| // SPDX-License-Identifier: GPL-2.0-only |
| /* |
| * Copyright (c) 2009, Microsoft Corporation. |
| * |
| * Authors: |
| * Haiyang Zhang <haiyangz@microsoft.com> |
| * Hank Janssen <hjanssen@microsoft.com> |
| */ |
| #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt |
| |
| #include <linux/kernel.h> |
| #include <linux/mm.h> |
| #include <linux/slab.h> |
| #include <linux/vmalloc.h> |
| #include <linux/hyperv.h> |
| #include <linux/version.h> |
| #include <linux/random.h> |
| #include <linux/clockchips.h> |
| #include <asm/mshyperv.h> |
| #include "hyperv_vmbus.h" |
| |
| /* The one and only */ |
| struct hv_context hv_context; |
| |
| /* |
| * 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. |
| */ |
| static bool direct_mode_enabled; |
| static int stimer0_irq; |
| static int stimer0_vector; |
| |
| #define HV_TIMER_FREQUENCY (10 * 1000 * 1000) /* 100ns period */ |
| #define HV_MAX_MAX_DELTA_TICKS 0xffffffff |
| #define HV_MIN_DELTA_TICKS 1 |
| |
| /* |
| * hv_init - Main initialization routine. |
| * |
| * This routine must be called before any other routines in here are called |
| */ |
| int hv_init(void) |
| { |
| hv_context.cpu_context = alloc_percpu(struct hv_per_cpu_context); |
| if (!hv_context.cpu_context) |
| return -ENOMEM; |
| |
| direct_mode_enabled = ms_hyperv.misc_features & |
| HV_STIMER_DIRECT_MODE_AVAILABLE; |
| return 0; |
| } |
| |
| /* |
| * hv_post_message - Post a message using the hypervisor message IPC. |
| * |
| * This involves a hypercall. |
| */ |
| int hv_post_message(union hv_connection_id connection_id, |
| enum hv_message_type message_type, |
| void *payload, size_t payload_size) |
| { |
| struct hv_input_post_message *aligned_msg; |
| struct hv_per_cpu_context *hv_cpu; |
| u64 status; |
| |
| if (payload_size > HV_MESSAGE_PAYLOAD_BYTE_COUNT) |
| return -EMSGSIZE; |
| |
| hv_cpu = get_cpu_ptr(hv_context.cpu_context); |
| aligned_msg = hv_cpu->post_msg_page; |
| aligned_msg->connectionid = connection_id; |
| aligned_msg->reserved = 0; |
| aligned_msg->message_type = message_type; |
| aligned_msg->payload_size = payload_size; |
| memcpy((void *)aligned_msg->payload, payload, payload_size); |
| |
| status = hv_do_hypercall(HVCALL_POST_MESSAGE, aligned_msg, NULL); |
| |
| /* Preemption must remain disabled until after the hypercall |
| * so some other thread can't get scheduled onto this cpu and |
| * corrupt the per-cpu post_msg_page |
| */ |
| put_cpu_ptr(hv_cpu); |
| |
| return status & 0xFFFF; |
| } |
| |
| /* |
| * 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. |
| */ |
| |
| static void hv_stimer0_isr(void) |
| { |
| struct hv_per_cpu_context *hv_cpu; |
| |
| hv_cpu = this_cpu_ptr(hv_context.cpu_context); |
| hv_cpu->clk_evt->event_handler(hv_cpu->clk_evt); |
| add_interrupt_randomness(stimer0_vector, 0); |
| } |
| |
| static int hv_ce_set_next_event(unsigned long delta, |
| struct clock_event_device *evt) |
| { |
| u64 current_tick; |
| |
| WARN_ON(!clockevent_state_oneshot(evt)); |
| |
| current_tick = hyperv_cs->read(NULL); |
| 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 = VMBUS_MESSAGE_SINT; |
| } |
| hv_init_timer_config(0, timer_cfg.as_uint64); |
| return 0; |
| } |
| |
| static void hv_init_clockevent_device(struct clock_event_device *dev, int cpu) |
| { |
| dev->name = "Hyper-V clockevent"; |
| dev->features = CLOCK_EVT_FEAT_ONESHOT; |
| dev->cpumask = cpumask_of(cpu); |
| dev->rating = 1000; |
| /* |
| * Avoid settint dev->owner = THIS_MODULE deliberately as doing so will |
| * result in clockevents_config_and_register() taking additional |
| * references to the hv_vmbus module making it impossible to unload. |
| */ |
| |
| dev->set_state_shutdown = hv_ce_shutdown; |
| dev->set_state_oneshot = hv_ce_set_oneshot; |
| dev->set_next_event = hv_ce_set_next_event; |
| } |
| |
| |
| int hv_synic_alloc(void) |
| { |
| int cpu; |
| struct hv_per_cpu_context *hv_cpu; |
| |
| /* |
| * First, zero all per-cpu memory areas so hv_synic_free() can |
| * detect what memory has been allocated and cleanup properly |
| * after any failures. |
| */ |
| for_each_present_cpu(cpu) { |
| hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu); |
| memset(hv_cpu, 0, sizeof(*hv_cpu)); |
| } |
| |
| hv_context.hv_numa_map = kcalloc(nr_node_ids, sizeof(struct cpumask), |
| GFP_KERNEL); |
| if (hv_context.hv_numa_map == NULL) { |
| pr_err("Unable to allocate NUMA map\n"); |
| goto err; |
| } |
| |
| for_each_present_cpu(cpu) { |
| hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu); |
| |
| tasklet_init(&hv_cpu->msg_dpc, |
| vmbus_on_msg_dpc, (unsigned long) hv_cpu); |
| |
| hv_cpu->clk_evt = kzalloc(sizeof(struct clock_event_device), |
| GFP_KERNEL); |
| if (hv_cpu->clk_evt == NULL) { |
| pr_err("Unable to allocate clock event device\n"); |
| goto err; |
| } |
| hv_init_clockevent_device(hv_cpu->clk_evt, cpu); |
| |
| hv_cpu->synic_message_page = |
| (void *)get_zeroed_page(GFP_ATOMIC); |
| if (hv_cpu->synic_message_page == NULL) { |
| pr_err("Unable to allocate SYNIC message page\n"); |
| goto err; |
| } |
| |
| hv_cpu->synic_event_page = (void *)get_zeroed_page(GFP_ATOMIC); |
| if (hv_cpu->synic_event_page == NULL) { |
| pr_err("Unable to allocate SYNIC event page\n"); |
| goto err; |
| } |
| |
| hv_cpu->post_msg_page = (void *)get_zeroed_page(GFP_ATOMIC); |
| if (hv_cpu->post_msg_page == NULL) { |
| pr_err("Unable to allocate post msg page\n"); |
| goto err; |
| } |
| |
| INIT_LIST_HEAD(&hv_cpu->chan_list); |
| } |
| |
| if (direct_mode_enabled && |
| hv_setup_stimer0_irq(&stimer0_irq, &stimer0_vector, |
| hv_stimer0_isr)) |
| goto err; |
| |
| return 0; |
| err: |
| /* |
| * Any memory allocations that succeeded will be freed when |
| * the caller cleans up by calling hv_synic_free() |
| */ |
| return -ENOMEM; |
| } |
| |
| |
| void hv_synic_free(void) |
| { |
| int cpu; |
| |
| for_each_present_cpu(cpu) { |
| struct hv_per_cpu_context *hv_cpu |
| = per_cpu_ptr(hv_context.cpu_context, cpu); |
| |
| kfree(hv_cpu->clk_evt); |
| free_page((unsigned long)hv_cpu->synic_event_page); |
| free_page((unsigned long)hv_cpu->synic_message_page); |
| free_page((unsigned long)hv_cpu->post_msg_page); |
| } |
| |
| kfree(hv_context.hv_numa_map); |
| } |
| |
| /* |
| * hv_synic_init - Initialize the Synthetic Interrupt Controller. |
| * |
| * If it is already initialized by another entity (ie x2v shim), we need to |
| * retrieve the initialized message and event pages. Otherwise, we create and |
| * initialize the message and event pages. |
| */ |
| int hv_synic_init(unsigned int cpu) |
| { |
| struct hv_per_cpu_context *hv_cpu |
| = per_cpu_ptr(hv_context.cpu_context, cpu); |
| union hv_synic_simp simp; |
| union hv_synic_siefp siefp; |
| union hv_synic_sint shared_sint; |
| union hv_synic_scontrol sctrl; |
| |
| /* Setup the Synic's message page */ |
| hv_get_simp(simp.as_uint64); |
| simp.simp_enabled = 1; |
| simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page) |
| >> PAGE_SHIFT; |
| |
| hv_set_simp(simp.as_uint64); |
| |
| /* Setup the Synic's event page */ |
| hv_get_siefp(siefp.as_uint64); |
| siefp.siefp_enabled = 1; |
| siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page) |
| >> PAGE_SHIFT; |
| |
| hv_set_siefp(siefp.as_uint64); |
| |
| /* Setup the shared SINT. */ |
| hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64); |
| |
| shared_sint.vector = HYPERVISOR_CALLBACK_VECTOR; |
| shared_sint.masked = false; |
| if (ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED) |
| shared_sint.auto_eoi = false; |
| else |
| shared_sint.auto_eoi = true; |
| |
| hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64); |
| |
| /* Enable the global synic bit */ |
| hv_get_synic_state(sctrl.as_uint64); |
| sctrl.enable = 1; |
| |
| hv_set_synic_state(sctrl.as_uint64); |
| |
| /* |
| * Register the per-cpu clockevent source. |
| */ |
| if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) |
| clockevents_config_and_register(hv_cpu->clk_evt, |
| HV_TIMER_FREQUENCY, |
| HV_MIN_DELTA_TICKS, |
| HV_MAX_MAX_DELTA_TICKS); |
| return 0; |
| } |
| |
| /* |
| * hv_synic_clockevents_cleanup - Cleanup clockevent devices |
| */ |
| void hv_synic_clockevents_cleanup(void) |
| { |
| int cpu; |
| |
| if (!(ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE)) |
| return; |
| |
| if (direct_mode_enabled) |
| hv_remove_stimer0_irq(stimer0_irq); |
| |
| for_each_present_cpu(cpu) { |
| struct hv_per_cpu_context *hv_cpu |
| = per_cpu_ptr(hv_context.cpu_context, cpu); |
| |
| clockevents_unbind_device(hv_cpu->clk_evt, cpu); |
| } |
| } |
| |
| /* |
| * hv_synic_cleanup - Cleanup routine for hv_synic_init(). |
| */ |
| int hv_synic_cleanup(unsigned int cpu) |
| { |
| union hv_synic_sint shared_sint; |
| union hv_synic_simp simp; |
| union hv_synic_siefp siefp; |
| union hv_synic_scontrol sctrl; |
| struct vmbus_channel *channel, *sc; |
| bool channel_found = false; |
| unsigned long flags; |
| |
| hv_get_synic_state(sctrl.as_uint64); |
| if (sctrl.enable != 1) |
| return -EFAULT; |
| |
| /* |
| * Search for channels which are bound to the CPU we're about to |
| * cleanup. In case we find one and vmbus is still connected we need to |
| * fail, this will effectively prevent CPU offlining. There is no way |
| * we can re-bind channels to different CPUs for now. |
| */ |
| mutex_lock(&vmbus_connection.channel_mutex); |
| list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) { |
| if (channel->target_cpu == cpu) { |
| channel_found = true; |
| break; |
| } |
| spin_lock_irqsave(&channel->lock, flags); |
| list_for_each_entry(sc, &channel->sc_list, sc_list) { |
| if (sc->target_cpu == cpu) { |
| channel_found = true; |
| break; |
| } |
| } |
| spin_unlock_irqrestore(&channel->lock, flags); |
| if (channel_found) |
| break; |
| } |
| mutex_unlock(&vmbus_connection.channel_mutex); |
| |
| if (channel_found && vmbus_connection.conn_state == CONNECTED) |
| return -EBUSY; |
| |
| /* Turn off clockevent device */ |
| if (ms_hyperv.features & HV_MSR_SYNTIMER_AVAILABLE) { |
| struct hv_per_cpu_context *hv_cpu |
| = this_cpu_ptr(hv_context.cpu_context); |
| |
| clockevents_unbind_device(hv_cpu->clk_evt, cpu); |
| hv_ce_shutdown(hv_cpu->clk_evt); |
| } |
| |
| hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64); |
| |
| shared_sint.masked = 1; |
| |
| /* Need to correctly cleanup in the case of SMP!!! */ |
| /* Disable the interrupt */ |
| hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64); |
| |
| hv_get_simp(simp.as_uint64); |
| simp.simp_enabled = 0; |
| simp.base_simp_gpa = 0; |
| |
| hv_set_simp(simp.as_uint64); |
| |
| hv_get_siefp(siefp.as_uint64); |
| siefp.siefp_enabled = 0; |
| siefp.base_siefp_gpa = 0; |
| |
| hv_set_siefp(siefp.as_uint64); |
| |
| /* Disable the global synic bit */ |
| sctrl.enable = 0; |
| hv_set_synic_state(sctrl.as_uint64); |
| |
| return 0; |
| } |