diff options
author | André Fabian Silva Delgado <emulatorman@parabola.nu> | 2016-03-25 03:53:42 -0300 |
---|---|---|
committer | André Fabian Silva Delgado <emulatorman@parabola.nu> | 2016-03-25 03:53:42 -0300 |
commit | 03dd4cb26d967f9588437b0fc9cc0e8353322bb7 (patch) | |
tree | fa581f6dc1c0596391690d1f67eceef3af8246dc /drivers/hv | |
parent | d4e493caf788ef44982e131ff9c786546904d934 (diff) |
Linux-libre 4.5-gnu
Diffstat (limited to 'drivers/hv')
-rw-r--r-- | drivers/hv/channel.c | 120 | ||||
-rw-r--r-- | drivers/hv/channel_mgmt.c | 48 | ||||
-rw-r--r-- | drivers/hv/connection.c | 18 | ||||
-rw-r--r-- | drivers/hv/hv.c | 29 | ||||
-rw-r--r-- | drivers/hv/hv_fcopy.c | 37 | ||||
-rw-r--r-- | drivers/hv/hv_kvp.c | 33 | ||||
-rw-r--r-- | drivers/hv/hv_snapshot.c | 36 | ||||
-rw-r--r-- | drivers/hv/hv_utils_transport.c | 130 | ||||
-rw-r--r-- | drivers/hv/hv_utils_transport.h | 3 | ||||
-rw-r--r-- | drivers/hv/hyperv_vmbus.h | 114 | ||||
-rw-r--r-- | drivers/hv/ring_buffer.c | 218 | ||||
-rw-r--r-- | drivers/hv/vmbus_drv.c | 82 |
12 files changed, 371 insertions, 497 deletions
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index 9098f13f2..1161d68a1 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -28,6 +28,7 @@ #include <linux/module.h> #include <linux/hyperv.h> #include <linux/uio.h> +#include <linux/interrupt.h> #include "hyperv_vmbus.h" @@ -496,8 +497,33 @@ static void reset_channel_cb(void *arg) static int vmbus_close_internal(struct vmbus_channel *channel) { struct vmbus_channel_close_channel *msg; + struct tasklet_struct *tasklet; int ret; + /* + * process_chn_event(), running in the tasklet, can race + * with vmbus_close_internal() in the case of SMP guest, e.g., when + * the former is accessing channel->inbound.ring_buffer, the latter + * could be freeing the ring_buffer pages. + * + * To resolve the race, we can serialize them by disabling the + * tasklet when the latter is running here. + */ + tasklet = hv_context.event_dpc[channel->target_cpu]; + tasklet_disable(tasklet); + + /* + * In case a device driver's probe() fails (e.g., + * util_probe() -> vmbus_open() returns -ENOMEM) and the device is + * rescinded later (e.g., we dynamically disble an Integrated Service + * in Hyper-V Manager), the driver's remove() invokes vmbus_close(): + * here we should skip most of the below cleanup work. + */ + if (channel->state != CHANNEL_OPENED_STATE) { + ret = -EINVAL; + goto out; + } + channel->state = CHANNEL_OPEN_STATE; channel->sc_creation_callback = NULL; /* Stop callback and cancel the timer asap */ @@ -525,7 +551,7 @@ static int vmbus_close_internal(struct vmbus_channel *channel) * If we failed to post the close msg, * it is perhaps better to leak memory. */ - return ret; + goto out; } /* Tear down the gpadl for the channel's ring buffer */ @@ -538,7 +564,7 @@ static int vmbus_close_internal(struct vmbus_channel *channel) * If we failed to teardown gpadl, * it is perhaps better to leak memory. */ - return ret; + goto out; } } @@ -549,12 +575,9 @@ static int vmbus_close_internal(struct vmbus_channel *channel) free_pages((unsigned long)channel->ringbuffer_pages, get_order(channel->ringbuffer_pagecount * PAGE_SIZE)); - /* - * If the channel has been rescinded; process device removal. - */ - if (channel->rescind) - hv_process_channel_removal(channel, - channel->offermsg.child_relid); +out: + tasklet_enable(tasklet); + return ret; } @@ -899,46 +922,29 @@ EXPORT_SYMBOL_GPL(vmbus_sendpacket_multipagebuffer); * * Mainly used by Hyper-V drivers. */ -int vmbus_recvpacket(struct vmbus_channel *channel, void *buffer, - u32 bufferlen, u32 *buffer_actual_len, u64 *requestid) +static inline int +__vmbus_recvpacket(struct vmbus_channel *channel, void *buffer, + u32 bufferlen, u32 *buffer_actual_len, u64 *requestid, + bool raw) { - struct vmpacket_descriptor desc; - u32 packetlen; - u32 userlen; int ret; bool signal = false; - *buffer_actual_len = 0; - *requestid = 0; - - - ret = hv_ringbuffer_peek(&channel->inbound, &desc, - sizeof(struct vmpacket_descriptor)); - if (ret != 0) - return 0; - - packetlen = desc.len8 << 3; - userlen = packetlen - (desc.offset8 << 3); - - *buffer_actual_len = userlen; - - if (userlen > bufferlen) { - - pr_err("Buffer too small - got %d needs %d\n", - bufferlen, userlen); - return -ETOOSMALL; - } - - *requestid = desc.trans_id; - - /* Copy over the packet to the user buffer */ - ret = hv_ringbuffer_read(&channel->inbound, buffer, userlen, - (desc.offset8 << 3), &signal); + ret = hv_ringbuffer_read(&channel->inbound, buffer, bufferlen, + buffer_actual_len, requestid, &signal, raw); if (signal) vmbus_setevent(channel); - return 0; + return ret; +} + +int vmbus_recvpacket(struct vmbus_channel *channel, void *buffer, + u32 bufferlen, u32 *buffer_actual_len, + u64 *requestid) +{ + return __vmbus_recvpacket(channel, buffer, bufferlen, + buffer_actual_len, requestid, false); } EXPORT_SYMBOL(vmbus_recvpacket); @@ -949,37 +955,7 @@ int vmbus_recvpacket_raw(struct vmbus_channel *channel, void *buffer, u32 bufferlen, u32 *buffer_actual_len, u64 *requestid) { - struct vmpacket_descriptor desc; - u32 packetlen; - int ret; - bool signal = false; - - *buffer_actual_len = 0; - *requestid = 0; - - - ret = hv_ringbuffer_peek(&channel->inbound, &desc, - sizeof(struct vmpacket_descriptor)); - if (ret != 0) - return 0; - - - packetlen = desc.len8 << 3; - - *buffer_actual_len = packetlen; - - if (packetlen > bufferlen) - return -ENOBUFS; - - *requestid = desc.trans_id; - - /* Copy over the entire packet to the user buffer */ - ret = hv_ringbuffer_read(&channel->inbound, buffer, packetlen, 0, - &signal); - - if (signal) - vmbus_setevent(channel); - - return ret; + return __vmbus_recvpacket(channel, buffer, bufferlen, + buffer_actual_len, requestid, true); } EXPORT_SYMBOL_GPL(vmbus_recvpacket_raw); diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 652afd11a..1c1ad4704 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -177,19 +177,24 @@ static void percpu_channel_deq(void *arg) } -void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid) +static void vmbus_release_relid(u32 relid) { struct vmbus_channel_relid_released msg; - unsigned long flags; - struct vmbus_channel *primary_channel; memset(&msg, 0, sizeof(struct vmbus_channel_relid_released)); msg.child_relid = relid; msg.header.msgtype = CHANNELMSG_RELID_RELEASED; vmbus_post_msg(&msg, sizeof(struct vmbus_channel_relid_released)); +} - if (channel == NULL) - return; +void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid) +{ + unsigned long flags; + struct vmbus_channel *primary_channel; + + vmbus_release_relid(relid); + + BUG_ON(!channel->rescind); if (channel->target_cpu != get_cpu()) { put_cpu(); @@ -201,9 +206,9 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid) } if (channel->primary_channel == NULL) { - spin_lock_irqsave(&vmbus_connection.channel_lock, flags); + mutex_lock(&vmbus_connection.channel_mutex); list_del(&channel->listentry); - spin_unlock_irqrestore(&vmbus_connection.channel_lock, flags); + mutex_unlock(&vmbus_connection.channel_mutex); primary_channel = channel; } else { @@ -230,9 +235,7 @@ void vmbus_free_channels(void) list_for_each_entry_safe(channel, tmp, &vmbus_connection.chn_list, listentry) { - /* if we don't set rescind to true, vmbus_close_internal() - * won't invoke hv_process_channel_removal(). - */ + /* hv_process_channel_removal() needs this */ channel->rescind = true; vmbus_device_unregister(channel->device_obj); @@ -250,7 +253,7 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) unsigned long flags; /* Make sure this is a new offer */ - spin_lock_irqsave(&vmbus_connection.channel_lock, flags); + mutex_lock(&vmbus_connection.channel_mutex); list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) { if (!uuid_le_cmp(channel->offermsg.offer.if_type, @@ -266,7 +269,7 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) list_add_tail(&newchannel->listentry, &vmbus_connection.chn_list); - spin_unlock_irqrestore(&vmbus_connection.channel_lock, flags); + mutex_unlock(&vmbus_connection.channel_mutex); if (!fnew) { /* @@ -336,9 +339,11 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) return; err_deq_chan: - spin_lock_irqsave(&vmbus_connection.channel_lock, flags); + vmbus_release_relid(newchannel->offermsg.child_relid); + + mutex_lock(&vmbus_connection.channel_mutex); list_del(&newchannel->listentry); - spin_unlock_irqrestore(&vmbus_connection.channel_lock, flags); + mutex_unlock(&vmbus_connection.channel_mutex); if (newchannel->target_cpu != get_cpu()) { put_cpu(); @@ -356,8 +361,10 @@ err_free_chan: enum { IDE = 0, SCSI, + FC, NIC, ND_NIC, + PCIE, MAX_PERF_CHN, }; @@ -371,10 +378,14 @@ static const struct hv_vmbus_device_id hp_devs[] = { { HV_IDE_GUID, }, /* Storage - SCSI */ { HV_SCSI_GUID, }, + /* Storage - FC */ + { HV_SYNTHFC_GUID, }, /* Network */ { HV_NIC_GUID, }, /* NetworkDirect Guest RDMA */ { HV_ND_GUID, }, + /* PCI Express Pass Through */ + { HV_PCIE_GUID, }, }; @@ -405,8 +416,7 @@ static void init_vp_index(struct vmbus_channel *channel, const uuid_le *type_gui struct cpumask *alloced_mask; for (i = IDE; i < MAX_PERF_CHN; i++) { - if (!memcmp(type_guid->b, hp_devs[i].guid, - sizeof(uuid_le))) { + if (!uuid_le_cmp(*type_guid, hp_devs[i].guid)) { perf_chn = true; break; } @@ -585,7 +595,11 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) channel = relid2channel(rescind->child_relid); if (channel == NULL) { - hv_process_channel_removal(NULL, rescind->child_relid); + /* + * This is very impossible, because in + * vmbus_process_offer(), we have already invoked + * vmbus_release_relid() on error. + */ return; } diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c index 4fc2e8836..3dc5a9c7f 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -83,10 +83,13 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, msg->interrupt_page = virt_to_phys(vmbus_connection.int_page); msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]); msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]); - if (version >= VERSION_WIN8_1) { - msg->target_vcpu = hv_context.vp_index[get_cpu()]; - put_cpu(); - } + /* + * We want all channel messages to be delivered on CPU 0. + * This has been the behavior pre-win8. This is not + * perf issue and having all channel messages delivered on CPU 0 + * would be ok. + */ + msg->target_vcpu = 0; /* * Add to list before we send the request since we may @@ -146,7 +149,7 @@ int vmbus_connect(void) spin_lock_init(&vmbus_connection.channelmsg_lock); INIT_LIST_HEAD(&vmbus_connection.chn_list); - spin_lock_init(&vmbus_connection.channel_lock); + mutex_init(&vmbus_connection.channel_mutex); /* * Setup the vmbus event connection for channel interrupt @@ -282,11 +285,10 @@ struct vmbus_channel *relid2channel(u32 relid) { struct vmbus_channel *channel; struct vmbus_channel *found_channel = NULL; - unsigned long flags; struct list_head *cur, *tmp; struct vmbus_channel *cur_sc; - spin_lock_irqsave(&vmbus_connection.channel_lock, flags); + mutex_lock(&vmbus_connection.channel_mutex); list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) { if (channel->offermsg.child_relid == relid) { found_channel = channel; @@ -305,7 +307,7 @@ struct vmbus_channel *relid2channel(u32 relid) } } } - spin_unlock_irqrestore(&vmbus_connection.channel_lock, flags); + mutex_unlock(&vmbus_connection.channel_mutex); return found_channel; } diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 6341be873..11bca51ef 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -89,9 +89,9 @@ static int query_hypervisor_info(void) } /* - * do_hypercall- Invoke the specified hypercall + * hv_do_hypercall- Invoke the specified hypercall */ -static u64 do_hypercall(u64 control, void *input, void *output) +u64 hv_do_hypercall(u64 control, void *input, void *output) { u64 input_address = (input) ? virt_to_phys(input) : 0; u64 output_address = (output) ? virt_to_phys(output) : 0; @@ -132,6 +132,7 @@ static u64 do_hypercall(u64 control, void *input, void *output) return hv_status_lo | ((u64)hv_status_hi << 32); #endif /* !x86_64 */ } +EXPORT_SYMBOL_GPL(hv_do_hypercall); #ifdef CONFIG_X86_64 static cycle_t read_hv_clock_tsc(struct clocksource *arg) @@ -139,7 +140,7 @@ static cycle_t read_hv_clock_tsc(struct clocksource *arg) cycle_t current_tick; struct ms_hyperv_tsc_page *tsc_pg = hv_context.tsc_page; - if (tsc_pg->tsc_sequence != -1) { + if (tsc_pg->tsc_sequence != 0) { /* * Use the tsc page to compute the value. */ @@ -161,7 +162,7 @@ static cycle_t read_hv_clock_tsc(struct clocksource *arg) if (tsc_pg->tsc_sequence == sequence) return current_tick; - if (tsc_pg->tsc_sequence != -1) + if (tsc_pg->tsc_sequence != 0) continue; /* * Fallback using MSR method. @@ -192,9 +193,7 @@ int hv_init(void) { int max_leaf; union hv_x64_msr_hypercall_contents hypercall_msr; - union hv_x64_msr_hypercall_contents tsc_msr; void *virtaddr = NULL; - void *va_tsc = NULL; memset(hv_context.synic_event_page, 0, sizeof(void *) * NR_CPUS); memset(hv_context.synic_message_page, 0, @@ -240,6 +239,9 @@ int hv_init(void) #ifdef CONFIG_X86_64 if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) { + union hv_x64_msr_hypercall_contents tsc_msr; + void *va_tsc; + va_tsc = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL); if (!va_tsc) goto cleanup; @@ -315,7 +317,7 @@ int hv_post_message(union hv_connection_id connection_id, { struct hv_input_post_message *aligned_msg; - u16 status; + u64 status; if (payload_size > HV_MESSAGE_PAYLOAD_BYTE_COUNT) return -EMSGSIZE; @@ -329,11 +331,10 @@ int hv_post_message(union hv_connection_id connection_id, aligned_msg->payload_size = payload_size; memcpy((void *)aligned_msg->payload, payload, payload_size); - status = do_hypercall(HVCALL_POST_MESSAGE, aligned_msg, NULL) - & 0xFFFF; + status = hv_do_hypercall(HVCALL_POST_MESSAGE, aligned_msg, NULL); put_cpu(); - return status; + return status & 0xFFFF; } @@ -343,13 +344,13 @@ int hv_post_message(union hv_connection_id connection_id, * * This involves a hypercall. */ -u16 hv_signal_event(void *con_id) +int hv_signal_event(void *con_id) { - u16 status; + u64 status; - status = (do_hypercall(HVCALL_SIGNAL_EVENT, con_id, NULL) & 0xFFFF); + status = hv_do_hypercall(HVCALL_SIGNAL_EVENT, con_id, NULL); - return status; + return status & 0xFFFF; } static int hv_ce_set_next_event(unsigned long delta, diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c index db4b887b8..c37a71e13 100644 --- a/drivers/hv/hv_fcopy.c +++ b/drivers/hv/hv_fcopy.c @@ -51,7 +51,6 @@ static struct { struct hv_fcopy_hdr *fcopy_msg; /* current message */ struct vmbus_channel *recv_channel; /* chn we got the request */ u64 recv_req_id; /* request ID. */ - void *fcopy_context; /* for the channel callback */ } fcopy_transaction; static void fcopy_respond_to_host(int error); @@ -67,6 +66,13 @@ static struct hvutil_transport *hvt; */ static int dm_reg_value; +static void fcopy_poll_wrapper(void *channel) +{ + /* Transaction is finished, reset the state here to avoid races. */ + fcopy_transaction.state = HVUTIL_READY; + hv_fcopy_onchannelcallback(channel); +} + static void fcopy_timeout_func(struct work_struct *dummy) { /* @@ -74,13 +80,7 @@ static void fcopy_timeout_func(struct work_struct *dummy) * process the pending transaction. */ fcopy_respond_to_host(HV_E_FAIL); - - /* Transaction is finished, reset the state. */ - if (fcopy_transaction.state > HVUTIL_READY) - fcopy_transaction.state = HVUTIL_READY; - - hv_poll_channel(fcopy_transaction.fcopy_context, - hv_fcopy_onchannelcallback); + hv_poll_channel(fcopy_transaction.recv_channel, fcopy_poll_wrapper); } static int fcopy_handle_handshake(u32 version) @@ -108,9 +108,7 @@ static int fcopy_handle_handshake(u32 version) return -EINVAL; } pr_debug("FCP: userspace daemon ver. %d registered\n", version); - fcopy_transaction.state = HVUTIL_READY; - hv_poll_channel(fcopy_transaction.fcopy_context, - hv_fcopy_onchannelcallback); + hv_poll_channel(fcopy_transaction.recv_channel, fcopy_poll_wrapper); return 0; } @@ -227,15 +225,8 @@ void hv_fcopy_onchannelcallback(void *context) int util_fw_version; int fcopy_srv_version; - if (fcopy_transaction.state > HVUTIL_READY) { - /* - * We will defer processing this callback once - * the current transaction is complete. - */ - fcopy_transaction.fcopy_context = context; + if (fcopy_transaction.state > HVUTIL_READY) return; - } - fcopy_transaction.fcopy_context = NULL; vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 2, &recvlen, &requestid); @@ -275,7 +266,8 @@ void hv_fcopy_onchannelcallback(void *context) * Send the information to the user-level daemon. */ schedule_work(&fcopy_send_work); - schedule_delayed_work(&fcopy_timeout_work, 5*HZ); + schedule_delayed_work(&fcopy_timeout_work, + HV_UTIL_TIMEOUT * HZ); return; } icmsghdr->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE; @@ -304,9 +296,8 @@ static int fcopy_on_msg(void *msg, int len) if (cancel_delayed_work_sync(&fcopy_timeout_work)) { fcopy_transaction.state = HVUTIL_USERSPACE_RECV; fcopy_respond_to_host(*val); - fcopy_transaction.state = HVUTIL_READY; - hv_poll_channel(fcopy_transaction.fcopy_context, - hv_fcopy_onchannelcallback); + hv_poll_channel(fcopy_transaction.recv_channel, + fcopy_poll_wrapper); } return 0; diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c index 74c38a9f3..d4ab81bcd 100644 --- a/drivers/hv/hv_kvp.c +++ b/drivers/hv/hv_kvp.c @@ -66,7 +66,6 @@ static struct { struct hv_kvp_msg *kvp_msg; /* current message */ struct vmbus_channel *recv_channel; /* chn we got the request */ u64 recv_req_id; /* request ID. */ - void *kvp_context; /* for the channel callback */ } kvp_transaction; /* @@ -94,6 +93,13 @@ static struct hvutil_transport *hvt; */ #define HV_DRV_VERSION "3.1" +static void kvp_poll_wrapper(void *channel) +{ + /* Transaction is finished, reset the state here to avoid races. */ + kvp_transaction.state = HVUTIL_READY; + hv_kvp_onchannelcallback(channel); +} + static void kvp_register(int reg_value) { @@ -121,12 +127,7 @@ static void kvp_timeout_func(struct work_struct *dummy) */ kvp_respond_to_host(NULL, HV_E_FAIL); - /* Transaction is finished, reset the state. */ - if (kvp_transaction.state > HVUTIL_READY) - kvp_transaction.state = HVUTIL_READY; - - hv_poll_channel(kvp_transaction.kvp_context, - hv_kvp_onchannelcallback); + hv_poll_channel(kvp_transaction.recv_channel, kvp_poll_wrapper); } static int kvp_handle_handshake(struct hv_kvp_msg *msg) @@ -153,7 +154,7 @@ static int kvp_handle_handshake(struct hv_kvp_msg *msg) pr_debug("KVP: userspace daemon ver. %d registered\n", KVP_OP_REGISTER); kvp_register(dm_reg_value); - kvp_transaction.state = HVUTIL_READY; + hv_poll_channel(kvp_transaction.recv_channel, kvp_poll_wrapper); return 0; } @@ -218,9 +219,7 @@ static int kvp_on_msg(void *msg, int len) */ if (cancel_delayed_work_sync(&kvp_timeout_work)) { kvp_respond_to_host(message, error); - kvp_transaction.state = HVUTIL_READY; - hv_poll_channel(kvp_transaction.kvp_context, - hv_kvp_onchannelcallback); + hv_poll_channel(kvp_transaction.recv_channel, kvp_poll_wrapper); } return 0; @@ -596,15 +595,8 @@ void hv_kvp_onchannelcallback(void *context) int util_fw_version; int kvp_srv_version; - if (kvp_transaction.state > HVUTIL_READY) { - /* - * We will defer processing this callback once - * the current transaction is complete. - */ - kvp_transaction.kvp_context = context; + if (kvp_transaction.state > HVUTIL_READY) return; - } - kvp_transaction.kvp_context = NULL; vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 4, &recvlen, &requestid); @@ -668,7 +660,8 @@ void hv_kvp_onchannelcallback(void *context) * user-mode not responding. */ schedule_work(&kvp_sendkey_work); - schedule_delayed_work(&kvp_timeout_work, 5*HZ); + schedule_delayed_work(&kvp_timeout_work, + HV_UTIL_TIMEOUT * HZ); return; diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c index 815405f2e..67def4a83 100644 --- a/drivers/hv/hv_snapshot.c +++ b/drivers/hv/hv_snapshot.c @@ -53,7 +53,6 @@ static struct { struct vmbus_channel *recv_channel; /* chn we got the request */ u64 recv_req_id; /* request ID. */ struct hv_vss_msg *msg; /* current message */ - void *vss_context; /* for the channel callback */ } vss_transaction; @@ -74,6 +73,13 @@ static void vss_timeout_func(struct work_struct *dummy); static DECLARE_DELAYED_WORK(vss_timeout_work, vss_timeout_func); static DECLARE_WORK(vss_send_op_work, vss_send_op); +static void vss_poll_wrapper(void *channel) +{ + /* Transaction is finished, reset the state here to avoid races. */ + vss_transaction.state = HVUTIL_READY; + hv_vss_onchannelcallback(channel); +} + /* * Callback when data is received from user mode. */ @@ -86,12 +92,7 @@ static void vss_timeout_func(struct work_struct *dummy) pr_warn("VSS: timeout waiting for daemon to reply\n"); vss_respond_to_host(HV_E_FAIL); - /* Transaction is finished, reset the state. */ - if (vss_transaction.state > HVUTIL_READY) - vss_transaction.state = HVUTIL_READY; - - hv_poll_channel(vss_transaction.vss_context, - hv_vss_onchannelcallback); + hv_poll_channel(vss_transaction.recv_channel, vss_poll_wrapper); } static int vss_handle_handshake(struct hv_vss_msg *vss_msg) @@ -112,7 +113,7 @@ static int vss_handle_handshake(struct hv_vss_msg *vss_msg) default: return -EINVAL; } - vss_transaction.state = HVUTIL_READY; + hv_poll_channel(vss_transaction.recv_channel, vss_poll_wrapper); pr_debug("VSS: userspace daemon ver. %d registered\n", dm_reg_value); return 0; } @@ -138,9 +139,8 @@ static int vss_on_msg(void *msg, int len) if (cancel_delayed_work_sync(&vss_timeout_work)) { vss_respond_to_host(vss_msg->error); /* Transaction is finished, reset the state. */ - vss_transaction.state = HVUTIL_READY; - hv_poll_channel(vss_transaction.vss_context, - hv_vss_onchannelcallback); + hv_poll_channel(vss_transaction.recv_channel, + vss_poll_wrapper); } } else { /* This is a spurious call! */ @@ -238,15 +238,8 @@ void hv_vss_onchannelcallback(void *context) struct icmsg_hdr *icmsghdrp; struct icmsg_negotiate *negop = NULL; - if (vss_transaction.state > HVUTIL_READY) { - /* - * We will defer processing this callback once - * the current transaction is complete. - */ - vss_transaction.vss_context = context; + if (vss_transaction.state > HVUTIL_READY) return; - } - vss_transaction.vss_context = NULL; vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 2, &recvlen, &requestid); @@ -338,6 +331,11 @@ static void vss_on_reset(void) int hv_vss_init(struct hv_util_service *srv) { + if (vmbus_proto_version < VERSION_WIN8_1) { + pr_warn("Integration service 'Backup (volume snapshot)'" + " not supported on this host version.\n"); + return -ENOTSUPP; + } recv_buffer = srv->recv_buffer; /* diff --git a/drivers/hv/hv_utils_transport.c b/drivers/hv/hv_utils_transport.c index 6a9d80a53..4f42c0e20 100644 --- a/drivers/hv/hv_utils_transport.c +++ b/drivers/hv/hv_utils_transport.c @@ -27,11 +27,9 @@ static struct list_head hvt_list = LIST_HEAD_INIT(hvt_list); static void hvt_reset(struct hvutil_transport *hvt) { - mutex_lock(&hvt->outmsg_lock); kfree(hvt->outmsg); hvt->outmsg = NULL; hvt->outmsg_len = 0; - mutex_unlock(&hvt->outmsg_lock); if (hvt->on_reset) hvt->on_reset(); } @@ -44,10 +42,17 @@ static ssize_t hvt_op_read(struct file *file, char __user *buf, hvt = container_of(file->f_op, struct hvutil_transport, fops); - if (wait_event_interruptible(hvt->outmsg_q, hvt->outmsg_len > 0)) + if (wait_event_interruptible(hvt->outmsg_q, hvt->outmsg_len > 0 || + hvt->mode != HVUTIL_TRANSPORT_CHARDEV)) return -EINTR; - mutex_lock(&hvt->outmsg_lock); + mutex_lock(&hvt->lock); + + if (hvt->mode == HVUTIL_TRANSPORT_DESTROY) { + ret = -EBADF; + goto out_unlock; + } + if (!hvt->outmsg) { ret = -EAGAIN; goto out_unlock; @@ -68,7 +73,7 @@ static ssize_t hvt_op_read(struct file *file, char __user *buf, hvt->outmsg_len = 0; out_unlock: - mutex_unlock(&hvt->outmsg_lock); + mutex_unlock(&hvt->lock); return ret; } @@ -77,19 +82,22 @@ static ssize_t hvt_op_write(struct file *file, const char __user *buf, { struct hvutil_transport *hvt; u8 *inmsg; + int ret; hvt = container_of(file->f_op, struct hvutil_transport, fops); - inmsg = kzalloc(count, GFP_KERNEL); - if (copy_from_user(inmsg, buf, count)) { - kfree(inmsg); - return -EFAULT; - } - if (hvt->on_msg(inmsg, count)) - return -EFAULT; + inmsg = memdup_user(buf, count); + if (IS_ERR(inmsg)) + return PTR_ERR(inmsg); + + if (hvt->mode == HVUTIL_TRANSPORT_DESTROY) + ret = -EBADF; + else + ret = hvt->on_msg(inmsg, count); + kfree(inmsg); - return count; + return ret ? ret : count; } static unsigned int hvt_op_poll(struct file *file, poll_table *wait) @@ -99,6 +107,10 @@ static unsigned int hvt_op_poll(struct file *file, poll_table *wait) hvt = container_of(file->f_op, struct hvutil_transport, fops); poll_wait(file, &hvt->outmsg_q, wait); + + if (hvt->mode == HVUTIL_TRANSPORT_DESTROY) + return POLLERR | POLLHUP; + if (hvt->outmsg_len > 0) return POLLIN | POLLRDNORM; @@ -108,40 +120,68 @@ static unsigned int hvt_op_poll(struct file *file, poll_table *wait) static int hvt_op_open(struct inode *inode, struct file *file) { struct hvutil_transport *hvt; + int ret = 0; + bool issue_reset = false; hvt = container_of(file->f_op, struct hvutil_transport, fops); - /* - * Switching to CHARDEV mode. We switch bach to INIT when device - * gets released. - */ - if (hvt->mode == HVUTIL_TRANSPORT_INIT) + mutex_lock(&hvt->lock); + + if (hvt->mode == HVUTIL_TRANSPORT_DESTROY) { + ret = -EBADF; + } else if (hvt->mode == HVUTIL_TRANSPORT_INIT) { + /* + * Switching to CHARDEV mode. We switch bach to INIT when + * device gets released. + */ hvt->mode = HVUTIL_TRANSPORT_CHARDEV; + } else if (hvt->mode == HVUTIL_TRANSPORT_NETLINK) { /* * We're switching from netlink communication to using char * device. Issue the reset first. */ - hvt_reset(hvt); + issue_reset = true; hvt->mode = HVUTIL_TRANSPORT_CHARDEV; - } else - return -EBUSY; + } else { + ret = -EBUSY; + } - return 0; + if (issue_reset) + hvt_reset(hvt); + + mutex_unlock(&hvt->lock); + + return ret; +} + +static void hvt_transport_free(struct hvutil_transport *hvt) +{ + misc_deregister(&hvt->mdev); + kfree(hvt->outmsg); + kfree(hvt); } static int hvt_op_release(struct inode *inode, struct file *file) { struct hvutil_transport *hvt; + int mode_old; hvt = container_of(file->f_op, struct hvutil_transport, fops); - hvt->mode = HVUTIL_TRANSPORT_INIT; + mutex_lock(&hvt->lock); + mode_old = hvt->mode; + if (hvt->mode != HVUTIL_TRANSPORT_DESTROY) + hvt->mode = HVUTIL_TRANSPORT_INIT; /* * Cleanup message buffers to avoid spurious messages when the daemon * connects back. */ hvt_reset(hvt); + mutex_unlock(&hvt->lock); + + if (mode_old == HVUTIL_TRANSPORT_DESTROY) + hvt_transport_free(hvt); return 0; } @@ -168,6 +208,7 @@ static void hvt_cn_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp) * Switching to NETLINK mode. Switching to CHARDEV happens when someone * opens the device. */ + mutex_lock(&hvt->lock); if (hvt->mode == HVUTIL_TRANSPORT_INIT) hvt->mode = HVUTIL_TRANSPORT_NETLINK; @@ -175,6 +216,7 @@ static void hvt_cn_callback(struct cn_msg *msg, struct netlink_skb_parms *nsp) hvt_found->on_msg(msg->data, msg->len); else pr_warn("hvt_cn_callback: unexpected netlink message!\n"); + mutex_unlock(&hvt->lock); } int hvutil_transport_send(struct hvutil_transport *hvt, void *msg, int len) @@ -182,7 +224,8 @@ int hvutil_transport_send(struct hvutil_transport *hvt, void *msg, int len) struct cn_msg *cn_msg; int ret = 0; - if (hvt->mode == HVUTIL_TRANSPORT_INIT) { + if (hvt->mode == HVUTIL_TRANSPORT_INIT || + hvt->mode == HVUTIL_TRANSPORT_DESTROY) { return -EINVAL; } else if (hvt->mode == HVUTIL_TRANSPORT_NETLINK) { cn_msg = kzalloc(sizeof(*cn_msg) + len, GFP_ATOMIC); @@ -197,18 +240,26 @@ int hvutil_transport_send(struct hvutil_transport *hvt, void *msg, int len) return ret; } /* HVUTIL_TRANSPORT_CHARDEV */ - mutex_lock(&hvt->outmsg_lock); + mutex_lock(&hvt->lock); + if (hvt->mode != HVUTIL_TRANSPORT_CHARDEV) { + ret = -EINVAL; + goto out_unlock; + } + if (hvt->outmsg) { /* Previous message wasn't received */ ret = -EFAULT; goto out_unlock; } hvt->outmsg = kzalloc(len, GFP_KERNEL); - memcpy(hvt->outmsg, msg, len); - hvt->outmsg_len = len; - wake_up_interruptible(&hvt->outmsg_q); + if (hvt->outmsg) { + memcpy(hvt->outmsg, msg, len); + hvt->outmsg_len = len; + wake_up_interruptible(&hvt->outmsg_q); + } else + ret = -ENOMEM; out_unlock: - mutex_unlock(&hvt->outmsg_lock); + mutex_unlock(&hvt->lock); return ret; } @@ -239,7 +290,7 @@ struct hvutil_transport *hvutil_transport_init(const char *name, hvt->mdev.fops = &hvt->fops; init_waitqueue_head(&hvt->outmsg_q); - mutex_init(&hvt->outmsg_lock); + mutex_init(&hvt->lock); spin_lock(&hvt_list_lock); list_add(&hvt->list, &hvt_list); @@ -265,12 +316,25 @@ err_free_hvt: void hvutil_transport_destroy(struct hvutil_transport *hvt) { + int mode_old; + + mutex_lock(&hvt->lock); + mode_old = hvt->mode; + hvt->mode = HVUTIL_TRANSPORT_DESTROY; + wake_up_interruptible(&hvt->outmsg_q); + mutex_unlock(&hvt->lock); + + /* + * In case we were in 'chardev' mode we still have an open fd so we + * have to defer freeing the device. Netlink interface can be freed + * now. + */ spin_lock(&hvt_list_lock); list_del(&hvt->list); spin_unlock(&hvt_list_lock); if (hvt->cn_id.idx > 0 && hvt->cn_id.val > 0) cn_del_callback(&hvt->cn_id); - misc_deregister(&hvt->mdev); - kfree(hvt->outmsg); - kfree(hvt); + + if (mode_old != HVUTIL_TRANSPORT_CHARDEV) + hvt_transport_free(hvt); } diff --git a/drivers/hv/hv_utils_transport.h b/drivers/hv/hv_utils_transport.h index 314c76ce1..06254a165 100644 --- a/drivers/hv/hv_utils_transport.h +++ b/drivers/hv/hv_utils_transport.h @@ -25,6 +25,7 @@ enum hvutil_transport_mode { HVUTIL_TRANSPORT_INIT = 0, HVUTIL_TRANSPORT_NETLINK, HVUTIL_TRANSPORT_CHARDEV, + HVUTIL_TRANSPORT_DESTROY, }; struct hvutil_transport { @@ -38,7 +39,7 @@ struct hvutil_transport { u8 *outmsg; /* message to the userspace */ int outmsg_len; /* its length */ wait_queue_head_t outmsg_q; /* poll/read wait queue */ - struct mutex outmsg_lock; /* protects outmsg */ + struct mutex lock; /* protects struct members */ }; struct hvutil_transport *hvutil_transport_init(const char *name, diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 378263656..4ebc796b4 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -31,6 +31,11 @@ #include <linux/hyperv.h> /* + * Timeout for services such as KVP and fcopy. + */ +#define HV_UTIL_TIMEOUT 30 + +/* * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent * is set by CPUID(HVCPUID_VERSION_FEATURES). */ @@ -63,10 +68,6 @@ enum hv_cpuid_function { /* Define version of the synthetic interrupt controller. */ #define HV_SYNIC_VERSION (1) -/* Define synthetic interrupt controller message constants. */ -#define HV_MESSAGE_SIZE (256) -#define HV_MESSAGE_PAYLOAD_BYTE_COUNT (240) -#define HV_MESSAGE_PAYLOAD_QWORD_COUNT (30) #define HV_ANY_VP (0xFFFFFFFF) /* Define synthetic interrupt controller flag constants. */ @@ -74,48 +75,9 @@ enum hv_cpuid_function { #define HV_EVENT_FLAGS_BYTE_COUNT (256) #define HV_EVENT_FLAGS_DWORD_COUNT (256 / sizeof(u32)) -/* Define hypervisor message types. */ -enum hv_message_type { - HVMSG_NONE = 0x00000000, - - /* Memory access messages. */ - HVMSG_UNMAPPED_GPA = 0x80000000, - HVMSG_GPA_INTERCEPT = 0x80000001, - - /* Timer notification messages. */ - HVMSG_TIMER_EXPIRED = 0x80000010, - - /* Error messages. */ - HVMSG_INVALID_VP_REGISTER_VALUE = 0x80000020, - HVMSG_UNRECOVERABLE_EXCEPTION = 0x80000021, - HVMSG_UNSUPPORTED_FEATURE = 0x80000022, - - /* Trace buffer complete messages. */ - HVMSG_EVENTLOG_BUFFERCOMPLETE = 0x80000040, - - /* Platform-specific processor intercept messages. */ - HVMSG_X64_IOPORT_INTERCEPT = 0x80010000, - HVMSG_X64_MSR_INTERCEPT = 0x80010001, - HVMSG_X64_CPUID_INTERCEPT = 0x80010002, - HVMSG_X64_EXCEPTION_INTERCEPT = 0x80010003, - HVMSG_X64_APIC_EOI = 0x80010004, - HVMSG_X64_LEGACY_FP_ERROR = 0x80010005 -}; - -#define HV_SYNIC_STIMER_COUNT (4) - /* Define invalid partition identifier. */ #define HV_PARTITION_ID_INVALID ((u64)0x0) -/* Define port identifier type. */ -union hv_port_id { - u32 asu32; - struct { - u32 id:24; - u32 reserved:8; - } u ; -}; - /* Define port type. */ enum hv_port_type { HVPORT_MSG = 1, @@ -163,27 +125,6 @@ struct hv_connection_info { }; }; -/* Define synthetic interrupt controller message flags. */ -union hv_message_flags { - u8 asu8; - struct { - u8 msg_pending:1; - u8 reserved:7; - }; -}; - -/* Define synthetic interrupt controller message header. */ -struct hv_message_header { - enum hv_message_type message_type; - u8 payload_size; - union hv_message_flags message_flags; - u8 reserved[2]; - union { - u64 sender; - union hv_port_id port; - }; -}; - /* * Timer configuration register. */ @@ -200,31 +141,9 @@ union hv_timer_config { }; }; - -/* Define timer message payload structure. */ -struct hv_timer_message_payload { - u32 timer_index; - u32 reserved; - u64 expiration_time; /* When the timer expired */ - u64 delivery_time; /* When the message was delivered */ -}; - -/* Define synthetic interrupt controller message format. */ -struct hv_message { - struct hv_message_header header; - union { - u64 payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT]; - } u ; -}; - /* Define the number of message buffers associated with each port. */ #define HV_PORT_MESSAGE_BUFFER_COUNT (16) -/* Define the synthetic interrupt message page layout. */ -struct hv_message_page { - struct hv_message sint_message[HV_SYNIC_SINT_COUNT]; -}; - /* Define the synthetic interrupt controller event flags format. */ union hv_synic_event_flags { u8 flags8[HV_EVENT_FLAGS_BYTE_COUNT]; @@ -347,7 +266,7 @@ enum hv_call_code { struct hv_input_post_message { union hv_connection_id connectionid; u32 reserved; - enum hv_message_type message_type; + u32 message_type; u32 payload_size; u64 payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT]; }; @@ -582,7 +501,7 @@ extern int hv_post_message(union hv_connection_id connection_id, enum hv_message_type message_type, void *payload, size_t payload_size); -extern u16 hv_signal_event(void *con_id); +extern int hv_signal_event(void *con_id); extern int hv_synic_alloc(void); @@ -614,14 +533,9 @@ int hv_ringbuffer_write(struct hv_ring_buffer_info *ring_info, struct kvec *kv_list, u32 kv_count, bool *signal); -int hv_ringbuffer_peek(struct hv_ring_buffer_info *ring_info, void *buffer, - u32 buflen); - -int hv_ringbuffer_read(struct hv_ring_buffer_info *ring_info, - void *buffer, - u32 buflen, - u32 offset, bool *signal); - +int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info, + void *buffer, u32 buflen, u32 *buffer_actual_len, + u64 *requestid, bool *signal, bool raw); void hv_ringbuffer_get_debuginfo(struct hv_ring_buffer_info *ring_info, struct hv_ring_buffer_debug_info *debug_info); @@ -678,7 +592,7 @@ struct vmbus_connection { /* List of channels */ struct list_head chn_list; - spinlock_t channel_lock; + struct mutex channel_mutex; struct workqueue_struct *work_queue; }; @@ -759,11 +673,7 @@ static inline void hv_poll_channel(struct vmbus_channel *channel, if (!channel) return; - if (channel->target_cpu != smp_processor_id()) - smp_call_function_single(channel->target_cpu, - cb, channel, true); - else - cb(channel); + smp_call_function_single(channel->target_cpu, cb, channel, true); } enum hvutil_device_state { diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c index 70a1a9a22..b53702ce6 100644 --- a/drivers/hv/ring_buffer.c +++ b/drivers/hv/ring_buffer.c @@ -112,9 +112,7 @@ static bool hv_need_to_signal_on_read(u32 prev_write_sz, u32 read_loc = rbi->ring_buffer->read_index; u32 pending_sz = rbi->ring_buffer->pending_send_sz; - /* - * If the other end is not blocked on write don't bother. - */ + /* If the other end is not blocked on write don't bother. */ if (pending_sz == 0) return false; @@ -128,12 +126,7 @@ static bool hv_need_to_signal_on_read(u32 prev_write_sz, return false; } -/* - * hv_get_next_write_location() - * - * Get the next write location for the specified ring buffer - * - */ +/* Get the next write location for the specified ring buffer. */ static inline u32 hv_get_next_write_location(struct hv_ring_buffer_info *ring_info) { @@ -142,12 +135,7 @@ hv_get_next_write_location(struct hv_ring_buffer_info *ring_info) return next; } -/* - * hv_set_next_write_location() - * - * Set the next write location for the specified ring buffer - * - */ +/* Set the next write location for the specified ring buffer. */ static inline void hv_set_next_write_location(struct hv_ring_buffer_info *ring_info, u32 next_write_location) @@ -155,11 +143,7 @@ hv_set_next_write_location(struct hv_ring_buffer_info *ring_info, ring_info->ring_buffer->write_index = next_write_location; } -/* - * hv_get_next_read_location() - * - * Get the next read location for the specified ring buffer - */ +/* Get the next read location for the specified ring buffer. */ static inline u32 hv_get_next_read_location(struct hv_ring_buffer_info *ring_info) { @@ -169,10 +153,8 @@ hv_get_next_read_location(struct hv_ring_buffer_info *ring_info) } /* - * hv_get_next_readlocation_withoffset() - * * Get the next read location + offset for the specified ring buffer. - * This allows the caller to skip + * This allows the caller to skip. */ static inline u32 hv_get_next_readlocation_withoffset(struct hv_ring_buffer_info *ring_info, @@ -186,13 +168,7 @@ hv_get_next_readlocation_withoffset(struct hv_ring_buffer_info *ring_info, return next; } -/* - * - * hv_set_next_read_location() - * - * Set the next read location for the specified ring buffer - * - */ +/* Set the next read location for the specified ring buffer. */ static inline void hv_set_next_read_location(struct hv_ring_buffer_info *ring_info, u32 next_read_location) @@ -201,12 +177,7 @@ hv_set_next_read_location(struct hv_ring_buffer_info *ring_info, } -/* - * - * hv_get_ring_buffer() - * - * Get the start of the ring buffer - */ +/* Get the start of the ring buffer. */ static inline void * hv_get_ring_buffer(struct hv_ring_buffer_info *ring_info) { @@ -214,25 +185,14 @@ hv_get_ring_buffer(struct hv_ring_buffer_info *ring_info) } -/* - * - * hv_get_ring_buffersize() - * - * Get the size of the ring buffer - */ +/* Get the size of the ring buffer. */ static inline u32 hv_get_ring_buffersize(struct hv_ring_buffer_info *ring_info) { return ring_info->ring_datasize; } -/* - * - * hv_get_ring_bufferindices() - * - * Get the read and write indices as u64 of the specified ring buffer - * - */ +/* Get the read and write indices as u64 of the specified ring buffer. */ static inline u64 hv_get_ring_bufferindices(struct hv_ring_buffer_info *ring_info) { @@ -240,12 +200,8 @@ hv_get_ring_bufferindices(struct hv_ring_buffer_info *ring_info) } /* - * - * hv_copyfrom_ringbuffer() - * * Helper routine to copy to source from ring buffer. * Assume there is enough room. Handles wrap-around in src case only!! - * */ static u32 hv_copyfrom_ringbuffer( struct hv_ring_buffer_info *ring_info, @@ -277,12 +233,8 @@ static u32 hv_copyfrom_ringbuffer( /* - * - * hv_copyto_ringbuffer() - * * Helper routine to copy from source to ring buffer. * Assume there is enough room. Handles wrap-around in dest case only!! - * */ static u32 hv_copyto_ringbuffer( struct hv_ring_buffer_info *ring_info, @@ -308,13 +260,7 @@ static u32 hv_copyto_ringbuffer( return start_write_offset; } -/* - * - * hv_ringbuffer_get_debuginfo() - * - * Get various debug metrics for the specified ring buffer - * - */ +/* Get various debug metrics for the specified ring buffer. */ void hv_ringbuffer_get_debuginfo(struct hv_ring_buffer_info *ring_info, struct hv_ring_buffer_debug_info *debug_info) { @@ -337,13 +283,7 @@ void hv_ringbuffer_get_debuginfo(struct hv_ring_buffer_info *ring_info, } } -/* - * - * hv_ringbuffer_init() - * - *Initialize the ring buffer - * - */ +/* Initialize the ring buffer. */ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, void *buffer, u32 buflen) { @@ -356,9 +296,7 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, ring_info->ring_buffer->read_index = ring_info->ring_buffer->write_index = 0; - /* - * Set the feature bit for enabling flow control. - */ + /* Set the feature bit for enabling flow control. */ ring_info->ring_buffer->feature_bits.value = 1; ring_info->ring_size = buflen; @@ -369,24 +307,12 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, return 0; } -/* - * - * hv_ringbuffer_cleanup() - * - * Cleanup the ring buffer - * - */ +/* Cleanup the ring buffer. */ void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info) { } -/* - * - * hv_ringbuffer_write() - * - * Write to the ring buffer - * - */ +/* 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) { @@ -411,10 +337,11 @@ int hv_ringbuffer_write(struct hv_ring_buffer_info *outring_info, &bytes_avail_toread, &bytes_avail_towrite); - - /* If there is only room for the packet, assume it is full. */ - /* Otherwise, the next time around, we think the ring buffer */ - /* is empty since the read index == write index */ + /* + * If there is only room for the packet, assume it is full. + * Otherwise, the next time around, we think the ring buffer + * is empty since the read index == write index. + */ if (bytes_avail_towrite <= totalbytes_towrite) { spin_unlock_irqrestore(&outring_info->ring_lock, flags); return -EAGAIN; @@ -453,80 +380,59 @@ int hv_ringbuffer_write(struct hv_ring_buffer_info *outring_info, return 0; } - -/* - * - * hv_ringbuffer_peek() - * - * Read without advancing the read index - * - */ -int hv_ringbuffer_peek(struct hv_ring_buffer_info *Inring_info, - void *Buffer, u32 buflen) -{ - u32 bytes_avail_towrite; - u32 bytes_avail_toread; - u32 next_read_location = 0; - unsigned long flags; - - spin_lock_irqsave(&Inring_info->ring_lock, flags); - - hv_get_ringbuffer_availbytes(Inring_info, - &bytes_avail_toread, - &bytes_avail_towrite); - - /* Make sure there is something to read */ - if (bytes_avail_toread < buflen) { - - spin_unlock_irqrestore(&Inring_info->ring_lock, flags); - - return -EAGAIN; - } - - /* Convert to byte offset */ - next_read_location = hv_get_next_read_location(Inring_info); - - next_read_location = hv_copyfrom_ringbuffer(Inring_info, - Buffer, - buflen, - next_read_location); - - spin_unlock_irqrestore(&Inring_info->ring_lock, flags); - - return 0; -} - - -/* - * - * hv_ringbuffer_read() - * - * Read and advance the read index - * - */ -int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info, void *buffer, - u32 buflen, u32 offset, bool *signal) +int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info, + void *buffer, u32 buflen, u32 *buffer_actual_len, + u64 *requestid, bool *signal, bool raw) { u32 bytes_avail_towrite; u32 bytes_avail_toread; u32 next_read_location = 0; u64 prev_indices = 0; unsigned long flags; + struct vmpacket_descriptor desc; + u32 offset; + u32 packetlen; + int ret = 0; if (buflen <= 0) return -EINVAL; spin_lock_irqsave(&inring_info->ring_lock, flags); + *buffer_actual_len = 0; + *requestid = 0; + hv_get_ringbuffer_availbytes(inring_info, &bytes_avail_toread, &bytes_avail_towrite); /* Make sure there is something to read */ - if (bytes_avail_toread < buflen) { - spin_unlock_irqrestore(&inring_info->ring_lock, flags); + if (bytes_avail_toread < sizeof(desc)) { + /* + * No error is set when there is even no header, drivers are + * supposed to analyze buffer_actual_len. + */ + goto out_unlock; + } - return -EAGAIN; + next_read_location = hv_get_next_read_location(inring_info); + next_read_location = hv_copyfrom_ringbuffer(inring_info, &desc, + sizeof(desc), + next_read_location); + + offset = raw ? 0 : (desc.offset8 << 3); + packetlen = (desc.len8 << 3) - offset; + *buffer_actual_len = packetlen; + *requestid = desc.trans_id; + + if (bytes_avail_toread < packetlen + offset) { + ret = -EAGAIN; + goto out_unlock; + } + + if (packetlen > buflen) { + ret = -ENOBUFS; + goto out_unlock; } next_read_location = @@ -534,7 +440,7 @@ int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info, void *buffer, next_read_location = hv_copyfrom_ringbuffer(inring_info, buffer, - buflen, + packetlen, next_read_location); next_read_location = hv_copyfrom_ringbuffer(inring_info, @@ -542,17 +448,19 @@ int hv_ringbuffer_read(struct hv_ring_buffer_info *inring_info, void *buffer, sizeof(u64), next_read_location); - /* Make sure all reads are done before we update the read index since */ - /* the writer may start writing to the read area once the read index */ - /*is updated */ + /* + * Make sure all reads are done before we update the read index since + * the writer may start writing to the read area once the read index + * is updated. + */ mb(); /* Update the read index */ hv_set_next_read_location(inring_info, next_read_location); - spin_unlock_irqrestore(&inring_info->ring_lock, flags); - *signal = hv_need_to_signal_on_read(bytes_avail_towrite, inring_info); - return 0; +out_unlock: + spin_unlock_irqrestore(&inring_info->ring_lock, flags); + return ret; } diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index f19b6f7a4..328e4c380 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -47,7 +47,6 @@ static struct acpi_device *hv_acpi_dev; static struct tasklet_struct msg_dpc; static struct completion probe_event; -static int irq; static void hyperv_report_panic(struct pt_regs *regs) @@ -531,9 +530,9 @@ static int vmbus_uevent(struct device *device, struct kobj_uevent_env *env) static const uuid_le null_guid; -static inline bool is_null_guid(const __u8 *guid) +static inline bool is_null_guid(const uuid_le *guid) { - if (memcmp(guid, &null_guid, sizeof(uuid_le))) + if (uuid_le_cmp(*guid, null_guid)) return false; return true; } @@ -544,10 +543,10 @@ static inline bool is_null_guid(const __u8 *guid) */ static const struct hv_vmbus_device_id *hv_vmbus_get_id( const struct hv_vmbus_device_id *id, - const __u8 *guid) + const uuid_le *guid) { - for (; !is_null_guid(id->guid); id++) - if (!memcmp(&id->guid, guid, sizeof(uuid_le))) + for (; !is_null_guid(&id->guid); id++) + if (!uuid_le_cmp(id->guid, *guid)) return id; return NULL; @@ -563,7 +562,7 @@ static int vmbus_match(struct device *device, struct device_driver *driver) struct hv_driver *drv = drv_to_hv_drv(driver); struct hv_device *hv_dev = device_to_hv_device(device); - if (hv_vmbus_get_id(drv->id_table, hv_dev->dev_type.b)) + if (hv_vmbus_get_id(drv->id_table, &hv_dev->dev_type)) return 1; return 0; @@ -580,7 +579,7 @@ 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.b); + dev_id = hv_vmbus_get_id(drv->id_table, &dev->dev_type); if (drv->probe) { ret = drv->probe(dev, dev_id); if (ret != 0) @@ -602,23 +601,11 @@ static int vmbus_remove(struct device *child_device) { struct hv_driver *drv; struct hv_device *dev = device_to_hv_device(child_device); - u32 relid = dev->channel->offermsg.child_relid; if (child_device->driver) { drv = drv_to_hv_drv(child_device->driver); if (drv->remove) drv->remove(dev); - else { - hv_process_channel_removal(dev->channel, relid); - pr_err("remove not set for driver %s\n", - dev_name(child_device)); - } - } else { - /* - * We don't have a driver for this device; deal with the - * rescind message by removing the channel. - */ - hv_process_channel_removal(dev->channel, relid); } return 0; @@ -653,7 +640,10 @@ static void vmbus_shutdown(struct device *child_device) static void vmbus_device_release(struct device *device) { struct hv_device *hv_dev = device_to_hv_device(device); + struct vmbus_channel *channel = hv_dev->channel; + hv_process_channel_removal(channel, + channel->offermsg.child_relid); kfree(hv_dev); } @@ -835,10 +825,9 @@ static void vmbus_isr(void) * Here, we * - initialize the vmbus driver context * - invoke the vmbus hv main init routine - * - get the irq resource * - retrieve the channel offers */ -static int vmbus_bus_init(int irq) +static int vmbus_bus_init(void) { int ret; @@ -867,7 +856,7 @@ static int vmbus_bus_init(int irq) on_each_cpu(hv_synic_init, NULL, 1); ret = vmbus_connect(); if (ret) - goto err_alloc; + goto err_connect; if (vmbus_proto_version > VERSION_WIN7) cpu_hotplug_disable(); @@ -885,6 +874,8 @@ static int vmbus_bus_init(int irq) return 0; +err_connect: + on_each_cpu(hv_synic_cleanup, NULL, 1); err_alloc: hv_synic_free(); hv_remove_vmbus_irq(); @@ -1031,9 +1022,6 @@ static acpi_status vmbus_walk_resources(struct acpi_resource *res, void *ctx) struct resource **prev_res = NULL; switch (res->type) { - case ACPI_RESOURCE_TYPE_IRQ: - irq = res->data.irq.interrupts[0]; - return AE_OK; /* * "Address" descriptors are for bus windows. Ignore @@ -1075,12 +1063,28 @@ static acpi_status vmbus_walk_resources(struct acpi_resource *res, void *ctx) new_res->start = start; new_res->end = end; + /* + * Stick ranges from higher in address space at the front of the list. + * If two ranges are adjacent, merge them. + */ do { if (!*old_res) { *old_res = new_res; break; } + if (((*old_res)->end + 1) == new_res->start) { + (*old_res)->end = new_res->end; + kfree(new_res); + break; + } + + if ((*old_res)->start == new_res->end + 1) { + (*old_res)->start = new_res->start; + kfree(new_res); + break; + } + if ((*old_res)->end < new_res->start) { new_res->sibling = *old_res; if (prev_res) @@ -1191,6 +1195,23 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj, } EXPORT_SYMBOL_GPL(vmbus_allocate_mmio); +/** + * vmbus_cpu_number_to_vp_number() - Map CPU to VP. + * @cpu_number: CPU number in Linux terms + * + * This function returns the mapping between the Linux processor + * number and the hypervisor's virtual processor number, useful + * in making hypercalls and such that talk about specific + * processors. + * + * Return: Virtual processor number in Hyper-V terms + */ +int vmbus_cpu_number_to_vp_number(int cpu_number) +{ + return hv_context.vp_index[cpu_number]; +} +EXPORT_SYMBOL_GPL(vmbus_cpu_number_to_vp_number); + static int vmbus_acpi_add(struct acpi_device *device) { acpi_status result; @@ -1275,7 +1296,7 @@ static int __init hv_acpi_init(void) init_completion(&probe_event); /* - * Get irq resources first. + * Get ACPI resources first. */ ret = acpi_bus_register_driver(&vmbus_acpi_driver); @@ -1288,12 +1309,7 @@ static int __init hv_acpi_init(void) goto cleanup; } - if (irq <= 0) { - ret = -ENODEV; - goto cleanup; - } - - ret = vmbus_bus_init(irq); + ret = vmbus_bus_init(); if (ret) goto cleanup; |