Blame view
drivers/clocksource/hyperv_timer.c
12.5 KB
fd1fea683
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 |
// SPDX-License-Identifier: GPL-2.0 /* * Clocksource driver for the synthetic counter and timers * provided by the Hyper-V hypervisor to guest VMs, as described * in the Hyper-V Top Level Functional Spec (TLFS). This driver * is instruction set architecture independent. * * Copyright (C) 2019, Microsoft, Inc. * * Author: Michael Kelley <mikelley@microsoft.com> */ #include <linux/percpu.h> #include <linux/cpumask.h> #include <linux/clockchips.h> |
dd2cb3486
|
17 18 |
#include <linux/clocksource.h> #include <linux/sched_clock.h> |
fd1fea683
|
19 |
#include <linux/mm.h> |
4df4cb9e9
|
20 |
#include <linux/cpuhotplug.h> |
fd1fea683
|
21 22 23 24 25 |
#include <clocksource/hyperv_timer.h> #include <asm/hyperv-tlfs.h> #include <asm/mshyperv.h> static struct clock_event_device __percpu *hv_clock_event; |
bd00cd52d
|
26 |
static u64 hv_sched_clock_offset __ro_after_init; |
fd1fea683
|
27 28 29 30 31 32 33 |
/* * If false, we're using the old mechanism for stimer0 interrupts * where it sends a VMbus message when it expires. The old * mechanism is used when running on older versions of Hyper-V * that don't support Direct Mode. While Hyper-V provides * four stimer's per CPU, Linux uses only stimer0. |
4df4cb9e9
|
34 35 36 37 38 39 40 41 42 |
* * Because Direct Mode does not require processing a VMbus * message, stimer interrupts can be enabled earlier in the * process of booting a CPU, and consistent with when timer * interrupts are enabled for other clocksource drivers. * However, for legacy versions of Hyper-V when Direct Mode * is not enabled, setting up stimer interrupts must be * delayed until VMbus is initialized and can process the * interrupt message. |
fd1fea683
|
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 |
*/ static bool direct_mode_enabled; static int stimer0_irq; static int stimer0_vector; static int stimer0_message_sint; /* * ISR for when stimer0 is operating in Direct Mode. Direct Mode * does not use VMbus or any VMbus messages, so process here and not * in the VMbus driver code. */ void hv_stimer0_isr(void) { struct clock_event_device *ce; ce = this_cpu_ptr(hv_clock_event); ce->event_handler(ce); } EXPORT_SYMBOL_GPL(hv_stimer0_isr); static int hv_ce_set_next_event(unsigned long delta, struct clock_event_device *evt) { u64 current_tick; |
0af3e137c
|
68 |
current_tick = hv_read_reference_counter(); |
fd1fea683
|
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 |
current_tick += delta; hv_init_timer(0, current_tick); return 0; } static int hv_ce_shutdown(struct clock_event_device *evt) { hv_init_timer(0, 0); hv_init_timer_config(0, 0); if (direct_mode_enabled) hv_disable_stimer0_percpu_irq(stimer0_irq); return 0; } static int hv_ce_set_oneshot(struct clock_event_device *evt) { union hv_stimer_config timer_cfg; timer_cfg.as_uint64 = 0; timer_cfg.enable = 1; timer_cfg.auto_enable = 1; if (direct_mode_enabled) { /* * When it expires, the timer will directly interrupt * on the specified hardware vector/IRQ. */ timer_cfg.direct_mode = 1; timer_cfg.apic_vector = stimer0_vector; hv_enable_stimer0_percpu_irq(stimer0_irq); } else { /* * When it expires, the timer will generate a VMbus message, * to be handled by the normal VMbus interrupt handler. */ timer_cfg.direct_mode = 0; timer_cfg.sintx = stimer0_message_sint; } hv_init_timer_config(0, timer_cfg.as_uint64); return 0; } /* * hv_stimer_init - Per-cpu initialization of the clockevent */ |
4df4cb9e9
|
114 |
static int hv_stimer_init(unsigned int cpu) |
fd1fea683
|
115 116 |
{ struct clock_event_device *ce; |
4df4cb9e9
|
117 118 |
if (!hv_clock_event) return 0; |
fd1fea683
|
119 120 121 122 123 124 125 126 127 128 129 130 131 132 |
ce = per_cpu_ptr(hv_clock_event, cpu); ce->name = "Hyper-V clockevent"; ce->features = CLOCK_EVT_FEAT_ONESHOT; ce->cpumask = cpumask_of(cpu); ce->rating = 1000; ce->set_state_shutdown = hv_ce_shutdown; ce->set_state_oneshot = hv_ce_set_oneshot; ce->set_next_event = hv_ce_set_next_event; clockevents_config_and_register(ce, HV_CLOCK_HZ, HV_MIN_DELTA_TICKS, HV_MAX_MAX_DELTA_TICKS); |
4df4cb9e9
|
133 |
return 0; |
fd1fea683
|
134 |
} |
fd1fea683
|
135 136 137 138 |
/* * hv_stimer_cleanup - Per-cpu cleanup of the clockevent */ |
4df4cb9e9
|
139 |
int hv_stimer_cleanup(unsigned int cpu) |
fd1fea683
|
140 141 |
{ struct clock_event_device *ce; |
4df4cb9e9
|
142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 |
if (!hv_clock_event) return 0; /* * In the legacy case where Direct Mode is not enabled * (which can only be on x86/64), stimer cleanup happens * relatively early in the CPU offlining process. We * must unbind the stimer-based clockevent device so * that the LAPIC timer can take over until clockevents * are no longer needed in the offlining process. Note * that clockevents_unbind_device() eventually calls * hv_ce_shutdown(). * * The unbind should not be done when Direct Mode is * enabled because we may be on an architecture where * there are no other clockevent devices to fallback to. */ ce = per_cpu_ptr(hv_clock_event, cpu); if (direct_mode_enabled) |
fd1fea683
|
161 |
hv_ce_shutdown(ce); |
4df4cb9e9
|
162 163 164 165 |
else clockevents_unbind_device(ce, cpu); return 0; |
fd1fea683
|
166 167 168 169 |
} EXPORT_SYMBOL_GPL(hv_stimer_cleanup); /* hv_stimer_alloc - Global initialization of the clockevent and stimer0 */ |
4df4cb9e9
|
170 |
int hv_stimer_alloc(void) |
fd1fea683
|
171 |
{ |
4df4cb9e9
|
172 173 174 175 176 177 178 179 180 |
int ret = 0; /* * Synthetic timers are always available except on old versions of * Hyper-V on x86. In that case, return as error as Linux will use a * clockevent based on emulated LAPIC timer hardware. */ if (!(ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE)) return -EINVAL; |
fd1fea683
|
181 182 183 184 185 186 187 188 189 190 |
hv_clock_event = alloc_percpu(struct clock_event_device); if (!hv_clock_event) return -ENOMEM; direct_mode_enabled = ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE; if (direct_mode_enabled) { ret = hv_setup_stimer0_irq(&stimer0_irq, &stimer0_vector, hv_stimer0_isr); |
4df4cb9e9
|
191 192 193 194 195 196 197 198 199 200 201 202 203 |
if (ret) goto free_percpu; /* * Since we are in Direct Mode, stimer initialization * can be done now with a CPUHP value in the same range * as other clockevent devices. */ ret = cpuhp_setup_state(CPUHP_AP_HYPERV_TIMER_STARTING, "clockevents/hyperv/stimer:starting", hv_stimer_init, hv_stimer_cleanup); if (ret < 0) goto free_stimer0_irq; |
fd1fea683
|
204 |
} |
4df4cb9e9
|
205 |
return ret; |
fd1fea683
|
206 |
|
4df4cb9e9
|
207 208 209 210 211 212 213 |
free_stimer0_irq: hv_remove_stimer0_irq(stimer0_irq); stimer0_irq = 0; free_percpu: free_percpu(hv_clock_event); hv_clock_event = NULL; return ret; |
fd1fea683
|
214 215 |
} EXPORT_SYMBOL_GPL(hv_stimer_alloc); |
4df4cb9e9
|
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 |
/* * hv_stimer_legacy_init -- Called from the VMbus driver to handle * the case when Direct Mode is not enabled, and the stimer * must be initialized late in the CPU onlining process. * */ void hv_stimer_legacy_init(unsigned int cpu, int sint) { if (direct_mode_enabled) return; /* * This function gets called by each vCPU, so setting the * global stimer_message_sint value each time is conceptually * not ideal, but the value passed in is always the same and * it avoids introducing yet another interface into this * clocksource driver just to set the sint in the legacy case. */ stimer0_message_sint = sint; (void)hv_stimer_init(cpu); } EXPORT_SYMBOL_GPL(hv_stimer_legacy_init); /* * hv_stimer_legacy_cleanup -- Called from the VMbus driver to * handle the case when Direct Mode is not enabled, and the * stimer must be cleaned up early in the CPU offlining * process. */ void hv_stimer_legacy_cleanup(unsigned int cpu) { if (direct_mode_enabled) return; (void)hv_stimer_cleanup(cpu); } EXPORT_SYMBOL_GPL(hv_stimer_legacy_cleanup); |
fd1fea683
|
252 253 254 |
/* hv_stimer_free - Free global resources allocated by hv_stimer_alloc() */ void hv_stimer_free(void) { |
4df4cb9e9
|
255 256 257 258 259 |
if (!hv_clock_event) return; if (direct_mode_enabled) { cpuhp_remove_state(CPUHP_AP_HYPERV_TIMER_STARTING); |
fd1fea683
|
260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 |
hv_remove_stimer0_irq(stimer0_irq); stimer0_irq = 0; } free_percpu(hv_clock_event); hv_clock_event = NULL; } EXPORT_SYMBOL_GPL(hv_stimer_free); /* * Do a global cleanup of clockevents for the cases of kexec and * vmbus exit */ void hv_stimer_global_cleanup(void) { int cpu; |
fd1fea683
|
275 |
|
4df4cb9e9
|
276 277 278 279 280 281 |
/* * hv_stime_legacy_cleanup() will stop the stimer if Direct * Mode is not enabled, and fallback to the LAPIC timer. */ for_each_present_cpu(cpu) { hv_stimer_legacy_cleanup(cpu); |
fd1fea683
|
282 |
} |
4df4cb9e9
|
283 284 285 286 287 288 |
/* * If Direct Mode is enabled, the cpuhp teardown callback * (hv_stimer_cleanup) will be run on all CPUs to stop the * stimers. */ |
fd1fea683
|
289 290 291 |
hv_stimer_free(); } EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup); |
dd2cb3486
|
292 293 294 295 296 297 298 |
/* * Code and definitions for the Hyper-V clocksources. Two * clocksources are defined: one that reads the Hyper-V defined MSR, and * the other that uses the TSC reference page feature as defined in the * TLFS. The MSR version is for compatibility with old versions of * Hyper-V and 32-bit x86. The TSC reference page version is preferred. |
9e0333ae3
|
299 300 301 302 303 304 305 306 |
* * The Hyper-V clocksource ratings of 250 are chosen to be below the * TSC clocksource rating of 300. In configurations where Hyper-V offers * an InvariantTSC, the TSC is not marked "unstable", so the TSC clocksource * is available and preferred. With the higher rating, it will be the * default. On older hardware and Hyper-V versions, the TSC is marked * "unstable", so no TSC clocksource is created and the selected Hyper-V * clocksource will be the default. |
dd2cb3486
|
307 |
*/ |
0af3e137c
|
308 309 |
u64 (*hv_read_reference_counter)(void); EXPORT_SYMBOL_GPL(hv_read_reference_counter); |
dd2cb3486
|
310 |
|
ddc61bbc4
|
311 312 313 314 |
static union { struct ms_hyperv_tsc_page page; u8 reserved[PAGE_SIZE]; } tsc_pg __aligned(PAGE_SIZE); |
dd2cb3486
|
315 316 317 |
struct ms_hyperv_tsc_page *hv_get_tsc_page(void) { |
ddc61bbc4
|
318 |
return &tsc_pg.page; |
dd2cb3486
|
319 320 |
} EXPORT_SYMBOL_GPL(hv_get_tsc_page); |
0af3e137c
|
321 |
static u64 notrace read_hv_clock_tsc(void) |
dd2cb3486
|
322 |
{ |
ddc61bbc4
|
323 |
u64 current_tick = hv_read_tsc_page(hv_get_tsc_page()); |
dd2cb3486
|
324 325 326 327 328 329 |
if (current_tick == U64_MAX) hv_get_time_ref_count(current_tick); return current_tick; } |
0af3e137c
|
330 331 332 333 |
static u64 notrace read_hv_clock_tsc_cs(struct clocksource *arg) { return read_hv_clock_tsc(); } |
1f3aed014
|
334 |
static u64 notrace read_hv_sched_clock_tsc(void) |
dd2cb3486
|
335 |
{ |
749da8ca9
|
336 337 |
return (read_hv_clock_tsc() - hv_sched_clock_offset) * (NSEC_PER_SEC / HV_CLOCK_HZ); |
dd2cb3486
|
338 |
} |
1349401ff
|
339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 |
static void suspend_hv_clock_tsc(struct clocksource *arg) { u64 tsc_msr; /* Disable the TSC page */ hv_get_reference_tsc(tsc_msr); tsc_msr &= ~BIT_ULL(0); hv_set_reference_tsc(tsc_msr); } static void resume_hv_clock_tsc(struct clocksource *arg) { phys_addr_t phys_addr = virt_to_phys(&tsc_pg); u64 tsc_msr; /* Re-enable the TSC page */ hv_get_reference_tsc(tsc_msr); tsc_msr &= GENMASK_ULL(11, 0); tsc_msr |= BIT_ULL(0) | (u64)phys_addr; hv_set_reference_tsc(tsc_msr); } |
eec399dd8
|
361 362 363 364 365 |
static int hv_cs_enable(struct clocksource *cs) { hv_enable_vdso_clocksource(); return 0; } |
dd2cb3486
|
366 367 |
static struct clocksource hyperv_cs_tsc = { .name = "hyperv_clocksource_tsc_page", |
9e0333ae3
|
368 |
.rating = 250, |
0af3e137c
|
369 |
.read = read_hv_clock_tsc_cs, |
dd2cb3486
|
370 371 |
.mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS, |
1349401ff
|
372 373 |
.suspend= suspend_hv_clock_tsc, .resume = resume_hv_clock_tsc, |
eec399dd8
|
374 |
.enable = hv_cs_enable, |
dd2cb3486
|
375 |
}; |
dd2cb3486
|
376 |
|
0af3e137c
|
377 |
static u64 notrace read_hv_clock_msr(void) |
dd2cb3486
|
378 379 380 381 382 383 384 385 386 387 |
{ u64 current_tick; /* * Read the partition counter to get the current tick count. This count * is set to 0 when the partition is created and is incremented in * 100 nanosecond units. */ hv_get_time_ref_count(current_tick); return current_tick; } |
0af3e137c
|
388 389 390 391 |
static u64 notrace read_hv_clock_msr_cs(struct clocksource *arg) { return read_hv_clock_msr(); } |
1f3aed014
|
392 |
static u64 notrace read_hv_sched_clock_msr(void) |
dd2cb3486
|
393 |
{ |
749da8ca9
|
394 395 |
return (read_hv_clock_msr() - hv_sched_clock_offset) * (NSEC_PER_SEC / HV_CLOCK_HZ); |
dd2cb3486
|
396 397 398 399 |
} static struct clocksource hyperv_cs_msr = { .name = "hyperv_clocksource_msr", |
9e0333ae3
|
400 |
.rating = 250, |
0af3e137c
|
401 |
.read = read_hv_clock_msr_cs, |
dd2cb3486
|
402 403 404 |
.mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS, }; |
dd2cb3486
|
405 406 407 408 409 410 411 |
static bool __init hv_init_tsc_clocksource(void) { u64 tsc_msr; phys_addr_t phys_addr; if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) return false; |
0af3e137c
|
412 |
hv_read_reference_counter = read_hv_clock_tsc; |
ddc61bbc4
|
413 |
phys_addr = virt_to_phys(hv_get_tsc_page()); |
dd2cb3486
|
414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 |
/* * The Hyper-V TLFS specifies to preserve the value of reserved * bits in registers. So read the existing value, preserve the * low order 12 bits, and add in the guest physical address * (which already has at least the low 12 bits set to zero since * it is page aligned). Also set the "enable" bit, which is bit 0. */ hv_get_reference_tsc(tsc_msr); tsc_msr &= GENMASK_ULL(11, 0); tsc_msr = tsc_msr | 0x1 | (u64)phys_addr; hv_set_reference_tsc(tsc_msr); hv_set_clocksource_vdso(hyperv_cs_tsc); clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100); |
0af3e137c
|
429 |
hv_sched_clock_offset = hv_read_reference_counter(); |
bd00cd52d
|
430 |
hv_setup_sched_clock(read_hv_sched_clock_tsc); |
dd2cb3486
|
431 432 |
return true; } |
dd2cb3486
|
433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 |
void __init hv_init_clocksource(void) { /* * Try to set up the TSC page clocksource. If it succeeds, we're * done. Otherwise, set up the MSR clocksoruce. At least one of * these will always be available except on very old versions of * Hyper-V on x86. In that case we won't have a Hyper-V * clocksource, but Linux will still run with a clocksource based * on the emulated PIT or LAPIC timer. */ if (hv_init_tsc_clocksource()) return; if (!(ms_hyperv.features & HV_MSR_TIME_REF_COUNT_AVAILABLE)) return; |
0af3e137c
|
449 |
hv_read_reference_counter = read_hv_clock_msr; |
dd2cb3486
|
450 |
clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100); |
0af3e137c
|
451 |
hv_sched_clock_offset = hv_read_reference_counter(); |
bd00cd52d
|
452 |
hv_setup_sched_clock(read_hv_sched_clock_msr); |
dd2cb3486
|
453 454 |
} EXPORT_SYMBOL_GPL(hv_init_clocksource); |