, int ssize)
391{
392	unsigned long v;
393	v = hpte_encode_avpn(vpn, base_psize, ssize);
394	if (actual_psize != MMU_PAGE_4K)
395		v |= HPTE_V_LARGE;
396	return v;
397}
398
399/*
400 * This function sets the ARPN, and LP fields of the HPTE appropriately
401 * for the page size. We assume the pa is already "clean" that is properly
402 * aligned for the requested page size
403 */
404static inline unsigned long hpte_encode_r(unsigned long pa, int base_psize,
405					  int actual_psize)
406{
407	/* A 4K page needs no special encoding */
408	if (actual_psize == MMU_PAGE_4K)
409		return pa & HPTE_R_RPN;
410	else {
411		unsigned int penc = mmu_psize_defs[base_psize].penc[actual_psize];
412		unsigned int shift = mmu_psize_defs[actual_psize].shift;
413		return (pa & ~((1ul << shift) - 1)) | (penc << LP_SHIFT);
414	}
415}
416
417/*
418 * Build a VPN_SHIFT bit shifted va given VSID, EA and segment size.
419 */
420static inline unsigned long hpt_vpn(unsigned long ea,
421				    unsigned long vsid, int ssize)
422{
423	unsigned long mask;
424	int s_shift = segment_shift(ssize);
425
426	mask = (1ul << (s_shift - VPN_SHIFT)) - 1;
427	return (vsid << (s_shift - VPN_SHIFT)) | ((ea >> VPN_SHIFT) & mask);
428}
429
430/*
431 * This hashes a virtual address
432 */
433static inline unsigned long hpt_hash(unsigned long vpn,
434				     unsigned int shift, int ssize)
435{
436	unsigned long mask;
437	unsigned long hash, vsid;
438
439	/* VPN_SHIFT can be atmost 12 */
440	if (ssize == MMU_SEGSIZE_256M) {
441		mask = (1ul << (SID_SHIFT - VPN_SHIFT)) - 1;
442		hash = (vpn >> (SID_SHIFT - VPN_SHIFT)) ^
443			((vpn & mask) >> (shift - VPN_SHIFT));
444	} else {
445		mask = (1ul << (SID_SHIFT_1T - VPN_SHIFT)) - 1;
446		vsid = vpn >> (SID_SHIFT_1T - VPN_SHIFT);
447		hash = vsid ^ (vsid << 25) ^
448			((vpn & mask) >> (shift - VPN_SHIFT)) ;
449	}
450	return hash & 0x7fffffffffUL;
451}
452
453#define HPTE_LOCAL_UPDATE	0x1
454#define HPTE_NOHPTE_UPDATE	0x2
455
456extern int __hash_page_4K(unsigned long ea, unsigned long access,
457			  unsigned long vsid, pte_t *ptep, unsigned long trap,
458			  unsigned long flags, int ssize, int subpage_prot);
459extern int __hash_page_64K(unsigned long ea, unsigned long access,
460			   unsigned long vsid, pte_t *ptep, unsigned long trap,
461			   unsigned long flags, int ssize);
462struct mm_struct;
463unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap);
464extern int hash_page_mm(struct mm_struct *mm, unsigned long ea,
465			unsigned long access, unsigned long trap,
466			unsigned long flags);
467extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
468		     unsigned long dsisr);
469int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
470		     pte_t *ptep, unsigned long trap, unsigned long flags,
471		     int ssize, unsigned int shift, unsigned int mmu_psize);
472#ifdef CONFIG_TRANSPARENT_HUGEPAGE
473extern int __hash_page_thp(unsigned long ea, unsigned long access,
474			   unsigned long vsid, pmd_t *pmdp, unsigned long trap,
475			   unsigned long flags, int ssize, unsigned int psize);
476#else
477static inline int __hash_page_thp(unsigned long ea, unsigned long access,
478				  unsigned long vsid, pmd_t *pmdp,
479				  unsigned long trap, unsigned long flags,
480				  int ssize, unsigned int psize)
481{
482	BUG();
483	return -1;
484}
485#endif
486extern void hash_failure_debug(unsigned long ea, unsigned long access,
487			       unsigned long vsid, unsigned long trap,
488			       int ssize, int psize, int lpsize,
489			       unsigned long pte);
490extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
491			     unsigned long pstart, unsigned long prot,
492			     int psize, int ssize);
493int htab_remove_mapping(unsigned long vstart, unsigned long vend,
494			int psize, int ssize);
495extern void pseries_add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages);
496extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr);
497
498extern void hash__setup_new_exec(void);
499
500#ifdef CONFIG_PPC_PSERIES
501void hpte_init_pseries(void);
502#else
503static inline void hpte_init_pseries(void) { }
504#endif
505
506extern void hpte_init_native(void);
507
508struct slb_entry {
509	u64	esid;
510	u64	vsid;
511};
512
513extern void slb_initialize(void);
514void slb_flush_and_restore_bolted(void);
515void slb_flush_all_realmode(void);
516void __slb_restore_bolted_realmode(void);
517void slb_restore_bolted_realmode(void);
518void slb_save_contents(struct slb_entry *slb_ptr);
519void slb_dump_contents(struct slb_entry *slb_ptr);
520
521extern void slb_vmalloc_update(void);
522extern void slb_set_size(u16 size);
523#endif /* __ASSEMBLY__ */
524
525/*
526 * VSID allocation (256MB segment)
527 *
528 * We first generate a 37-bit "proto-VSID". Proto-VSIDs are generated
529 * from mmu context id and effective segment id of the address.
530 *
531 * For user processes max context id is limited to MAX_USER_CONTEXT.
532 * more details in get_user_context
533 *
534 * For kernel space get_kernel_context
535 *
536 * The proto-VSIDs are then scrambled into real VSIDs with the
537 * multiplicative hash:
538 *
539 *	VSID = (proto-VSID * VSID_MULTIPLIER) % VSID_MODULUS
540 *
541 * VSID_MULTIPLIER is prime, so in particular it is
542 * co-prime to VSID_MODULUS, making this a 1:1 scrambling function.
543 * Because the modulus is 2^n-1 we can compute it efficiently without
544 * a divide or extra multiply (see below). The scramble function gives
545 * robust scattering in the hash table (at least based on some initial
546 * results).
547 *
548 * We use VSID 0 to indicate an invalid VSID. The means we can't use context id
549 * 0, because a context id of 0 and an EA of 0 gives a proto-VSID of 0, which
550 * will produce a VSID of 0.
551 *
552 * We also need to avoid the last segment of the last context, because that
553 * would give a protovsid of 0x1fffffffff. That will result in a VSID 0
554 * because of the modulo operation in vsid scramble.
555 */
556
557/*
558 * Max Va bits we support as of now is 68 bits. We want 19 bit
559 * context ID.
560 * Restrictions:
561 * GPU has restrictions of not able to access beyond 128TB
562 * (47 bit effective address). We also cannot do more than 20bit PID.
563 * For p4 and p5 which can only do 65 bit VA, we restrict our CONTEXT_BITS
564 * to 16 bits (ie, we can only have 2^16 pids at the same time).
565 */
566#define VA_BITS			68
567#define CONTEXT_BITS		19
568#define ESID_BITS		(VA_BITS - (SID_SHIFT + CONTEXT_BITS))
569#define ESID_BITS_1T		(VA_BITS - (SID_SHIFT_1T + CONTEXT_BITS))
570
571#define ESID_BITS_MASK		((1 << ESID_BITS) - 1)
572#define ESID_BITS_1T_MASK	((1 << ESID_BITS_1T) - 1)
573
574/*
575 * Now certain config support MAX_PHYSMEM more than 512TB. Hence we will need
576 * to use more than one context for linear mapping the kernel.
577 * For vmalloc and memmap, we use just one context with 512TB. With 64 byte
578 * struct page size, we need ony 32 TB in memmap for 2PB (51 bits (MAX_PHYSMEM_BITS)).
579 */
580#if (H_MAX_PHYSMEM_BITS > MAX_EA_BITS_PER_CONTEXT)
581#define MAX_KERNEL_CTX_CNT	(1UL << (H_MAX_PHYSMEM_BITS - MAX_EA_BITS_PER_CONTEXT))
582#else
583#define MAX_KERNEL_CTX_CNT	1
584#endif
585
586#define MAX_VMALLOC_CTX_CNT	1
587#define MAX_IO_CTX_CNT		1
588#define MAX_VMEMMAP_CTX_CNT	1
589
590/*
591 * 256MB segment
592 * The proto-VSID space has 2^(CONTEX_BITS + ESID_BITS) - 1 segments
593 * available for user + kernel mapping. VSID 0 is reserved as invalid, contexts
594 * 1-4 are used for kernel mapping. Each segment contains 2^28 bytes. Each
595 * context maps 2^49 bytes (512TB).
596 *
597 * We also need to avoid the last segment of the last context, because that
598 * would give a protovsid of 0x1fffffffff. That will result in a VSID 0
599 * because of the modulo operation in vsid scramble.
600 *
601 */
602#define MAX_USER_CONTEXT	((ASM_CONST(1) << CONTEXT_BITS) - 2)
603
604// The + 2 accounts for INVALID_REGION and 1 more to avoid overlap with kernel
605#define MIN_USER_CONTEXT	(MAX_KERNEL_CTX_CNT + MAX_VMALLOC_CTX_CNT + \
606				 MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT + 2)
607
608/*
609 * For platforms that support on 65bit VA we limit the context bits
610 */
611#define MAX_USER_CONTEXT_65BIT_VA ((ASM_CONST(1) << (65 - (SID_SHIFT + ESID_BITS))) - 2)
612
613/*
614 * This should be computed such that protovosid * vsid_mulitplier
615 * doesn't overflow 64 bits. The vsid_mutliplier should also be
616 * co-prime to vsid_modulus. We also need to make sure that number
617 * of bits in multiplied result (dividend) is less than twice the number of
618 * protovsid bits for our modulus optmization to work.
619 *
620 * The below table shows the current values used.
621 * |-------+------------+----------------------+------------+-------------------|
622 * |       | Prime Bits | proto VSID_BITS_65VA | Total Bits | 2* prot VSID_BITS |
623 * |-------+------------+----------------------+------------+-------------------|
624 * | 1T    |         24 |                   25 |         49 |                50 |
625 * |-------+------------+----------------------+------------+-------------------|
626 * | 256MB |         24 |                   37 |         61 |                74 |
627 * |-------+------------+----------------------+------------+-------------------|
628 *
629 * |-------+------------+----------------------+------------+--------------------|
630 * |       | Prime Bits | proto VSID_BITS_68VA | Total Bits | 2* proto VSID_BITS |
631 * |-------+------------+----------------------+------------+--------------------|
632 * | 1T    |         24 |                   28 |         52 |                 56 |
633 * |-------+------------+----------------------+------------+--------------------|
634 * | 256MB |         24 |                   40 |         64 |                 80 |
635 * |-------+------------+----------------------+------------+--------------------|
636 *
637 */
638#define VSID_MULTIPLIER_256M	ASM_CONST(12538073)	/* 24-bit prime */
639#define VSID_BITS_256M		(VA_BITS - SID_SHIFT)
640#define VSID_BITS_65_256M	(65 - SID_SHIFT)
641/*
642 * Modular multiplicative inverse of VSID_MULTIPLIER under modulo VSID_MODULUS
643 */
644#define VSID_MULINV_256M	ASM_CONST(665548017062)
645
646#define VSID_MULTIPLIER_1T	ASM_CONST(12538073)	/* 24-bit prime */
647#define VSID_BITS_1T		(VA_BITS - SID_SHIFT_1T)
648#define VSID_BITS_65_1T		(65 - SID_SHIFT_1T)
649#define VSID_MULINV_1T		ASM_CONST(209034062)
650
651/* 1TB VSID reserved for VRMA */
652#define VRMA_VSID	0x1ffffffUL
653#define USER_VSID_RANGE	(1UL << (ESID_BITS + SID_SHIFT))
654
655/* 4 bits per slice and we have one slice per 1TB */
656#define SLICE_ARRAY_SIZE	(H_PGTABLE_RANGE >> 41)
657#define LOW_SLICE_ARRAY_SZ	(BITS_PER_LONG / BITS_PER_BYTE)
658#define TASK_SLICE_ARRAY_SZ(x)	((x)->hash_context->slb_addr_limit >> 41)
659#ifndef __ASSEMBLY__
660
661#ifdef CONFIG_PPC_SUBPAGE_PROT
662/*
663 * For the sub-page protection option, we extend the PGD with one of
664 * these.  Basically we have a 3-level tree, with the top level being
665 * the protptrs array.  To optimize speed and memory consumption when
666 * only addresses < 4GB are being protected, pointers to the first
667 * four pages of sub-page protection words are stored in the low_prot
668 * array.
669 * Each page of sub-page protection words protects 1GB (4 bytes
670 * protects 64k).  For the 3-level tree, each page of pointers then
671 * protects 8TB.
672 */
673struct subpage_prot_table {
674	unsigned long maxaddr;	/* only addresses < this are protected */
675	unsigned int **protptrs[(TASK_SIZE_USER64 >> 43)];
676	unsigned int *low_prot[4];
677};
678
679#define SBP_L1_BITS		(PAGE_SHIFT - 2)
680#define SBP_L2_BITS		(PAGE_SHIFT - 3)
681#define SBP_L1_COUNT		(1 << SBP_L1_BITS)
682#define SBP_L2_COUNT		(1 << SBP_L2_BITS)
683#define SBP_L2_SHIFT		(PAGE_SHIFT + SBP_L1_BITS)
684#define SBP_L3_SHIFT		(SBP_L2_SHIFT + SBP_L2_BITS)
685
686extern void subpage_prot_free(struct mm_struct *mm);
687#else
688static inline void subpage_prot_free(struct mm_struct *mm) {}
689#endif /* CONFIG_PPC_SUBPAGE_PROT */
690
691/*
692 * One bit per slice. We have lower slices which cover 256MB segments
693 * upto 4G range. That gets us 16 low slices. For the rest we track slices
694 * in 1TB size.
695 */
696struct slice_mask {
697	u64 low_slices;
698	DECLARE_BITMAP(high_slices, SLICE_NUM_HIGH);
699};
700
701struct hash_mm_context {
702	u16 user_psize; /* page size index */
703
704	/* SLB page size encodings*/
705	unsigned char low_slices_psize[LOW_SLICE_ARRAY_SZ];
706	unsigned char high_slices_psize[SLICE_ARRAY_SIZE];
707	unsigned long slb_addr_limit;
708#ifdef CONFIG_PPC_64K_PAGES
709	struct slice_mask mask_64k;
710#endif
711	struct slice_mask mask_4k;
712#ifdef CONFIG_HUGETLB_PAGE
713	struct slice_mask mask_16m;
714	struct slice_mask mask_16g;
715#endif
716
717#ifdef CONFIG_PPC_SUBPAGE_PROT
718	struct subpage_prot_table *spt;
719#endif /* CONFIG_PPC_SUBPAGE_PROT */
720};
721
722#if 0
723/*
724 * The code below is equivalent to this function for arguments
725 * < 2^VSID_BITS, which is all this should ever be called
726 * with.  However gcc is not clever enough to compute the
727 * modulus (2^n-1) without a second multiply.
728 */
729#define vsid_scramble(protovsid, size) \
730	((((protovsid) * VSID_MULTIPLIER_##size) % VSID_MODULUS_##size))
731
732/* simplified form avoiding mod operation */
733#define vsid_scramble(protovsid, size) \
734	({								 \
735		unsigned long x;					 \
736		x = (protovsid) * VSID_MULTIPLIER_##size;		 \
737		x = (x >> VSID_BITS_##size) + (x & VSID_MODULUS_##size); \
738		(x + ((x+1) >> VSID_BITS_##size)) & VSID_MODULUS_##size; \
739	})
740
741#else /* 1 */
742static inline unsigned long vsid_scramble(unsigned long protovsid,
743				  unsigned long vsid_multiplier, int vsid_bits)
744{
745	unsigned long vsid;
746	unsigned long vsid_modulus = ((1UL << vsid_bits) - 1);
747	/*
748	 * We have same multipler for both 256 and 1T segements now
749	 */
750	vsid = protovsid * vsid_multiplier;
751	vsid = (vsid >> vsid_bits) + (vsid & vsid_modulus);
752	return (vsid + ((vsid + 1) >> vsid_bits)) & vsid_modulus;
753}
754
755#endif /* 1 */
756
757/* Returns the segment size indicator for a user address */
758static inline int user_segment_size(unsigned long addr)
759{
760	/* Use 1T segments if possible for addresses >= 1T */
761	if (addr >= (1UL << SID_SHIFT_1T))
762		return mmu_highuser_ssize;
763	return MMU_SEGSIZE_256M;
764}
765
766static inline unsigned long get_vsid(unsigned long context, unsigned long ea,
767				     int ssize)
768{
769	unsigned long va_bits = VA_BITS;
770	unsigned long vsid_bits;
771	unsigned long protovsid;
772
773	/*
774	 * Bad address. We return VSID 0 for that
775	 */
776	if ((ea & EA_MASK)  >= H_PGTABLE_RANGE)
777		return 0;
778
779	if (!mmu_has_feature(MMU_FTR_68_BIT_VA))
780		va_bits = 65;
781
782	if (ssize == MMU_SEGSIZE_256M) {
783		vsid_bits = va_bits - SID_SHIFT;
784		protovsid = (context << ESID_BITS) |
785			((ea >> SID_SHIFT) & ESID_BITS_MASK);
786		return vsid_scramble(protovsid, VSID_MULTIPLIER_256M, vsid_bits);
787	}
788	/* 1T segment */
789	vsid_bits = va_bits - SID_SHIFT_1T;
790	protovsid = (context << ESID_BITS_1T) |
791		((ea >> SID_SHIFT_1T) & ESID_BITS_1T_MASK);
792	return vsid_scramble(protovsid, VSID_MULTIPLIER_1T, vsid_bits);
793}
794
795/*
796 * For kernel space, we use context ids as
797 * below. Range is 512TB per context.
798 *
799 * 0x00001 -  [ 0xc000000000000000 - 0xc001ffffffffffff]
800 * 0x00002 -  [ 0xc002000000000000 - 0xc003ffffffffffff]
801 * 0x00003 -  [ 0xc004000000000000 - 0xc005ffffffffffff]
802 * 0x00004 -  [ 0xc006000000000000 - 0xc007ffffffffffff]
803 *
804 * vmap, IO, vmemap
805 *
806 * 0x00005 -  [ 0xc008000000000000 - 0xc009ffffffffffff]
807 * 0x00006 -  [ 0xc00a000000000000 - 0xc00bffffffffffff]
808 * 0x00007 -  [ 0xc00c000000000000 - 0xc00dffffffffffff]
809 *
810 */
811static inline unsigned long get_kernel_context(unsigned long ea)
812{
813	unsigned long region_id = get_region_id(ea);
814	unsigned long ctx;
815	/*
816	 * Depending on Kernel config, kernel region can have one context
817	 * or more.
818	 */
819	if (region_id == LINEAR_MAP_REGION_ID) {
820		/*
821		 * We already verified ea to be not beyond the addr limit.
822		 */
823		ctx =  1 + ((ea & EA_MASK) >> MAX_EA_BITS_PER_CONTEXT);
824	} else
825		ctx = region_id + MAX_KERNEL_CTX_CNT - 1;
826	return ctx;
827}
828
829/*
830 * This is only valid for addresses >= PAGE_OFFSET
831 */
832static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize)
833{
834	unsigned long context;
835
836	if (!is_kernel_addr(ea))
837		return 0;
838
839	context = get_kernel_context(ea);
840	return get_vsid(context, ea, ssize);
841}
842
843unsigned htab_shift_for_mem_size(unsigned long mem_size);
844
845#endif /* __ASSEMBLY__ */
846
847#endif /* _ASM_POWERPC_BOOK3S_64_MMU_HASH_H_ */
848