summaryrefslogtreecommitdiffstats
path: root/kernel/arch/x86/xen/apic.c
blob: 70e060ad879a129effcbc1043222162f5429b7e6 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
#include <linux/init.h>

#include <asm/x86_init.h>
#include <asm/apic.h>
#include <asm/xen/hypercall.h>

#include <xen/xen.h>
#include <xen/interface/physdev.h>
#include "xen-ops.h"
#include "smp.h"

static unsigned int xen_io_apic_read(unsigned apic, unsigned reg)
{
	struct physdev_apic apic_op;
	int ret;

	apic_op.apic_physbase = mpc_ioapic_addr(apic);
	apic_op.reg = reg;
	ret = HYPERVISOR_physdev_op(PHYSDEVOP_apic_read, &apic_op);
	if (!ret)
		return apic_op.value;

	/* fallback to return an emulated IO_APIC values */
	if (reg == 0x1)
		return 0x00170020;
	else if (reg == 0x0)
		return apic << 24;

	return 0xfd;
}

static unsigned long xen_set_apic_id(unsigned int x)
{
	WARN_ON(1);
	return x;
}

static unsigned int xen_get_apic_id(unsigned long x)
{
	return ((x)>>24) & 0xFFu;
}

static u32 xen_apic_read(u32 reg)
{
	struct xen_platform_op op = {
		.cmd = XENPF_get_cpuinfo,
		.interface_version = XENPF_INTERFACE_VERSION,
		.u.pcpu_info.xen_cpuid = 0,
	};
	int ret = 0;

	/* Shouldn't need this as APIC is turned off for PV, and we only
	 * get called on the bootup processor. But just in case. */
	if (!xen_initial_domain() || smp_processor_id())
		return 0;

	if (reg == APIC_LVR)
		return 0x10;
#ifdef CONFIG_X86_32
	if (reg == APIC_LDR)
		return SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
#endif
	if (reg != APIC_ID)
		return 0;

	ret = HYPERVISOR_dom0_op(&op);
	if (ret)
		return 0;

	return op.u.pcpu_info.apic_id << 24;
}

static void xen_apic_write(u32 reg, u32 val)
{
	/* Warn to see if there's any stray references */
	WARN(1,"register: %x, value: %x\n", reg, val);
}

static u64 xen_apic_icr_read(void)
{
	return 0;
}

static void xen_apic_icr_write(u32 low, u32 id)
{
	/* Warn to see if there's any stray references */
	WARN_ON(1);
}

static u32 xen_safe_apic_wait_icr_idle(void)
{
        return 0;
}

static int xen_apic_probe_pv(void)
{
	if (xen_pv_domain())
		return 1;

	return 0;
}

static int xen_madt_oem_check(char *oem_id, char *oem_table_id)
{
	return xen_pv_domain();
}

static int xen_id_always_valid(int apicid)
{
	return 1;
}

static int xen_id_always_registered(void)
{
	return 1;
}

static int xen_phys_pkg_id(int initial_apic_id, int index_msb)
{
	return initial_apic_id >> index_msb;
}

#ifdef CONFIG_X86_32
static int xen_x86_32_early_logical_apicid(int cpu)
{
	/* Match with APIC_LDR read. Otherwise setup_local_APIC complains. */
	return 1 << cpu;
}
#endif

static void xen_noop(void)
{
}

static void xen_silent_inquire(int apicid)
{
}

static struct apic xen_pv_apic = {
	.name 				= "Xen PV",
	.probe 				= xen_apic_probe_pv,
	.acpi_madt_oem_check		= xen_madt_oem_check,
	.apic_id_valid 			= xen_id_always_valid,
	.apic_id_registered 		= xen_id_always_registered,

	/* .irq_delivery_mode - used in native_compose_msi_msg only */
	/* .irq_dest_mode     - used in native_compose_msi_msg only */

	.target_cpus			= default_target_cpus,
	.disable_esr			= 0,
	/* .dest_logical      -  default_send_IPI_ use it but we use our own. */
	.check_apicid_used		= default_check_apicid_used, /* Used on 32-bit */

	.vector_allocation_domain	= flat_vector_allocation_domain,
	.init_apic_ldr			= xen_noop, /* setup_local_APIC calls it */

	.ioapic_phys_id_map		= default_ioapic_phys_id_map, /* Used on 32-bit */
	.setup_apic_routing		= NULL,
	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
	.apicid_to_cpu_present		= physid_set_mask_of_physid, /* Used on 32-bit */
	.check_phys_apicid_present	= default_check_phys_apicid_present, /* smp_sanity_check needs it */
	.phys_pkg_id			= xen_phys_pkg_id, /* detect_ht */

	.get_apic_id 			= xen_get_apic_id,
	.set_apic_id 			= xen_set_apic_id, /* Can be NULL on 32-bit. */
	.apic_id_mask			= 0xFF << 24, /* Used by verify_local_APIC. Match with what xen_get_apic_id does. */

	.cpu_mask_to_apicid_and		= flat_cpu_mask_to_apicid_and,

#ifdef CONFIG_SMP
	.send_IPI_mask 			= xen_send_IPI_mask,
	.send_IPI_mask_allbutself 	= xen_send_IPI_mask_allbutself,
	.send_IPI_allbutself 		= xen_send_IPI_allbutself,
	.send_IPI_all 			= xen_send_IPI_all,
	.send_IPI_self 			= xen_send_IPI_self,
#endif
	/* .wait_for_init_deassert- used  by AP bootup - smp_callin which we don't use */
	.inquire_remote_apic		= xen_silent_inquire,

	.read				= xen_apic_read,
	.write				= xen_apic_write,
	.eoi_write			= xen_apic_write,

	.icr_read 			= xen_apic_icr_read,
	.icr_write 			= xen_apic_icr_write,
	.wait_icr_idle 			= xen_noop,
	.safe_wait_icr_idle 		= xen_safe_apic_wait_icr_idle,

#ifdef CONFIG_X86_32
	/* generic_processor_info and setup_local_APIC. */
	.x86_32_early_logical_apicid	= xen_x86_32_early_logical_apicid,
#endif
};

static void __init xen_apic_check(void)
{
	if (apic == &xen_pv_apic)
		return;

	pr_info("Switched APIC routing from %s to %s.\n", apic->name,
		xen_pv_apic.name);
	apic = &xen_pv_apic;
}
void __init xen_init_apic(void)
{
	x86_io_apic_ops.read = xen_io_apic_read;
	/* On PV guests the APIC CPUID bit is disabled so none of the
	 * routines end up executing. */
	if (!xen_initial_domain())
		apic = &xen_pv_apic;

	x86_platform.apic_post_init = xen_apic_check;
}
apic_driver(xen_pv_apic);
U General Public License for * more details. * * You should have received a copy of the GNU General Public License along with * this program; if not, write to the Free Software Foundation, Inc., 59 Temple * Place - Suite 330, Boston, MA 02111-1307 USA. * * Authors: * Haiyang Zhang <haiyangz@microsoft.com> * Hank Janssen <hjanssen@microsoft.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/module.h> #include <linux/completion.h> #include <linux/hyperv.h> #include "hyperv_vmbus.h" /** * vmbus_prep_negotiate_resp() - Create default response for Hyper-V Negotiate message * @icmsghdrp: Pointer to msg header structure * @icmsg_negotiate: Pointer to negotiate message structure * @buf: Raw buffer channel data * * @icmsghdrp is of type &struct icmsg_hdr. * @negop is of type &struct icmsg_negotiate. * Set up and fill in default negotiate response message. * * The fw_version specifies the framework version that * we can support and srv_version specifies the service * version we can support. * * Mainly used by Hyper-V drivers. */ bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, struct icmsg_negotiate *negop, u8 *buf, int fw_version, int srv_version) { int icframe_major, icframe_minor; int icmsg_major, icmsg_minor; int fw_major, fw_minor; int srv_major, srv_minor; int i; bool found_match = false; icmsghdrp->icmsgsize = 0x10; fw_major = (fw_version >> 16); fw_minor = (fw_version & 0xFFFF); srv_major = (srv_version >> 16); srv_minor = (srv_version & 0xFFFF); negop = (struct icmsg_negotiate *)&buf[ sizeof(struct vmbuspipe_hdr) + sizeof(struct icmsg_hdr)]; icframe_major = negop->icframe_vercnt; icframe_minor = 0; icmsg_major = negop->icmsg_vercnt; icmsg_minor = 0; /* * Select the framework version number we will * support. */ for (i = 0; i < negop->icframe_vercnt; i++) { if ((negop->icversion_data[i].major == fw_major) && (negop->icversion_data[i].minor == fw_minor)) { icframe_major = negop->icversion_data[i].major; icframe_minor = negop->icversion_data[i].minor; found_match = true; } } if (!found_match) goto fw_error; found_match = false; for (i = negop->icframe_vercnt; (i < negop->icframe_vercnt + negop->icmsg_vercnt); i++) { if ((negop->icversion_data[i].major == srv_major) && (negop->icversion_data[i].minor == srv_minor)) { icmsg_major = negop->icversion_data[i].major; icmsg_minor = negop->icversion_data[i].minor; found_match = true; } } /* * Respond with the framework and service * version numbers we can support. */ fw_error: if (!found_match) { negop->icframe_vercnt = 0; negop->icmsg_vercnt = 0; } else { negop->icframe_vercnt = 1; negop->icmsg_vercnt = 1; } negop->icversion_data[0].major = icframe_major; negop->icversion_data[0].minor = icframe_minor; negop->icversion_data[1].major = icmsg_major; negop->icversion_data[1].minor = icmsg_minor; return found_match; } EXPORT_SYMBOL_GPL(vmbus_prep_negotiate_resp); /* * alloc_channel - Allocate and initialize a vmbus channel object */ static struct vmbus_channel *alloc_channel(void) { static atomic_t chan_num = ATOMIC_INIT(0); struct vmbus_channel *channel; channel = kzalloc(sizeof(*channel), GFP_ATOMIC); if (!channel) return NULL; channel->id = atomic_inc_return(&chan_num); spin_lock_init(&channel->inbound_lock); spin_lock_init(&channel->lock); INIT_LIST_HEAD(&channel->sc_list); INIT_LIST_HEAD(&channel->percpu_list); return channel; } /* * free_channel - Release the resources used by the vmbus channel object */ static void free_channel(struct vmbus_channel *channel) { kfree(channel); } static void percpu_channel_enq(void *arg) { struct vmbus_channel *channel = arg; int cpu = smp_processor_id(); list_add_tail(&channel->percpu_list, &hv_context.percpu_list[cpu]); } static void percpu_channel_deq(void *arg) { struct vmbus_channel *channel = arg; list_del(&channel->percpu_list); } void hv_process_channel_removal(struct vmbus_channel *channel, 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; if (channel->target_cpu != get_cpu()) { put_cpu(); smp_call_function_single(channel->target_cpu, percpu_channel_deq, channel, true); } else { percpu_channel_deq(channel); put_cpu(); } if (channel->primary_channel == NULL) { spin_lock_irqsave(&vmbus_connection.channel_lock, flags); list_del(&channel->listentry); spin_unlock_irqrestore(&vmbus_connection.channel_lock, flags); } else { primary_channel = channel->primary_channel; spin_lock_irqsave(&primary_channel->lock, flags); list_del(&channel->sc_list); spin_unlock_irqrestore(&primary_channel->lock, flags); } free_channel(channel); } void vmbus_free_channels(void) { struct vmbus_channel *channel; list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) { vmbus_device_unregister(channel->device_obj); free_channel(channel); } } /* * vmbus_process_offer - Process the offer by creating a channel/device * associated with this offer */ static void vmbus_process_offer(struct vmbus_channel *newchannel) { struct vmbus_channel *channel; bool fnew = true; bool enq = false; unsigned long flags; /* Make sure this is a new offer */ spin_lock_irqsave(&vmbus_connection.channel_lock, flags); list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) { if (!uuid_le_cmp(channel->offermsg.offer.if_type, newchannel->offermsg.offer.if_type) && !uuid_le_cmp(channel->offermsg.offer.if_instance, newchannel->offermsg.offer.if_instance)) { fnew = false; break; } } if (fnew) { list_add_tail(&newchannel->listentry, &vmbus_connection.chn_list); enq = true; } spin_unlock_irqrestore(&vmbus_connection.channel_lock, flags); if (enq) { if (newchannel->target_cpu != get_cpu()) { put_cpu(); smp_call_function_single(newchannel->target_cpu, percpu_channel_enq, newchannel, true); } else { percpu_channel_enq(newchannel); put_cpu(); } } if (!fnew) { /* * Check to see if this is a sub-channel. */ if (newchannel->offermsg.offer.sub_channel_index != 0) { /* * Process the sub-channel. */ newchannel->primary_channel = channel; spin_lock_irqsave(&channel->lock, flags); list_add_tail(&newchannel->sc_list, &channel->sc_list); spin_unlock_irqrestore(&channel->lock, flags); if (newchannel->target_cpu != get_cpu()) { put_cpu(); smp_call_function_single(newchannel->target_cpu, percpu_channel_enq, newchannel, true); } else { percpu_channel_enq(newchannel); put_cpu(); } newchannel->state = CHANNEL_OPEN_STATE; channel->num_sc++; if (channel->sc_creation_callback != NULL) channel->sc_creation_callback(newchannel); return; } goto err_free_chan; } /* * This state is used to indicate a successful open * so that when we do close the channel normally, we * can cleanup properly */ newchannel->state = CHANNEL_OPEN_STATE; /* * Start the process of binding this offer to the driver * We need to set the DeviceObject field before calling * vmbus_child_dev_add() */ newchannel->device_obj = vmbus_device_create( &newchannel->offermsg.offer.if_type, &newchannel->offermsg.offer.if_instance, newchannel); if (!newchannel->device_obj) goto err_deq_chan; /* * Add the new device to the bus. This will kick off device-driver * binding which eventually invokes the device driver's AddDevice() * method. */ if (vmbus_device_register(newchannel->device_obj) != 0) { pr_err("unable to add child device object (relid %d)\n", newchannel->offermsg.child_relid); kfree(newchannel->device_obj); goto err_deq_chan; } return; err_deq_chan: spin_lock_irqsave(&vmbus_connection.channel_lock, flags); list_del(&newchannel->listentry); spin_unlock_irqrestore(&vmbus_connection.channel_lock, flags); if (newchannel->target_cpu != get_cpu()) { put_cpu(); smp_call_function_single(newchannel->target_cpu, percpu_channel_deq, newchannel, true); } else { percpu_channel_deq(newchannel); put_cpu(); } err_free_chan: free_channel(newchannel); } enum { IDE = 0, SCSI, NIC, MAX_PERF_CHN, }; /* * This is an array of device_ids (device types) that are performance critical. * We attempt to distribute the interrupt load for these devices across * all available CPUs. */ static const struct hv_vmbus_device_id hp_devs[] = { /* IDE */ { HV_IDE_GUID, }, /* Storage - SCSI */ { HV_SCSI_GUID, }, /* Network */ { HV_NIC_GUID, }, /* NetworkDirect Guest RDMA */ { HV_ND_GUID, }, }; /* * We use this state to statically distribute the channel interrupt load. */ static u32 next_vp; /* * Starting with Win8, we can statically distribute the incoming * channel interrupt load by binding a channel to VCPU. We * implement here a simple round robin scheme for distributing * the interrupt load. * We will bind channels that are not performance critical to cpu 0 and * performance critical channels (IDE, SCSI and Network) will be uniformly * distributed across all available CPUs. */ static void init_vp_index(struct vmbus_channel *channel, const uuid_le *type_guid) { u32 cur_cpu; int i; bool perf_chn = false; u32 max_cpus = num_online_cpus(); for (i = IDE; i < MAX_PERF_CHN; i++) { if (!memcmp(type_guid->b, hp_devs[i].guid, sizeof(uuid_le))) { perf_chn = true; break; } } if ((vmbus_proto_version == VERSION_WS2008) || (vmbus_proto_version == VERSION_WIN7) || (!perf_chn)) { /* * Prior to win8, all channel interrupts are * delivered on cpu 0. * Also if the channel is not a performance critical * channel, bind it to cpu 0. */ channel->target_cpu = 0; channel->target_vp = 0; return; } cur_cpu = (++next_vp % max_cpus); channel->target_cpu = cur_cpu; channel->target_vp = hv_context.vp_index[cur_cpu]; } /* * vmbus_onoffer - Handler for channel offers from vmbus in parent partition. * */ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr) { struct vmbus_channel_offer_channel *offer; struct vmbus_channel *newchannel; offer = (struct vmbus_channel_offer_channel *)hdr; /* Allocate the channel object and save this offer. */ newchannel = alloc_channel(); if (!newchannel) { pr_err("Unable to allocate channel object\n"); return; } /* * By default we setup state to enable batched * reading. A specific service can choose to * disable this prior to opening the channel. */ newchannel->batched_reading = true; /* * Setup state for signalling the host. */ newchannel->sig_event = (struct hv_input_signal_event *) (ALIGN((unsigned long) &newchannel->sig_buf, HV_HYPERCALL_PARAM_ALIGN)); newchannel->sig_event->connectionid.asu32 = 0; newchannel->sig_event->connectionid.u.id = VMBUS_EVENT_CONNECTION_ID; newchannel->sig_event->flag_number = 0; newchannel->sig_event->rsvdz = 0; if (vmbus_proto_version != VERSION_WS2008) { newchannel->is_dedicated_interrupt = (offer->is_dedicated_interrupt != 0); newchannel->sig_event->connectionid.u.id = offer->connection_id; } init_vp_index(newchannel, &offer->offer.if_type); memcpy(&newchannel->offermsg, offer, sizeof(struct vmbus_channel_offer_channel)); newchannel->monitor_grp = (u8)offer->monitorid / 32; newchannel->monitor_bit = (u8)offer->monitorid % 32; vmbus_process_offer(newchannel); } /* * vmbus_onoffer_rescind - Rescind offer handler. * * We queue a work item to process this offer synchronously */ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) { struct vmbus_channel_rescind_offer *rescind; struct vmbus_channel *channel; unsigned long flags; struct device *dev; rescind = (struct vmbus_channel_rescind_offer *)hdr; channel = relid2channel(rescind->child_relid); if (channel == NULL) { hv_process_channel_removal(NULL, rescind->child_relid); return; } spin_lock_irqsave(&channel->lock, flags); channel->rescind = true; spin_unlock_irqrestore(&channel->lock, flags); if (channel->device_obj) { /* * We will have to unregister this device from the * driver core. */ dev = get_device(&channel->device_obj->device); if (dev) { vmbus_device_unregister(channel->device_obj); put_device(dev); } } else { hv_process_channel_removal(channel, channel->offermsg.child_relid); } } /* * vmbus_onoffers_delivered - * This is invoked when all offers have been delivered. * * Nothing to do here. */ static void vmbus_onoffers_delivered( struct vmbus_channel_message_header *hdr) { } /* * vmbus_onopen_result - Open result handler. * * This is invoked when we received a response to our channel open request. * Find the matching request, copy the response and signal the requesting * thread. */ static void vmbus_onopen_result(struct vmbus_channel_message_header *hdr) { struct vmbus_channel_open_result *result; struct vmbus_channel_msginfo *msginfo; struct vmbus_channel_message_header *requestheader; struct vmbus_channel_open_channel *openmsg; unsigned long flags; result = (struct vmbus_channel_open_result *)hdr; /* * Find the open msg, copy the result and signal/unblock the wait event */ spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags); list_for_each_entry(msginfo, &vmbus_connection.chn_msg_list, msglistentry) { requestheader = (struct vmbus_channel_message_header *)msginfo->msg; if (requestheader->msgtype == CHANNELMSG_OPENCHANNEL) { openmsg = (struct vmbus_channel_open_channel *)msginfo->msg; if (openmsg->child_relid == result->child_relid && openmsg->openid == result->openid) { memcpy(&msginfo->response.open_result, result, sizeof( struct vmbus_channel_open_result)); complete(&msginfo->waitevent); break; } } } spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags); } /* * vmbus_ongpadl_created - GPADL created handler. * * This is invoked when we received a response to our gpadl create request. * Find the matching request, copy the response and signal the requesting * thread. */ static void vmbus_ongpadl_created(struct vmbus_channel_message_header *hdr) { struct vmbus_channel_gpadl_created *gpadlcreated; struct vmbus_channel_msginfo *msginfo; struct vmbus_channel_message_header *requestheader; struct vmbus_channel_gpadl_header *gpadlheader; unsigned long flags; gpadlcreated = (struct vmbus_channel_gpadl_created *)hdr; /* * Find the establish msg, copy the result and signal/unblock the wait * event */ spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags); list_for_each_entry(msginfo, &vmbus_connection.chn_msg_list, msglistentry) { requestheader = (struct vmbus_channel_message_header *)msginfo->msg; if (requestheader->msgtype == CHANNELMSG_GPADL_HEADER) { gpadlheader = (struct vmbus_channel_gpadl_header *)requestheader; if ((gpadlcreated->child_relid == gpadlheader->child_relid) && (gpadlcreated->gpadl == gpadlheader->gpadl)) { memcpy(&msginfo->response.gpadl_created, gpadlcreated, sizeof( struct vmbus_channel_gpadl_created)); complete(&msginfo->waitevent); break; } } } spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags); } /* * vmbus_ongpadl_torndown - GPADL torndown handler. * * This is invoked when we received a response to our gpadl teardown request. * Find the matching request, copy the response and signal the requesting * thread. */ static void vmbus_ongpadl_torndown( struct vmbus_channel_message_header *hdr) { struct vmbus_channel_gpadl_torndown *gpadl_torndown; struct vmbus_channel_msginfo *msginfo; struct vmbus_channel_message_header *requestheader; struct vmbus_channel_gpadl_teardown *gpadl_teardown; unsigned long flags; gpadl_torndown = (struct vmbus_channel_gpadl_torndown *)hdr; /* * Find the open msg, copy the result and signal/unblock the wait event */ spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags); list_for_each_entry(msginfo, &vmbus_connection.chn_msg_list, msglistentry) { requestheader = (struct vmbus_channel_message_header *)msginfo->msg; if (requestheader->msgtype == CHANNELMSG_GPADL_TEARDOWN) { gpadl_teardown = (struct vmbus_channel_gpadl_teardown *)requestheader; if (gpadl_torndown->gpadl == gpadl_teardown->gpadl) { memcpy(&msginfo->response.gpadl_torndown, gpadl_torndown, sizeof( struct vmbus_channel_gpadl_torndown)); complete(&msginfo->waitevent); break; } } } spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags); } /* * vmbus_onversion_response - Version response handler * * This is invoked when we received a response to our initiate contact request. * Find the matching request, copy the response and signal the requesting * thread. */ static void vmbus_onversion_response( struct vmbus_channel_message_header *hdr) { struct vmbus_channel_msginfo *msginfo; struct vmbus_channel_message_header *requestheader; struct vmbus_channel_version_response *version_response; unsigned long flags; version_response = (struct vmbus_channel_version_response *)hdr; spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags); list_for_each_entry(msginfo, &vmbus_connection.chn_msg_list, msglistentry) { requestheader = (struct vmbus_channel_message_header *)msginfo->msg; if (requestheader->msgtype == CHANNELMSG_INITIATE_CONTACT) { memcpy(&msginfo->response.version_response, version_response, sizeof(struct vmbus_channel_version_response)); complete(&msginfo->waitevent); } } spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags); } /* Channel message dispatch table */ struct vmbus_channel_message_table_entry channel_message_table[CHANNELMSG_COUNT] = { {CHANNELMSG_INVALID, 0, NULL}, {CHANNELMSG_OFFERCHANNEL, 0, vmbus_onoffer}, {CHANNELMSG_RESCIND_CHANNELOFFER, 0, vmbus_onoffer_rescind}, {CHANNELMSG_REQUESTOFFERS, 0, NULL}, {CHANNELMSG_ALLOFFERS_DELIVERED, 1, vmbus_onoffers_delivered}, {CHANNELMSG_OPENCHANNEL, 0, NULL}, {CHANNELMSG_OPENCHANNEL_RESULT, 1, vmbus_onopen_result}, {CHANNELMSG_CLOSECHANNEL, 0, NULL}, {CHANNELMSG_GPADL_HEADER, 0, NULL}, {CHANNELMSG_GPADL_BODY, 0, NULL}, {CHANNELMSG_GPADL_CREATED, 1, vmbus_ongpadl_created}, {CHANNELMSG_GPADL_TEARDOWN, 0, NULL}, {CHANNELMSG_GPADL_TORNDOWN, 1, vmbus_ongpadl_torndown}, {CHANNELMSG_RELID_RELEASED, 0, NULL}, {CHANNELMSG_INITIATE_CONTACT, 0, NULL}, {CHANNELMSG_VERSION_RESPONSE, 1, vmbus_onversion_response}, {CHANNELMSG_UNLOAD, 0, NULL}, }; /* * vmbus_onmessage - Handler for channel protocol messages. * * This is invoked in the vmbus worker thread context. */ void vmbus_onmessage(void *context) { struct hv_message *msg = context; struct vmbus_channel_message_header *hdr; int size; hdr = (struct vmbus_channel_message_header *)msg->u.payload; size = msg->header.payload_size; if (hdr->msgtype >= CHANNELMSG_COUNT) { pr_err("Received invalid channel message type %d size %d\n", hdr->msgtype, size); print_hex_dump_bytes("", DUMP_PREFIX_NONE, (unsigned char *)msg->u.payload, size); return; } if (channel_message_table[hdr->msgtype].message_handler) channel_message_table[hdr->msgtype].message_handler(hdr); else pr_err("Unhandled channel message type %d\n", hdr->msgtype); } /* * vmbus_request_offers - Send a request to get all our pending offers. */ int vmbus_request_offers(void) { struct vmbus_channel_message_header *msg; struct vmbus_channel_msginfo *msginfo; int ret; msginfo = kmalloc(sizeof(*msginfo) + sizeof(struct vmbus_channel_message_header), GFP_KERNEL); if (!msginfo) return -ENOMEM; msg = (struct vmbus_channel_message_header *)msginfo->msg; msg->msgtype = CHANNELMSG_REQUESTOFFERS; ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_message_header)); if (ret != 0) { pr_err("Unable to request offers - %d\n", ret); goto cleanup; } cleanup: kfree(msginfo); return ret; } /* * Retrieve the (sub) channel on which to send an outgoing request. * When a primary channel has multiple sub-channels, we try to * distribute the load equally amongst all available channels. */ struct vmbus_channel *vmbus_get_outgoing_channel(struct vmbus_channel *primary) { struct list_head *cur, *tmp; int cur_cpu; struct vmbus_channel *cur_channel; struct vmbus_channel *outgoing_channel = primary; int next_channel; int i = 1; if (list_empty(&primary->sc_list)) return outgoing_channel; next_channel = primary->next_oc++; if (next_channel > (primary->num_sc)) { primary->next_oc = 0; return outgoing_channel; } cur_cpu = hv_context.vp_index[get_cpu()]; put_cpu(); list_for_each_safe(cur, tmp, &primary->sc_list) { cur_channel = list_entry(cur, struct vmbus_channel, sc_list); if (cur_channel->state != CHANNEL_OPENED_STATE) continue; if (cur_channel->target_vp == cur_cpu) return cur_channel; if (i == next_channel) return cur_channel; i++; } return outgoing_channel; } EXPORT_SYMBOL_GPL(vmbus_get_outgoing_channel); static void invoke_sc_cb(struct vmbus_channel *primary_channel) { struct list_head *cur, *tmp; struct vmbus_channel *cur_channel; if (primary_channel->sc_creation_callback == NULL) return; list_for_each_safe(cur, tmp, &primary_channel->sc_list) { cur_channel = list_entry(cur, struct vmbus_channel, sc_list); primary_channel->sc_creation_callback(cur_channel); } } void vmbus_set_sc_create_callback(struct vmbus_channel *primary_channel, void (*sc_cr_cb)(struct vmbus_channel *new_sc)) { primary_channel->sc_creation_callback = sc_cr_cb; } EXPORT_SYMBOL_GPL(vmbus_set_sc_create_callback); bool vmbus_are_subchannels_present(struct vmbus_channel *primary) { bool ret; ret = !list_empty(&primary->sc_list); if (ret) { /* * Invoke the callback on sub-channel creation. * This will present a uniform interface to the * clients. */ invoke_sc_cb(primary); } return ret; } EXPORT_SYMBOL_GPL(vmbus_are_subchannels_present);