diff options
Diffstat (limited to 'drivers/hv')
| -rw-r--r-- | drivers/hv/channel_mgmt.c | 3 | ||||
| -rw-r--r-- | drivers/hv/hv.c | 6 | ||||
| -rw-r--r-- | drivers/hv/hv_balloon.c | 25 | ||||
| -rw-r--r-- | drivers/hv/hv_debugfs.c | 2 | ||||
| -rw-r--r-- | drivers/hv/hv_trace.h | 4 | ||||
| -rw-r--r-- | drivers/hv/hyperv_vmbus.h | 2 | ||||
| -rw-r--r-- | drivers/hv/vmbus_drv.c | 105 |
7 files changed, 96 insertions, 51 deletions
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 0370364169c4..501c43c5851d 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -839,6 +839,9 @@ void vmbus_initiate_unload(bool crash) { struct vmbus_channel_message_header hdr; + if (xchg(&vmbus_connection.conn_state, DISCONNECTED) == DISCONNECTED) + return; + /* Pre-Win2012R2 hosts don't support reconnect */ if (vmbus_proto_version < VERSION_WIN8_1) return; diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 6098e0cbdb4b..533c8b82b344 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -184,11 +184,7 @@ void hv_synic_enable_regs(unsigned int cpu) 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; - + shared_sint.auto_eoi = hv_recommend_using_aeoi(); hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64); /* Enable the global synic bit */ diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index a02ce43d778d..32e3bc0aa665 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -533,7 +533,6 @@ struct hv_dynmem_device { * State to synchronize hot-add. */ struct completion ol_waitevent; - bool ha_waiting; /* * This thread handles hot-add * requests from the host as well as notifying @@ -634,10 +633,7 @@ static int hv_memory_notifier(struct notifier_block *nb, unsigned long val, switch (val) { case MEM_ONLINE: case MEM_CANCEL_ONLINE: - if (dm_device.ha_waiting) { - dm_device.ha_waiting = false; - complete(&dm_device.ol_waitevent); - } + complete(&dm_device.ol_waitevent); break; case MEM_OFFLINE: @@ -726,8 +722,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, has->covered_end_pfn += processed_pfn; spin_unlock_irqrestore(&dm_device.ha_lock, flags); - init_completion(&dm_device.ol_waitevent); - dm_device.ha_waiting = !memhp_auto_online; + reinit_completion(&dm_device.ol_waitevent); nid = memory_add_physaddr_to_nid(PFN_PHYS(start_pfn)); ret = add_memory(nid, PFN_PHYS((start_pfn)), @@ -753,15 +748,14 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, } /* - * Wait for the memory block to be onlined when memory onlining - * is done outside of kernel (memhp_auto_online). Since the hot - * add has succeeded, it is ok to proceed even if the pages in - * the hot added region have not been "onlined" within the - * allowed time. + * Wait for memory to get onlined. If the kernel onlined the + * memory when adding it, this will return directly. Otherwise, + * it will wait for user space to online the memory. This helps + * to avoid adding memory faster than it is getting onlined. As + * adding succeeded, it is ok to proceed even if the memory was + * not onlined in time. */ - if (dm_device.ha_waiting) - wait_for_completion_timeout(&dm_device.ol_waitevent, - 5*HZ); + wait_for_completion_timeout(&dm_device.ol_waitevent, 5 * HZ); post_status(&dm_device); } } @@ -1706,6 +1700,7 @@ static int balloon_probe(struct hv_device *dev, #ifdef CONFIG_MEMORY_HOTPLUG set_online_page_callback(&hv_online_page); + init_completion(&dm_device.ol_waitevent); register_memory_notifier(&hv_memory_nb); #endif diff --git a/drivers/hv/hv_debugfs.c b/drivers/hv/hv_debugfs.c index 8a2878573582..ccf752b6659a 100644 --- a/drivers/hv/hv_debugfs.c +++ b/drivers/hv/hv_debugfs.c @@ -11,7 +11,7 @@ #include "hyperv_vmbus.h" -struct dentry *hv_debug_root; +static struct dentry *hv_debug_root; static int hv_debugfs_delay_get(void *data, u64 *val) { diff --git a/drivers/hv/hv_trace.h b/drivers/hv/hv_trace.h index e70783e33680..f9d14db980cb 100644 --- a/drivers/hv/hv_trace.h +++ b/drivers/hv/hv_trace.h @@ -286,8 +286,8 @@ TRACE_EVENT(vmbus_send_tl_connect_request, __field(int, ret) ), TP_fast_assign( - memcpy(__entry->guest_id, &msg->guest_endpoint_id.b, 16); - memcpy(__entry->host_id, &msg->host_service_id.b, 16); + export_guid(__entry->guest_id, &msg->guest_endpoint_id); + export_guid(__entry->host_id, &msg->host_service_id); __entry->ret = ret; ), TP_printk("sending guest_endpoint_id %pUl, host_service_id %pUl, " diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index f5fa3b3c9baf..70b30e223a57 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -292,7 +292,7 @@ struct vmbus_msginfo { struct list_head msglist_entry; /* The message itself */ - unsigned char msg[0]; + unsigned char msg[]; }; diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 029378c27421..e06c6b9555cf 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -31,6 +31,7 @@ #include <linux/kdebug.h> #include <linux/efi.h> #include <linux/random.h> +#include <linux/kernel.h> #include <linux/syscore_ops.h> #include <clocksource/hyperv_timer.h> #include "hyperv_vmbus.h" @@ -48,14 +49,35 @@ static int hyperv_cpuhp_online; static void *hv_panic_page; +/* + * Boolean to control whether to report panic messages over Hyper-V. + * + * It can be set via /proc/sys/kernel/hyperv/record_panic_msg + */ +static int sysctl_record_panic_msg = 1; + +static int hyperv_report_reg(void) +{ + return !sysctl_record_panic_msg || !hv_panic_page; +} + static int hyperv_panic_event(struct notifier_block *nb, unsigned long val, void *args) { struct pt_regs *regs; - regs = current_pt_regs(); + vmbus_initiate_unload(true); - hyperv_report_panic(regs, val); + /* + * Hyper-V should be notified only once about a panic. If we will be + * doing hyperv_report_panic_msg() later with kmsg data, don't do + * the notification here. + */ + if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE + && hyperv_report_reg()) { + regs = current_pt_regs(); + hyperv_report_panic(regs, val, false); + } return NOTIFY_DONE; } @@ -65,7 +87,13 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val, struct die_args *die = (struct die_args *)args; struct pt_regs *regs = die->regs; - hyperv_report_panic(regs, val); + /* + * Hyper-V should be notified only once about a panic. If we will be + * doing hyperv_report_panic_msg() later with kmsg data, don't do + * the notification here. + */ + if (hyperv_report_reg()) + hyperv_report_panic(regs, val, true); return NOTIFY_DONE; } @@ -950,6 +978,9 @@ static int vmbus_resume(struct device *child_device) return drv->resume(dev); } +#else +#define vmbus_suspend NULL +#define vmbus_resume NULL #endif /* CONFIG_PM_SLEEP */ /* @@ -969,11 +1000,22 @@ static void vmbus_device_release(struct device *device) } /* - * Note: we must use SET_NOIRQ_SYSTEM_SLEEP_PM_OPS rather than - * SET_SYSTEM_SLEEP_PM_OPS: see the comment before vmbus_bus_pm. + * Note: we must use the "noirq" ops: see the comment before vmbus_bus_pm. + * + * suspend_noirq/resume_noirq are set to NULL to support Suspend-to-Idle: we + * shouldn't suspend the vmbus devices upon Suspend-to-Idle, otherwise there + * is no way to wake up a Generation-2 VM. + * + * The other 4 ops are for hibernation. */ + static const struct dev_pm_ops vmbus_pm = { - SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(vmbus_suspend, vmbus_resume) + .suspend_noirq = NULL, + .resume_noirq = NULL, + .freeze_noirq = vmbus_suspend, + .thaw_noirq = vmbus_resume, + .poweroff_noirq = vmbus_suspend, + .restore_noirq = vmbus_resume, }; /* The one and only one */ @@ -1253,13 +1295,6 @@ static void vmbus_isr(void) } /* - * Boolean to control whether to report panic messages over Hyper-V. - * - * It can be set via /proc/sys/kernel/hyperv/record_panic_msg - */ -static int sysctl_record_panic_msg = 1; - -/* * Callback from kmsg_dump. Grab as much as possible from the end of the kmsg * buffer and call into Hyper-V to transfer the data. */ @@ -1382,19 +1417,29 @@ static int vmbus_bus_init(void) hv_panic_page = (void *)hv_alloc_hyperv_zeroed_page(); if (hv_panic_page) { ret = kmsg_dump_register(&hv_kmsg_dumper); - if (ret) + if (ret) { pr_err("Hyper-V: kmsg dump register " "error 0x%x\n", ret); + hv_free_hyperv_page( + (unsigned long)hv_panic_page); + hv_panic_page = NULL; + } } else pr_err("Hyper-V: panic message page memory " "allocation failed"); } register_die_notifier(&hyperv_die_block); - atomic_notifier_chain_register(&panic_notifier_list, - &hyperv_panic_block); } + /* + * Always register the panic notifier because we need to unload + * the VMbus channel connection to prevent any VMbus + * activity after the VM panics. + */ + atomic_notifier_chain_register(&panic_notifier_list, + &hyperv_panic_block); + vmbus_request_offers(); return 0; @@ -1407,7 +1452,6 @@ err_alloc: hv_remove_vmbus_irq(); bus_unregister(&hv_bus); - hv_free_hyperv_page((unsigned long)hv_panic_page); unregister_sysctl_table(hv_ctl_table_hdr); hv_ctl_table_hdr = NULL; return ret; @@ -2204,8 +2248,6 @@ static int vmbus_bus_suspend(struct device *dev) vmbus_initiate_unload(false); - vmbus_connection.conn_state = DISCONNECTED; - /* Reset the event for the next resume. */ reinit_completion(&vmbus_connection.ready_for_resume_event); @@ -2253,6 +2295,9 @@ static int vmbus_bus_resume(struct device *dev) return 0; } +#else +#define vmbus_bus_suspend NULL +#define vmbus_bus_resume NULL #endif /* CONFIG_PM_SLEEP */ static const struct acpi_device_id vmbus_acpi_device_ids[] = { @@ -2263,16 +2308,24 @@ static const struct acpi_device_id vmbus_acpi_device_ids[] = { MODULE_DEVICE_TABLE(acpi, vmbus_acpi_device_ids); /* - * Note: we must use SET_NOIRQ_SYSTEM_SLEEP_PM_OPS rather than - * SET_SYSTEM_SLEEP_PM_OPS, otherwise NIC SR-IOV can not work, because the - * "pci_dev_pm_ops" uses the "noirq" callbacks: in the resume path, the - * pci "noirq" restore callback runs before "non-noirq" callbacks (see + * Note: we must use the "no_irq" ops, otherwise hibernation can not work with + * PCI device assignment, because "pci_dev_pm_ops" uses the "noirq" ops: in + * the resume path, the pci "noirq" restore op runs before "non-noirq" op (see * resume_target_kernel() -> dpm_resume_start(), and hibernation_restore() -> * dpm_resume_end()). This means vmbus_bus_resume() and the pci-hyperv's - * resume callback must also run via the "noirq" callbacks. + * resume callback must also run via the "noirq" ops. + * + * Set suspend_noirq/resume_noirq to NULL for Suspend-to-Idle: see the comment + * earlier in this file before vmbus_pm. */ + static const struct dev_pm_ops vmbus_bus_pm = { - SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(vmbus_bus_suspend, vmbus_bus_resume) + .suspend_noirq = NULL, + .resume_noirq = NULL, + .freeze_noirq = vmbus_bus_suspend, + .thaw_noirq = vmbus_bus_resume, + .poweroff_noirq = vmbus_bus_suspend, + .restore_noirq = vmbus_bus_resume }; static struct acpi_driver vmbus_acpi_driver = { @@ -2289,7 +2342,6 @@ static void hv_kexec_handler(void) { hv_stimer_global_cleanup(); vmbus_initiate_unload(false); - vmbus_connection.conn_state = DISCONNECTED; /* Make sure conn_state is set as hv_synic_cleanup checks for it */ mb(); cpuhp_remove_state(hyperv_cpuhp_online); @@ -2306,7 +2358,6 @@ static void hv_crash_handler(struct pt_regs *regs) * doing the cleanup for current CPU only. This should be sufficient * for kdump. */ - vmbus_connection.conn_state = DISCONNECTED; cpu = smp_processor_id(); hv_stimer_cleanup(cpu); hv_synic_disable_regs(cpu); |