diff options
Diffstat (limited to 'drivers/hv')
| -rw-r--r-- | drivers/hv/channel.c | 93 | ||||
| -rw-r--r-- | drivers/hv/channel_mgmt.c | 10 | ||||
| -rw-r--r-- | drivers/hv/connection.c | 1 | ||||
| -rw-r--r-- | drivers/hv/hv.c | 14 | ||||
| -rw-r--r-- | drivers/hv/hv_balloon.c | 44 | ||||
| -rw-r--r-- | drivers/hv/hv_snapshot.c | 33 | ||||
| -rw-r--r-- | drivers/hv/hv_util.c | 9 | ||||
| -rw-r--r-- | drivers/hv/hyperv_vmbus.h | 12 | ||||
| -rw-r--r-- | drivers/hv/ring_buffer.c | 44 | ||||
| -rw-r--r-- | drivers/hv/vmbus_drv.c | 174 |
10 files changed, 293 insertions, 141 deletions
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 16f91c8490fe..5fb4c6d9209b 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -39,7 +39,7 @@ * vmbus_setevent- Trigger an event notification on the specified * channel. */ -static void vmbus_setevent(struct vmbus_channel *channel) +void vmbus_setevent(struct vmbus_channel *channel) { struct hv_monitor_page *monitorpage; @@ -65,6 +65,7 @@ static void vmbus_setevent(struct vmbus_channel *channel) vmbus_set_event(channel); } } +EXPORT_SYMBOL_GPL(vmbus_setevent); /* * vmbus_open - Open the specified channel. @@ -635,8 +636,6 @@ int vmbus_sendpacket_ctl(struct vmbus_channel *channel, void *buffer, u32 packetlen_aligned = ALIGN(packetlen, sizeof(u64)); struct kvec bufferlist[3]; u64 aligned_data = 0; - int ret; - bool signal = false; bool lock = channel->acquire_ring_lock; int num_vecs = ((bufferlen != 0) ? 3 : 1); @@ -656,33 +655,9 @@ int vmbus_sendpacket_ctl(struct vmbus_channel *channel, void *buffer, bufferlist[2].iov_base = &aligned_data; bufferlist[2].iov_len = (packetlen_aligned - packetlen); - ret = hv_ringbuffer_write(&channel->outbound, bufferlist, num_vecs, - &signal, lock, channel->signal_policy); - - /* - * Signalling the host is conditional on many factors: - * 1. The ring state changed from being empty to non-empty. - * This is tracked by the variable "signal". - * 2. The variable kick_q tracks if more data will be placed - * on the ring. We will not signal if more data is - * to be placed. - * - * Based on the channel signal state, we will decide - * which signaling policy will be applied. - * - * If we cannot write to the ring-buffer; signal the host - * even if we may not have written anything. This is a rare - * enough condition that it should not matter. - * NOTE: in this case, the hvsock channel is an exception, because - * it looks the host side's hvsock implementation has a throttling - * mechanism which can hurt the performance otherwise. - */ - - if (((ret == 0) && kick_q && signal) || - (ret && !is_hvsock_channel(channel))) - vmbus_setevent(channel); + return hv_ringbuffer_write(channel, bufferlist, num_vecs, + lock, kick_q); - return ret; } EXPORT_SYMBOL(vmbus_sendpacket_ctl); @@ -723,7 +698,6 @@ int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel, u32 flags, bool kick_q) { - int ret; int i; struct vmbus_channel_packet_page_buffer desc; u32 descsize; @@ -731,7 +705,6 @@ int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel, u32 packetlen_aligned; struct kvec bufferlist[3]; u64 aligned_data = 0; - bool signal = false; bool lock = channel->acquire_ring_lock; if (pagecount > MAX_PAGE_BUFFER_COUNT) @@ -769,29 +742,8 @@ int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel, bufferlist[2].iov_base = &aligned_data; bufferlist[2].iov_len = (packetlen_aligned - packetlen); - ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3, - &signal, lock, channel->signal_policy); - - /* - * Signalling the host is conditional on many factors: - * 1. The ring state changed from being empty to non-empty. - * This is tracked by the variable "signal". - * 2. The variable kick_q tracks if more data will be placed - * on the ring. We will not signal if more data is - * to be placed. - * - * Based on the channel signal state, we will decide - * which signaling policy will be applied. - * - * If we cannot write to the ring-buffer; signal the host - * even if we may not have written anything. This is a rare - * enough condition that it should not matter. - */ - - if (((ret == 0) && kick_q && signal) || (ret)) - vmbus_setevent(channel); - - return ret; + return hv_ringbuffer_write(channel, bufferlist, 3, + lock, kick_q); } EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer_ctl); @@ -822,12 +774,10 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, u32 desc_size, void *buffer, u32 bufferlen, u64 requestid) { - int ret; u32 packetlen; u32 packetlen_aligned; struct kvec bufferlist[3]; u64 aligned_data = 0; - bool signal = false; bool lock = channel->acquire_ring_lock; packetlen = desc_size + bufferlen; @@ -848,13 +798,8 @@ int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel, bufferlist[2].iov_base = &aligned_data; bufferlist[2].iov_len = (packetlen_aligned - packetlen); - ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3, - &signal, lock, channel->signal_policy); - - if (ret == 0 && signal) - vmbus_setevent(channel); - - return ret; + return hv_ringbuffer_write(channel, bufferlist, 3, + lock, true); } EXPORT_SYMBOL_GPL(vmbus_sendpacket_mpb_desc); @@ -866,14 +811,12 @@ int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel, struct hv_multipage_buffer *multi_pagebuffer, void *buffer, u32 bufferlen, u64 requestid) { - int ret; struct vmbus_channel_packet_multipage_buffer desc; u32 descsize; u32 packetlen; u32 packetlen_aligned; struct kvec bufferlist[3]; u64 aligned_data = 0; - bool signal = false; bool lock = channel->acquire_ring_lock; u32 pfncount = NUM_PAGES_SPANNED(multi_pagebuffer->offset, multi_pagebuffer->len); @@ -913,13 +856,8 @@ int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel, bufferlist[2].iov_base = &aligned_data; bufferlist[2].iov_len = (packetlen_aligned - packetlen); - ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3, - &signal, lock, channel->signal_policy); - - if (ret == 0 && signal) - vmbus_setevent(channel); - - return ret; + return hv_ringbuffer_write(channel, bufferlist, 3, + lock, true); } EXPORT_SYMBOL_GPL(vmbus_sendpacket_multipagebuffer); @@ -941,16 +879,9 @@ __vmbus_recvpacket(struct vmbus_channel *channel, void *buffer, u32 bufferlen, u32 *buffer_actual_len, u64 *requestid, bool raw) { - int ret; - bool signal = false; + return hv_ringbuffer_read(channel, buffer, bufferlen, + buffer_actual_len, requestid, raw); - ret = hv_ringbuffer_read(&channel->inbound, buffer, bufferlen, - buffer_actual_len, requestid, &signal, raw); - - if (signal) - vmbus_setevent(channel); - - return ret; } int vmbus_recvpacket(struct vmbus_channel *channel, void *buffer, diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 96a85cd39580..26b419203f16 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -134,7 +134,7 @@ static const struct vmbus_device vmbus_devs[] = { }, /* Unknown GUID */ - { .dev_type = HV_UNKOWN, + { .dev_type = HV_UNKNOWN, .perf_device = false, }, }; @@ -163,9 +163,9 @@ static u16 hv_get_dev_type(const struct vmbus_channel *channel) u16 i; if (is_hvsock_channel(channel) || is_unsupported_vmbus_devs(guid)) - return HV_UNKOWN; + return HV_UNKNOWN; - for (i = HV_IDE; i < HV_UNKOWN; i++) { + for (i = HV_IDE; i < HV_UNKNOWN; i++) { if (!uuid_le_cmp(*guid, vmbus_devs[i].guid)) return i; } @@ -389,6 +389,7 @@ void vmbus_free_channels(void) { struct vmbus_channel *channel, *tmp; + mutex_lock(&vmbus_connection.channel_mutex); list_for_each_entry_safe(channel, tmp, &vmbus_connection.chn_list, listentry) { /* hv_process_channel_removal() needs this */ @@ -396,6 +397,7 @@ void vmbus_free_channels(void) vmbus_device_unregister(channel->device_obj); } + mutex_unlock(&vmbus_connection.channel_mutex); } /* @@ -447,8 +449,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) } dev_type = hv_get_dev_type(newchannel); - if (dev_type == HV_NIC) - set_channel_signal_state(newchannel, HV_SIGNAL_POLICY_EXPLICIT); init_vp_index(newchannel, dev_type); diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index 78e6368a4423..6ce8b874e833 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -39,6 +39,7 @@ struct vmbus_connection vmbus_connection = { .conn_state = DISCONNECTED, .next_gpadl_handle = ATOMIC_INIT(0xE1E10), }; +EXPORT_SYMBOL_GPL(vmbus_connection); /* * Negotiated protocol version with the host. diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 60dbd6cb4640..b44b32f21e61 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -135,9 +135,9 @@ u64 hv_do_hypercall(u64 control, void *input, void *output) EXPORT_SYMBOL_GPL(hv_do_hypercall); #ifdef CONFIG_X86_64 -static cycle_t read_hv_clock_tsc(struct clocksource *arg) +static u64 read_hv_clock_tsc(struct clocksource *arg) { - cycle_t current_tick; + u64 current_tick; struct ms_hyperv_tsc_page *tsc_pg = hv_context.tsc_page; if (tsc_pg->tsc_sequence != 0) { @@ -146,7 +146,7 @@ static cycle_t read_hv_clock_tsc(struct clocksource *arg) */ while (1) { - cycle_t tmp; + u64 tmp; u32 sequence = tsc_pg->tsc_sequence; u64 cur_tsc; u64 scale = tsc_pg->tsc_scale; @@ -350,7 +350,7 @@ int hv_post_message(union hv_connection_id connection_id, static int hv_ce_set_next_event(unsigned long delta, struct clock_event_device *evt) { - cycle_t current_tick; + u64 current_tick; WARN_ON(!clockevent_state_oneshot(evt)); @@ -575,7 +575,7 @@ void hv_synic_clockevents_cleanup(void) if (!(ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE)) return; - for_each_online_cpu(cpu) + for_each_present_cpu(cpu) clockevents_unbind_device(hv_context.clk_evt[cpu], cpu); } @@ -594,8 +594,10 @@ void hv_synic_cleanup(void *arg) return; /* Turn off clockevent device */ - if (ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE) + if (ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE) { + clockevents_unbind_device(hv_context.clk_evt[cpu], cpu); hv_ce_shutdown(hv_context.clk_evt[cpu]); + } rdmsrl(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64); diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index fdf8da929cbe..14c3dc4bd23c 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -564,6 +564,11 @@ struct hv_dynmem_device { * next version to try. */ __u32 next_version; + + /* + * The negotiated version agreed by host. + */ + __u32 version; }; static struct hv_dynmem_device dm_device; @@ -645,6 +650,7 @@ static void hv_bring_pgs_online(struct hv_hotadd_state *has, { int i; + pr_debug("Online %lu pages starting at pfn 0x%lx\n", size, start_pfn); for (i = 0; i < size; i++) hv_page_online_one(has, pfn_to_page(start_pfn + i)); } @@ -685,7 +691,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, (HA_CHUNK << PAGE_SHIFT)); if (ret) { - pr_info("hot_add memory failed error is %d\n", ret); + pr_warn("hot_add memory failed error is %d\n", ret); if (ret == -EEXIST) { /* * This error indicates that the error @@ -814,6 +820,9 @@ static unsigned long handle_pg_range(unsigned long pg_start, unsigned long old_covered_state; unsigned long res = 0, flags; + pr_debug("Hot adding %lu pages starting at pfn 0x%lx.\n", pg_count, + pg_start); + spin_lock_irqsave(&dm_device.ha_lock, flags); list_for_each_entry(has, &dm_device.ha_region_list, list) { /* @@ -1025,8 +1034,13 @@ static void process_info(struct hv_dynmem_device *dm, struct dm_info_msg *msg) switch (info_hdr->type) { case INFO_TYPE_MAX_PAGE_CNT: - pr_info("Received INFO_TYPE_MAX_PAGE_CNT\n"); - pr_info("Data Size is %d\n", info_hdr->data_size); + if (info_hdr->data_size == sizeof(__u64)) { + __u64 *max_page_count = (__u64 *)&info_hdr[1]; + + pr_info("INFO_TYPE_MAX_PAGE_CNT = %llu\n", + *max_page_count); + } + break; default: pr_info("Received Unknown type: %d\n", info_hdr->type); @@ -1196,8 +1210,6 @@ static unsigned int alloc_balloon_pages(struct hv_dynmem_device *dm, return num_pages; } - - static void balloon_up(struct work_struct *dummy) { unsigned int num_pages = dm_device.balloon_wrk.num_pages; @@ -1224,6 +1236,10 @@ static void balloon_up(struct work_struct *dummy) /* Refuse to balloon below the floor, keep the 2M granularity. */ if (avail_pages < num_pages || avail_pages - num_pages < floor) { + pr_warn("Balloon request will be partially fulfilled. %s\n", + avail_pages < num_pages ? "Not enough memory." : + "Balloon floor reached."); + num_pages = avail_pages > floor ? (avail_pages - floor) : 0; num_pages -= num_pages % PAGES_IN_2M; } @@ -1245,6 +1261,9 @@ static void balloon_up(struct work_struct *dummy) } if (num_ballooned == 0 || num_ballooned == num_pages) { + pr_debug("Ballooned %u out of %u requested pages.\n", + num_pages, dm_device.balloon_wrk.num_pages); + bl_resp->more_pages = 0; done = true; dm_device.state = DM_INITIALIZED; @@ -1292,12 +1311,16 @@ static void balloon_down(struct hv_dynmem_device *dm, int range_count = req->range_count; struct dm_unballoon_response resp; int i; + unsigned int prev_pages_ballooned = dm->num_pages_ballooned; for (i = 0; i < range_count; i++) { free_balloon_pages(dm, &range_array[i]); complete(&dm_device.config_event); } + pr_debug("Freed %u ballooned pages.\n", + prev_pages_ballooned - dm->num_pages_ballooned); + if (req->more_pages == 1) return; @@ -1365,6 +1388,7 @@ static void version_resp(struct hv_dynmem_device *dm, version_req.hdr.size = sizeof(struct dm_version_request); version_req.hdr.trans_id = atomic_inc_return(&trans_id); version_req.version.version = dm->next_version; + dm->version = version_req.version.version; /* * Set the next version to try in case current version fails. @@ -1501,7 +1525,11 @@ static int balloon_probe(struct hv_device *dev, struct dm_version_request version_req; struct dm_capabilities cap_msg; +#ifdef CONFIG_MEMORY_HOTPLUG do_hot_add = hot_add; +#else + do_hot_add = false; +#endif /* * First allocate a send buffer. @@ -1553,6 +1581,7 @@ static int balloon_probe(struct hv_device *dev, version_req.hdr.trans_id = atomic_inc_return(&trans_id); version_req.version.version = DYNMEM_PROTOCOL_VERSION_WIN10; version_req.is_last_attempt = 0; + dm_device.version = version_req.version.version; ret = vmbus_sendpacket(dev->channel, &version_req, sizeof(struct dm_version_request), @@ -1575,6 +1604,11 @@ static int balloon_probe(struct hv_device *dev, ret = -ETIMEDOUT; goto probe_error2; } + + pr_info("Using Dynamic Memory protocol version %u.%u\n", + DYNMEM_MAJOR_VERSION(dm_device.version), + DYNMEM_MINOR_VERSION(dm_device.version)); + /* * Now submit our capabilities to the host. */ diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c index a6707133c297..eee238cc60bd 100644 --- a/drivers/hv/hv_snapshot.c +++ b/drivers/hv/hv_snapshot.c @@ -31,7 +31,10 @@ #define VSS_MINOR 0 #define VSS_VERSION (VSS_MAJOR << 16 | VSS_MINOR) -#define VSS_USERSPACE_TIMEOUT (msecs_to_jiffies(10 * 1000)) +/* + * Timeout values are based on expecations from host + */ +#define VSS_FREEZE_TIMEOUT (15 * 60) /* * Global state maintained for transaction that is being processed. For a class @@ -120,7 +123,7 @@ static int vss_handle_handshake(struct hv_vss_msg *vss_msg) default: return -EINVAL; } - pr_debug("VSS: userspace daemon ver. %d connected\n", dm_reg_value); + pr_info("VSS: userspace daemon ver. %d connected\n", dm_reg_value); return 0; } @@ -128,8 +131,10 @@ static int vss_on_msg(void *msg, int len) { struct hv_vss_msg *vss_msg = (struct hv_vss_msg *)msg; - if (len != sizeof(*vss_msg)) + if (len != sizeof(*vss_msg)) { + pr_debug("VSS: Message size does not match length\n"); return -EINVAL; + } if (vss_msg->vss_hdr.operation == VSS_OP_REGISTER || vss_msg->vss_hdr.operation == VSS_OP_REGISTER1) { @@ -137,8 +142,11 @@ static int vss_on_msg(void *msg, int len) * Don't process registration messages if we're in the middle * of a transaction processing. */ - if (vss_transaction.state > HVUTIL_READY) + if (vss_transaction.state > HVUTIL_READY) { + pr_debug("VSS: Got unexpected registration request\n"); return -EINVAL; + } + return vss_handle_handshake(vss_msg); } else if (vss_transaction.state == HVUTIL_USERSPACE_REQ) { vss_transaction.state = HVUTIL_USERSPACE_RECV; @@ -155,7 +163,7 @@ static int vss_on_msg(void *msg, int len) } } else { /* This is a spurious call! */ - pr_warn("VSS: Transaction not active\n"); + pr_debug("VSS: Transaction not active\n"); return -EINVAL; } return 0; @@ -168,8 +176,10 @@ static void vss_send_op(void) struct hv_vss_msg *vss_msg; /* The transaction state is wrong. */ - if (vss_transaction.state != HVUTIL_HOSTMSG_RECEIVED) + if (vss_transaction.state != HVUTIL_HOSTMSG_RECEIVED) { + pr_debug("VSS: Unexpected attempt to send to daemon\n"); return; + } vss_msg = kzalloc(sizeof(*vss_msg), GFP_KERNEL); if (!vss_msg) @@ -179,7 +189,8 @@ static void vss_send_op(void) vss_transaction.state = HVUTIL_USERSPACE_REQ; - schedule_delayed_work(&vss_timeout_work, VSS_USERSPACE_TIMEOUT); + schedule_delayed_work(&vss_timeout_work, op == VSS_OP_FREEZE ? + VSS_FREEZE_TIMEOUT * HZ : HV_UTIL_TIMEOUT * HZ); rc = hvutil_transport_send(hvt, vss_msg, sizeof(*vss_msg), NULL); if (rc) { @@ -210,9 +221,13 @@ static void vss_handle_request(struct work_struct *dummy) case VSS_OP_HOT_BACKUP: if (vss_transaction.state < HVUTIL_READY) { /* Userspace is not registered yet */ + pr_debug("VSS: Not ready for request.\n"); vss_respond_to_host(HV_E_FAIL); return; } + + pr_debug("VSS: Received request for op code: %d\n", + vss_transaction.msg->vss_hdr.operation); vss_transaction.state = HVUTIL_HOSTMSG_RECEIVED; vss_send_op(); return; @@ -353,8 +368,10 @@ hv_vss_init(struct hv_util_service *srv) hvt = hvutil_transport_init(vss_devname, CN_VSS_IDX, CN_VSS_VAL, vss_on_msg, vss_on_reset); - if (!hvt) + if (!hvt) { + pr_warn("VSS: Failed to initialize transport\n"); return -EFAULT; + } return 0; } diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index bcd06306f3e8..e7707747f56d 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -389,16 +389,19 @@ static int util_probe(struct hv_device *dev, ts_srv_version = TS_VERSION_1; hb_srv_version = HB_VERSION_1; break; - case(VERSION_WIN10): + case VERSION_WIN7: + case VERSION_WIN8: + case VERSION_WIN8_1: util_fw_version = UTIL_FW_VERSION; sd_srv_version = SD_VERSION; - ts_srv_version = TS_VERSION; + ts_srv_version = TS_VERSION_3; hb_srv_version = HB_VERSION; break; + case VERSION_WIN10: default: util_fw_version = UTIL_FW_VERSION; sd_srv_version = SD_VERSION; - ts_srv_version = TS_VERSION_3; + ts_srv_version = TS_VERSION; hb_srv_version = HB_VERSION; } diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index a5b4442433c8..0675b395ce5c 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -38,7 +38,7 @@ /* * Timeout for guest-host handshake for services. */ -#define HV_UTIL_NEGO_TIMEOUT 60 +#define HV_UTIL_NEGO_TIMEOUT 55 /* * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent @@ -527,14 +527,14 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info); -int hv_ringbuffer_write(struct hv_ring_buffer_info *ring_info, +int hv_ringbuffer_write(struct vmbus_channel *channel, struct kvec *kv_list, - u32 kv_count, bool *signal, bool lock, - enum hv_signal_policy policy); + u32 kv_count, bool lock, + bool kick_q); -int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info, +int hv_ringbuffer_read(struct vmbus_channel *channel, void *buffer, u32 buflen, u32 *buffer_actual_len, - u64 *requestid, bool *signal, bool raw); + u64 *requestid, bool raw); void hv_ringbuffer_get_debuginfo(struct hv_ring_buffer_info *ring_info, struct hv_ring_buffer_debug_info *debug_info); diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 08043da1a61c..cd49cb17eb7f 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -66,21 +66,25 @@ u32 hv_end_read(struct hv_ring_buffer_info *rbi) * once the ring buffer is empty, it will clear the * interrupt_mask and re-check to see if new data has * arrived. + * + * KYS: Oct. 30, 2016: + * It looks like Windows hosts have logic to deal with DOS attacks that + * can be triggered if it receives interrupts when it is not expecting + * the interrupt. The host expects interrupts only when the ring + * transitions from empty to non-empty (or full to non full on the guest + * to host ring). + * So, base the signaling decision solely on the ring state until the + * host logic is fixed. */ -static bool hv_need_to_signal(u32 old_write, struct hv_ring_buffer_info *rbi, - enum hv_signal_policy policy) +static void hv_signal_on_write(u32 old_write, struct vmbus_channel *channel, + bool kick_q) { + struct hv_ring_buffer_info *rbi = &channel->outbound; + virt_mb(); if (READ_ONCE(rbi->ring_buffer->interrupt_mask)) - return false; - - /* - * When the client wants to control signaling, - * we only honour the host interrupt mask. - */ - if (policy == HV_SIGNAL_POLICY_EXPLICIT) - return true; + return; /* check interrupt_mask before read_index */ virt_rmb(); @@ -89,9 +93,9 @@ static bool hv_need_to_signal(u32 old_write, struct hv_ring_buffer_info *rbi, * ring transitions from being empty to non-empty. */ if (old_write == READ_ONCE(rbi->ring_buffer->read_index)) - return true; + vmbus_setevent(channel); - return false; + return; } /* Get the next write location for the specified ring buffer. */ @@ -280,9 +284,9 @@ void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info) } /* Write to the ring buffer. */ -int hv_ringbuffer_write(struct hv_ring_buffer_info *outring_info, - struct kvec *kv_list, u32 kv_count, bool *signal, bool lock, - enum hv_signal_policy policy) +int hv_ringbuffer_write(struct vmbus_channel *channel, + struct kvec *kv_list, u32 kv_count, bool lock, + bool kick_q) { int i = 0; u32 bytes_avail_towrite; @@ -292,6 +296,7 @@ int hv_ringbuffer_write(struct hv_ring_buffer_info *outring_info, u32 old_write; u64 prev_indices = 0; unsigned long flags = 0; + struct hv_ring_buffer_info *outring_info = &channel->outbound; for (i = 0; i < kv_count; i++) totalbytes_towrite += kv_list[i].iov_len; @@ -344,13 +349,13 @@ int hv_ringbuffer_write(struct hv_ring_buffer_info *outring_info, if (lock) spin_unlock_irqrestore(&outring_info->ring_lock, flags); - *signal = hv_need_to_signal(old_write, outring_info, policy); + hv_signal_on_write(old_write, channel, kick_q); return 0; } -int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info, +int hv_ringbuffer_read(struct vmbus_channel *channel, void *buffer, u32 buflen, u32 *buffer_actual_len, - u64 *requestid, bool *signal, bool raw) + u64 *requestid, bool raw) { u32 bytes_avail_toread; u32 next_read_location = 0; @@ -359,6 +364,7 @@ int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info, u32 offset; u32 packetlen; int ret = 0; + struct hv_ring_buffer_info *inring_info = &channel->inbound; if (buflen <= 0) return -EINVAL; @@ -416,7 +422,7 @@ int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info, /* Update the read index */ hv_set_next_read_location(inring_info, next_read_location); - *signal = hv_need_to_signal_on_read(inring_info); + hv_signal_on_read(channel); return ret; } diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 0276d2ef06ee..230c62e7f567 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -45,6 +45,11 @@ #include <linux/random.h> #include "hyperv_vmbus.h" +struct vmbus_dynid { + struct list_head node; + struct hv_vmbus_device_id id; +}; + static struct acpi_device *hv_acpi_dev; static struct completion probe_event; @@ -500,7 +505,7 @@ static ssize_t device_show(struct device *dev, static DEVICE_ATTR_RO(device); /* Set up per device attributes in /sys/bus/vmbus/devices/<bus device> */ -static struct attribute *vmbus_attrs[] = { +static struct attribute *vmbus_dev_attrs[] = { &dev_attr_id.attr, &dev_attr_state.attr, &dev_attr_monitor_id.attr, @@ -528,7 +533,7 @@ static struct attribute *vmbus_attrs[] = { &dev_attr_device.attr, NULL, }; -ATTRIBUTE_GROUPS(vmbus); +ATTRIBUTE_GROUPS(vmbus_dev); /* * vmbus_uevent - add uevent for our device @@ -565,10 +570,29 @@ static inline bool is_null_guid(const uuid_le *guid) * Return a matching hv_vmbus_device_id pointer. * If there is no match, return NULL. */ -static const struct hv_vmbus_device_id *hv_vmbus_get_id( - const struct hv_vmbus_device_id *id, +static const struct hv_vmbus_device_id *hv_vmbus_get_id(struct hv_driver *drv, const uuid_le *guid) { + const struct hv_vmbus_device_id *id = NULL; + struct vmbus_dynid *dynid; + + /* Look at the dynamic ids first, before the static ones */ + spin_lock(&drv->dynids.lock); + list_for_each_entry(dynid, &drv->dynids.list, node) { + if (!uuid_le_cmp(dynid->id.guid, *guid)) { + id = &dynid->id; + break; + } + } + spin_unlock(&drv->dynids.lock); + + if (id) + return id; + + id = drv->id_table; + if (id == NULL) + return NULL; /* empty device table */ + for (; !is_null_guid(&id->guid); id++) if (!uuid_le_cmp(id->guid, *guid)) return id; @@ -576,6 +600,134 @@ static const struct hv_vmbus_device_id *hv_vmbus_get_id( return NULL; } +/* vmbus_add_dynid - add a new device ID to this driver and re-probe devices */ +static int vmbus_add_dynid(struct hv_driver *drv, uuid_le *guid) +{ + struct vmbus_dynid *dynid; + + dynid = kzalloc(sizeof(*dynid), GFP_KERNEL); + if (!dynid) + return -ENOMEM; + + dynid->id.guid = *guid; + + spin_lock(&drv->dynids.lock); + list_add_tail(&dynid->node, &drv->dynids.list); + spin_unlock(&drv->dynids.lock); + + return driver_attach(&drv->driver); +} + +static void vmbus_free_dynids(struct hv_driver *drv) +{ + struct vmbus_dynid *dynid, *n; + + spin_lock(&drv->dynids.lock); + list_for_each_entry_safe(dynid, n, &drv->dynids.list, node) { + list_del(&dynid->node); + kfree(dynid); + } + spin_unlock(&drv->dynids.lock); +} + +/* Parse string of form: 1b4e28ba-2fa1-11d2-883f-b9a761bde3f */ +static int get_uuid_le(const char *str, uuid_le *uu) +{ + unsigned int b[16]; + int i; + + if (strlen(str) < 37) + return -1; + + for (i = 0; i < 36; i++) { + switch (i) { + case 8: case 13: case 18: case 23: + if (str[i] != '-') + return -1; + break; + default: + if (!isxdigit(str[i])) + return -1; + } + } + + /* unparse little endian output byte order */ + if (sscanf(str, + "%2x%2x%2x%2x-%2x%2x-%2x%2x-%2x%2x-%2x%2x%2x%2x%2x%2x", + &b[3], &b[2], &b[1], &b[0], + &b[5], &b[4], &b[7], &b[6], &b[8], &b[9], + &b[10], &b[11], &b[12], &b[13], &b[14], &b[15]) != 16) + return -1; + + for (i = 0; i < 16; i++) + uu->b[i] = b[i]; + return 0; +} + +/* + * store_new_id - sysfs frontend to vmbus_add_dynid() + * + * Allow GUIDs to be added to an existing driver via sysfs. + */ +static ssize_t new_id_store(struct device_driver *driver, const char *buf, + size_t count) +{ + struct hv_driver *drv = drv_to_hv_drv(driver); + uuid_le guid = NULL_UUID_LE; + ssize_t retval; + + if (get_uuid_le(buf, &guid) != 0) + return -EINVAL; + + if (hv_vmbus_get_id(drv, &guid)) + return -EEXIST; + + retval = vmbus_add_dynid(drv, &guid); + if (retval) + return retval; + return count; +} +static DRIVER_ATTR_WO(new_id); + +/* + * store_remove_id - remove a PCI device ID from this driver + * + * Removes a dynamic pci device ID to this driver. + */ +static ssize_t remove_id_store(struct device_driver *driver, const char *buf, + size_t count) +{ + struct hv_driver *drv = drv_to_hv_drv(driver); + struct vmbus_dynid *dynid, *n; + uuid_le guid = NULL_UUID_LE; + size_t retval = -ENODEV; + + if (get_uuid_le(buf, &guid)) + return -EINVAL; + + spin_lock(&drv->dynids.lock); + list_for_each_entry_safe(dynid, n, &drv->dynids.list, node) { + struct hv_vmbus_device_id *id = &dynid->id; + + if (!uuid_le_cmp(id->guid, guid)) { + list_del(&dynid->node); + kfree(dynid); + retval = count; + break; + } + } + spin_unlock(&drv->dynids.lock); + + return retval; +} +static DRIVER_ATTR_WO(remove_id); + +static struct attribute *vmbus_drv_attrs[] = { + &driver_attr_new_id.attr, + &driver_attr_remove_id.attr, + NULL, +}; +ATTRIBUTE_GROUPS(vmbus_drv); /* @@ -590,7 +742,7 @@ static int vmbus_match(struct device *device, struct device_driver *driver) if (is_hvsock_channel(hv_dev->channel)) return drv->hvsock; - if (hv_vmbus_get_id(drv->id_table, &hv_dev->dev_type)) + if (hv_vmbus_get_id(drv, &hv_dev->dev_type)) return 1; return 0; @@ -607,7 +759,7 @@ static int vmbus_probe(struct device *child_device) struct hv_device *dev = device_to_hv_device(child_device); const struct hv_vmbus_device_id *dev_id; - dev_id = hv_vmbus_get_id(drv->id_table, &dev->dev_type); + dev_id = hv_vmbus_get_id(drv, &dev->dev_type); if (drv->probe) { ret = drv->probe(dev, dev_id); if (ret != 0) @@ -684,7 +836,8 @@ static struct bus_type hv_bus = { .remove = vmbus_remove, .probe = vmbus_probe, .uevent = vmbus_uevent, - .dev_groups = vmbus_groups, + .dev_groups = vmbus_dev_groups, + .drv_groups = vmbus_drv_groups, }; struct onmessage_work_context { @@ -905,6 +1058,9 @@ int __vmbus_driver_register(struct hv_driver *hv_driver, struct module *owner, c hv_driver->driver.mod_name = mod_name; hv_driver->driver.bus = &hv_bus; + spin_lock_init(&hv_driver->dynids.lock); + INIT_LIST_HEAD(&hv_driver->dynids.list); + ret = driver_register(&hv_driver->driver); return ret; @@ -923,8 +1079,10 @@ void vmbus_driver_unregister(struct hv_driver *hv_driver) { pr_info("unregistering driver %s\n", hv_driver->name); - if (!vmbus_exists()) + if (!vmbus_exists()) { driver_unregister(&hv_driver->driver); + vmbus_free_dynids(hv_driver); + } } EXPORT_SYMBOL_GPL(vmbus_driver_unregister); |