diff options
Diffstat (limited to 'drivers/hv')
| -rw-r--r-- | drivers/hv/Kconfig | 2 | ||||
| -rw-r--r-- | drivers/hv/channel.c | 8 | ||||
| -rw-r--r-- | drivers/hv/channel_mgmt.c | 189 | ||||
| -rw-r--r-- | drivers/hv/connection.c | 24 | ||||
| -rw-r--r-- | drivers/hv/hv.c | 2 | ||||
| -rw-r--r-- | drivers/hv/hv_balloon.c | 19 | ||||
| -rw-r--r-- | drivers/hv/hv_kvp.c | 26 | ||||
| -rw-r--r-- | drivers/hv/hyperv_vmbus.h | 75 | ||||
| -rw-r--r-- | drivers/hv/vmbus_drv.c | 20 |
9 files changed, 216 insertions, 149 deletions
diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig index 97954f575c3f..1c1a2514d6f3 100644 --- a/drivers/hv/Kconfig +++ b/drivers/hv/Kconfig @@ -4,7 +4,7 @@ menu "Microsoft Hyper-V guest support" config HYPERV tristate "Microsoft Hyper-V client drivers" - depends on X86 && ACPI && PCI && X86_LOCAL_APIC && HYPERVISOR_GUEST + depends on X86 && ACPI && X86_LOCAL_APIC && HYPERVISOR_GUEST select PARAVIRT help Select this option to run Linux as a Hyper-V client operating diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index de8193f3b838..fe00b12e4417 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -516,6 +516,14 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer, } wait_for_completion(&msginfo->waitevent); + if (msginfo->response.gpadl_created.creation_status != 0) { + pr_err("Failed to establish GPADL: err = 0x%x\n", + msginfo->response.gpadl_created.creation_status); + + ret = -EDQUOT; + goto cleanup; + } + if (channel->rescind) { ret = -ENODEV; goto cleanup; diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 6277597d3d58..edd34c167a9b 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -435,61 +435,16 @@ void vmbus_free_channels(void) } } -/* - * vmbus_process_offer - Process the offer by creating a channel/device - * associated with this offer - */ -static void vmbus_process_offer(struct vmbus_channel *newchannel) +/* Note: the function can run concurrently for primary/sub channels. */ +static void vmbus_add_channel_work(struct work_struct *work) { - struct vmbus_channel *channel; - bool fnew = true; + struct vmbus_channel *newchannel = + container_of(work, struct vmbus_channel, add_channel_work); + struct vmbus_channel *primary_channel = newchannel->primary_channel; unsigned long flags; u16 dev_type; int ret; - /* Make sure this is a new offer */ - mutex_lock(&vmbus_connection.channel_mutex); - - /* - * Now that we have acquired the channel_mutex, - * we can release the potentially racing rescind thread. - */ - atomic_dec(&vmbus_connection.offer_in_progress); - - list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) { - if (!uuid_le_cmp(channel->offermsg.offer.if_type, - newchannel->offermsg.offer.if_type) && - !uuid_le_cmp(channel->offermsg.offer.if_instance, - newchannel->offermsg.offer.if_instance)) { - fnew = false; - break; - } - } - - if (fnew) - list_add_tail(&newchannel->listentry, - &vmbus_connection.chn_list); - - mutex_unlock(&vmbus_connection.channel_mutex); - - if (!fnew) { - /* - * Check to see if this is a sub-channel. - */ - if (newchannel->offermsg.offer.sub_channel_index != 0) { - /* - * Process the sub-channel. - */ - newchannel->primary_channel = channel; - spin_lock_irqsave(&channel->lock, flags); - list_add_tail(&newchannel->sc_list, &channel->sc_list); - channel->num_sc++; - spin_unlock_irqrestore(&channel->lock, flags); - } else { - goto err_free_chan; - } - } - dev_type = hv_get_dev_type(newchannel); init_vp_index(newchannel, dev_type); @@ -507,27 +462,26 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) /* * This state is used to indicate a successful open * so that when we do close the channel normally, we - * can cleanup properly + * can cleanup properly. */ newchannel->state = CHANNEL_OPEN_STATE; - if (!fnew) { - struct hv_device *dev - = newchannel->primary_channel->device_obj; + if (primary_channel != NULL) { + /* newchannel is a sub-channel. */ + struct hv_device *dev = primary_channel->device_obj; if (vmbus_add_channel_kobj(dev, newchannel)) - goto err_free_chan; + goto err_deq_chan; + + if (primary_channel->sc_creation_callback != NULL) + primary_channel->sc_creation_callback(newchannel); - if (channel->sc_creation_callback != NULL) - channel->sc_creation_callback(newchannel); newchannel->probe_done = true; return; } /* - * Start the process of binding this offer to the driver - * We need to set the DeviceObject field before calling - * vmbus_child_dev_add() + * Start the process of binding the primary channel to the driver */ newchannel->device_obj = vmbus_device_create( &newchannel->offermsg.offer.if_type, @@ -556,13 +510,28 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) err_deq_chan: mutex_lock(&vmbus_connection.channel_mutex); - list_del(&newchannel->listentry); + + /* + * We need to set the flag, otherwise + * vmbus_onoffer_rescind() can be blocked. + */ + newchannel->probe_done = true; + + if (primary_channel == NULL) { + list_del(&newchannel->listentry); + } else { + spin_lock_irqsave(&primary_channel->lock, flags); + list_del(&newchannel->sc_list); + spin_unlock_irqrestore(&primary_channel->lock, flags); + } + mutex_unlock(&vmbus_connection.channel_mutex); if (newchannel->target_cpu != get_cpu()) { put_cpu(); smp_call_function_single(newchannel->target_cpu, - percpu_channel_deq, newchannel, true); + percpu_channel_deq, + newchannel, true); } else { percpu_channel_deq(newchannel); put_cpu(); @@ -570,14 +539,104 @@ err_deq_chan: vmbus_release_relid(newchannel->offermsg.child_relid); -err_free_chan: free_channel(newchannel); } /* + * vmbus_process_offer - Process the offer by creating a channel/device + * associated with this offer + */ +static void vmbus_process_offer(struct vmbus_channel *newchannel) +{ + struct vmbus_channel *channel; + struct workqueue_struct *wq; + unsigned long flags; + bool fnew = true; + + mutex_lock(&vmbus_connection.channel_mutex); + + /* + * Now that we have acquired the channel_mutex, + * we can release the potentially racing rescind thread. + */ + atomic_dec(&vmbus_connection.offer_in_progress); + + list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) { + if (!uuid_le_cmp(channel->offermsg.offer.if_type, + newchannel->offermsg.offer.if_type) && + !uuid_le_cmp(channel->offermsg.offer.if_instance, + newchannel->offermsg.offer.if_instance)) { + fnew = false; + break; + } + } + + if (fnew) + list_add_tail(&newchannel->listentry, + &vmbus_connection.chn_list); + else { + /* + * Check to see if this is a valid sub-channel. + */ + if (newchannel->offermsg.offer.sub_channel_index == 0) { + mutex_unlock(&vmbus_connection.channel_mutex); + /* + * Don't call free_channel(), because newchannel->kobj + * is not initialized yet. + */ + kfree(newchannel); + WARN_ON_ONCE(1); + return; + } + /* + * Process the sub-channel. + */ + newchannel->primary_channel = channel; + spin_lock_irqsave(&channel->lock, flags); + list_add_tail(&newchannel->sc_list, &channel->sc_list); + spin_unlock_irqrestore(&channel->lock, flags); + } + + mutex_unlock(&vmbus_connection.channel_mutex); + + /* + * vmbus_process_offer() mustn't call channel->sc_creation_callback() + * directly for sub-channels, because sc_creation_callback() -> + * vmbus_open() may never get the host's response to the + * OPEN_CHANNEL message (the host may rescind a channel at any time, + * e.g. in the case of hot removing a NIC), and vmbus_onoffer_rescind() + * may not wake up the vmbus_open() as it's blocked due to a non-zero + * vmbus_connection.offer_in_progress, and finally we have a deadlock. + * + * The above is also true for primary channels, if the related device + * drivers use sync probing mode by default. + * + * And, usually the handling of primary channels and sub-channels can + * depend on each other, so we should offload them to different + * workqueues to avoid possible deadlock, e.g. in sync-probing mode, + * NIC1's netvsc_subchan_work() can race with NIC2's netvsc_probe() -> + * rtnl_lock(), and causes deadlock: the former gets the rtnl_lock + * and waits for all the sub-channels to appear, but the latter + * can't get the rtnl_lock and this blocks the handling of + * sub-channels. + */ + INIT_WORK(&newchannel->add_channel_work, vmbus_add_channel_work); + wq = fnew ? vmbus_connection.handle_primary_chan_wq : + vmbus_connection.handle_sub_chan_wq; + queue_work(wq, &newchannel->add_channel_work); +} + +/* * We use this state to statically distribute the channel interrupt load. */ static int next_numa_node_id; +/* + * init_vp_index() accesses global variables like next_numa_node_id, and + * it can run concurrently for primary channels and sub-channels: see + * vmbus_process_offer(), so we need the lock to protect the global + * variables. + */ +static DEFINE_SPINLOCK(bind_channel_to_cpu_lock); /* * Starting with Win8, we can statically distribute the incoming @@ -613,6 +672,8 @@ static void init_vp_index(struct vmbus_channel *channel, u16 dev_type) return; } + spin_lock(&bind_channel_to_cpu_lock); + /* * Based on the channel affinity policy, we will assign the NUMA * nodes. @@ -695,6 +756,8 @@ static void init_vp_index(struct vmbus_channel *channel, u16 dev_type) channel->target_cpu = cur_cpu; channel->target_vp = hv_cpu_number_to_vp_number(cur_cpu); + spin_unlock(&bind_channel_to_cpu_lock); + free_cpumask_var(available_mask); } diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index f4d08c8ac7f8..4fe117b761ce 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -190,6 +190,20 @@ int vmbus_connect(void) goto cleanup; } + vmbus_connection.handle_primary_chan_wq = + create_workqueue("hv_pri_chan"); + if (!vmbus_connection.handle_primary_chan_wq) { + ret = -ENOMEM; + goto cleanup; + } + + vmbus_connection.handle_sub_chan_wq = + create_workqueue("hv_sub_chan"); + if (!vmbus_connection.handle_sub_chan_wq) { + ret = -ENOMEM; + goto cleanup; + } + INIT_LIST_HEAD(&vmbus_connection.chn_msg_list); spin_lock_init(&vmbus_connection.channelmsg_lock); @@ -280,10 +294,14 @@ void vmbus_disconnect(void) */ vmbus_initiate_unload(false); - if (vmbus_connection.work_queue) { - drain_workqueue(vmbus_connection.work_queue); + if (vmbus_connection.handle_sub_chan_wq) + destroy_workqueue(vmbus_connection.handle_sub_chan_wq); + + if (vmbus_connection.handle_primary_chan_wq) + destroy_workqueue(vmbus_connection.handle_primary_chan_wq); + + if (vmbus_connection.work_queue) destroy_workqueue(vmbus_connection.work_queue); - } if (vmbus_connection.int_page) { free_pages((unsigned long)vmbus_connection.int_page, 0); diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 332d7c34be5c..11273cd384d6 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -143,7 +143,7 @@ static int hv_ce_shutdown(struct clock_event_device *evt) static int hv_ce_set_oneshot(struct clock_event_device *evt) { - union hv_timer_config timer_cfg; + union hv_stimer_config timer_cfg; timer_cfg.as_uint64 = 0; timer_cfg.enable = 1; diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index 41631512ae97..5301fef16c31 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -1090,6 +1090,7 @@ static void process_info(struct hv_dynmem_device *dm, struct dm_info_msg *msg) static unsigned long compute_balloon_floor(void) { unsigned long min_pages; + unsigned long nr_pages = totalram_pages(); #define MB2PAGES(mb) ((mb) << (20 - PAGE_SHIFT)) /* Simple continuous piecewiese linear function: * max MiB -> min MiB gradient @@ -1102,16 +1103,16 @@ static unsigned long compute_balloon_floor(void) * 8192 744 (1/16) * 32768 1512 (1/32) */ - if (totalram_pages < MB2PAGES(128)) - min_pages = MB2PAGES(8) + (totalram_pages >> 1); - else if (totalram_pages < MB2PAGES(512)) - min_pages = MB2PAGES(40) + (totalram_pages >> 2); - else if (totalram_pages < MB2PAGES(2048)) - min_pages = MB2PAGES(104) + (totalram_pages >> 3); - else if (totalram_pages < MB2PAGES(8192)) - min_pages = MB2PAGES(232) + (totalram_pages >> 4); + if (nr_pages < MB2PAGES(128)) + min_pages = MB2PAGES(8) + (nr_pages >> 1); + else if (nr_pages < MB2PAGES(512)) + min_pages = MB2PAGES(40) + (nr_pages >> 2); + else if (nr_pages < MB2PAGES(2048)) + min_pages = MB2PAGES(104) + (nr_pages >> 3); + else if (nr_pages < MB2PAGES(8192)) + min_pages = MB2PAGES(232) + (nr_pages >> 4); else - min_pages = MB2PAGES(488) + (totalram_pages >> 5); + min_pages = MB2PAGES(488) + (nr_pages >> 5); #undef MB2PAGES return min_pages; } diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c index a7513a8a8e37..d6106e1a0d4a 100644 --- a/drivers/hv/hv_kvp.c +++ b/drivers/hv/hv_kvp.c @@ -353,6 +353,9 @@ static void process_ib_ipinfo(void *in_msg, void *out_msg, int op) out->body.kvp_ip_val.dhcp_enabled = in->kvp_ip_val.dhcp_enabled; + /* fallthrough */ + + case KVP_OP_GET_IP_INFO: utf16s_to_utf8s((wchar_t *)in->kvp_ip_val.adapter_id, MAX_ADAPTER_ID_SIZE, UTF16_LITTLE_ENDIAN, @@ -405,7 +408,11 @@ kvp_send_key(struct work_struct *dummy) process_ib_ipinfo(in_msg, message, KVP_OP_SET_IP_INFO); break; case KVP_OP_GET_IP_INFO: - /* We only need to pass on message->kvp_hdr.operation. */ + /* + * We only need to pass on the info of operation, adapter_id + * and addr_family to the userland kvp daemon. + */ + process_ib_ipinfo(in_msg, message, KVP_OP_GET_IP_INFO); break; case KVP_OP_SET: switch (in_msg->body.kvp_set.data.value_type) { @@ -446,9 +453,9 @@ kvp_send_key(struct work_struct *dummy) } - break; - - case KVP_OP_GET: + /* + * The key is always a string - utf16 encoding. + */ message->body.kvp_set.data.key_size = utf16s_to_utf8s( (wchar_t *)in_msg->body.kvp_set.data.key, @@ -456,6 +463,17 @@ kvp_send_key(struct work_struct *dummy) UTF16_LITTLE_ENDIAN, message->body.kvp_set.data.key, HV_KVP_EXCHANGE_MAX_KEY_SIZE - 1) + 1; + + break; + + case KVP_OP_GET: + message->body.kvp_get.data.key_size = + utf16s_to_utf8s( + (wchar_t *)in_msg->body.kvp_get.data.key, + in_msg->body.kvp_get.data.key_size, + UTF16_LITTLE_ENDIAN, + message->body.kvp_get.data.key, + HV_KVP_EXCHANGE_MAX_KEY_SIZE - 1) + 1; break; case KVP_OP_DELETE: diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 72eaba3d50fc..ea201034b248 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -44,74 +44,6 @@ */ #define HV_UTIL_NEGO_TIMEOUT 55 -/* Define synthetic interrupt controller flag constants. */ -#define HV_EVENT_FLAGS_COUNT (256 * 8) -#define HV_EVENT_FLAGS_LONG_COUNT (256 / sizeof(unsigned long)) - -/* - * Timer configuration register. - */ -union hv_timer_config { - u64 as_uint64; - struct { - u64 enable:1; - u64 periodic:1; - u64 lazy:1; - u64 auto_enable:1; - u64 apic_vector:8; - u64 direct_mode:1; - u64 reserved_z0:3; - u64 sintx:4; - u64 reserved_z1:44; - }; -}; - - -/* Define the synthetic interrupt controller event flags format. */ -union hv_synic_event_flags { - unsigned long flags[HV_EVENT_FLAGS_LONG_COUNT]; -}; - -/* Define SynIC control register. */ -union hv_synic_scontrol { - u64 as_uint64; - struct { - u64 enable:1; - u64 reserved:63; - }; -}; - -/* Define synthetic interrupt source. */ -union hv_synic_sint { - u64 as_uint64; - struct { - u64 vector:8; - u64 reserved1:8; - u64 masked:1; - u64 auto_eoi:1; - u64 reserved2:46; - }; -}; - -/* Define the format of the SIMP register */ -union hv_synic_simp { - u64 as_uint64; - struct { - u64 simp_enabled:1; - u64 preserved:11; - u64 base_simp_gpa:52; - }; -}; - -/* Define the format of the SIEFP register */ -union hv_synic_siefp { - u64 as_uint64; - struct { - u64 siefp_enabled:1; - u64 preserved:11; - u64 base_siefp_gpa:52; - }; -}; /* Definitions for the monitored notification facility */ union hv_monitor_trigger_group { @@ -335,7 +267,14 @@ struct vmbus_connection { struct list_head chn_list; struct mutex channel_mutex; + /* + * An offer message is handled first on the work_queue, and then + * is further handled on handle_primary_chan_wq or + * handle_sub_chan_wq. + */ struct workqueue_struct *work_queue; + struct workqueue_struct *handle_primary_chan_wq; + struct workqueue_struct *handle_sub_chan_wq; }; diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 283d184280af..d0ff65675292 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -316,6 +316,8 @@ static ssize_t out_intr_mask_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound); return sprintf(buf, "%d\n", outbound.current_interrupt_mask); } @@ -329,6 +331,8 @@ static ssize_t out_read_index_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound); return sprintf(buf, "%d\n", outbound.current_read_index); } @@ -343,6 +347,8 @@ static ssize_t out_write_index_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound); return sprintf(buf, "%d\n", outbound.current_write_index); } @@ -357,6 +363,8 @@ static ssize_t out_read_bytes_avail_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound); return sprintf(buf, "%d\n", outbound.bytes_avail_toread); } @@ -371,6 +379,8 @@ static ssize_t out_write_bytes_avail_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->outbound, &outbound); return sprintf(buf, "%d\n", outbound.bytes_avail_towrite); } @@ -384,6 +394,8 @@ static ssize_t in_intr_mask_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); return sprintf(buf, "%d\n", inbound.current_interrupt_mask); } @@ -397,6 +409,8 @@ static ssize_t in_read_index_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); return sprintf(buf, "%d\n", inbound.current_read_index); } @@ -410,6 +424,8 @@ static ssize_t in_write_index_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); return sprintf(buf, "%d\n", inbound.current_write_index); } @@ -424,6 +440,8 @@ static ssize_t in_read_bytes_avail_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); return sprintf(buf, "%d\n", inbound.bytes_avail_toread); } @@ -438,6 +456,8 @@ static ssize_t in_write_bytes_avail_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; + if (hv_dev->channel->state != CHANNEL_OPENED_STATE) + return -EINVAL; hv_ringbuffer_get_debuginfo(&hv_dev->channel->inbound, &inbound); return sprintf(buf, "%d\n", inbound.bytes_avail_towrite); } |