8 files changed, 54 insertions, 233 deletions
diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile
index 3a1548054b48..d55f494f471d 100644
--- a/arch/x86/hyperv/Makefile
+++ b/arch/x86/hyperv/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y			:= hv_init.o mmu.o nested.o irqdomain.o ivm.o
-obj-$(CONFIG_X86_64)	+= hv_apic.o hv_proc.o
+obj-$(CONFIG_X86_64)	+= hv_apic.o
 obj-$(CONFIG_HYPERV_VTL_MODE)	+= hv_vtl.o
 
 ifdef CONFIG_X86_64
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index f022d5f64fb6..6d91ac5f9836 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -145,6 +145,11 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector,
 		ipi_arg->vp_set.format = HV_GENERIC_SET_ALL;
 	}
 
+	/*
+	 * For this hypercall, Hyper-V treats the valid_bank_mask field
+	 * of ipi_arg->vp_set as part of the fixed size input header.
+	 * So the variable input header size is equal to nr_bank.
+	 */
 	status = hv_do_rep_hypercall(HVCALL_SEND_IPI_EX, 0, nr_bank,
 				     ipi_arg, NULL);
 
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 173005e6a95d..ddeb40930bc8 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -34,9 +34,6 @@
 #include <clocksource/hyperv_timer.h>
 #include <linux/highmem.h>
 
-u64 hv_current_partition_id = ~0ull;
-EXPORT_SYMBOL_GPL(hv_current_partition_id);
-
 void *hv_hypercall_pg;
 EXPORT_SYMBOL_GPL(hv_hypercall_pg);
 
@@ -93,7 +90,7 @@ static int hv_cpu_init(unsigned int cpu)
 		return 0;
 
 	hvp = &hv_vp_assist_page[cpu];
-	if (hv_root_partition) {
+	if (hv_root_partition()) {
 		/*
 		 * For root partition we get the hypervisor provided VP assist
 		 * page, instead of allocating a new page.
@@ -245,7 +242,7 @@ static int hv_cpu_die(unsigned int cpu)
 
 	if (hv_vp_assist_page && hv_vp_assist_page[cpu]) {
 		union hv_vp_assist_msr_contents msr = { 0 };
-		if (hv_root_partition) {
+		if (hv_root_partition()) {
 			/*
 			 * For root partition the VP assist page is mapped to
 			 * hypervisor provided page, and thus we unmap the
@@ -320,7 +317,7 @@ static int hv_suspend(void)
 	union hv_x64_msr_hypercall_contents hypercall_msr;
 	int ret;
 
-	if (hv_root_partition)
+	if (hv_root_partition())
 		return -EPERM;
 
 	/*
@@ -393,24 +390,6 @@ static void __init hv_stimer_setup_percpu_clockev(void)
 		old_setup_percpu_clockev();
 }
 
-static void __init hv_get_partition_id(void)
-{
-	struct hv_get_partition_id *output_page;
-	u64 status;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	output_page = *this_cpu_ptr(hyperv_pcpu_output_arg);
-	status = hv_do_hypercall(HVCALL_GET_PARTITION_ID, NULL, output_page);
-	if (!hv_result_success(status)) {
-		/* No point in proceeding if this failed */
-		pr_err("Failed to get partition ID: %lld\n", status);
-		BUG();
-	}
-	hv_current_partition_id = output_page->partition_id;
-	local_irq_restore(flags);
-}
-
 #if IS_ENABLED(CONFIG_HYPERV_VTL_MODE)
 static u8 __init get_vtl(void)
 {
@@ -539,7 +518,7 @@ void __init hyperv_init(void)
 	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 	hypercall_msr.enable = 1;
 
-	if (hv_root_partition) {
+	if (hv_root_partition()) {
 		struct page *pg;
 		void *src;
 
@@ -605,17 +584,15 @@ skip_hypercall_pg_init:
 
 	register_syscore_ops(&hv_syscore_ops);
 
-	if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_ACCESS_PARTITION_ID)
+	if (ms_hyperv.priv_high & HV_ACCESS_PARTITION_ID)
 		hv_get_partition_id();
 
-	BUG_ON(hv_root_partition && hv_current_partition_id == ~0ull);
-
 #ifdef CONFIG_PCI_MSI
 	/*
 	 * If we're running as root, we want to create our own PCI MSI domain.
 	 * We can't set this in hv_pci_init because that would be too late.
 	 */
-	if (hv_root_partition)
+	if (hv_root_partition())
 		x86_init.irqs.create_pci_msi_domain = hv_create_pci_msi_domain;
 #endif
 
diff --git a/arch/x86/hyperv/hv_proc.c b/arch/x86/hyperv/hv_proc.c
deleted file mode 100644
index ac4c834d4435..000000000000
--- a/arch/x86/hyperv/hv_proc.c
+++ /dev/null
@@ -1,198 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/types.h>
-#include <linux/vmalloc.h>
-#include <linux/mm.h>
-#include <linux/clockchips.h>
-#include <linux/slab.h>
-#include <linux/cpuhotplug.h>
-#include <linux/minmax.h>
-#include <asm/hypervisor.h>
-#include <asm/mshyperv.h>
-#include <asm/apic.h>
-
-#include <asm/trace/hyperv.h>
-
-/*
- * See struct hv_deposit_memory. The first u64 is partition ID, the rest
- * are GPAs.
- */
-#define HV_DEPOSIT_MAX (HV_HYP_PAGE_SIZE / sizeof(u64) - 1)
-
-/* Deposits exact number of pages. Must be called with interrupts enabled.  */
-int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages)
-{
-	struct page **pages, *page;
-	int *counts;
-	int num_allocations;
-	int i, j, page_count;
-	int order;
-	u64 status;
-	int ret;
-	u64 base_pfn;
-	struct hv_deposit_memory *input_page;
-	unsigned long flags;
-
-	if (num_pages > HV_DEPOSIT_MAX)
-		return -E2BIG;
-	if (!num_pages)
-		return 0;
-
-	/* One buffer for page pointers and counts */
-	page = alloc_page(GFP_KERNEL);
-	if (!page)
-		return -ENOMEM;
-	pages = page_address(page);
-
-	counts = kcalloc(HV_DEPOSIT_MAX, sizeof(int), GFP_KERNEL);
-	if (!counts) {
-		free_page((unsigned long)pages);
-		return -ENOMEM;
-	}
-
-	/* Allocate all the pages before disabling interrupts */
-	i = 0;
-
-	while (num_pages) {
-		/* Find highest order we can actually allocate */
-		order = 31 - __builtin_clz(num_pages);
-
-		while (1) {
-			pages[i] = alloc_pages_node(node, GFP_KERNEL, order);
-			if (pages[i])
-				break;
-			if (!order) {
-				ret = -ENOMEM;
-				num_allocations = i;
-				goto err_free_allocations;
-			}
-			--order;
-		}
-
-		split_page(pages[i], order);
-		counts[i] = 1 << order;
-		num_pages -= counts[i];
-		i++;
-	}
-	num_allocations = i;
-
-	local_irq_save(flags);
-
-	input_page = *this_cpu_ptr(hyperv_pcpu_input_arg);
-
-	input_page->partition_id = partition_id;
-
-	/* Populate gpa_page_list - these will fit on the input page */
-	for (i = 0, page_count = 0; i < num_allocations; ++i) {
-		base_pfn = page_to_pfn(pages[i]);
-		for (j = 0; j < counts[i]; ++j, ++page_count)
-			input_page->gpa_page_list[page_count] = base_pfn + j;
-	}
-	status = hv_do_rep_hypercall(HVCALL_DEPOSIT_MEMORY,
-				     page_count, 0, input_page, NULL);
-	local_irq_restore(flags);
-	if (!hv_result_success(status)) {
-		pr_err("Failed to deposit pages: %lld\n", status);
-		ret = hv_result(status);
-		goto err_free_allocations;
-	}
-
-	ret = 0;
-	goto free_buf;
-
-err_free_allocations:
-	for (i = 0; i < num_allocations; ++i) {
-		base_pfn = page_to_pfn(pages[i]);
-		for (j = 0; j < counts[i]; ++j)
-			__free_page(pfn_to_page(base_pfn + j));
-	}
-
-free_buf:
-	free_page((unsigned long)pages);
-	kfree(counts);
-	return ret;
-}
-
-int hv_call_add_logical_proc(int node, u32 lp_index, u32 apic_id)
-{
-	struct hv_input_add_logical_processor *input;
-	struct hv_output_add_logical_processor *output;
-	u64 status;
-	unsigned long flags;
-	int ret = HV_STATUS_SUCCESS;
-
-	/*
-	 * When adding a logical processor, the hypervisor may return
-	 * HV_STATUS_INSUFFICIENT_MEMORY. When that happens, we deposit more
-	 * pages and retry.
-	 */
-	do {
-		local_irq_save(flags);
-
-		input = *this_cpu_ptr(hyperv_pcpu_input_arg);
-		/* We don't do anything with the output right now */
-		output = *this_cpu_ptr(hyperv_pcpu_output_arg);
-
-		input->lp_index = lp_index;
-		input->apic_id = apic_id;
-		input->proximity_domain_info = hv_numa_node_to_pxm_info(node);
-		status = hv_do_hypercall(HVCALL_ADD_LOGICAL_PROCESSOR,
-					 input, output);
-		local_irq_restore(flags);
-
-		if (hv_result(status) != HV_STATUS_INSUFFICIENT_MEMORY) {
-			if (!hv_result_success(status)) {
-				pr_err("%s: cpu %u apic ID %u, %lld\n", __func__,
-				       lp_index, apic_id, status);
-				ret = hv_result(status);
-			}
-			break;
-		}
-		ret = hv_call_deposit_pages(node, hv_current_partition_id, 1);
-	} while (!ret);
-
-	return ret;
-}
-
-int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags)
-{
-	struct hv_create_vp *input;
-	u64 status;
-	unsigned long irq_flags;
-	int ret = HV_STATUS_SUCCESS;
-
-	/* Root VPs don't seem to need pages deposited */
-	if (partition_id != hv_current_partition_id) {
-		/* The value 90 is empirically determined. It may change. */
-		ret = hv_call_deposit_pages(node, partition_id, 90);
-		if (ret)
-			return ret;
-	}
-
-	do {
-		local_irq_save(irq_flags);
-
-		input = *this_cpu_ptr(hyperv_pcpu_input_arg);
-
-		input->partition_id = partition_id;
-		input->vp_index = vp_index;
-		input->flags = flags;
-		input->subnode_type = HV_SUBNODE_ANY;
-		input->proximity_domain_info = hv_numa_node_to_pxm_info(node);
-		status = hv_do_hypercall(HVCALL_CREATE_VP, input, NULL);
-		local_irq_restore(irq_flags);
-
-		if (hv_result(status) != HV_STATUS_INSUFFICIENT_MEMORY) {
-			if (!hv_result_success(status)) {
-				pr_err("%s: vcpu %u, lp %u, %lld\n", __func__,
-				       vp_index, flags, status);
-				ret = hv_result(status);
-			}
-			break;
-		}
-		ret = hv_call_deposit_pages(node, partition_id, 1);
-
-	} while (!ret);
-
-	return ret;
-}
-
diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c
index 3f4e20d7b724..13242ed8ff16 100644
--- a/arch/x86/hyperv/hv_vtl.c
+++ b/arch/x86/hyperv/hv_vtl.c
@@ -12,6 +12,7 @@
 #include <asm/i8259.h>
 #include <asm/mshyperv.h>
 #include <asm/realmode.h>
+#include <asm/reboot.h>
 #include <../kernel/smpboot.h>
 
 extern struct boot_params boot_params;
@@ -22,6 +23,36 @@ static bool __init hv_vtl_msi_ext_dest_id(void)
 	return true;
 }
 
+/*
+ * The `native_machine_emergency_restart` function from `reboot.c` writes
+ * to the physical address 0x472 to indicate the type of reboot for the
+ * firmware. We cannot have that in VSM as the memory composition might
+ * be more generic, and such write effectively corrupts the memory thus
+ * making diagnostics harder at the very least.
+ */
+static void  __noreturn hv_vtl_emergency_restart(void)
+{
+	/*
+	 * Cause a triple fault and the immediate reset. Here the code does not run
+	 * on the top of any firmware, whereby cannot reach out to its services.
+	 * The inifinite loop is for the improbable case that the triple fault does
+	 * not work and have to preserve the state intact for debugging.
+	 */
+	for (;;) {
+		idt_invalidate();
+		__asm__ __volatile__("int3");
+	}
+}
+
+/*
+ * The only way to restart in the VTL mode is to triple fault as the kernel runs
+ * as firmware.
+ */
+static void  __noreturn hv_vtl_restart(char __maybe_unused *cmd)
+{
+	hv_vtl_emergency_restart();
+}
+
 void __init hv_vtl_init_platform(void)
 {
 	pr_info("Linux runs in Hyper-V Virtual Trust Level\n");
@@ -236,6 +267,9 @@ static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip)
 
 int __init hv_vtl_early_init(void)
 {
+	machine_ops.emergency_restart = hv_vtl_emergency_restart;
+	machine_ops.restart = hv_vtl_restart;
+
 	/*
 	 * `boot_cpu_has` returns the runtime feature support,
 	 * and here is the earliest it can be used.
diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c
index 64b921360b0f..31f0d29cbc5e 100644
--- a/arch/x86/hyperv/irqdomain.c
+++ b/arch/x86/hyperv/irqdomain.c
@@ -64,7 +64,7 @@ static int hv_map_interrupt(union hv_device_id device_id, bool level,
 	local_irq_restore(flags);
 
 	if (!hv_result_success(status))
-		pr_err("%s: hypercall failed, status %lld\n", __func__, status);
+		hv_status_err(status, "\n");
 
 	return hv_result(status);
 }
@@ -224,7 +224,7 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		kfree(stored_entry);
 
 		if (status != HV_STATUS_SUCCESS) {
-			pr_debug("%s: failed to unmap, status %lld", __func__, status);
+			hv_status_debug(status, "failed to unmap\n");
 			return;
 		}
 	}
@@ -273,7 +273,7 @@ static void hv_teardown_msi_irq(struct pci_dev *dev, struct irq_data *irqd)
 	status = hv_unmap_msi_interrupt(dev, &old_entry);
 
 	if (status != HV_STATUS_SUCCESS)
-		pr_err("%s: hypercall failed, status %lld\n", __func__, status);
+		hv_status_err(status, "\n");
 }
 
 static void hv_msi_free_irq(struct irq_domain *domain,
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index ec7880271cf9..77bf05f06b9e 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -338,7 +338,7 @@ int hv_snp_boot_ap(u32 cpu, unsigned long start_ip)
 	vmsa->sev_features = sev_status >> 2;
 
 	ret = snp_set_vmsa(vmsa, true);
-	if (!ret) {
+	if (ret) {
 		pr_err("RMPADJUST(%llx) failed: %llx\n", (u64)vmsa, ret);
 		free_page((u64)vmsa);
 		return ret;
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index cc8c3bd0e7c2..cfcb60468b01 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -205,6 +205,10 @@ static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 	/*
 	 * We can flush not more than max_gvas with one hypercall. Flush the
 	 * whole address space if we were asked to do more.
+	 *
+	 * For these hypercalls, Hyper-V treats the valid_bank_mask field
+	 * of flush->hv_vp_set as part of the fixed size input header.
+	 * So the variable input header size is equal to nr_bank.
 	 */
 	max_gvas =
 		(PAGE_SIZE - sizeof(*flush) - nr_bank *
@@ -239,5 +243,4 @@ void hyperv_setup_mmu_ops(void)
 
 	pr_info("Using hypercall for remote TLB flush\n");
 	pv_ops.mmu.flush_tlb_multi = hyperv_flush_tlb_multi;
-	pv_ops.mmu.tlb_remove_table = tlb_remove_table;
 }