1// SPDX-License-Identifier: GPL-2.0-or-later
2/*
3 * PowerPC64 SLB support.
4 *
5 * Copyright (C) 2004 David Gibson <dwg@au.ibm.com>, IBM
6 * Based on earlier code written by:
7 * Dave Engebretsen and Mike Corrigan {engebret|mikejc}@us.ibm.com
8 *    Copyright (c) 2001 Dave Engebretsen
9 * Copyright (C) 2002 Anton Blanchard <anton@au.ibm.com>, IBM
10 */
11
12#include <asm/asm-prototypes.h>
13#include <asm/mmu.h>
14#include <asm/mmu_context.h>
15#include <asm/paca.h>
16#include <asm/lppaca.h>
17#include <asm/ppc-opcode.h>
18#include <asm/cputable.h>
19#include <asm/cacheflush.h>
20#include <asm/smp.h>
21#include <linux/compiler.h>
22#include <linux/context_tracking.h>
23#include <linux/mm_types.h>
24#include <linux/pgtable.h>
25
26#include <asm/udbg.h>
27#include <asm/code-patching.h>
28
29#include "internal.h"
30
31
32enum slb_index {
33	LINEAR_INDEX	= 0, /* Kernel linear map  (0xc000000000000000) */
34	KSTACK_INDEX	= 1, /* Kernel stack map */
35};
36
37static long slb_allocate_user(struct mm_struct *mm, unsigned long ea);
38
39#define slb_esid_mask(ssize)	\
40	(((ssize) == MMU_SEGSIZE_256M)? ESID_MASK: ESID_MASK_1T)
41
42static inline unsigned long mk_esid_data(unsigned long ea, int ssize,
43					 enum slb_index index)
44{
45	return (ea & slb_esid_mask(ssize)) | SLB_ESID_V | index;
46}
47
48static inline unsigned long __mk_vsid_data(unsigned long vsid, int ssize,
49					 unsigned long flags)
50{
51	return (vsid << slb_vsid_shift(ssize)) | flags |
52		((unsigned long) ssize << SLB_VSID_SSIZE_SHIFT);
53}
54
55static inline unsigned long mk_vsid_data(unsigned long ea, int ssize,
56					 unsigned long flags)
57{
58	return __mk_vsid_data(get_kernel_vsid(ea, ssize), ssize, flags);
59}
60
61bool stress_slb_enabled __initdata;
62
63static int __init parse_stress_slb(char *p)
64{
65	stress_slb_enabled = true;
66	return 0;
67}
68early_param("stress_slb", parse_stress_slb);
69
70__ro_after_init DEFINE_STATIC_KEY_FALSE(stress_slb_key);
71
72static void assert_slb_presence(bool present, unsigned long ea)
73{
74#ifdef CONFIG_DEBUG_VM
75	unsigned long tmp;
76
77	WARN_ON_ONCE(mfmsr() & MSR_EE);
78
79	if (!cpu_has_feature(CPU_FTR_ARCH_206))
80		return;
81
82	/*
83	 * slbfee. requires bit 24 (PPC bit 39) be clear in RB. Hardware
84	 * ignores all other bits from 0-27, so just clear them all.
85	 */
86	ea &= ~((1UL << SID_SHIFT) - 1);
87	asm volatile(__PPC_SLBFEE_DOT(%0, %1) : "=r"(tmp) : "r"(ea) : "cr0");
88
89	WARN_ON(present == (tmp == 0));
90#endif
91}
92
93static inline void slb_shadow_update(unsigned long ea, int ssize,
94				     unsigned long flags,
95				     enum slb_index index)
96{
97	struct slb_shadow *p = get_slb_shadow();
98
99	/*
100	 * Clear the ESID first so the entry is not valid while we are
101	 * updating it.  No write barriers are needed here, provided
102	 * we only update the current CPU's SLB shadow buffer.
103	 */
104	WRITE_ONCE(p->save_area[index].esid, 0);
105	WRITE_ONCE(p->save_area[index].vsid, cpu_to_be64(mk_vsid_data(ea, ssize, flags)));
106	WRITE_ONCE(p->save_area[index].esid, cpu_to_be64(mk_esid_data(ea, ssize, index)));
107}
108
109static inline void slb_shadow_clear(enum slb_index index)
110{
111	WRITE_ONCE(get_slb_shadow()->save_area[index].esid, cpu_to_be64(index));
112}
113
114static inline void create_shadowed_slbe(unsigned long ea, int ssize,
115					unsigned long flags,
116					enum slb_index index)
117{
118	/*
119	 * Updating the shadow buffer before writing the SLB ensures
120	 * we don't get a stale entry here if we get preempted by PHYP
121	 * between these two statements.
122	 */
123	slb_shadow_update(ea, ssize, flags, index);
124
125	assert_slb_presence(false, ea);
126	asm volatile("slbmte  %0,%1" :
127		     : "r" (mk_vsid_data(ea, ssize, flags)),
128		       "r" (mk_esid_data(ea, ssize, index))
129		     : "memory" );
130}
131
132/*
133 * Insert bolted entries into SLB (which may not be empty, so don't clear
134 * slb_cache_ptr).
135 */
136void __slb_restore_bolted_realmode(void)
137{
138	struct slb_shadow *p = get_slb_shadow();
139	enum slb_index index;
140
141	 /* No isync needed because realmode. */
142	for (index = 0; index < SLB_NUM_BOLTED; index++) {
143		asm volatile("slbmte  %0,%1" :
144		     : "r" (be64_to_cpu(p->save_area[index].vsid)),
145		       "r" (be64_to_cpu(p->save_area[index].esid)));
146	}
147
148	assert_slb_presence(true, local_paca->kstack);
149}
150
151/*
152 * Insert the bolted entries into an empty SLB.
153 */
154void slb_restore_bolted_realmode(void)
155{
156	__slb_restore_bolted_realmode();
157	get_paca()->slb_cache_ptr = 0;
158
159	get_paca()->slb_kern_bitmap = (1U << SLB_NUM_BOLTED) - 1;
160	get_paca()->slb_used_bitmap = get_paca()->slb_kern_bitmap;
161}
162
163/*
164 * This flushes all SLB entries including 0, so it must be realmode.
165 */
166void slb_flush_all_realmode(void)
167{
168	asm volatile("slbmte %0,%0; slbia" : : "r" (0));
169}
170
171static __always_inline void __slb_flush_and_restore_bolted(bool preserve_kernel_lookaside)
172{
173	struct slb_shadow *p = get_slb_shadow();
174	unsigned long ksp_esid_data, ksp_vsid_data;
175	u32 ih;
176
177	/*
178	 * SLBIA IH=1 on ISA v2.05 and newer processors may preserve lookaside
179	 * information created with Class=0 entries, which we use for kernel
180	 * SLB entries (the SLB entries themselves are still invalidated).
181	 *
182	 * Older processors will ignore this optimisation. Over-invalidation
183	 * is fine because we never rely on lookaside information existing.
184	 */
185	if (preserve_kernel_lookaside)
186		ih = 1;
187	else
188		ih = 0;
189
190	ksp_esid_data = be64_to_cpu(p->save_area[KSTACK_INDEX].esid);
191	ksp_vsid_data = be64_to_cpu(p->save_area[KSTACK_INDEX].vsid);
192
193	asm volatile(PPC_SLBIA(%0)"	\n"
194		     "slbmte	%1, %2	\n"
195		     :: "i" (ih),
196			"r" (ksp_vsid_data),
197			"r" (ksp_esid_data)
198		     : "memory");
199}
200
201/*
202 * This flushes non-bolted entries, it can be run in virtual mode. Must
203 * be called with interrupts disabled.
204 */
205void slb_flush_and_restore_bolted(void)
206{
207	BUILD_BUG_ON(SLB_NUM_BOLTED != 2);
208
209	WARN_ON(!irqs_disabled());
210
211	/*
212	 * We can't take a PMU exception in the following code, so hard
213	 * disable interrupts.
214	 */
215	hard_irq_disable();
216
217	isync();
218	__slb_flush_and_restore_bolted(false);
219	isync();
220
221	assert_slb_presence(true, get_paca()->kstack);
222
223	get_paca()->slb_cache_ptr = 0;
224
225	get_paca()->slb_kern_bitmap = (1U << SLB_NUM_BOLTED) - 1;
226	get_paca()->slb_used_bitmap = get_paca()->slb_kern_bitmap;
227}
228
229void slb_save_contents(struct slb_entry *slb_ptr)
230{
231	int i;
232	unsigned long e, v;
233
234	/* Save slb_cache_ptr value. */
235	get_paca()->slb_save_cache_ptr = get_paca()->slb_cache_ptr;
236
237	if (!slb_ptr)
238		return;
239
240	for (i = 0; i < mmu_slb_size; i++) {
241		asm volatile("slbmfee  %0,%1" : "=r" (e) : "r" (i));
242		asm volatile("slbmfev  %0,%1" : "=r" (v) : "r" (i));
243		slb_ptr->esid = e;
244		slb_ptr->vsid = v;
245		slb_ptr++;
246	}
247}
248
249void slb_dump_contents(struct slb_entry *slb_ptr)
250{
251	int i, n;
252	unsigned long e, v;
253	unsigned long llp;
254
255	if (!slb_ptr)
256		return;
257
258	pr_err("SLB contents of cpu 0x%x\n", smp_processor_id());
259	pr_err("Last SLB entry inserted at slot %d\n", get_paca()->stab_rr);
260
261	for (i = 0; i < mmu_slb_size; i++) {
262		e = slb_ptr->esid;
263		v = slb_ptr->vsid;
264		slb_ptr++;
265
266		if (!e && !v)
267			continue;
268
269		pr_err("%02d %016lx %016lx\n", i, e, v);
270
271		if (!(e & SLB_ESID_V)) {
272			pr_err("\n");
273			continue;
274		}
275		llp = v & SLB_VSID_LLP;
276		if (v & SLB_VSID_B_1T) {
277			pr_err("  1T  ESID=%9lx  VSID=%13lx LLP:%3lx\n",
278			       GET_ESID_1T(e),
279			       (v & ~SLB_VSID_B) >> SLB_VSID_SHIFT_1T, llp);
280		} else {
281			pr_err(" 256M ESID=%9lx  VSID=%13lx LLP:%3lx\n",
282			       GET_ESID(e),
283			       (v & ~SLB_VSID_B) >> SLB_VSID_SHIFT, llp);
284		}
285	}
286	pr_err("----------------------------------\n");
287
288	/* Dump slb cache entires as well. */
289	pr_err("SLB cache ptr value = %d\n", get_paca()->slb_save_cache_ptr);
290	pr_err("Valid SLB cache entries:\n");
291	n = min_t(int, get_paca()->slb_save_cache_ptr, SLB_CACHE_ENTRIES);
292	for (i = 0; i < n; i++)
293		pr_err("%02d EA[0-35]=%9x\n", i, get_paca()->slb_cache[i]);
294	pr_err("Rest of SLB cache entries:\n");
295	for (i = n; i < SLB_CACHE_ENTRIES; i++)
296		pr_err("%02d EA[0-35]=%9x\n", i, get_paca()->slb_cache[i]);
297}
298
299void slb_vmalloc_update(void)
300{
301	/*
302	 * vmalloc is not bolted, so just have to flush non-bolted.
303	 */
304	slb_flush_and_restore_bolted();
305}
306
307static bool preload_hit(struct thread_info *ti, unsigned long esid)
308{
309	unsigned char i;
310
311	for (i = 0; i < ti->slb_preload_nr; i++) {
312		unsigned char idx;
313
314		idx = (ti->slb_preload_tail + i) % SLB_PRELOAD_NR;
315		if (esid == ti->slb_preload_esid[idx])
316			return true;
317	}
318	return false;
319}
320
321static bool preload_add(struct thread_info *ti, unsigned long ea)
322{
323	unsigned char idx;
324	unsigned long esid;
325
326	if (mmu_has_feature(MMU_FTR_1T_SEGMENT)) {
327		/* EAs are stored >> 28 so 256MB segments don't need clearing */
328		if (ea & ESID_MASK_1T)
329			ea &= ESID_MASK_1T;
330	}
331
332	esid = ea >> SID_SHIFT;
333
334	if (preload_hit(ti, esid))
335		return false;
336
337	idx = (ti->slb_preload_tail + ti->slb_preload_nr) % SLB_PRELOAD_NR;
338	ti->slb_preload_esid[idx] = esid;
339	if (ti->slb_preload_nr == SLB_PRELOAD_NR)
340		ti->slb_preload_tail = (ti->slb_preload_tail + 1) % SLB_PRELOAD_NR;
341	else
342		ti->slb_preload_nr++;
343
344	return true;
345}
346
347static void preload_age(struct thread_info *ti)
348{
349	if (!ti->slb_preload_nr)
350		return;
351	ti->slb_preload_nr--;
352	ti->slb_preload_tail = (ti->slb_preload_tail + 1) % SLB_PRELOAD_NR;
353}
354
355void slb_setup_new_exec(void)
356{
357	struct thread_info *ti = current_thread_info();
358	struct mm_struct *mm = current->mm;
359	unsigned long exec = 0x10000000;
360
361	WARN_ON(irqs_disabled());
362
363	/*
364	 * preload cache can only be used to determine whether a SLB
365	 * entry exists if it does not start to overflow.
366	 */
367	if (ti->slb_preload_nr + 2 > SLB_PRELOAD_NR)
368		return;
369
370	hard_irq_disable();
371
372	/*
373	 * We have no good place to clear the slb preload cache on exec,
374	 * flush_thread is about the earliest arch hook but that happens
375	 * after we switch to the mm and have aleady preloaded the SLBEs.
376	 *
377	 * For the most part that's probably okay to use entries from the
378	 * previous exec, they will age out if unused. It may turn out to
379	 * be an advantage to clear the cache before switching to it,
380	 * however.
381	 */
382
383	/*
384	 * preload some userspace segments into the SLB.
385	 * Almost all 32 and 64bit PowerPC executables are linked at
386	 * 0x10000000 so it makes sense to preload this segment.
387	 */
388	if (!is_kernel_addr(exec)) {
389		if (preload_add(ti, exec))
390			slb_allocate_user(mm, exec);
391	}
392
393	/* Libraries and mmaps. */
394	if (!is_kernel_addr(mm->mmap_base)) {
395		if (preload_add(ti, mm->mmap_base))
396			slb_allocate_user(mm, mm->mmap_base);
397	}
398
399	/* see switch_slb */
400	asm volatile("isync" : : : "memory");
401
402	local_irq_enable();
403}
404
405void preload_new_slb_context(unsigned long start, unsigned long sp)
406{
407	struct thread_info *ti = current_thread_info();
408	struct mm_struct *mm = current->mm;
409	unsigned long heap = mm->start_brk;
410
411	WARN_ON(irqs_disabled());
412
413	/* see above */
414	if (ti->slb_preload_nr + 3 > SLB_PRELOAD_NR)
415		return;
416
417	hard_irq_disable();
418
419	/* Userspace entry address. */
420	if (!is_kernel_addr(start)) {
421		if (preload_add(ti, start))
422			slb_allocate_user(mm, start);
423	}
424
425	/* Top of stack, grows down. */
426	if (!is_kernel_addr(sp)) {
427		if (preload_add(ti, sp))
428			slb_allocate_user(mm, sp);
429	}
430
431	/* Bottom of heap, grows up. */
432	if (heap && !is_kernel_addr(heap)) {
433		if (preload_add(ti, heap))
434			slb_allocate_user(mm, heap);
435	}
436
437	/* see switch_slb */
438	asm volatile("isync" : : : "memory");
439
440	local_irq_enable();
441}
442
443static void slb_cache_slbie_kernel(unsigned int index)
444{
445	unsigned long slbie_data = get_paca()->slb_cache[index];
446	unsigned long ksp = get_paca()->kstack;
447
448	slbie_data <<= SID_SHIFT;
449	slbie_data |= 0xc000000000000000ULL;
450	if ((ksp & slb_esid_mask(mmu_kernel_ssize)) == slbie_data)
451		return;
452	slbie_data |= mmu_kernel_ssize << SLBIE_SSIZE_SHIFT;
453
454	asm volatile("slbie %0" : : "r" (slbie_data));
455}
456
457static void slb_cache_slbie_user(unsigned int index)
458{
459	unsigned long slbie_data = get_paca()->slb_cache[index];
460
461	slbie_data <<= SID_SHIFT;
462	slbie_data |= user_segment_size(slbie_data) << SLBIE_SSIZE_SHIFT;
463	slbie_data |= SLBIE_C; /* user slbs have C=1 */
464
465	asm volatile("slbie %0" : : "r" (slbie_data));
466}
467
468/* Flush all user entries from the segment table of the current processor. */
469void switch_slb(struct task_struct *tsk, struct mm_struct *mm)
470{
471	struct thread_info *ti = task_thread_info(tsk);
472	unsigned char i;
473
474	/*
475	 * We need interrupts hard-disabled here, not just soft-disabled,
476	 * so that a PMU interrupt can't occur, which might try to access
477	 * user memory (to get a stack trace) and possible cause an SLB miss
478	 * which would update the slb_cache/slb_cache_ptr fields in the PACA.
479	 */
480	hard_irq_disable();
481	isync();
482	if (stress_slb()) {
483		__slb_flush_and_restore_bolted(false);
484		isync();
485		get_paca()->slb_cache_ptr = 0;
486		get_paca()->slb_kern_bitmap = (1U << SLB_NUM_BOLTED) - 1;
487
488	} else if (cpu_has_feature(CPU_FTR_ARCH_300)) {
489		/*
490		 * SLBIA IH=3 invalidates all Class=1 SLBEs and their
491		 * associated lookaside structures, which matches what
492		 * switch_slb wants. So ARCH_300 does not use the slb
493		 * cache.
494		 */
495		asm volatile(PPC_SLBIA(3));
496
497	} else {
498		unsigned long offset = get_paca()->slb_cache_ptr;
499
500		if (!mmu_has_feature(MMU_FTR_NO_SLBIE_B) &&
501		    offset <= SLB_CACHE_ENTRIES) {
502			/*
503			 * Could assert_slb_presence(true) here, but
504			 * hypervisor or machine check could have come
505			 * in and removed the entry at this point.
506			 */
507
508			for (i = 0; i < offset; i++)
509				slb_cache_slbie_user(i);
510
511			/* Workaround POWER5 < DD2.1 issue */
512			if (!cpu_has_feature(CPU_FTR_ARCH_207S) && offset == 1)
513				slb_cache_slbie_user(0);
514
515		} else {
516			/* Flush but retain kernel lookaside information */
517			__slb_flush_and_restore_bolted(true);
518			isync();
519
520			get_paca()->slb_kern_bitmap = (1U << SLB_NUM_BOLTED) - 1;
521		}
522
523		get_paca()->slb_cache_ptr = 0;
524	}
525	get_paca()->slb_used_bitmap = get_paca()->slb_kern_bitmap;
526
527	copy_mm_to_paca(mm);
528
529	/*
530	 * We gradually age out SLBs after a number of context switches to
531	 * reduce reload overhead of unused entries (like we do with FP/VEC
532	 * reload). Each time we wrap 256 switches, take an entry out of the
533	 * SLB preload cache.
534	 */
535	tsk->thread.load_slb++;
536	if (!tsk->thread.load_slb) {
537		unsigned long pc = KSTK_EIP(tsk);
538
539		preload_age(ti);
540		preload_add(ti, pc);
541	}
542
543	for (i = 0; i < ti->slb_preload_nr; i++) {
544		unsigned char idx;
545		unsigned long ea;
546
547		idx = (ti->slb_preload_tail + i) % SLB_PRELOAD_NR;
548		ea = (unsigned long)ti->slb_preload_esid[idx] << SID_SHIFT;
549
550		slb_allocate_user(mm, ea);
551	}
552
553	/*
554	 * Synchronize slbmte preloads with possible subsequent user memory
555	 * address accesses by the kernel (user mode won't happen until
556	 * rfid, which is safe).
557	 */
558	isync();
559}
560
561void slb_set_size(u16 size)
562{
563	mmu_slb_size = size;
564}
565
566void slb_initialize(void)
567{
568	unsigned long linear_llp, vmalloc_llp, io_llp;
569	unsigned long lflags;
570	static int slb_encoding_inited;
571#ifdef CONFIG_SPARSEMEM_VMEMMAP
572	unsigned long vmemmap_llp;
573#endif
574
575	/* Prepare our SLB miss handler based on our page size */
576	linear_llp = mmu_psize_defs[mmu_linear_psize].sllp;
577	io_llp = mmu_psize_defs[mmu_io_psize].sllp;
578	vmalloc_llp = mmu_psize_defs[mmu_vmalloc_psize].sllp;
579	get_paca()->vmalloc_sllp = SLB_VSID_KERNEL | vmalloc_llp;
580#ifdef CONFIG_SPARSEMEM_VMEMMAP
581	vmemmap_llp = mmu_psize_defs[mmu_vmemmap_psize].sllp;
582#endif
583	if (!slb_encoding_inited) {
584		slb_encoding_inited = 1;
585		pr_devel("SLB: linear  LLP = %04lx\n", linear_llp);
586		pr_devel("SLB: io      LLP = %04lx\n", io_llp);
587#ifdef CONFIG_SPARSEMEM_VMEMMAP
588		pr_devel("SLB: vmemmap LLP = %04lx\n", vmemmap_llp);
589#endif
590	}
591
592	get_paca()->stab_rr = SLB_NUM_BOLTED - 1;
593	get_paca()->slb_kern_bitmap = (1U << SLB_NUM_BOLTED) - 1;
594	get_paca()->slb_used_bitmap = get_paca()->slb_kern_bitmap;
595
596	lflags = SLB_VSID_KERNEL | linear_llp;
597
598	/* Invalidate the entire SLB (even entry 0) & all the ERATS */
599	asm volatile("isync":::"memory");
600	asm volatile("slbmte  %0,%0"::"r" (0) : "memory");
601	asm volatile("isync; slbia; isync":::"memory");
602	create_shadowed_slbe(PAGE_OFFSET, mmu_kernel_ssize, lflags, LINEAR_INDEX);
603
604	/*
605	 * For the boot cpu, we're running on the stack in init_thread_union,
606	 * which is in the first segment of the linear mapping, and also
607	 * get_paca()->kstack hasn't been initialized yet.
608	 * For secondary cpus, we need to bolt the kernel stack entry now.
609	 */
610	slb_shadow_clear(KSTACK_INDEX);
611	if (raw_smp_processor_id() != boot_cpuid &&
612	    (get_paca()->kstack & slb_esid_mask(mmu_kernel_ssize)) > PAGE_OFFSET)
613		create_shadowed_slbe(get_paca()->kstack,
614				     mmu_kernel_ssize, lflags, KSTACK_INDEX);
615
616	asm volatile("isync":::"memory");
617}
618
619static void slb_cache_update(unsigned long esid_data)
620{
621	int slb_cache_index;
622
623	if (cpu_has_feature(CPU_FTR_ARCH_300))
624		return; /* ISAv3.0B and later does not use slb_cache */
625
626	if (stress_slb())
627		return;
628
629	/*
630	 * Now update slb cache entries
631	 */
632	slb_cache_index = local_paca->slb_cache_ptr;
633	if (slb_cache_index < SLB_CACHE_ENTRIES) {
634		/*
635		 * We have space in slb cache for optimized switch_slb().
636		 * Top 36 bits from esid_data as per ISA
637		 */
638		local_paca->slb_cache[slb_cache_index++] = esid_data >> SID_SHIFT;
639		local_paca->slb_cache_ptr++;
640	} else {
641		/*
642		 * Our cache is full and the current cache content strictly
643		 * doesn't indicate the active SLB conents. Bump the ptr
644		 * so that switch_slb() will ignore the cache.
645		 */
646		local_paca->slb_cache_ptr = SLB_CACHE_ENTRIES + 1;
647	}
648}
649
650static enum slb_index alloc_slb_index(bool kernel)
651{
652	enum slb_index index;
653
654	/*
655	 * The allocation bitmaps can become out of synch with the SLB
656	 * when the _switch code does slbie when bolting a new stack
657	 * segment and it must not be anywhere else in the SLB. This leaves
658	 * a kernel allocated entry that is unused in the SLB. With very
659	 * large systems or small segment sizes, the bitmaps could slowly
660	 * fill with these entries. They will eventually be cleared out
661	 * by the round robin allocator in that case, so it's probably not
662	 * worth accounting for.
663	 */
664
665	/*
666	 * SLBs beyond 32 entries are allocated with stab_rr only
667	 * POWER7/8/9 have 32 SLB entries, this could be expanded if a
668	 * future CPU has more.
669	 */
670	if (local_paca->slb_used_bitmap != U32_MAX) {
671		index = ffz(local_paca->slb_used_bitmap);
672		local_paca->slb_used_bitmap |= 1U << index;
673		if (kernel)
674			local_paca->slb_kern_bitmap |= 1U << index;
675	} else {
676		/* round-robin replacement of slb starting at SLB_NUM_BOLTED. */
677		index = local_paca->stab_rr;
678		if (index < (mmu_slb_size - 1))
679			index++;
680		else
681			index = SLB_NUM_BOLTED;
682		local_paca->stab_rr = index;
683		if (index < 32) {
684			if (kernel)
685				local_paca->slb_kern_bitmap |= 1U << index;
686			else
687				local_paca->slb_kern_bitmap &= ~(1U << index);
688		}
689	}
690	BUG_ON(index < SLB_NUM_BOLTED);
691
692	return index;
693}
694
695static long slb_insert_entry(unsigned long ea, unsigned long context,
696				unsigned long flags, int ssize, bool kernel)
697{
698	unsigned long vsid;
699	unsigned long vsid_data, esid_data;
700	enum slb_index index;
701
702	vsid = get_vsid(context, ea, ssize);
703	if (!vsid)
704		return -EFAULT;
705
706	/*
707	 * There must not be a kernel SLB fault in alloc_slb_index or before
708	 * slbmte here or the allocation bitmaps could get out of whack with
709	 * the SLB.
710	 *
711	 * User SLB faults or preloads take this path which might get inlined
712	 * into the caller, so add compiler barriers here to ensure unsafe
713	 * memory accesses do not come between.
714	 */
715	barrier();
716
717	index = alloc_slb_index(kernel);
718
719	vsid_data = __mk_vsid_data(vsid, ssize, flags);
720	esid_data = mk_esid_data(ea, ssize, index);
721
722	/*
723	 * No need for an isync before or after this slbmte. The exception
724	 * we enter with and the rfid we exit with are context synchronizing.
725	 * User preloads should add isync afterwards in case the kernel
726	 * accesses user memory before it returns to userspace with rfid.
727	 */
728	assert_slb_presence(false, ea);
729	if (stress_slb()) {
730		int slb_cache_index = local_paca->slb_cache_ptr;
731
732		/*
733		 * stress_slb() does not use slb cache, repurpose as a
734		 * cache of inserted (non-bolted) kernel SLB entries. All
735		 * non-bolted kernel entries are flushed on any user fault,
736		 * or if there are already 3 non-boled kernel entries.
737		 */
738		BUILD_BUG_ON(SLB_CACHE_ENTRIES < 3);
739		if (!kernel || slb_cache_index == 3) {
740			int i;
741
742			for (i = 0; i < slb_cache_index; i++)
743				slb_cache_slbie_kernel(i);
744			slb_cache_index = 0;
745		}
746
747		if (kernel)
748			local_paca->slb_cache[slb_cache_index++] = esid_data >> SID_SHIFT;
749		local_paca->slb_cache_ptr = slb_cache_index;
750	}
751	asm volatile("slbmte %0, %1" : : "r" (vsid_data), "r" (esid_data));
752
753	barrier();
754
755	if (!kernel)
756		slb_cache_update(esid_data);
757
758	return 0;
759}
760
761static long slb_allocate_kernel(unsigned long ea, unsigned long id)
762{
763	unsigned long context;
764	unsigned long flags;
765	int ssize;
766
767	if (id == LINEAR_MAP_REGION_ID) {
768
769		/* We only support upto H_MAX_PHYSMEM_BITS */
770		if ((ea & EA_MASK) > (1UL << H_MAX_PHYSMEM_BITS))
771			return -EFAULT;
772
773		flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_linear_psize].sllp;
774
775#ifdef CONFIG_SPARSEMEM_VMEMMAP
776	} else if (id == VMEMMAP_REGION_ID) {
777
778		if (ea >= H_VMEMMAP_END)
779			return -EFAULT;
780
781		flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_vmemmap_psize].sllp;
782#endif
783	} else if (id == VMALLOC_REGION_ID) {
784
785		if (ea >= H_VMALLOC_END)
786			return -EFAULT;
787
788		flags = local_paca->vmalloc_sllp;
789
790	} else if (id == IO_REGION_ID) {
791
792		if (ea >= H_KERN_IO_END)
793			return -EFAULT;
794
795		flags = SLB_VSID_KERNEL | mmu_psize_defs[mmu_io_psize].sllp;
796
797	} else {
798		return -EFAULT;
799	}
800
801	ssize = MMU_SEGSIZE_1T;
802	if (!mmu_has_feature(MMU_FTR_1T_SEGMENT))
803		ssize = MMU_SEGSIZE_256M;
804
805	context = get_kernel_context(ea);
806
807	return slb_insert_entry(ea, context, flags, ssize, true);
808}
809
810static long slb_allocate_user(struct mm_struct *mm, unsigned long ea)
811{
812	unsigned long context;
813	unsigned long flags;
814	int bpsize;
815	int ssize;
816
817	/*
818	 * consider this as bad access if we take a SLB miss
819	 * on an address above addr limit.
820	 */
821	if (ea >= mm_ctx_slb_addr_limit(&mm->context))
822		return -EFAULT;
823
824	context = get_user_context(&mm->context, ea);
825	if (!context)
826		return -EFAULT;
827
828	if (unlikely(ea >= H_PGTABLE_RANGE)) {
829		WARN_ON(1);
830		return -EFAULT;
831	}
832
833	ssize = user_segment_size(ea);
834
835	bpsize = get_slice_psize(mm, ea);
836	flags = SLB_VSID_USER | mmu_psize_defs[bpsize].sllp;
837
838	return slb_insert_entry(ea, context, flags, ssize, false);
839}
840
841long do_slb_fault(struct pt_regs *regs, unsigned long ea)
842{
843	unsigned long id = get_region_id(ea);
844
845	/* IRQs are not reconciled here, so can't check irqs_disabled */
846	VM_WARN_ON(mfmsr() & MSR_EE);
847
848	if (unlikely(!(regs->msr & MSR_RI)))
849		return -EINVAL;
850
851	/*
852	 * SLB kernel faults must be very careful not to touch anything
853	 * that is not bolted. E.g., PACA and global variables are okay,
854	 * mm->context stuff is not.
855	 *
856	 * SLB user faults can access all of kernel memory, but must be
857	 * careful not to touch things like IRQ state because it is not
858	 * "reconciled" here. The difficulty is that we must use
859	 * fast_exception_return to return from kernel SLB faults without
860	 * looking at possible non-bolted memory. We could test user vs
861	 * kernel faults in the interrupt handler asm and do a full fault,
862	 * reconcile, ret_from_except for user faults which would make them
863	 * first class kernel code. But for performance it's probably nicer
864	 * if they go via fast_exception_return too.
865	 */
866	if (id >= LINEAR_MAP_REGION_ID) {
867		long err;
868#ifdef CONFIG_DEBUG_VM
869		/* Catch recursive kernel SLB faults. */
870		BUG_ON(local_paca->in_kernel_slb_handler);
871		local_paca->in_kernel_slb_handler = 1;
872#endif
873		err = slb_allocate_kernel(ea, id);
874#ifdef CONFIG_DEBUG_VM
875		local_paca->in_kernel_slb_handler = 0;
876#endif
877		return err;
878	} else {
879		struct mm_struct *mm = current->mm;
880		long err;
881
882		if (unlikely(!mm))
883			return -EFAULT;
884
885		err = slb_allocate_user(mm, ea);
886		if (!err)
887			preload_add(current_thread_info(), ea);
888
889		return err;
890	}
891}
892
893void do_bad_slb_fault(struct pt_regs *regs, unsigned long ea, long err)
894{
895	if (err == -EFAULT) {
896		if (user_mode(regs))
897			_exception(SIGSEGV, regs, SEGV_BNDERR, ea);
898		else
899			bad_page_fault(regs, ea, SIGSEGV);
900	} else if (err == -EINVAL) {
901		unrecoverable_exception(regs);
902	} else {
903		BUG();
904	}
905}
906