x86/hyperv: fix root partition faults when writing to VP assist page MSR

For root partition the VP assist pages are pre-determined by the
hypervisor. The root kernel is not allowed to change them to
different locations. And thus, we are getting below stack as in
current implementation root is trying to perform write to specific
MSR.

    [ 2.778197] unchecked MSR access error: WRMSR to 0x40000073 (tried to write 0x0000000145ac5001) at rIP: 0xffffffff810c1084 (native_write_msr+0x4/0x30)
    [ 2.784867] Call Trace:
    [ 2.791507] hv_cpu_init+0xf1/0x1c0
    [ 2.798144] ? hyperv_report_panic+0xd0/0xd0
    [ 2.804806] cpuhp_invoke_callback+0x11a/0x440
    [ 2.811465] ? hv_resume+0x90/0x90
    [ 2.818137] cpuhp_issue_call+0x126/0x130
    [ 2.824782] __cpuhp_setup_state_cpuslocked+0x102/0x2b0
    [ 2.831427] ? hyperv_report_panic+0xd0/0xd0
    [ 2.838075] ? hyperv_report_panic+0xd0/0xd0
    [ 2.844723] ? hv_resume+0x90/0x90
    [ 2.851375] __cpuhp_setup_state+0x3d/0x90
    [ 2.858030] hyperv_init+0x14e/0x410
    [ 2.864689] ? enable_IR_x2apic+0x190/0x1a0
    [ 2.871349] apic_intr_mode_init+0x8b/0x100
    [ 2.878017] x86_late_time_init+0x20/0x30
    [ 2.884675] start_kernel+0x459/0x4fb
    [ 2.891329] secondary_startup_64_no_verify+0xb0/0xbb

Since the hypervisor already provides the VP assist pages for root
partition, we need to memremap the memory from hypervisor for root
kernel to use. The mapping is done in hv_cpu_init during bringup and is
unmapped in hv_cpu_die during teardown.
Signed-off-by: Praveen Kumar <kumarpraveen@linux.microsoft.com>
Reviewed-by: Sunil Muthuswamy <sunilmut@microsoft.com>
Link: https://lore.kernel.org/r/20210731120519.17154-1-kumarpraveen@linux.microsoft.comSigned-off-by: Wei Liu <wei.liu@kernel.org>

arch/x86/hyperv/hv_init.c

@@ -44,6 +44,7 @@ EXPORT_SYMBOL_GPL(hv_vp_assist_page);
 
 static int hv_cpu_init(unsigned int cpu)
 {
+	union hv_vp_assist_msr_contents msr = { 0 };
 	struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()];
 	int ret;
 
@@ -54,25 +55,34 @@ static int hv_cpu_init(unsigned int cpu)
 	if (!hv_vp_assist_page)
 		return 0;
 
-	/*
-	 * The VP ASSIST PAGE is an "overlay" page (see Hyper-V TLFS's Section
-	 * 5.2.1 "GPA Overlay Pages"). Here it must be zeroed out to make sure
-	 * we always write the EOI MSR in hv_apic_eoi_write() *after* the
-	 * EOI optimization is disabled in hv_cpu_die(), otherwise a CPU may
-	 * not be stopped in the case of CPU offlining and the VM will hang.
-	 */
 	if (!*hvp) {
-		*hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO);
-	}
-
-	if (*hvp) {
-		u64 val;
-
-		val = vmalloc_to_pfn(*hvp);
-		val = (val << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT) |
-			HV_X64_MSR_VP_ASSIST_PAGE_ENABLE;
-
-		wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, val);
+		if (hv_root_partition) {
+			/*
+			 * For root partition we get the hypervisor provided VP assist
+			 * page, instead of allocating a new page.
+			 */
+			rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+			*hvp = memremap(msr.pfn <<
+					HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT,
+					PAGE_SIZE, MEMREMAP_WB);
+		} else {
+			/*
+			 * The VP assist page is an "overlay" page (see Hyper-V TLFS's
+			 * Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed
+			 * out to make sure we always write the EOI MSR in
+			 * hv_apic_eoi_write() *after* the EOI optimization is disabled
+			 * in hv_cpu_die(), otherwise a CPU may not be stopped in the
+			 * case of CPU offlining and the VM will hang.
+			 */
+			*hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO);
+			if (*hvp)
+				msr.pfn = vmalloc_to_pfn(*hvp);
+		}
+		WARN_ON(!(*hvp));
+		if (*hvp) {
+			msr.enable = 1;
+			wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+		}
 	}
 
 	return 0;
@@ -170,8 +180,22 @@ static int hv_cpu_die(unsigned int cpu)
 
 	hv_common_cpu_die(cpu);
 
-	if (hv_vp_assist_page && hv_vp_assist_page[cpu])
-		wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, 0);
+	if (hv_vp_assist_page && hv_vp_assist_page[cpu]) {
+		union hv_vp_assist_msr_contents msr = { 0 };
+		if (hv_root_partition) {
+			/*
+			 * For root partition the VP assist page is mapped to
+			 * hypervisor provided page, and thus we unmap the
+			 * page here and nullify it, so that in future we have
+			 * correct page address mapped in hv_cpu_init.
+			 */
+			memunmap(hv_vp_assist_page[cpu]);
+			hv_vp_assist_page[cpu] = NULL;
+			rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+			msr.enable = 0;
+		}
+		wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+	}
 
 	if (hv_reenlightenment_cb == NULL)
 		return 0;

arch/x86/include/asm/hyperv-tlfs.h

@@ -288,6 +288,15 @@ union hv_x64_msr_hypercall_contents {
 	} __packed;
 };
 
+union hv_vp_assist_msr_contents {
+	u64 as_uint64;
+	struct {
+		u64 enable:1;
+		u64 reserved:11;
+		u64 pfn:52;
+	} __packed;
+};
+
 struct hv_reenlightenment_control {
 	__u64 vector:8;
 	__u64 reserved1:8;