From 52f993b8e89487ec9ee15a7fb4979e0f09a45b27 Mon Sep 17 00:00:00 2001 From: Yunhong Jiang Date: Wed, 8 Mar 2017 23:13:28 -0800 Subject: Upgrade to 4.4.50-rt62 The current kernel is based on rt kernel v4.4.6-rt14. We will upgrade it to 4.4.50-rt62. The command to achieve it is: a) Clone a git repo from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-stable-rt.git b) Get the diff between this two changesets: git diff 640eca2901f3435e616157b11379d3223a44b391 705619beeea1b0b48219a683fd1a901a86fdaf5e where the two commits are: [yjiang5@jnakajim-build linux-stable-rt]$ git show --oneline --name-only 640eca2901f3435e616157b11379d3223a44b391 640eca2901f3 v4.4.6-rt14 localversion-rt [yjiang5@jnakajim-build linux-stable-rt]$ git show --oneline --name-only 705619beeea1b0b48219a683fd1a901a86fdaf5e 705619beeea1 Linux 4.4.50-rt62 localversion-rt c) One patch has been backported thus revert the patch before applying. filterdiff -p1 -x scripts/package/Makefile ~/tmp/v4.4.6-rt14-4.4.50-rt62.diff |patch -p1 --dry-run Upstream status: backport Change-Id: I244d57a32f6066e5a5b9915f9fbf99e7bbca6e01 Signed-off-by: Yunhong Jiang --- kernel/drivers/hv/channel.c | 27 ++++++++++----- kernel/drivers/hv/channel_mgmt.c | 61 +++++++++++++++++++++++++++++++--- kernel/drivers/hv/hv.c | 10 ++++-- kernel/drivers/hv/hv_fcopy.c | 37 ++++++++------------- kernel/drivers/hv/hv_kvp.c | 31 +++++++---------- kernel/drivers/hv/hv_snapshot.c | 34 +++++++++---------- kernel/drivers/hv/hv_util.c | 10 ++++-- kernel/drivers/hv/hv_utils_transport.c | 9 +++-- kernel/drivers/hv/hyperv_vmbus.h | 11 +++--- kernel/drivers/hv/vmbus_drv.c | 38 +++++++++++---------- 10 files changed, 166 insertions(+), 102 deletions(-) (limited to 'kernel/drivers/hv') diff --git a/kernel/drivers/hv/channel.c b/kernel/drivers/hv/channel.c index 9098f13f2..1ef37c727 100644 --- a/kernel/drivers/hv/channel.c +++ b/kernel/drivers/hv/channel.c @@ -28,6 +28,7 @@ #include #include #include +#include #include "hyperv_vmbus.h" @@ -496,8 +497,21 @@ 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); + channel->state = CHANNEL_OPEN_STATE; channel->sc_creation_callback = NULL; /* Stop callback and cancel the timer asap */ @@ -525,7 +539,7 @@ 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 +552,7 @@ 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 +563,9 @@ 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; } diff --git a/kernel/drivers/hv/channel_mgmt.c b/kernel/drivers/hv/channel_mgmt.c index 652afd11a..37238dffd 100644 --- a/kernel/drivers/hv/channel_mgmt.c +++ b/kernel/drivers/hv/channel_mgmt.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include "hyperv_vmbus.h" @@ -191,6 +192,8 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid) if (channel == NULL) return; + BUG_ON(!channel->rescind); + if (channel->target_cpu != get_cpu()) { put_cpu(); smp_call_function_single(channel->target_cpu, @@ -230,9 +233,7 @@ 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); @@ -459,6 +460,17 @@ static void init_vp_index(struct vmbus_channel *channel, const uuid_le *type_gui cpumask_of_node(primary->numa_node)); cur_cpu = -1; + + /* + * Normally Hyper-V host doesn't create more subchannels than there + * are VCPUs on the node but it is possible when not all present VCPUs + * on the node are initialized by guest. Clear the alloced_cpus_in_node + * to start over. + */ + if (cpumask_equal(&primary->alloced_cpus_in_node, + cpumask_of_node(primary->numa_node))) + cpumask_clear(&primary->alloced_cpus_in_node); + while (true) { cur_cpu = cpumask_next(cur_cpu, &available_mask); if (cur_cpu >= nr_cpu_ids) { @@ -488,6 +500,40 @@ static void init_vp_index(struct vmbus_channel *channel, const uuid_le *type_gui channel->target_vp = hv_context.vp_index[cur_cpu]; } +static void vmbus_wait_for_unload(void) +{ + int cpu = smp_processor_id(); + void *page_addr = hv_context.synic_message_page[cpu]; + struct hv_message *msg = (struct hv_message *)page_addr + + VMBUS_MESSAGE_SINT; + struct vmbus_channel_message_header *hdr; + bool unloaded = false; + + while (1) { + if (msg->header.message_type == HVMSG_NONE) { + mdelay(10); + continue; + } + + hdr = (struct vmbus_channel_message_header *)msg->u.payload; + if (hdr->msgtype == CHANNELMSG_UNLOAD_RESPONSE) + unloaded = true; + + msg->header.message_type = HVMSG_NONE; + /* + * header.message_type needs to be written before we do + * wrmsrl() below. + */ + mb(); + + if (msg->header.message_flags.msg_pending) + wrmsrl(HV_X64_MSR_EOM, 0); + + if (unloaded) + break; + } +} + /* * vmbus_unload_response - Handler for the unload response. */ @@ -513,7 +559,14 @@ void vmbus_initiate_unload(void) hdr.msgtype = CHANNELMSG_UNLOAD; vmbus_post_msg(&hdr, sizeof(struct vmbus_channel_message_header)); - wait_for_completion(&vmbus_connection.unload_event); + /* + * vmbus_initiate_unload() is also called on crash and the crash can be + * happening in an interrupt context, where scheduling is impossible. + */ + if (!in_interrupt()) + wait_for_completion(&vmbus_connection.unload_event); + else + vmbus_wait_for_unload(); } /* diff --git a/kernel/drivers/hv/hv.c b/kernel/drivers/hv/hv.c index 6341be873..63194a9a7 100644 --- a/kernel/drivers/hv/hv.c +++ b/kernel/drivers/hv/hv.c @@ -293,8 +293,14 @@ void hv_cleanup(void) * Cleanup the TSC page based CS. */ if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) { - clocksource_change_rating(&hyperv_cs_tsc, 10); - clocksource_unregister(&hyperv_cs_tsc); + /* + * Crash can happen in an interrupt context and unregistering + * a clocksource is impossible and redundant in this case. + */ + if (!oops_in_progress) { + clocksource_change_rating(&hyperv_cs_tsc, 10); + clocksource_unregister(&hyperv_cs_tsc); + } hypercall_msr.as_uint64 = 0; wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64); diff --git a/kernel/drivers/hv/hv_fcopy.c b/kernel/drivers/hv/hv_fcopy.c index db4b887b8..c37a71e13 100644 --- a/kernel/drivers/hv/hv_fcopy.c +++ b/kernel/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/kernel/drivers/hv/hv_kvp.c b/kernel/drivers/hv/hv_kvp.c index 74c38a9f3..2a3420c4c 100644 --- a/kernel/drivers/hv/hv_kvp.c +++ b/kernel/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) @@ -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/kernel/drivers/hv/hv_snapshot.c b/kernel/drivers/hv/hv_snapshot.c index 815405f2e..81882d484 100644 --- a/kernel/drivers/hv/hv_snapshot.c +++ b/kernel/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) @@ -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/kernel/drivers/hv/hv_util.c b/kernel/drivers/hv/hv_util.c index 7994ec2e4..41f589622 100644 --- a/kernel/drivers/hv/hv_util.c +++ b/kernel/drivers/hv/hv_util.c @@ -283,10 +283,14 @@ static void heartbeat_onchannelcallback(void *context) u8 *hbeat_txf_buf = util_heartbeat.recv_buffer; struct icmsg_negotiate *negop = NULL; - vmbus_recvpacket(channel, hbeat_txf_buf, - PAGE_SIZE, &recvlen, &requestid); + while (1) { + + vmbus_recvpacket(channel, hbeat_txf_buf, + PAGE_SIZE, &recvlen, &requestid); + + if (!recvlen) + break; - if (recvlen > 0) { icmsghdrp = (struct icmsg_hdr *)&hbeat_txf_buf[ sizeof(struct vmbuspipe_hdr)]; diff --git a/kernel/drivers/hv/hv_utils_transport.c b/kernel/drivers/hv/hv_utils_transport.c index 6a9d80a53..1505ee6e6 100644 --- a/kernel/drivers/hv/hv_utils_transport.c +++ b/kernel/drivers/hv/hv_utils_transport.c @@ -204,9 +204,12 @@ int hvutil_transport_send(struct hvutil_transport *hvt, void *msg, int len) 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); return ret; diff --git a/kernel/drivers/hv/hyperv_vmbus.h b/kernel/drivers/hv/hyperv_vmbus.h index 378263656..12156db2e 100644 --- a/kernel/drivers/hv/hyperv_vmbus.h +++ b/kernel/drivers/hv/hyperv_vmbus.h @@ -30,6 +30,11 @@ #include #include +/* + * 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). @@ -759,11 +764,7 @@ 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/kernel/drivers/hv/vmbus_drv.c b/kernel/drivers/hv/vmbus_drv.c index f19b6f7a4..b2498b270 100644 --- a/kernel/drivers/hv/vmbus_drv.c +++ b/kernel/drivers/hv/vmbus_drv.c @@ -41,6 +41,7 @@ #include #include #include +#include #include "hyperv_vmbus.h" static struct acpi_device *hv_acpi_dev; @@ -104,6 +105,7 @@ static struct notifier_block hyperv_panic_block = { }; struct resource *hyperv_mmio; +DEFINE_SEMAPHORE(hyperv_mmio_lock); static int vmbus_exists(void) { @@ -602,23 +604,11 @@ 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 +643,10 @@ 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); } @@ -826,6 +819,8 @@ static void vmbus_isr(void) else tasklet_schedule(&msg_dpc); } + + add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0, 0); } @@ -867,7 +862,7 @@ 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 +880,8 @@ 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(); @@ -1144,7 +1141,10 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj, resource_size_t range_min, range_max, start, local_min, local_max; const char *dev_n = dev_name(&device_obj->device); u32 fb_end = screen_info.lfb_base + (screen_info.lfb_size << 1); - int i; + int i, retval; + + retval = -ENXIO; + down(&hyperv_mmio_lock); for (iter = hyperv_mmio; iter; iter = iter->sibling) { if ((iter->start >= max) || (iter->end <= min)) @@ -1181,13 +1181,17 @@ int vmbus_allocate_mmio(struct resource **new, struct hv_device *device_obj, for (; start + size - 1 <= local_max; start += align) { *new = request_mem_region_exclusive(start, size, dev_n); - if (*new) - return 0; + if (*new) { + retval = 0; + goto exit; + } } } } - return -ENXIO; +exit: + up(&hyperv_mmio_lock); + return retval; } EXPORT_SYMBOL_GPL(vmbus_allocate_mmio); -- cgit 1.2.3-korg