xref: /kernel/linux/linux-6.6/arch/x86/xen/smp_pv.c (revision 62306a36) 
1// SPDX-License-Identifier: GPL-2.0
2/*
3 * Xen SMP support
4 *
5 * This file implements the Xen versions of smp_ops.  SMP under Xen is
6 * very straightforward.  Bringing a CPU up is simply a matter of
7 * loading its initial context and setting it running.
8 *
9 * IPIs are handled through the Xen event mechanism.
10 *
11 * Because virtual CPUs can be scheduled onto any real CPU, there's no
12 * useful topology information for the kernel to make use of.  As a
13 * result, all CPUs are treated as if they're single-core and
14 * single-threaded.
15 */
16#include <linux/sched.h>
17#include <linux/sched/task_stack.h>
18#include <linux/err.h>
19#include <linux/slab.h>
20#include <linux/smp.h>
21#include <linux/irq_work.h>
22#include <linux/tick.h>
23#include <linux/nmi.h>
24#include <linux/cpuhotplug.h>
25#include <linux/stackprotector.h>
26#include <linux/pgtable.h>
27
28#include <asm/paravirt.h>
29#include <asm/idtentry.h>
30#include <asm/desc.h>
31#include <asm/cpu.h>
32#include <asm/io_apic.h>
33
34#include <xen/interface/xen.h>
35#include <xen/interface/vcpu.h>
36#include <xen/interface/xenpmu.h>
37
38#include <asm/spec-ctrl.h>
39#include <asm/xen/interface.h>
40#include <asm/xen/hypercall.h>
41
42#include <xen/xen.h>
43#include <xen/page.h>
44#include <xen/events.h>
45
46#include <xen/hvc-console.h>
47#include "xen-ops.h"
48#include "mmu.h"
49#include "smp.h"
50#include "pmu.h"
51
52cpumask_var_t xen_cpu_initialized_map;
53
54static DEFINE_PER_CPU(struct xen_common_irq, xen_irq_work) = { .irq = -1 };
55static DEFINE_PER_CPU(struct xen_common_irq, xen_pmu_irq) = { .irq = -1 };
56
57static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id);
58
59static void cpu_bringup(void)
60{
61	int cpu;
62
63	cr4_init();
64	cpuhp_ap_sync_alive();
65	cpu_init();
66	fpu__init_cpu();
67	touch_softlockup_watchdog();
68
69	/* PVH runs in ring 0 and allows us to do native syscalls. Yay! */
70	if (!xen_feature(XENFEAT_supervisor_mode_kernel)) {
71		xen_enable_sysenter();
72		xen_enable_syscall();
73	}
74	cpu = smp_processor_id();
75	smp_store_cpu_info(cpu);
76	cpu_data(cpu).x86_max_cores = 1;
77	set_cpu_sibling_map(cpu);
78
79	speculative_store_bypass_ht_init();
80
81	xen_setup_cpu_clockevents();
82
83	notify_cpu_starting(cpu);
84
85	set_cpu_online(cpu, true);
86
87	smp_mb();
88
89	/* We can take interrupts now: we're officially "up". */
90	local_irq_enable();
91}
92
93asmlinkage __visible void cpu_bringup_and_idle(void)
94{
95	cpu_bringup();
96	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
97}
98
99void xen_smp_intr_free_pv(unsigned int cpu)
100{
101	kfree(per_cpu(xen_irq_work, cpu).name);
102	per_cpu(xen_irq_work, cpu).name = NULL;
103	if (per_cpu(xen_irq_work, cpu).irq >= 0) {
104		unbind_from_irqhandler(per_cpu(xen_irq_work, cpu).irq, NULL);
105		per_cpu(xen_irq_work, cpu).irq = -1;
106	}
107
108	kfree(per_cpu(xen_pmu_irq, cpu).name);
109	per_cpu(xen_pmu_irq, cpu).name = NULL;
110	if (per_cpu(xen_pmu_irq, cpu).irq >= 0) {
111		unbind_from_irqhandler(per_cpu(xen_pmu_irq, cpu).irq, NULL);
112		per_cpu(xen_pmu_irq, cpu).irq = -1;
113	}
114}
115
116int xen_smp_intr_init_pv(unsigned int cpu)
117{
118	int rc;
119	char *callfunc_name, *pmu_name;
120
121	callfunc_name = kasprintf(GFP_KERNEL, "irqwork%d", cpu);
122	per_cpu(xen_irq_work, cpu).name = callfunc_name;
123	rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR,
124				    cpu,
125				    xen_irq_work_interrupt,
126				    IRQF_PERCPU|IRQF_NOBALANCING,
127				    callfunc_name,
128				    NULL);
129	if (rc < 0)
130		goto fail;
131	per_cpu(xen_irq_work, cpu).irq = rc;
132
133	if (is_xen_pmu) {
134		pmu_name = kasprintf(GFP_KERNEL, "pmu%d", cpu);
135		per_cpu(xen_pmu_irq, cpu).name = pmu_name;
136		rc = bind_virq_to_irqhandler(VIRQ_XENPMU, cpu,
137					     xen_pmu_irq_handler,
138					     IRQF_PERCPU|IRQF_NOBALANCING,
139					     pmu_name, NULL);
140		if (rc < 0)
141			goto fail;
142		per_cpu(xen_pmu_irq, cpu).irq = rc;
143	}
144
145	return 0;
146
147 fail:
148	xen_smp_intr_free_pv(cpu);
149	return rc;
150}
151
152static void __init _get_smp_config(unsigned int early)
153{
154	int i, rc;
155	unsigned int subtract = 0;
156
157	if (early)
158		return;
159
160	num_processors = 0;
161	disabled_cpus = 0;
162	for (i = 0; i < nr_cpu_ids; i++) {
163		rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL);
164		if (rc >= 0) {
165			num_processors++;
166			set_cpu_possible(i, true);
167		} else {
168			set_cpu_possible(i, false);
169			set_cpu_present(i, false);
170			subtract++;
171		}
172	}
173#ifdef CONFIG_HOTPLUG_CPU
174	/* This is akin to using 'nr_cpus' on the Linux command line.
175	 * Which is OK as when we use 'dom0_max_vcpus=X' we can only
176	 * have up to X, while nr_cpu_ids is greater than X. This
177	 * normally is not a problem, except when CPU hotplugging
178	 * is involved and then there might be more than X CPUs
179	 * in the guest - which will not work as there is no
180	 * hypercall to expand the max number of VCPUs an already
181	 * running guest has. So cap it up to X. */
182	if (subtract)
183		set_nr_cpu_ids(nr_cpu_ids - subtract);
184#endif
185	/* Pretend to be a proper enumerated system */
186	smp_found_config = 1;
187}
188
189static void __init xen_pv_smp_prepare_boot_cpu(void)
190{
191	BUG_ON(smp_processor_id() != 0);
192	native_smp_prepare_boot_cpu();
193
194	if (!xen_feature(XENFEAT_writable_page_tables))
195		/* We've switched to the "real" per-cpu gdt, so make
196		 * sure the old memory can be recycled. */
197		make_lowmem_page_readwrite(xen_initial_gdt);
198
199	xen_setup_vcpu_info_placement();
200
201	/*
202	 * The alternative logic (which patches the unlock/lock) runs before
203	 * the smp bootup up code is activated. Hence we need to set this up
204	 * the core kernel is being patched. Otherwise we will have only
205	 * modules patched but not core code.
206	 */
207	xen_init_spinlocks();
208}
209
210static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus)
211{
212	unsigned cpu;
213
214	if (ioapic_is_disabled) {
215		char *m = (max_cpus == 0) ?
216			"The nosmp parameter is incompatible with Xen; " \
217			"use Xen dom0_max_vcpus=1 parameter" :
218			"The noapic parameter is incompatible with Xen";
219
220		xen_raw_printk(m);
221		panic(m);
222	}
223	xen_init_lock_cpu(0);
224
225	smp_prepare_cpus_common();
226
227	cpu_data(0).x86_max_cores = 1;
228
229	speculative_store_bypass_ht_init();
230
231	xen_pmu_init(0);
232
233	if (xen_smp_intr_init(0) || xen_smp_intr_init_pv(0))
234		BUG();
235
236	if (!alloc_cpumask_var(&xen_cpu_initialized_map, GFP_KERNEL))
237		panic("could not allocate xen_cpu_initialized_map\n");
238
239	cpumask_copy(xen_cpu_initialized_map, cpumask_of(0));
240
241	/* Restrict the possible_map according to max_cpus. */
242	while ((num_possible_cpus() > 1) && (num_possible_cpus() > max_cpus)) {
243		for (cpu = nr_cpu_ids - 1; !cpu_possible(cpu); cpu--)
244			continue;
245		set_cpu_possible(cpu, false);
246	}
247
248	for_each_possible_cpu(cpu)
249		set_cpu_present(cpu, true);
250}
251
252static int
253cpu_initialize_context(unsigned int cpu, struct task_struct *idle)
254{
255	struct vcpu_guest_context *ctxt;
256	struct desc_struct *gdt;
257	unsigned long gdt_mfn;
258
259	if (cpumask_test_and_set_cpu(cpu, xen_cpu_initialized_map))
260		return 0;
261
262	ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL);
263	if (ctxt == NULL) {
264		cpumask_clear_cpu(cpu, xen_cpu_initialized_map);
265		return -ENOMEM;
266	}
267
268	gdt = get_cpu_gdt_rw(cpu);
269
270	/*
271	 * Bring up the CPU in cpu_bringup_and_idle() with the stack
272	 * pointing just below where pt_regs would be if it were a normal
273	 * kernel entry.
274	 */
275	ctxt->user_regs.eip = (unsigned long)asm_cpu_bringup_and_idle;
276	ctxt->flags = VGCF_IN_KERNEL;
277	ctxt->user_regs.eflags = 0x1000; /* IOPL_RING1 */
278	ctxt->user_regs.ds = __USER_DS;
279	ctxt->user_regs.es = __USER_DS;
280	ctxt->user_regs.ss = __KERNEL_DS;
281	ctxt->user_regs.cs = __KERNEL_CS;
282	ctxt->user_regs.esp = (unsigned long)task_pt_regs(idle);
283
284	xen_copy_trap_info(ctxt->trap_ctxt);
285
286	BUG_ON((unsigned long)gdt & ~PAGE_MASK);
287
288	gdt_mfn = arbitrary_virt_to_mfn(gdt);
289	make_lowmem_page_readonly(gdt);
290	make_lowmem_page_readonly(mfn_to_virt(gdt_mfn));
291
292	ctxt->gdt_frames[0] = gdt_mfn;
293	ctxt->gdt_ents      = GDT_ENTRIES;
294
295	/*
296	 * Set SS:SP that Xen will use when entering guest kernel mode
297	 * from guest user mode.  Subsequent calls to load_sp0() can
298	 * change this value.
299	 */
300	ctxt->kernel_ss = __KERNEL_DS;
301	ctxt->kernel_sp = task_top_of_stack(idle);
302
303	ctxt->gs_base_kernel = per_cpu_offset(cpu);
304	ctxt->event_callback_eip    =
305		(unsigned long)xen_asm_exc_xen_hypervisor_callback;
306	ctxt->failsafe_callback_eip =
307		(unsigned long)xen_failsafe_callback;
308	per_cpu(xen_cr3, cpu) = __pa(swapper_pg_dir);
309
310	ctxt->ctrlreg[3] = xen_pfn_to_cr3(virt_to_gfn(swapper_pg_dir));
311	if (HYPERVISOR_vcpu_op(VCPUOP_initialise, xen_vcpu_nr(cpu), ctxt))
312		BUG();
313
314	kfree(ctxt);
315	return 0;
316}
317
318static int xen_pv_kick_ap(unsigned int cpu, struct task_struct *idle)
319{
320	int rc;
321
322	rc = common_cpu_up(cpu, idle);
323	if (rc)
324		return rc;
325
326	xen_setup_runstate_info(cpu);
327
328	/* make sure interrupts start blocked */
329	per_cpu(xen_vcpu, cpu)->evtchn_upcall_mask = 1;
330
331	rc = cpu_initialize_context(cpu, idle);
332	if (rc)
333		return rc;
334
335	xen_pmu_init(cpu);
336
337	/*
338	 * Why is this a BUG? If the hypercall fails then everything can be
339	 * rolled back, no?
340	 */
341	BUG_ON(HYPERVISOR_vcpu_op(VCPUOP_up, xen_vcpu_nr(cpu), NULL));
342
343	return 0;
344}
345
346static void xen_pv_poll_sync_state(void)
347{
348	HYPERVISOR_sched_op(SCHEDOP_yield, NULL);
349}
350
351#ifdef CONFIG_HOTPLUG_CPU
352static int xen_pv_cpu_disable(void)
353{
354	unsigned int cpu = smp_processor_id();
355	if (cpu == 0)
356		return -EBUSY;
357
358	cpu_disable_common();
359
360	load_cr3(swapper_pg_dir);
361	return 0;
362}
363
364static void xen_pv_cpu_die(unsigned int cpu)
365{
366	while (HYPERVISOR_vcpu_op(VCPUOP_is_up, xen_vcpu_nr(cpu), NULL)) {
367		__set_current_state(TASK_UNINTERRUPTIBLE);
368		schedule_timeout(HZ/10);
369	}
370}
371
372static void xen_pv_cleanup_dead_cpu(unsigned int cpu)
373{
374	xen_smp_intr_free(cpu);
375	xen_uninit_lock_cpu(cpu);
376	xen_teardown_timer(cpu);
377	xen_pmu_finish(cpu);
378}
379
380static void __noreturn xen_pv_play_dead(void) /* used only with HOTPLUG_CPU */
381{
382	play_dead_common();
383	HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(smp_processor_id()), NULL);
384	xen_cpu_bringup_again((unsigned long)task_pt_regs(current));
385	BUG();
386}
387
388#else /* !CONFIG_HOTPLUG_CPU */
389static int xen_pv_cpu_disable(void)
390{
391	return -ENOSYS;
392}
393
394static void xen_pv_cpu_die(unsigned int cpu)
395{
396	BUG();
397}
398
399static void xen_pv_cleanup_dead_cpu(unsigned int cpu)
400{
401	BUG();
402}
403
404static void __noreturn xen_pv_play_dead(void)
405{
406	BUG();
407}
408
409#endif
410static void stop_self(void *v)
411{
412	int cpu = smp_processor_id();
413
414	/* make sure we're not pinning something down */
415	load_cr3(swapper_pg_dir);
416	/* should set up a minimal gdt */
417
418	set_cpu_online(cpu, false);
419
420	HYPERVISOR_vcpu_op(VCPUOP_down, xen_vcpu_nr(cpu), NULL);
421	BUG();
422}
423
424static void xen_pv_stop_other_cpus(int wait)
425{
426	smp_call_function(stop_self, NULL, wait);
427}
428
429static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id)
430{
431	irq_work_run();
432	inc_irq_stat(apic_irq_work_irqs);
433
434	return IRQ_HANDLED;
435}
436
437static const struct smp_ops xen_smp_ops __initconst = {
438	.smp_prepare_boot_cpu = xen_pv_smp_prepare_boot_cpu,
439	.smp_prepare_cpus = xen_pv_smp_prepare_cpus,
440	.smp_cpus_done = xen_smp_cpus_done,
441
442	.kick_ap_alive = xen_pv_kick_ap,
443	.cpu_die = xen_pv_cpu_die,
444	.cleanup_dead_cpu = xen_pv_cleanup_dead_cpu,
445	.poll_sync_state = xen_pv_poll_sync_state,
446	.cpu_disable = xen_pv_cpu_disable,
447	.play_dead = xen_pv_play_dead,
448
449	.stop_other_cpus = xen_pv_stop_other_cpus,
450	.smp_send_reschedule = xen_smp_send_reschedule,
451
452	.send_call_func_ipi = xen_smp_send_call_function_ipi,
453	.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi,
454};
455
456void __init xen_smp_init(void)
457{
458	smp_ops = xen_smp_ops;
459
460	/* Avoid searching for BIOS MP tables */
461	x86_init.mpparse.find_smp_config = x86_init_noop;
462	x86_init.mpparse.get_smp_config = _get_smp_config;
463}
464