/* The one and only */ struct hv_context hv_context;
/* * hv_init - Main initialization routine. * * This routine must be called before any other routines in here are called
*/ int hv_init(void)
{
hv_context.cpu_context = alloc_percpu(struct hv_per_cpu_context); if (!hv_context.cpu_context) return -ENOMEM; return 0;
}
/* * hv_post_message - Post a message using the hypervisor message IPC. * * This involves a hypercall.
*/ int hv_post_message(union hv_connection_id connection_id, enum hv_message_type message_type, void *payload, size_t payload_size)
{ struct hv_input_post_message *aligned_msg; unsignedlong flags;
u64 status;
if (payload_size > HV_MESSAGE_PAYLOAD_BYTE_COUNT) return -EMSGSIZE;
local_irq_save(flags);
/* * A TDX VM with the paravisor must use the decrypted post_msg_page: see * the comment in struct hv_per_cpu_context. A SNP VM with the paravisor * can use the encrypted hyperv_pcpu_input_arg because it copies the * input into the GHCB page, which has been decrypted by the paravisor.
*/ if (hv_isolation_type_tdx() && ms_hyperv.paravisor_present)
aligned_msg = this_cpu_ptr(hv_context.cpu_context)->post_msg_page; else
aligned_msg = *this_cpu_ptr(hyperv_pcpu_input_arg);
if (ms_hyperv.paravisor_present) { if (hv_isolation_type_tdx())
status = hv_tdx_hypercall(HVCALL_POST_MESSAGE,
virt_to_phys(aligned_msg), 0); elseif (hv_isolation_type_snp())
status = hv_ghcb_hypercall(HVCALL_POST_MESSAGE,
aligned_msg, NULL, sizeof(*aligned_msg)); else
status = HV_STATUS_INVALID_PARAMETER;
} else {
u64 control = HVCALL_POST_MESSAGE;
control |= hv_nested ? HV_HYPERCALL_NESTED : 0;
status = hv_do_hypercall(control, aligned_msg, NULL);
}
local_irq_restore(flags);
return hv_result(status);
}
int hv_synic_alloc(void)
{ int cpu, ret = -ENOMEM; struct hv_per_cpu_context *hv_cpu;
/* * First, zero all per-cpu memory areas so hv_synic_free() can * detect what memory has been allocated and cleanup properly * after any failures.
*/
for_each_present_cpu(cpu) {
hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu);
memset(hv_cpu, 0, sizeof(*hv_cpu));
}
hv_context.hv_numa_map = kcalloc(nr_node_ids, sizeof(struct cpumask),
GFP_KERNEL); if (!hv_context.hv_numa_map) {
pr_err("Unable to allocate NUMA map\n"); goto err;
}
if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) {
hv_cpu->post_msg_page = (void *)get_zeroed_page(GFP_ATOMIC); if (!hv_cpu->post_msg_page) {
pr_err("Unable to allocate post msg page\n"); goto err;
}
ret = set_memory_decrypted((unsignedlong)hv_cpu->post_msg_page, 1); if (ret) {
pr_err("Failed to decrypt post msg page: %d\n", ret); /* Just leak the page, as it's unsafe to free the page. */
hv_cpu->post_msg_page = NULL; goto err;
}
memset(hv_cpu->post_msg_page, 0, PAGE_SIZE);
}
/* * Synic message and event pages are allocated by paravisor. * Skip these pages allocation here.
*/ if (!ms_hyperv.paravisor_present && !hv_root_partition()) {
hv_cpu->synic_message_page =
(void *)get_zeroed_page(GFP_ATOMIC); if (!hv_cpu->synic_message_page) {
pr_err("Unable to allocate SYNIC message page\n"); goto err;
}
hv_cpu->synic_event_page =
(void *)get_zeroed_page(GFP_ATOMIC); if (!hv_cpu->synic_event_page) {
pr_err("Unable to allocate SYNIC event page\n");
if (!ms_hyperv.paravisor_present &&
(hv_isolation_type_snp() || hv_isolation_type_tdx())) {
ret = set_memory_decrypted((unsignedlong)
hv_cpu->synic_message_page, 1); if (ret) {
pr_err("Failed to decrypt SYNIC msg page: %d\n", ret);
hv_cpu->synic_message_page = NULL;
/* * Free the event page here so that hv_synic_free() * won't later try to re-encrypt it.
*/
free_page((unsignedlong)hv_cpu->synic_event_page);
hv_cpu->synic_event_page = NULL; goto err;
}
ret = set_memory_decrypted((unsignedlong)
hv_cpu->synic_event_page, 1); if (ret) {
pr_err("Failed to decrypt SYNIC event page: %d\n", ret);
hv_cpu->synic_event_page = NULL; goto err;
}
/* It's better to leak the page if the encryption fails. */ if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) { if (hv_cpu->post_msg_page) {
ret = set_memory_encrypted((unsignedlong)
hv_cpu->post_msg_page, 1); if (ret) {
pr_err("Failed to encrypt post msg page: %d\n", ret);
hv_cpu->post_msg_page = NULL;
}
}
}
if (!ms_hyperv.paravisor_present &&
(hv_isolation_type_snp() || hv_isolation_type_tdx())) { if (hv_cpu->synic_message_page) {
ret = set_memory_encrypted((unsignedlong)
hv_cpu->synic_message_page, 1); if (ret) {
pr_err("Failed to encrypt SYNIC msg page: %d\n", ret);
hv_cpu->synic_message_page = NULL;
}
}
if (hv_cpu->synic_event_page) {
ret = set_memory_encrypted((unsignedlong)
hv_cpu->synic_event_page, 1); if (ret) {
pr_err("Failed to encrypt SYNIC event page: %d\n", ret);
hv_cpu->synic_event_page = NULL;
}
}
}
/* * hv_synic_init - Initialize the Synthetic Interrupt Controller. * * If it is already initialized by another entity (ie x2v shim), we need to * retrieve the initialized message and event pages. Otherwise, we create and * initialize the message and event pages.
*/ void hv_synic_enable_regs(unsignedint cpu)
{ struct hv_per_cpu_context *hv_cpu =
per_cpu_ptr(hv_context.cpu_context, cpu); union hv_synic_simp simp; union hv_synic_siefp siefp; union hv_synic_sint shared_sint; union hv_synic_scontrol sctrl;
/* Need to correctly cleanup in the case of SMP!!! */ /* Disable the interrupt */
hv_set_msr(HV_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
simp.as_uint64 = hv_get_msr(HV_MSR_SIMP); /* * In Isolation VM, sim and sief pages are allocated by * paravisor. These pages also will be used by kdump * kernel. So just reset enable bit here and keep page * addresses.
*/
simp.simp_enabled = 0; if (ms_hyperv.paravisor_present || hv_root_partition()) {
iounmap(hv_cpu->synic_message_page);
hv_cpu->synic_message_page = NULL;
} else {
simp.base_simp_gpa = 0;
}
/* Disable the global synic bit */
sctrl.as_uint64 = hv_get_msr(HV_MSR_SCONTROL);
sctrl.enable = 0;
hv_set_msr(HV_MSR_SCONTROL, sctrl.as_uint64);
if (vmbus_irq != -1)
disable_percpu_irq(vmbus_irq);
}
#define HV_MAX_TRIES 3 /* * Scan the event flags page of 'this' CPU looking for any bit that is set. If we find one * bit set, then wait for a few milliseconds. Repeat these steps for a maximum of 3 times. * Return 'true', if there is still any set bit after this operation; 'false', otherwise. * * If a bit is set, that means there is a pending channel interrupt. The expectation is * that the normal interrupt handling mechanism will find and process the channel interrupt * "very soon", and in the process clear the bit.
*/ staticbool hv_synic_event_pending(void)
{ struct hv_per_cpu_context *hv_cpu = this_cpu_ptr(hv_context.cpu_context); union hv_synic_event_flags *event =
(union hv_synic_event_flags *)hv_cpu->synic_event_page + VMBUS_MESSAGE_SINT; unsignedlong *recv_int_page = event->flags; /* assumes VMBus version >= VERSION_WIN8 */ bool pending;
u32 relid; int tries = 0;
/* * We can't assume that the relevant interrupts will be sent before * the cpu is offlined on older versions of hyperv.
*/ if (vmbus_proto_version < VERSION_WIN10_V5_3) return -EBUSY;
start = get_random_u32_below(nr_cpu_ids);
for_each_cpu_wrap(cpu, cpu_online_mask, start) { if (channel->target_cpu == cpu ||
channel->target_cpu == VMBUS_CONNECT_CPU) continue;
ret = vmbus_channel_set_cpu(channel, cpu); if (!ret) break;
}
if (ret)
ret = vmbus_channel_set_cpu(channel, VMBUS_CONNECT_CPU);
return ret;
}
/* * hv_synic_cleanup - Cleanup routine for hv_synic_init().
*/ int hv_synic_cleanup(unsignedint cpu)
{ struct vmbus_channel *channel, *sc; int ret = 0;
if (vmbus_connection.conn_state != CONNECTED) goto always_cleanup;
/* * Hyper-V does not provide a way to change the connect CPU once * it is set; we must prevent the connect CPU from going offline * while the VM is running normally. But in the panic or kexec() * path where the vmbus is already disconnected, the CPU must be * allowed to shut down.
*/ if (cpu == VMBUS_CONNECT_CPU) return -EBUSY;
/* * Search for channels which are bound to the CPU we're about to * cleanup.
*/
mutex_lock(&vmbus_connection.channel_mutex);
list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) { if (channel->target_cpu == cpu) {
ret = hv_pick_new_cpu(channel); if (ret) {
mutex_unlock(&vmbus_connection.channel_mutex); return ret;
}
}
list_for_each_entry(sc, &channel->sc_list, sc_list) { if (sc->target_cpu == cpu) {
ret = hv_pick_new_cpu(sc); if (ret) {
mutex_unlock(&vmbus_connection.channel_mutex); return ret;
}
}
}
}
mutex_unlock(&vmbus_connection.channel_mutex);
/* * Scan the event flags page looking for bits that are set and waiting * with a timeout for vmbus_chan_sched() to process such bits. If bits * are still set after this operation and VMBus is connected, fail the * CPU offlining operation.
*/ if (vmbus_proto_version >= VERSION_WIN10_V4_1 && hv_synic_event_pending()) return -EBUSY;
always_cleanup:
hv_stimer_legacy_cleanup(cpu);
hv_synic_disable_regs(cpu);
return ret;
}
Messung V0.5
¤ Dauer der Verarbeitung: 0.12 Sekunden
(vorverarbeitet)
¤
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.