RE: [RFC PATCH 11/18] virt/mshv: set up synic pages for intercept messages

From: Nuno Das Neves <redacted> Sent: Friday, November 20, 2020 4:31 PM

I have a separate patch series that moves this enum to the
asm-generic portion of hyperv-tlfs.h because there's not a good way
to separate the arch neutral from arch dependent values.

+
+
+union hv_x64_vp_execution_state {
+	__u16 as_uint16;
+	struct {
+		__u16 cpl:2;
+		__u16 cr0_pe:1;
+		__u16 cr0_am:1;
+		__u16 efer_lma:1;
+		__u16 debug_active:1;
+		__u16 interruption_pending:1;
+		__u16 vtl:4;
+		__u16 enclave_mode:1;
+		__u16 interrupt_shadow:1;
+		__u16 virtualization_fault_active:1;
+		__u16 reserved:2;
+	};
+};
+
+/* Values for intercept_access_type field */
+#define HV_INTERCEPT_ACCESS_READ	0
+#define HV_INTERCEPT_ACCESS_WRITE	1
+#define HV_INTERCEPT_ACCESS_EXECUTE	2
+
+struct hv_x64_intercept_message_header {
+	__u32 vp_index;
+	__u8 instruction_length:4;
+	__u8 cr8:4; // only set for exo partitions
+	__u8 intercept_access_type;
+	union hv_x64_vp_execution_state execution_state;
+	struct hv_x64_segment_register cs_segment;
+	__u64 rip;
+	__u64 rflags;
+};
+
+#define HV_HYPERCALL_INTERCEPT_MAX_XMM_REGISTERS 6
+
+struct hv_x64_hypercall_intercept_message {
+	struct hv_x64_intercept_message_header header;
+	__u64 rax;
+	__u64 rbx;
+	__u64 rcx;
+	__u64 rdx;
+	__u64 r8;
+	__u64 rsi;
+	__u64 rdi;
+	struct hv_u128 xmmregisters[HV_HYPERCALL_INTERCEPT_MAX_XMM_REGISTERS];
+	struct {
+		__u32 isolated:1;
+		__u32 reserved:31;
+	};
+};
+
+union hv_x64_register_access_info {
+	union hv_register_value source_value;
+	enum hv_register_name destination_register;
+	__u64 source_address;
+	__u64 destination_address;
+};
+
+struct hv_x64_register_intercept_message {
+	struct hv_x64_intercept_message_header header;
+	struct {
+		__u8 is_memory_op:1;
+		__u8 reserved:7;
+	};
+	__u8 reserved8;
+	__u16 reserved16;
+	enum hv_register_name register_name;
+	union hv_x64_register_access_info access_info;
+};
+
+union hv_x64_memory_access_info {
+	__u8 as_uint8;
+	struct {
+		__u8 gva_valid:1;
+		__u8 gva_gpa_valid:1;
+		__u8 hypercall_output_pending:1;
+		__u8 tlb_locked_no_overlay:1;
+		__u8 reserved:4;
+	};
+};
+
+union hv_x64_io_port_access_info {
+	__u8 as_uint8;
+	struct {
+		__u8 access_size:3;
+		__u8 string_op:1;
+		__u8 rep_prefix:1;
+		__u8 reserved:3;
+	};
+};
+
+union hv_x64_exception_info {
+	__u8 as_uint8;
+	struct {
+		__u8 error_code_valid:1;
+		__u8 software_exception:1;
+		__u8 reserved:6;
+	};
+};
+
+enum hv_cache_type {
+	HV_CACHE_TYPE_UNCACHED	   = 0,
+	HV_CACHE_TYPE_WRITE_COMBINING = 1,
+	HV_CACHE_TYPE_WRITE_THROUGH   = 4,
+	HV_CACHE_TYPE_WRITE_PROTECTED = 5,
+	HV_CACHE_TYPE_WRITE_BACK	  = 6
+};
+
+struct hv_x64_memory_intercept_message {
+	struct hv_x64_intercept_message_header header;
+	enum hv_cache_type cache_type;
+	__u8 instruction_byte_count;
+	union hv_x64_memory_access_info memory_access_info;
+	__u8 tpr_priority;
+	__u8 reserved1;
+	__u64 guest_virtual_address;
+	__u64 guest_physical_address;
+	__u8 instruction_bytes[16];
+};
+
+struct hv_x64_cpuid_intercept_message {
+	struct hv_x64_intercept_message_header header;
+	__u64 rax;
+	__u64 rcx;
+	__u64 rdx;
+	__u64 rbx;
+	__u64 default_result_rax;
+	__u64 default_result_rcx;
+	__u64 default_result_rdx;
+	__u64 default_result_rbx;
+};
+
+struct hv_x64_msr_intercept_message {
+	struct hv_x64_intercept_message_header header;
+	__u32 msr_number;
+	__u32 reserved;
+	__u64 rdx;
+	__u64 rax;
+};
+
+struct hv_x64_io_port_intercept_message {
+	struct hv_x64_intercept_message_header header;
+	__u16 port_number;
+	union hv_x64_io_port_access_info access_info;
+	__u8 instruction_byte_count;
+	__u32 reserved;
+	__u64 rax;
+	__u8 instruction_bytes[16];
+	struct hv_x64_segment_register ds_segment;
+	struct hv_x64_segment_register es_segment;
+	__u64 rcx;
+	__u64 rsi;
+	__u64 rdi;
+};
+
+struct hv_x64_exception_intercept_message {
+	struct hv_x64_intercept_message_header header;
+	__u16 exception_vector;
+	union hv_x64_exception_info exception_info;
+	__u8 instruction_byte_count;
+	__u32 error_code;
+	__u64 exception_parameter;
+	__u64 reserved;
+	__u8 instruction_bytes[16];
+	struct hv_x64_segment_register ds_segment;
+	struct hv_x64_segment_register ss_segment;
+	__u64 rax;
+	__u64 rcx;
+	__u64 rdx;
+	__u64 rbx;

Is the above the correct ordering (rax, rcd, rdx, rbx)?
It's just what you would expect ....

+	__u64 rsp;
+	__u64 rbp;
+	__u64 rsi;
+	__u64 rdi;
+	__u64 r8;
+	__u64 r9;
+	__u64 r10;
+	__u64 r11;
+	__u64 r12;
+	__u64 r13;
+	__u64 r14;
+	__u64 r15;
+};
+
+struct hv_x64_invalid_vp_register_message {
+	__u32 vp_index;
+	__u32 reserved;
+};
+
+struct hv_x64_unrecoverable_exception_message {
+	struct hv_x64_intercept_message_header header;
+};
+
+enum hv_x64_unsupported_feature_code {
+	hv_unsupported_feature_intercept = 1,
+	hv_unsupported_feature_task_switch_tss = 2
+};
+
+struct hv_x64_unsupported_feature_message {
+	__u32 vp_index;
+	enum hv_x64_unsupported_feature_code feature_code;
+	__u64 feature_parameter;
+};
+
+struct hv_x64_halt_message {
+	struct hv_x64_intercept_message_header header;
+};
+
+enum hv_x64_pending_interruption_type {
+	HV_X64_PENDING_INTERRUPT	= 0,
+	HV_X64_PENDING_NMI		= 2,
+	HV_X64_PENDING_EXCEPTION	= 3
+};
+
+struct hv_x64_interruption_deliverable_message {
+	struct hv_x64_intercept_message_header header;
+	enum hv_x64_pending_interruption_type deliverable_type;
+	__u32 rsvd;
+};
+
+struct hv_x64_sipi_intercept_message {
+	struct hv_x64_intercept_message_header header;
+	__u32 target_vp_index;
+	__u32 interrupt_vector;
+};
+
+struct hv_x64_apic_eoi_message {
+	__u32 vp_index;
+	__u32 interrupt_vector;
+};

Same comments as before about enum types, not depending
on the compiler to add padding, and marking as __packed.

Use HV_HYP_PAGE_SHIFT and HV_HYP_PAGE_SIZE.

+	if (!msg_page) {
+		pr_err("%s: memremap failed\n", __func__);
+		return -EFAULT;
+	}
+	hv_set_simp(simp.as_uint64);
+
+	/* Enable intercepts */
+	sint.as_uint64 = 0;
+	sint.vector = HYPERVISOR_CALLBACK_VECTOR;
+	sint.masked = false;
+	sint.auto_eoi = hv_recommend_using_aeoi();
+	hv_set_synint_state(HV_SYNIC_INTERCEPTION_SINT_INDEX, sint.as_uint64);
+
+	/* Enable global synic bit */
+	hv_get_synic_state(sctrl.as_uint64);
+	sctrl.enable = 1;
+	hv_set_synic_state(sctrl.as_uint64);
+
+	return 0;
+}
+
+static int
+mshv_synic_cleanup(unsigned int cpu)
+{
+	union hv_synic_sint sint;
+	union hv_synic_simp simp;
+	union hv_synic_scontrol sctrl;
+	struct hv_message_page **msg_page =
+			this_cpu_ptr(mshv.synic_message_page);
+
+	/* Disable the interrupt */
+	hv_get_synint_state(HV_SYNIC_INTERCEPTION_SINT_INDEX, sint.as_uint64);
+	sint.masked = true;
+	hv_set_synint_state(HV_SYNIC_INTERCEPTION_SINT_INDEX, sint.as_uint64);
+
+	/* Disable Synic's message page */
+	hv_get_simp(simp.as_uint64);
+	simp.simp_enabled = false;
+	hv_set_simp(simp.as_uint64);
+	memunmap(*msg_page);
+
+	/* Disable global synic bit */
+	hv_get_synic_state(sctrl.as_uint64);
+	sctrl.enable = 0;
+	hv_set_synic_state(sctrl.as_uint64);
+
+	return 0;
+}
+
+static int mshv_cpuhp_online;
+
 static int
 __init mshv_init(void)
 {
-	int r;
+	int ret;

Ideally, change the name of the variable in the earlier patch so this
one isn't cluttered with the change.

-	r = misc_register(&mshv_dev);
-	if (r)
+	ret = misc_register(&mshv_dev);
+	if (ret) {
 		pr_err("%s: misc device register failed\n", __func__);
+		return ret;
+	}
+	spin_lock_init(&mshv.partitions.lock);

+	mshv.synic_message_page = alloc_percpu(struct hv_message_page *);
+	if (!mshv.synic_message_page) {
+		pr_err("%s: failed to allocate percpu synic page\n", __func__);
+		misc_deregister(&mshv_dev);
+		return -ENOMEM;
+	}
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mshv_synic",
+				mshv_synic_init,
+				mshv_synic_cleanup);
+	if (ret < 0) {
+		pr_err("%s: failed to setup cpu hotplug state: %i\n",
+		       __func__, ret);
+		return ret;
+	}
+
+	mshv_cpuhp_online = ret;
 	spin_lock_init(&mshv.partitions.lock);

It looks like the spin lock is being initialized twice.

-	return r;
+	return 0;
 }

 static void
 __exit mshv_exit(void)
 {
+	cpuhp_remove_state(mshv_cpuhp_online);
+	free_percpu(mshv.synic_message_page);
+
 	misc_deregister(&mshv_dev);
 }

--
2.25.1

_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization