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
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
|
/*
*
* Common boot and setup code.
*
* Copyright (C) 2001 PPC64 Team, IBM Corp
*
* 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.
*/
#define DEBUG
#include <linux/export.h>
#include <linux/string.h>
#include <linux/sched.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/reboot.h>
#include <linux/delay.h>
#include <linux/initrd.h>
#include <linux/seq_file.h>
#include <linux/ioport.h>
#include <linux/console.h>
#include <linux/utsname.h>
#include <linux/tty.h>
#include <linux/root_dev.h>
#include <linux/notifier.h>
#include <linux/cpu.h>
#include <linux/unistd.h>
#include <linux/serial.h>
#include <linux/serial_8250.h>
#include <linux/bootmem.h>
#include <linux/pci.h>
#include <linux/lockdep.h>
#include <linux/memblock.h>
#include <linux/memory.h>
#include <linux/nmi.h>
#include <linux/debugfs.h>
#include <asm/io.h>
#include <asm/kdump.h>
#include <asm/prom.h>
#include <asm/processor.h>
#include <asm/pgtable.h>
#include <asm/smp.h>
#include <asm/elf.h>
#include <asm/machdep.h>
#include <asm/paca.h>
#include <asm/time.h>
#include <asm/cputable.h>
#include <asm/sections.h>
#include <asm/btext.h>
#include <asm/nvram.h>
#include <asm/setup.h>
#include <asm/rtas.h>
#include <asm/iommu.h>
#include <asm/serial.h>
#include <asm/cache.h>
#include <asm/page.h>
#include <asm/mmu.h>
#include <asm/firmware.h>
#include <asm/xmon.h>
#include <asm/udbg.h>
#include <asm/kexec.h>
#include <asm/code-patching.h>
#include <asm/livepatch.h>
#include <asm/opal.h>
#include <asm/cputhreads.h>
#ifdef DEBUG
#define DBG(fmt...) udbg_printf(fmt)
#else
#define DBG(fmt...)
#endif
int spinning_secondaries;
u64 ppc64_pft_size;
/* Pick defaults since we might want to patch instructions
* before we've read this from the device tree.
*/
struct ppc64_caches ppc64_caches = {
.dline_size = 0x40,
.log_dline_size = 6,
.iline_size = 0x40,
.log_iline_size = 6
};
EXPORT_SYMBOL_GPL(ppc64_caches);
/*
* These are used in binfmt_elf.c to put aux entries on the stack
* for each elf executable being started.
*/
int dcache_bsize;
int icache_bsize;
int ucache_bsize;
#if defined(CONFIG_PPC_BOOK3E) && defined(CONFIG_SMP)
void __init setup_tlb_core_data(void)
{
int cpu;
BUILD_BUG_ON(offsetof(struct tlb_core_data, lock) != 0);
for_each_possible_cpu(cpu) {
int first = cpu_first_thread_sibling(cpu);
/*
* If we boot via kdump on a non-primary thread,
* make sure we point at the thread that actually
* set up this TLB.
*/
if (cpu_first_thread_sibling(boot_cpuid) == first)
first = boot_cpuid;
paca[cpu].tcd_ptr = &paca[first].tcd;
/*
* If we have threads, we need either tlbsrx.
* or e6500 tablewalk mode, or else TLB handlers
* will be racy and could produce duplicate entries.
*/
if (smt_enabled_at_boot >= 2 &&
!mmu_has_feature(MMU_FTR_USE_TLBRSRV) &&
book3e_htw_mode != PPC_HTW_E6500) {
/* Should we panic instead? */
WARN_ONCE("%s: unsupported MMU configuration -- expect problems\n",
__func__);
}
}
}
#endif
#ifdef CONFIG_SMP
static char *smt_enabled_cmdline;
/* Look for ibm,smt-enabled OF option */
void __init check_smt_enabled(void)
{
struct device_node *dn;
const char *smt_option;
/* Default to enabling all threads */
smt_enabled_at_boot = threads_per_core;
/* Allow the command line to overrule the OF option */
if (smt_enabled_cmdline) {
if (!strcmp(smt_enabled_cmdline, "on"))
smt_enabled_at_boot = threads_per_core;
else if (!strcmp(smt_enabled_cmdline, "off"))
smt_enabled_at_boot = 0;
else {
int smt;
int rc;
rc = kstrtoint(smt_enabled_cmdline, 10, &smt);
if (!rc)
smt_enabled_at_boot =
min(threads_per_core, smt);
}
} else {
dn = of_find_node_by_path("/options");
if (dn) {
smt_option = of_get_property(dn, "ibm,smt-enabled",
NULL);
if (smt_option) {
if (!strcmp(smt_option, "on"))
smt_enabled_at_boot = threads_per_core;
else if (!strcmp(smt_option, "off"))
smt_enabled_at_boot = 0;
}
of_node_put(dn);
}
}
}
/* Look for smt-enabled= cmdline option */
static int __init early_smt_enabled(char *p)
{
smt_enabled_cmdline = p;
return 0;
}
early_param("smt-enabled", early_smt_enabled);
#endif /* CONFIG_SMP */
/** Fix up paca fields required for the boot cpu */
static void __init fixup_boot_paca(void)
{
/* The boot cpu is started */
get_paca()->cpu_start = 1;
/* Allow percpu accesses to work until we setup percpu data */
get_paca()->data_offset = 0;
}
static void __init configure_exceptions(void)
{
/*
* Setup the trampolines from the lowmem exception vectors
* to the kdump kernel when not using a relocatable kernel.
*/
setup_kdump_trampoline();
/* Under a PAPR hypervisor, we need hypercalls */
if (firmware_has_feature(FW_FEATURE_SET_MODE)) {
/* Enable AIL if possible */
pseries_enable_reloc_on_exc();
/*
* Tell the hypervisor that we want our exceptions to
* be taken in little endian mode.
*
* We don't call this for big endian as our calling convention
* makes us always enter in BE, and the call may fail under
* some circumstances with kdump.
*/
#ifdef __LITTLE_ENDIAN__
pseries_little_endian_exceptions();
#endif
} else {
/* Set endian mode using OPAL */
if (firmware_has_feature(FW_FEATURE_OPAL))
opal_configure_cores();
/* AIL on native is done in cpu_ready_for_interrupts() */
}
}
static void cpu_ready_for_interrupts(void)
{
/*
* Enable AIL if supported, and we are in hypervisor mode. This
* is called once for every processor.
*
* If we are not in hypervisor mode the job is done once for
* the whole partition in configure_exceptions().
*/
if (early_cpu_has_feature(CPU_FTR_HVMODE) &&
early_cpu_has_feature(CPU_FTR_ARCH_207S)) {
unsigned long lpcr = mfspr(SPRN_LPCR);
mtspr(SPRN_LPCR, lpcr | LPCR_AIL_3);
}
/*
* Fixup HFSCR:TM based on CPU features. The bit is set by our
* early asm init because at that point we haven't updated our
* CPU features from firmware and device-tree. Here we have,
* so let's do it.
*/
if (cpu_has_feature(CPU_FTR_HVMODE) && !cpu_has_feature(CPU_FTR_TM_COMP))
mtspr(SPRN_HFSCR, mfspr(SPRN_HFSCR) & ~HFSCR_TM);
/* Set IR and DR in PACA MSR */
get_paca()->kernel_msr = MSR_KERNEL;
}
/*
* Early initialization entry point. This is called by head.S
* with MMU translation disabled. We rely on the "feature" of
* the CPU that ignores the top 2 bits of the address in real
* mode so we can access kernel globals normally provided we
* only toy with things in the RMO region. From here, we do
* some early parsing of the device-tree to setup out MEMBLOCK
* data structures, and allocate & initialize the hash table
* and segment tables so we can start running with translation
* enabled.
*
* It is this function which will call the probe() callback of
* the various platform types and copy the matching one to the
* global ppc_md structure. Your platform can eventually do
* some very early initializations from the probe() routine, but
* this is not recommended, be very careful as, for example, the
* device-tree is not accessible via normal means at this point.
*/
void __init early_setup(unsigned long dt_ptr)
{
static __initdata struct paca_struct boot_paca;
/* -------- printk is _NOT_ safe to use here ! ------- */
/* Identify CPU type */
identify_cpu(0, mfspr(SPRN_PVR));
/* Assume we're on cpu 0 for now. Don't write to the paca yet! */
initialise_paca(&boot_paca, 0);
setup_paca(&boot_paca);
fixup_boot_paca();
/* -------- printk is now safe to use ------- */
/* Enable early debugging if any specified (see udbg.h) */
udbg_early_init();
DBG(" -> early_setup(), dt_ptr: 0x%lx\n", dt_ptr);
/*
* Do early initialization using the flattened device
* tree, such as retrieving the physical memory map or
* calculating/retrieving the hash table size.
*/
early_init_devtree(__va(dt_ptr));
/* Now we know the logical id of our boot cpu, setup the paca. */
setup_paca(&paca[boot_cpuid]);
fixup_boot_paca();
/*
* Configure exception handlers. This include setting up trampolines
* if needed, setting exception endian mode, etc...
*/
configure_exceptions();
/* Apply all the dynamic patching */
apply_feature_fixups();
setup_feature_keys();
/* Initialize the hash table or TLB handling */
early_init_mmu();
/*
* At this point, we can let interrupts switch to virtual mode
* (the MMU has been setup), so adjust the MSR in the PACA to
* have IR and DR set and enable AIL if it exists
*/
cpu_ready_for_interrupts();
DBG(" <- early_setup()\n");
#ifdef CONFIG_PPC_EARLY_DEBUG_BOOTX
/*
* This needs to be done *last* (after the above DBG() even)
*
* Right after we return from this function, we turn on the MMU
* which means the real-mode access trick that btext does will
* no longer work, it needs to switch to using a real MMU
* mapping. This call will ensure that it does
*/
btext_map();
#endif /* CONFIG_PPC_EARLY_DEBUG_BOOTX */
}
#ifdef CONFIG_SMP
void early_setup_secondary(void)
{
/* Mark interrupts disabled in PACA */
get_paca()->soft_enabled = 0;
/* Initialize the hash table or TLB handling */
early_init_mmu_secondary();
/*
* At this point, we can let interrupts switch to virtual mode
* (the MMU has been setup), so adjust the MSR in the PACA to
* have IR and DR set.
*/
cpu_ready_for_interrupts();
}
#endif /* CONFIG_SMP */
#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC)
static bool use_spinloop(void)
{
if (!IS_ENABLED(CONFIG_PPC_BOOK3E))
return true;
/*
* When book3e boots from kexec, the ePAPR spin table does
* not get used.
*/
return of_property_read_bool(of_chosen, "linux,booted-from-kexec");
}
void smp_release_cpus(void)
{
unsigned long *ptr;
int i;
if (!use_spinloop())
return;
DBG(" -> smp_release_cpus()\n");
/* All secondary cpus are spinning on a common spinloop, release them
* all now so they can start to spin on their individual paca
* spinloops. For non SMP kernels, the secondary cpus never get out
* of the common spinloop.
*/
ptr = (unsigned long *)((unsigned long)&__secondary_hold_spinloop
- PHYSICAL_START);
*ptr = ppc_function_entry(generic_secondary_smp_init);
/* And wait a bit for them to catch up */
for (i = 0; i < 100000; i++) {
mb();
HMT_low();
if (spinning_secondaries == 0)
break;
udelay(1);
}
DBG("spinning_secondaries = %d\n", spinning_secondaries);
DBG(" <- smp_release_cpus()\n");
}
#endif /* CONFIG_SMP || CONFIG_KEXEC */
/*
* Initialize some remaining members of the ppc64_caches and systemcfg
* structures
* (at least until we get rid of them completely). This is mostly some
* cache informations about the CPU that will be used by cache flush
* routines and/or provided to userland
*/
void __init initialize_cache_info(void)
{
struct device_node *np;
unsigned long num_cpus = 0;
DBG(" -> initialize_cache_info()\n");
for_each_node_by_type(np, "cpu") {
num_cpus += 1;
/*
* We're assuming *all* of the CPUs have the same
* d-cache and i-cache sizes... -Peter
*/
if (num_cpus == 1) {
const __be32 *sizep, *lsizep;
u32 size, lsize;
size = 0;
lsize = cur_cpu_spec->dcache_bsize;
sizep = of_get_property(np, "d-cache-size", NULL);
if (sizep != NULL)
size = be32_to_cpu(*sizep);
lsizep = of_get_property(np, "d-cache-block-size",
NULL);
/* fallback if block size missing */
if (lsizep == NULL)
lsizep = of_get_property(np,
"d-cache-line-size",
NULL);
if (lsizep != NULL)
lsize = be32_to_cpu(*lsizep);
if (sizep == NULL || lsizep == NULL)
DBG("Argh, can't find dcache properties ! "
"sizep: %p, lsizep: %p\n", sizep, lsizep);
ppc64_caches.dsize = size;
ppc64_caches.dline_size = lsize;
ppc64_caches.log_dline_size = __ilog2(lsize);
ppc64_caches.dlines_per_page = PAGE_SIZE / lsize;
size = 0;
lsize = cur_cpu_spec->icache_bsize;
sizep = of_get_property(np, "i-cache-size", NULL);
if (sizep != NULL)
size = be32_to_cpu(*sizep);
lsizep = of_get_property(np, "i-cache-block-size",
NULL);
if (lsizep == NULL)
lsizep = of_get_property(np,
"i-cache-line-size",
NULL);
if (lsizep != NULL)
lsize = be32_to_cpu(*lsizep);
if (sizep == NULL || lsizep == NULL)
DBG("Argh, can't find icache properties ! "
"sizep: %p, lsizep: %p\n", sizep, lsizep);
ppc64_caches.isize = size;
ppc64_caches.iline_size = lsize;
ppc64_caches.log_iline_size = __ilog2(lsize);
ppc64_caches.ilines_per_page = PAGE_SIZE / lsize;
}
}
/* For use by binfmt_elf */
dcache_bsize = ppc64_caches.dline_size;
icache_bsize = ppc64_caches.iline_size;
DBG(" <- initialize_cache_info()\n");
}
/* This returns the limit below which memory accesses to the linear
* mapping are guarnateed not to cause a TLB or SLB miss. This is
* used to allocate interrupt or emergency stacks for which our
* exception entry path doesn't deal with being interrupted.
*/
static __init u64 safe_stack_limit(void)
{
#ifdef CONFIG_PPC_BOOK3E
/* Freescale BookE bolts the entire linear mapping */
if (mmu_has_feature(MMU_FTR_TYPE_FSL_E))
return linear_map_top;
/* Other BookE, we assume the first GB is bolted */
return 1ul << 30;
#else
/* BookS, the first segment is bolted */
if (mmu_has_feature(MMU_FTR_1T_SEGMENT))
return 1UL << SID_SHIFT_1T;
return 1UL << SID_SHIFT;
#endif
}
void __init irqstack_early_init(void)
{
u64 limit = safe_stack_limit();
unsigned int i;
/*
* Interrupt stacks must be in the first segment since we
* cannot afford to take SLB misses on them.
*/
for_each_possible_cpu(i) {
softirq_ctx[i] = (struct thread_info *)
__va(memblock_alloc_base(THREAD_SIZE,
THREAD_SIZE, limit));
hardirq_ctx[i] = (struct thread_info *)
__va(memblock_alloc_base(THREAD_SIZE,
THREAD_SIZE, limit));
}
}
#ifdef CONFIG_PPC_BOOK3E
void __init exc_lvl_early_init(void)
{
unsigned int i;
unsigned long sp;
for_each_possible_cpu(i) {
sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE);
critirq_ctx[i] = (struct thread_info *)__va(sp);
paca[i].crit_kstack = __va(sp + THREAD_SIZE);
sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE);
dbgirq_ctx[i] = (struct thread_info *)__va(sp);
paca[i].dbg_kstack = __va(sp + THREAD_SIZE);
sp = memblock_alloc(THREAD_SIZE, THREAD_SIZE);
mcheckirq_ctx[i] = (struct thread_info *)__va(sp);
paca[i].mc_kstack = __va(sp + THREAD_SIZE);
}
if (cpu_has_feature(CPU_FTR_DEBUG_LVL_EXC))
patch_exception(0x040, exc_debug_debug_book3e);
}
#endif
/*
* Stack space used when we detect a bad kernel stack pointer, and
* early in SMP boots before relocation is enabled. Exclusive emergency
* stack for machine checks.
*/
void __init emergency_stack_init(void)
{
u64 limit;
unsigned int i;
/*
* Emergency stacks must be under 256MB, we cannot afford to take
* SLB misses on them. The ABI also requires them to be 128-byte
* aligned.
*
* Since we use these as temporary stacks during secondary CPU
* bringup, we need to get at them in real mode. This means they
* must also be within the RMO region.
*/
limit = min(safe_stack_limit(), ppc64_rma_size);
for_each_possible_cpu(i) {
struct thread_info *ti;
ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
klp_init_thread_info(ti);
paca[i].emergency_sp = (void *)ti + THREAD_SIZE;
#ifdef CONFIG_PPC_BOOK3S_64
/* emergency stack for machine check exception handling. */
ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
klp_init_thread_info(ti);
paca[i].mc_emergency_sp = (void *)ti + THREAD_SIZE;
#endif
}
}
#ifdef CONFIG_SMP
#define PCPU_DYN_SIZE ()
static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
{
return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align,
__pa(MAX_DMA_ADDRESS));
}
static void __init pcpu_fc_free(void *ptr, size_t size)
{
free_bootmem(__pa(ptr), size);
}
static int pcpu_cpu_distance(unsigned int from, unsigned int to)
{
if (cpu_to_node(from) == cpu_to_node(to))
return LOCAL_DISTANCE;
else
return REMOTE_DISTANCE;
}
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(__per_cpu_offset);
void __init setup_per_cpu_areas(void)
{
const size_t dyn_size = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
size_t atom_size;
unsigned long delta;
unsigned int cpu;
int rc;
/*
* Linear mapping is one of 4K, 1M and 16M. For 4K, no need
* to group units. For larger mappings, use 1M atom which
* should be large enough to contain a number of units.
*/
if (mmu_linear_psize == MMU_PAGE_4K)
atom_size = PAGE_SIZE;
else
atom_size = 1 << 20;
rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance,
pcpu_fc_alloc, pcpu_fc_free);
if (rc < 0)
panic("cannot initialize percpu area (err=%d)", rc);
delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
for_each_possible_cpu(cpu) {
__per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
paca[cpu].data_offset = __per_cpu_offset[cpu];
}
}
#endif
#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
unsigned long memory_block_size_bytes(void)
{
if (ppc_md.memory_block_size)
return ppc_md.memory_block_size();
return MIN_MEMORY_BLOCK_SIZE;
}
#endif
#if defined(CONFIG_PPC_INDIRECT_PIO) || defined(CONFIG_PPC_INDIRECT_MMIO)
struct ppc_pci_io ppc_pci_io;
EXPORT_SYMBOL(ppc_pci_io);
#endif
#ifdef CONFIG_HARDLOCKUP_DETECTOR
u64 hw_nmi_get_sample_period(int watchdog_thresh)
{
return ppc_proc_freq * watchdog_thresh;
}
/*
* The hardlockup detector breaks PMU event based branches and is likely
* to get false positives in KVM guests, so disable it by default.
*/
static int __init disable_hardlockup_detector(void)
{
hardlockup_detector_disable();
return 0;
}
early_initcall(disable_hardlockup_detector);
#endif /* CONFIG_HARDLOCKUP_DETECTOR */
#ifdef CONFIG_PPC_BOOK3S_64
static enum l1d_flush_type enabled_flush_types;
static void *l1d_flush_fallback_area;
static bool no_rfi_flush;
bool rfi_flush;
static int __init handle_no_rfi_flush(char *p)
{
pr_info("rfi-flush: disabled on command line.");
no_rfi_flush = true;
return 0;
}
early_param("no_rfi_flush", handle_no_rfi_flush);
/*
* The RFI flush is not KPTI, but because users will see doco that says to use
* nopti we hijack that option here to also disable the RFI flush.
*/
static int __init handle_no_pti(char *p)
{
pr_info("rfi-flush: disabling due to 'nopti' on command line.\n");
handle_no_rfi_flush(NULL);
return 0;
}
early_param("nopti", handle_no_pti);
static void do_nothing(void *unused)
{
/*
* We don't need to do the flush explicitly, just enter+exit kernel is
* sufficient, the RFI exit handlers will do the right thing.
*/
}
void rfi_flush_enable(bool enable)
{
if (enable) {
do_rfi_flush_fixups(enabled_flush_types);
on_each_cpu(do_nothing, NULL, 1);
} else
do_rfi_flush_fixups(L1D_FLUSH_NONE);
rfi_flush = enable;
}
static void init_fallback_flush(void)
{
u64 l1d_size, limit;
int cpu;
/* Only allocate the fallback flush area once (at boot time). */
if (l1d_flush_fallback_area)
return;
l1d_size = ppc64_caches.dsize;
limit = min(safe_stack_limit(), ppc64_rma_size);
/*
* Align to L1d size, and size it at 2x L1d size, to catch possible
* hardware prefetch runoff. We don't have a recipe for load patterns to
* reliably avoid the prefetcher.
*/
l1d_flush_fallback_area = __va(memblock_alloc_base(l1d_size * 2, l1d_size, limit));
memset(l1d_flush_fallback_area, 0, l1d_size * 2);
for_each_possible_cpu(cpu) {
paca[cpu].rfi_flush_fallback_area = l1d_flush_fallback_area;
paca[cpu].l1d_flush_size = l1d_size;
}
}
void setup_rfi_flush(enum l1d_flush_type types, bool enable)
{
if (types & L1D_FLUSH_FALLBACK) {
pr_info("rfi-flush: Using fallback displacement flush\n");
init_fallback_flush();
}
if (types & L1D_FLUSH_ORI)
pr_info("rfi-flush: Using ori type flush\n");
if (types & L1D_FLUSH_MTTRIG)
pr_info("rfi-flush: Using mttrig type flush\n");
enabled_flush_types = types;
if (!no_rfi_flush)
rfi_flush_enable(enable);
}
#ifdef CONFIG_DEBUG_FS
static int rfi_flush_set(void *data, u64 val)
{
bool enable;
if (val == 1)
enable = true;
else if (val == 0)
enable = false;
else
return -EINVAL;
/* Only do anything if we're changing state */
if (enable != rfi_flush)
rfi_flush_enable(enable);
return 0;
}
static int rfi_flush_get(void *data, u64 *val)
{
*val = rfi_flush ? 1 : 0;
return 0;
}
DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n");
static __init int rfi_flush_debugfs_init(void)
{
debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush);
return 0;
}
device_initcall(rfi_flush_debugfs_init);
#endif
ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf)
{
if (rfi_flush)
return sprintf(buf, "Mitigation: RFI Flush\n");
return sprintf(buf, "Vulnerable\n");
}
#endif /* CONFIG_PPC_BOOK3S_64 */
|