From e96204e5e96ea3cacb5686e06ed29977c023254f Mon Sep 17 00:00:00 2001 From: Nuno Das Neves Date: Fri, 7 Feb 2025 11:03:21 -0800 Subject: hyperv: Move hv_current_partition_id to arch-generic code Move hv_current_partition_id and hv_get_partition_id() to hv_common.c, and call hv_get_partition_id() on arm64 in hyperv_init(). These aren't specific to x86_64 and will be needed by common code. Set hv_current_partition_id to HV_PARTITION_ID_SELF by default. Rename struct hv_get_partition_id to hv_output_get_partition_id, to make it distinct from the function hv_get_partition_id(), and match the original Hyper-V struct name. Remove the BUG()s. Failing to get the id need not crash the machine. Signed-off-by: Nuno Das Neves Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/1738955002-20821-2-git-send-email-nunodasneves@linux.microsoft.com Signed-off-by: Wei Liu Message-ID: <1738955002-20821-2-git-send-email-nunodasneves@linux.microsoft.com> --- arch/x86/hyperv/hv_init.c | 25 +------------------------ arch/x86/include/asm/mshyperv.h | 2 -- 2 files changed, 1 insertion(+), 26 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 173005e6a95d..9be1446f5bd3 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -34,9 +34,6 @@ #include #include -u64 hv_current_partition_id = ~0ull; -EXPORT_SYMBOL_GPL(hv_current_partition_id); - void *hv_hypercall_pg; EXPORT_SYMBOL_GPL(hv_hypercall_pg); @@ -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) { @@ -605,11 +584,9 @@ 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. diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index f91ab1e75f9f..8d3ada3e8d0d 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -43,8 +43,6 @@ extern bool hyperv_paravisor_present; extern void *hv_hypercall_pg; -extern u64 hv_current_partition_id; - extern union hv_ghcb * __percpu *hv_ghcb_pg; bool hv_isolation_type_snp(void); -- cgit v1.2.3 From 0222eb30a3572cc9c4e2f0a3bb37f8f71089f2b6 Mon Sep 17 00:00:00 2001 From: Nuno Das Neves Date: Fri, 7 Feb 2025 11:03:22 -0800 Subject: hyperv: Move arch/x86/hyperv/hv_proc.c to drivers/hv These helpers are not specific to x86_64 and will be needed by common code. Remove some unnecessary #includes. Reviewed-by: Michael Kelley Signed-off-by: Nuno Das Neves Link: https://lore.kernel.org/r/1738955002-20821-3-git-send-email-nunodasneves@linux.microsoft.com Signed-off-by: Wei Liu Message-ID: <1738955002-20821-3-git-send-email-nunodasneves@linux.microsoft.com> --- arch/x86/hyperv/Makefile | 2 +- arch/x86/hyperv/hv_proc.c | 198 ---------------------------------------- arch/x86/include/asm/mshyperv.h | 4 - 3 files changed, 1 insertion(+), 203 deletions(-) delete mode 100644 arch/x86/hyperv/hv_proc.c (limited to 'arch/x86') 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_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 -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include - -/* - * 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/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 8d3ada3e8d0d..7dfca93ef048 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -56,10 +56,6 @@ u64 hv_tdx_hypercall(u64 control, u64 param1, u64 param2); #define HV_AP_INIT_GPAT_DEFAULT 0x0007040600070406ULL #define HV_AP_SEGMENT_LIMIT 0xffffffff -int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages); -int hv_call_add_logical_proc(int node, u32 lp_index, u32 acpi_id); -int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags); - /* * If the hypercall involves no input or output parameters, the hypervisor * ignores the corresponding GPA pointer. -- cgit v1.2.3 From db912b8954c23a55dbc6dc683e0e06ffcb433848 Mon Sep 17 00:00:00 2001 From: Nuno Das Neves Date: Fri, 21 Feb 2025 11:56:34 -0800 Subject: hyperv: Change hv_root_partition into a function Introduce hv_curr_partition_type to store the partition type as an enum. Right now this is limited to guest or root partition, but there will be other kinds in future and the enum is easily extensible. Set up hv_curr_partition_type early in Hyper-V initialization with hv_identify_partition_type(). hv_root_partition() just queries this value, and shouldn't be called before that. Making this check into a function sets the stage for adding a config option to gate the compilation of root partition code. In particular, hv_root_partition() can be stubbed out always be false if root partition support isn't desired. Signed-off-by: Nuno Das Neves Reviewed-by: Easwar Hariharan Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/1740167795-13296-3-git-send-email-nunodasneves@linux.microsoft.com Signed-off-by: Wei Liu Message-ID: <1740167795-13296-3-git-send-email-nunodasneves@linux.microsoft.com> --- arch/x86/hyperv/hv_init.c | 10 +++++----- arch/x86/kernel/cpu/mshyperv.c | 24 ++---------------------- 2 files changed, 7 insertions(+), 27 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 9be1446f5bd3..ddeb40930bc8 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -90,7 +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. @@ -242,7 +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 @@ -317,7 +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; /* @@ -518,7 +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; @@ -592,7 +592,7 @@ skip_hypercall_pg_init: * 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/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index f285757618fc..4f01f424ea5b 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -33,8 +33,6 @@ #include #include -/* Is Linux running as the root partition? */ -bool hv_root_partition; /* Is Linux running on nested Microsoft Hypervisor */ bool hv_nested; struct ms_hyperv_info ms_hyperv; @@ -451,25 +449,7 @@ static void __init ms_hyperv_init_platform(void) pr_debug("Hyper-V: max %u virtual processors, %u logical processors\n", ms_hyperv.max_vp_index, ms_hyperv.max_lp_index); - /* - * Check CPU management privilege. - * - * To mirror what Windows does we should extract CPU management - * features and use the ReservedIdentityBit to detect if Linux is the - * root partition. But that requires negotiating CPU management - * interface (a process to be finalized). For now, use the privilege - * flag as the indicator for running as root. - * - * Hyper-V should never specify running as root and as a Confidential - * VM. But to protect against a compromised/malicious Hyper-V trying - * to exploit root behavior to expose Confidential VM memory, ignore - * the root partition setting if also a Confidential VM. - */ - if ((ms_hyperv.priv_high & HV_CPU_MANAGEMENT) && - !(ms_hyperv.priv_high & HV_ISOLATION)) { - hv_root_partition = true; - pr_info("Hyper-V: running as root partition\n"); - } + hv_identify_partition_type(); if (ms_hyperv.hints & HV_X64_HYPERV_NESTED) { hv_nested = true; @@ -618,7 +598,7 @@ static void __init ms_hyperv_init_platform(void) # ifdef CONFIG_SMP smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu; - if (hv_root_partition || + if (hv_root_partition() || (!ms_hyperv.paravisor_present && hv_isolation_type_snp())) smp_ops.smp_prepare_cpus = hv_smp_prepare_cpus; # endif -- cgit v1.2.3 From ced518ad55b4118dd77f8a455a06801b89f2f877 Mon Sep 17 00:00:00 2001 From: Roman Kisel Date: Thu, 27 Feb 2025 13:47:27 -0800 Subject: x86/hyperv: Add VTL mode emergency restart callback By default, X86(-64) systems use the emergecy restart routine in the course of which the code unconditionally writes to the physical address of 0x472 to indicate the boot mode to the firmware (BIOS or UEFI). When the kernel itself runs as a firmware in the VTL mode, that write corrupts the memory of the guest upon emergency restarting. Preserving the state intact in that situation is important for debugging, at least. Define the specialized machine callback to avoid that write and use the triple fault to perform emergency restart. Signed-off-by: Roman Kisel Link: https://lore.kernel.org/r/20250227214728.15672-2-romank@linux.microsoft.com Signed-off-by: Wei Liu Message-ID: <20250227214728.15672-2-romank@linux.microsoft.com> --- arch/x86/hyperv/hv_vtl.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index 4e1b1e3b5658..4421b75ad9a9 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -12,6 +12,7 @@ #include #include #include +#include #include <../kernel/smpboot.h> extern struct boot_params boot_params; @@ -22,6 +23,27 @@ 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"); + } +} + void __init hv_vtl_init_platform(void) { pr_info("Linux runs in Hyper-V Virtual Trust Level\n"); @@ -235,6 +257,7 @@ 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; /* * `boot_cpu_has` returns the runtime feature support, * and here is the earliest it can be used. -- cgit v1.2.3 From 07b74192e6170571892c09bf5c4352a85db22557 Mon Sep 17 00:00:00 2001 From: Roman Kisel Date: Thu, 27 Feb 2025 13:47:28 -0800 Subject: x86/hyperv: Add VTL mode callback for restarting the system The kernel runs as a firmware in the VTL mode, and the only way to restart in the VTL mode on x86 is to triple fault. Thus, one has to always supply "reboot=t" on the kernel command line in the VTL mode, and missing that renders rebooting not working. Define the machine restart callback to always use the triple fault to provide the robust configuration by default. Signed-off-by: Roman Kisel Link: https://lore.kernel.org/r/20250227214728.15672-3-romank@linux.microsoft.com Signed-off-by: Wei Liu Message-ID: <20250227214728.15672-3-romank@linux.microsoft.com> --- arch/x86/hyperv/hv_vtl.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index 4421b75ad9a9..582fe820e29c 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -44,6 +44,15 @@ static void __noreturn hv_vtl_emergency_restart(void) } } +/* + * 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"); @@ -258,6 +267,8 @@ 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. -- cgit v1.2.3 From e792d843aa3c9d039074cdce728d5803262e57a7 Mon Sep 17 00:00:00 2001 From: Tianyu Lan Date: Thu, 13 Mar 2025 04:52:17 -0400 Subject: x86/hyperv: Fix check of return value from snp_set_vmsa() snp_set_vmsa() returns 0 as success result and so fix it. Cc: stable@vger.kernel.org Fixes: 44676bb9d566 ("x86/hyperv: Add smp support for SEV-SNP guest") Signed-off-by: Tianyu Lan Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/20250313085217.45483-1-ltykernel@gmail.com Signed-off-by: Wei Liu Message-ID: <20250313085217.45483-1-ltykernel@gmail.com> --- arch/x86/hyperv/ivm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index dd68d9ad9b22..c0039a90e9e0 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; -- cgit v1.2.3 From 3817854ba892016ddb03ee31208e9f8e440f5bee Mon Sep 17 00:00:00 2001 From: Nuno Das Neves Date: Fri, 14 Mar 2025 12:28:47 -0700 Subject: hyperv: Log hypercall status codes as strings Introduce hv_status_printk() macros as a convenience to log hypercall errors, formatting them with the status code (HV_STATUS_*) as a raw hex value and also as a string, which saves some time while debugging. Create a table of HV_STATUS_ codes with strings and mapped errnos, and use it for hv_result_to_string() and hv_result_to_errno(). Use the new hv_status_printk()s in hv_proc.c, hyperv-iommu.c, and irqdomain.c hypercalls to aid debugging in the root partition. Signed-off-by: Nuno Das Neves Reviewed-by: Stanislav Kinsburskii Link: https://lore.kernel.org/r/1741980536-3865-2-git-send-email-nunodasneves@linux.microsoft.com Signed-off-by: Wei Liu Message-ID: <1741980536-3865-2-git-send-email-nunodasneves@linux.microsoft.com> --- arch/x86/hyperv/irqdomain.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/x86') 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, -- cgit v1.2.3 From 8cac51796ecb162c437cc651f37152095af76591 Mon Sep 17 00:00:00 2001 From: Stanislav Kinsburskii Date: Fri, 14 Mar 2025 12:28:48 -0700 Subject: x86/mshyperv: Add support for extended Hyper-V features Extend the "ms_hyperv_info" structure to include a new field, "ext_features", for capturing extended Hyper-V features. Update the "ms_hyperv_init_platform" function to retrieve these features using the cpuid instruction and include them in the informational output. Signed-off-by: Stanislav Kinsburskii Signed-off-by: Nuno Das Neves Reviewed-by: Easwar Hariharan Reviewed-by: Roman Kisel Reviewed-by: Tianyu Lan Reviewed-by: Michael Kelley Link: https://lore.kernel.org/r/1741980536-3865-3-git-send-email-nunodasneves@linux.microsoft.com Signed-off-by: Wei Liu Message-ID: <1741980536-3865-3-git-send-email-nunodasneves@linux.microsoft.com> --- arch/x86/kernel/cpu/mshyperv.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 4f01f424ea5b..fd285b18d6b4 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -434,13 +434,15 @@ static void __init ms_hyperv_init_platform(void) */ ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES); ms_hyperv.priv_high = cpuid_ebx(HYPERV_CPUID_FEATURES); + ms_hyperv.ext_features = cpuid_ecx(HYPERV_CPUID_FEATURES); ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES); ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO); hv_max_functions_eax = cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS); - pr_info("Hyper-V: privilege flags low 0x%x, high 0x%x, hints 0x%x, misc 0x%x\n", - ms_hyperv.features, ms_hyperv.priv_high, ms_hyperv.hints, + pr_info("Hyper-V: privilege flags low %#x, high %#x, ext %#x, hints %#x, misc %#x\n", + ms_hyperv.features, ms_hyperv.priv_high, + ms_hyperv.ext_features, ms_hyperv.hints, ms_hyperv.misc_features); ms_hyperv.max_vp_index = cpuid_eax(HYPERV_CPUID_IMPLEMENT_LIMITS); -- cgit v1.2.3 From 21050f619720029e89d365b0e1328eafe088dbd8 Mon Sep 17 00:00:00 2001 From: Nuno Das Neves Date: Fri, 14 Mar 2025 12:28:52 -0700 Subject: Drivers: hv: Export some functions for use by root partition module hv_get_hypervisor_version(), hv_call_deposit_pages(), and hv_call_create_vp(), are all needed in-module with CONFIG_MSHV_ROOT=m. Signed-off-by: Nuno Das Neves Reviewed-by: Stanislav Kinsburskii Reviewed-by: Roman Kisel Reviewed-by: Easwar Hariharan Reviewed-by: Tianyu Lan Link: https://lore.kernel.org/r/1741980536-3865-7-git-send-email-nunodasneves@linux.microsoft.com Signed-off-by: Wei Liu Message-ID: <1741980536-3865-7-git-send-email-nunodasneves@linux.microsoft.com> --- arch/x86/kernel/cpu/mshyperv.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index fd285b18d6b4..fcd0e066d9bd 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -420,6 +420,7 @@ int hv_get_hypervisor_version(union hv_hypervisor_version_info *info) return 0; } +EXPORT_SYMBOL_GPL(hv_get_hypervisor_version); static void __init ms_hyperv_init_platform(void) { -- cgit v1.2.3 From e2575ffe57ac07e730be16a6c451efca0471af7c Mon Sep 17 00:00:00 2001 From: Nuno Das Neves Date: Fri, 14 Mar 2025 12:28:54 -0700 Subject: x86: hyperv: Add mshv_handler() irq handler and setup function Add mshv_handler() to process messages related to managing guest partitions such as intercepts, doorbells, and scheduling messages. In a (non-nested) root partition, the same interrupt vector is shared between the vmbus and mshv_root drivers. Introduce a stub for mshv_handler() and call it in sysvec_hyperv_callback alongside vmbus_handler(). Even though both handlers will be called for every Hyper-V interrupt, the messages for each driver are delivered to different offsets within the SYNIC message page, so they won't step on each other. Signed-off-by: Nuno Das Neves Reviewed-by: Wei Liu Reviewed-by: Tianyu Lan Reviewed-by: Stanislav Kinsburskii Link: https://lore.kernel.org/r/1741980536-3865-9-git-send-email-nunodasneves@linux.microsoft.com Signed-off-by: Wei Liu Message-ID: <1741980536-3865-9-git-send-email-nunodasneves@linux.microsoft.com> --- arch/x86/kernel/cpu/mshyperv.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index fcd0e066d9bd..3e2533954675 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -107,6 +107,7 @@ void hv_set_msr(unsigned int reg, u64 value) } EXPORT_SYMBOL_GPL(hv_set_msr); +static void (*mshv_handler)(void); static void (*vmbus_handler)(void); static void (*hv_stimer0_handler)(void); static void (*hv_kexec_handler)(void); @@ -117,6 +118,9 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback) struct pt_regs *old_regs = set_irq_regs(regs); inc_irq_stat(irq_hv_callback_count); + if (mshv_handler) + mshv_handler(); + if (vmbus_handler) vmbus_handler(); @@ -126,6 +130,11 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback) set_irq_regs(old_regs); } +void hv_setup_mshv_handler(void (*handler)(void)) +{ + mshv_handler = handler; +} + void hv_setup_vmbus_handler(void (*handler)(void)) { vmbus_handler = handler; -- cgit v1.2.3 From 999ad14259a0d45cb3b616e2e95a7c8b622a7ecd Mon Sep 17 00:00:00 2001 From: Michael Kelley Date: Tue, 18 Mar 2025 14:49:19 -0700 Subject: x86/hyperv: Add comments about hv_vpset and var size hypercall input args Current code varies in how the size of the variable size input header for hypercalls is calculated when the input contains struct hv_vpset. Surprisingly, this variation is correct, as different hypercalls make different choices for what portion of struct hv_vpset is treated as part of the variable size input header. The Hyper-V TLFS is silent on these details, but the behavior has been confirmed with Hyper-V developers. To avoid future confusion about these differences, add comments to struct hv_vpset, and to hypercall call sites with input that contains a struct hv_vpset. The comments describe the overall situation and the calculation that should be used at each particular call site. No functional change as only comments are updated. Signed-off-by: Michael Kelley Link: https://lore.kernel.org/r/20250318214919.958953-1-mhklinux@outlook.com Signed-off-by: Wei Liu Message-ID: <20250318214919.958953-1-mhklinux@outlook.com> --- arch/x86/hyperv/hv_apic.c | 5 +++++ arch/x86/hyperv/mmu.c | 4 ++++ 2 files changed, 9 insertions(+) (limited to 'arch/x86') 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/mmu.c b/arch/x86/hyperv/mmu.c index cc8c3bd0e7c2..80d9350612d2 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 * -- cgit v1.2.3 From 628cc040b3a2980df6032766e8ef0688e981ab95 Mon Sep 17 00:00:00 2001 From: Wei Liu Date: Fri, 21 Mar 2025 22:40:14 +0000 Subject: x86/hyperv: fix an indentation issue in mshyperv.h Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202503220640.hjiacW2C-lkp@intel.com/ Signed-off-by: Wei Liu --- arch/x86/include/asm/mshyperv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 7dfca93ef048..07aadf0e839f 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -154,7 +154,7 @@ static inline u64 _hv_do_fast_hypercall8(u64 control, u64 input1) : "cc", "edi", "esi"); } #endif - return hv_status; + return hv_status; } static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) -- cgit v1.2.3