summaryrefslogtreecommitdiff
path: root/arch/x86/hyperv/hv_init.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/hyperv/hv_init.c')
-rw-r--r--arch/x86/hyperv/hv_init.c410
1 files changed, 271 insertions, 139 deletions
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 8b392b6b7b93..14de43f4bc6c 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -7,35 +7,74 @@
* Author : K. Y. Srinivasan <kys@microsoft.com>
*/
+#define pr_fmt(fmt) "Hyper-V: " fmt
+
#include <linux/efi.h>
#include <linux/types.h>
#include <linux/bitfield.h>
#include <linux/io.h>
#include <asm/apic.h>
#include <asm/desc.h>
+#include <asm/e820/api.h>
+#include <asm/sev.h>
#include <asm/hypervisor.h>
-#include <asm/hyperv-tlfs.h>
+#include <hyperv/hvhdk.h>
#include <asm/mshyperv.h>
+#include <asm/msr.h>
#include <asm/idtentry.h>
+#include <asm/set_memory.h>
#include <linux/kexec.h>
#include <linux/version.h>
#include <linux/vmalloc.h>
#include <linux/mm.h>
-#include <linux/hyperv.h>
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/cpuhotplug.h>
#include <linux/syscore_ops.h>
#include <clocksource/hyperv_timer.h>
#include <linux/highmem.h>
-#include <linux/swiotlb.h>
-
-int hyperv_init_cpuhp;
-u64 hv_current_partition_id = ~0ull;
-EXPORT_SYMBOL_GPL(hv_current_partition_id);
+#include <linux/export.h>
void *hv_hypercall_pg;
+
+#ifdef CONFIG_X86_64
+static u64 __hv_hyperfail(u64 control, u64 param1, u64 param2)
+{
+ return U64_MAX;
+}
+
+DEFINE_STATIC_CALL(__hv_hypercall, __hv_hyperfail);
+
+u64 hv_std_hypercall(u64 control, u64 param1, u64 param2)
+{
+ u64 hv_status;
+
+ register u64 __r8 asm("r8") = param2;
+ asm volatile ("call " STATIC_CALL_TRAMP_STR(__hv_hypercall)
+ : "=a" (hv_status), ASM_CALL_CONSTRAINT,
+ "+c" (control), "+d" (param1), "+r" (__r8)
+ : : "cc", "memory", "r9", "r10", "r11");
+
+ return hv_status;
+}
+
+typedef u64 (*hv_hypercall_f)(u64 control, u64 param1, u64 param2);
+
+static inline void hv_set_hypercall_pg(void *ptr)
+{
+ hv_hypercall_pg = ptr;
+
+ if (!ptr)
+ ptr = &__hv_hyperfail;
+ static_call_update(__hv_hypercall, (hv_hypercall_f)ptr);
+}
+#else
+static inline void hv_set_hypercall_pg(void *ptr)
+{
+ hv_hypercall_pg = ptr;
+}
EXPORT_SYMBOL_GPL(hv_hypercall_pg);
+#endif
union hv_ghcb * __percpu *hv_ghcb_pg;
@@ -51,7 +90,7 @@ static int hyperv_init_ghcb(void)
void *ghcb_va;
void **ghcb_base;
- if (!hv_isolation_type_snp())
+ if (!ms_hyperv.paravisor_present || !hv_isolation_type_snp())
return 0;
if (!hv_ghcb_pg)
@@ -62,8 +101,11 @@ static int hyperv_init_ghcb(void)
* returned by MSR_AMD64_SEV_ES_GHCB is above shared
* memory boundary and map it here.
*/
- rdmsrl(MSR_AMD64_SEV_ES_GHCB, ghcb_gpa);
- ghcb_va = memremap(ghcb_gpa, HV_HYP_PAGE_SIZE, MEMREMAP_WB);
+ rdmsrq(MSR_AMD64_SEV_ES_GHCB, ghcb_gpa);
+
+ /* Mask out vTOM bit. ioremap_cache() maps decrypted */
+ ghcb_gpa &= ~ms_hyperv.shared_gpa_boundary;
+ ghcb_va = (void *)ioremap_cache(ghcb_gpa, HV_HYP_PAGE_SIZE);
if (!ghcb_va)
return -ENOMEM;
@@ -76,7 +118,7 @@ static int hyperv_init_ghcb(void)
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()];
+ struct hv_vp_assist_page **hvp;
int ret;
ret = hv_common_cpu_init(cpu);
@@ -86,35 +128,51 @@ static int hv_cpu_init(unsigned int cpu)
if (!hv_vp_assist_page)
return 0;
- if (!*hvp) {
- 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 {
+ hvp = &hv_vp_assist_page[cpu];
+ if (hv_root_partition()) {
+ /*
+ * For root partition we get the hypervisor provided VP assist
+ * page, instead of allocating a new page.
+ */
+ rdmsrq(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.
+ */
+ if (!*hvp) {
+ *hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO);
+
/*
- * 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.
+ * Hyper-V should never specify a VM that is a Confidential
+ * VM and also running in the root partition. Root partition
+ * is blocked to run in Confidential VM. So only decrypt assist
+ * page in non-root partition here.
*/
- *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);
+ if (*hvp && !ms_hyperv.paravisor_present && hv_isolation_type_snp()) {
+ WARN_ON_ONCE(set_memory_decrypted((unsigned long)(*hvp), 1));
+ memset(*hvp, 0, PAGE_SIZE);
+ }
}
+
+ if (*hvp)
+ msr.pfn = vmalloc_to_pfn(*hvp);
+
}
+ if (!WARN_ON(!(*hvp))) {
+ msr.enable = 1;
+ wrmsrq(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+ }
+
+ /* Allow Hyper-V stimer vector to be injected from Hypervisor. */
+ if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE)
+ apic_update_vector(cpu, HYPERV_STIMER0_VECTOR, true);
return hyperv_init_ghcb();
}
@@ -125,7 +183,7 @@ static void hv_reenlightenment_notify(struct work_struct *dummy)
{
struct hv_tsc_emulation_status emu_status;
- rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
+ rdmsrq(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
/* Don't issue the callback if TSC accesses are not emulated */
if (hv_reenlightenment_cb && emu_status.inprogress)
@@ -138,11 +196,11 @@ void hyperv_stop_tsc_emulation(void)
u64 freq;
struct hv_tsc_emulation_status emu_status;
- rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
+ rdmsrq(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
emu_status.inprogress = 0;
- wrmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
+ wrmsrq(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
- rdmsrl(HV_X64_MSR_TSC_FREQUENCY, freq);
+ rdmsrq(HV_X64_MSR_TSC_FREQUENCY, freq);
tsc_khz = div64_u64(freq, 1000);
}
EXPORT_SYMBOL_GPL(hyperv_stop_tsc_emulation);
@@ -160,7 +218,7 @@ static inline bool hv_reenlightenment_available(void)
DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_reenlightenment)
{
- ack_APIC_irq();
+ apic_eoi();
inc_irq_stat(irq_hv_reenlightenment_count);
schedule_delayed_work(&hv_reenlightenment_work, HZ/10);
}
@@ -174,7 +232,7 @@ void set_hv_tscchange_cb(void (*cb)(void))
struct hv_tsc_emulation_control emu_ctrl = {.enabled = 1};
if (!hv_reenlightenment_available()) {
- pr_warn("Hyper-V: reenlightenment support is unavailable\n");
+ pr_warn("reenlightenment support is unavailable\n");
return;
}
@@ -188,8 +246,8 @@ void set_hv_tscchange_cb(void (*cb)(void))
re_ctrl.target_vp = hv_vp_index[get_cpu()];
- wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
- wrmsrl(HV_X64_MSR_TSC_EMULATION_CONTROL, *((u64 *)&emu_ctrl));
+ wrmsrq(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
+ wrmsrq(HV_X64_MSR_TSC_EMULATION_CONTROL, *((u64 *)&emu_ctrl));
put_cpu();
}
@@ -202,9 +260,9 @@ void clear_hv_tscchange_cb(void)
if (!hv_reenlightenment_available())
return;
- rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
+ rdmsrq(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
re_ctrl.enabled = 0;
- wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
+ wrmsrq(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
hv_reenlightenment_cb = NULL;
}
@@ -219,15 +277,18 @@ static int hv_cpu_die(unsigned int cpu)
if (hv_ghcb_pg) {
ghcb_va = (void **)this_cpu_ptr(hv_ghcb_pg);
if (*ghcb_va)
- memunmap(*ghcb_va);
+ iounmap(*ghcb_va);
*ghcb_va = NULL;
}
+ if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE)
+ apic_update_vector(cpu, HYPERV_STIMER0_VECTOR, false);
+
hv_common_cpu_die(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
@@ -236,16 +297,16 @@ static int hv_cpu_die(unsigned int cpu)
*/
memunmap(hv_vp_assist_page[cpu]);
hv_vp_assist_page[cpu] = NULL;
- rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+ rdmsrq(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
msr.enable = 0;
}
- wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+ wrmsrq(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
}
if (hv_reenlightenment_cb == NULL)
return 0;
- rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
+ rdmsrq(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
if (re_ctrl.target_vp == hv_vp_index[cpu]) {
/*
* Reassign reenlightenment notifications to some other online
@@ -259,7 +320,7 @@ static int hv_cpu_die(unsigned int cpu)
else
re_ctrl.enabled = 0;
- wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
+ wrmsrq(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
}
return 0;
@@ -267,26 +328,42 @@ static int hv_cpu_die(unsigned int cpu)
static int __init hv_pci_init(void)
{
- int gen2vm = efi_enabled(EFI_BOOT);
+ bool gen2vm = efi_enabled(EFI_BOOT);
/*
- * For Generation-2 VM, we exit from pci_arch_init() by returning 0.
- * The purpose is to suppress the harmless warning:
+ * A Generation-2 VM doesn't support legacy PCI/PCIe, so both
+ * raw_pci_ops and raw_pci_ext_ops are NULL, and pci_subsys_init() ->
+ * pcibios_init() doesn't call pcibios_resource_survey() ->
+ * e820__reserve_resources_late(); as a result, any emulated persistent
+ * memory of E820_TYPE_PRAM (12) via the kernel parameter
+ * memmap=nn[KMG]!ss is not added into iomem_resource and hence can't be
+ * detected by register_e820_pmem(). Fix this by directly calling
+ * e820__reserve_resources_late() here: e820__reserve_resources_late()
+ * depends on e820__reserve_resources(), which has been called earlier
+ * from setup_arch(). Note: e820__reserve_resources_late() also adds
+ * any memory of E820_TYPE_PMEM (7) into iomem_resource, and
+ * acpi_nfit_register_region() -> acpi_nfit_insert_resource() ->
+ * region_intersects() returns REGION_INTERSECTS, so the memory of
+ * E820_TYPE_PMEM won't get added twice.
+ *
+ * We return 0 here so that pci_arch_init() won't print the warning:
* "PCI: Fatal: No config space access function found"
*/
- if (gen2vm)
+ if (gen2vm) {
+ e820__reserve_resources_late();
return 0;
+ }
/* For Generation-1 VM, we'll proceed in pci_arch_init(). */
return 1;
}
-static int hv_suspend(void)
+static int hv_suspend(void *data)
{
union hv_x64_msr_hypercall_contents hypercall_msr;
int ret;
- if (hv_root_partition)
+ if (hv_root_partition())
return -EPERM;
/*
@@ -297,18 +374,18 @@ static int hv_suspend(void)
* pointer is restored on resume.
*/
hv_hypercall_pg_saved = hv_hypercall_pg;
- hv_hypercall_pg = NULL;
+ hv_set_hypercall_pg(NULL);
/* Disable the hypercall page in the hypervisor */
- rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+ rdmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
hypercall_msr.enable = 0;
- wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+ wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
ret = hv_cpu_die(0);
return ret;
}
-static void hv_resume(void)
+static void hv_resume(void *data)
{
union hv_x64_msr_hypercall_contents hypercall_msr;
int ret;
@@ -317,13 +394,13 @@ static void hv_resume(void)
WARN_ON(ret);
/* Re-enable the hypercall page */
- rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+ rdmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
hypercall_msr.enable = 1;
hypercall_msr.guest_physical_address =
vmalloc_to_pfn(hv_hypercall_pg_saved);
- wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+ wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
- hv_hypercall_pg = hv_hypercall_pg_saved;
+ hv_set_hypercall_pg(hv_hypercall_pg_saved);
hv_hypercall_pg_saved = NULL;
/*
@@ -335,11 +412,15 @@ static void hv_resume(void)
}
/* Note: when the ops are called, only CPU0 is online and IRQs are disabled. */
-static struct syscore_ops hv_syscore_ops = {
+static const struct syscore_ops hv_syscore_ops = {
.suspend = hv_suspend,
.resume = hv_resume,
};
+static struct syscore hv_syscore = {
+ .ops = &hv_syscore_ops,
+};
+
static void (* __initdata old_setup_percpu_clockev)(void);
static void __init hv_stimer_setup_percpu_clockev(void)
@@ -359,24 +440,6 @@ 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);
-}
-
/*
* This function is to be invoked early in the boot sequence after the
* hypervisor has been detected.
@@ -397,20 +460,35 @@ void __init hyperv_init(void)
if (hv_common_init())
return;
- hv_vp_assist_page = kcalloc(num_possible_cpus(),
- sizeof(*hv_vp_assist_page), GFP_KERNEL);
+ /*
+ * The VP assist page is useless to a TDX guest: the only use we
+ * would have for it is lazy EOI, which can not be used with TDX.
+ */
+ if (hv_isolation_type_tdx())
+ hv_vp_assist_page = NULL;
+ else
+ hv_vp_assist_page = kcalloc(nr_cpu_ids,
+ sizeof(*hv_vp_assist_page),
+ GFP_KERNEL);
if (!hv_vp_assist_page) {
ms_hyperv.hints &= ~HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;
- goto common_free;
+
+ if (!hv_isolation_type_tdx())
+ goto common_free;
}
- if (hv_isolation_type_snp()) {
+ if (ms_hyperv.paravisor_present && hv_isolation_type_snp()) {
+ /* Negotiate GHCB Version. */
+ if (!hv_ghcb_negotiate_protocol())
+ hv_ghcb_terminate(SEV_TERM_SET_GEN,
+ GHCB_SEV_ES_PROT_UNSUPPORTED);
+
hv_ghcb_pg = alloc_percpu(union hv_ghcb *);
if (!hv_ghcb_pg)
goto free_vp_assist_page;
}
- cpuhp = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online",
+ cpuhp = cpuhp_setup_state(CPUHP_AP_HYPERV_ONLINE, "x86/hyperv_init:online",
hv_cpu_init, hv_cpu_die);
if (cpuhp < 0)
goto free_ghcb_page;
@@ -419,26 +497,46 @@ void __init hyperv_init(void)
* Setup the hypercall page and enable hypercalls.
* 1. Register the guest ID
* 2. Enable the hypercall and register the hypercall page
+ *
+ * A TDX VM with no paravisor only uses TDX GHCI rather than hv_hypercall_pg:
+ * when the hypercall input is a page, such a VM must pass a decrypted
+ * page to Hyper-V, e.g. hv_post_message() uses the per-CPU page
+ * hyperv_pcpu_input_arg, which is decrypted if no paravisor is present.
+ *
+ * A TDX VM with the paravisor uses hv_hypercall_pg for most hypercalls,
+ * which are handled by the paravisor and the VM must use an encrypted
+ * input page: in such a VM, the hyperv_pcpu_input_arg is encrypted and
+ * used in the hypercalls, e.g. see hv_mark_gpa_visibility() and
+ * hv_arch_irq_unmask(). Such a VM uses TDX GHCI for two hypercalls:
+ * 1. HVCALL_SIGNAL_EVENT: see vmbus_set_event() and _hv_do_fast_hypercall8().
+ * 2. HVCALL_POST_MESSAGE: the input page must be a decrypted page, i.e.
+ * hv_post_message() in such a VM can't use the encrypted hyperv_pcpu_input_arg;
+ * instead, hv_post_message() uses the post_msg_page, which is decrypted
+ * in such a VM and is only used in such a VM.
*/
- guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0);
- wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id);
+ guest_id = hv_generate_guest_id(LINUX_VERSION_CODE);
+ wrmsrq(HV_X64_MSR_GUEST_OS_ID, guest_id);
+
+ /* With the paravisor, the VM must also write the ID via GHCB/GHCI */
+ hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, guest_id);
- /* Hyper-V requires to write guest os id via ghcb in SNP IVM. */
- hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, guest_id);
+ /* A TDX VM with no paravisor only uses TDX GHCI rather than hv_hypercall_pg */
+ if (hv_isolation_type_tdx() && !ms_hyperv.paravisor_present)
+ goto skip_hypercall_pg_init;
- hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START,
- VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_ROX,
+ hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, MODULES_VADDR,
+ MODULES_END, GFP_KERNEL, PAGE_KERNEL_ROX,
VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
__builtin_return_address(0));
if (hv_hypercall_pg == NULL)
goto clean_guest_os_id;
- rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+ rdmsrq(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, *dst;
+ void *src;
/*
* For the root partition, the hypervisor will set up its
@@ -450,21 +548,26 @@ void __init hyperv_init(void)
* so it is populated with code, then copy the code to an
* executable page.
*/
- wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+ wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
pg = vmalloc_to_page(hv_hypercall_pg);
- dst = kmap(pg);
src = memremap(hypercall_msr.guest_physical_address << PAGE_SHIFT, PAGE_SIZE,
MEMREMAP_WB);
- BUG_ON(!(src && dst));
- memcpy(dst, src, HV_HYP_PAGE_SIZE);
+ BUG_ON(!src);
+ memcpy_to_page(pg, 0, src, HV_HYP_PAGE_SIZE);
memunmap(src);
- kunmap(pg);
+
+ hv_remap_tsc_clocksource();
+ hv_root_crash_init();
+ hv_sleep_notifiers_register();
} else {
hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
- wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+ wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
}
+ hv_set_hypercall_pg(hv_hypercall_pg);
+
+skip_hypercall_pg_init:
/*
* hyperv_init() is called before LAPIC is initialized: see
* apic_intr_mode_init() -> x86_platform.apic_post_init() and
@@ -479,43 +582,35 @@ void __init hyperv_init(void)
x86_init.pci.arch_init = hv_pci_init;
- register_syscore_ops(&hv_syscore_ops);
-
- hyperv_init_cpuhp = cpuhp;
+ register_syscore(&hv_syscore);
- 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
/* Query the VMs extended capability once, so that it can be cached. */
hv_query_ext_cap(0);
-#ifdef CONFIG_SWIOTLB
- /*
- * Swiotlb bounce buffer needs to be mapped in extra address
- * space. Map function doesn't work in the early place and so
- * call swiotlb_update_mem_attributes() here.
- */
- if (hv_is_isolation_supported())
- swiotlb_update_mem_attributes();
-#endif
+ /* Find the VTL */
+ ms_hyperv.vtl = get_vtl();
+
+ if (ms_hyperv.vtl > 0) /* non default VTL */
+ hv_vtl_early_init();
return;
clean_guest_os_id:
- wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
- hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
- cpuhp_remove_state(cpuhp);
+ wrmsrq(HV_X64_MSR_GUEST_OS_ID, 0);
+ hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
+ cpuhp_remove_state(CPUHP_AP_HYPERV_ONLINE);
free_ghcb_page:
free_percpu(hv_ghcb_pg);
free_vp_assist_page:
@@ -531,12 +626,11 @@ common_free:
void hyperv_cleanup(void)
{
union hv_x64_msr_hypercall_contents hypercall_msr;
-
- unregister_syscore_ops(&hv_syscore_ops);
+ union hv_reference_tsc_msr tsc_msr;
/* Reset our OS id */
- wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
- hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
+ wrmsrq(HV_X64_MSR_GUEST_OS_ID, 0);
+ hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
/*
* Reset hypercall page reference before reset the page,
@@ -546,12 +640,14 @@ void hyperv_cleanup(void)
hv_hypercall_pg = NULL;
/* Reset the hypercall page */
- hypercall_msr.as_uint64 = 0;
- wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+ hypercall_msr.as_uint64 = hv_get_msr(HV_X64_MSR_HYPERCALL);
+ hypercall_msr.enable = 0;
+ hv_set_msr(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
/* Reset the TSC page */
- hypercall_msr.as_uint64 = 0;
- wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64);
+ tsc_msr.as_uint64 = hv_get_msr(HV_X64_MSR_REFERENCE_TSC);
+ tsc_msr.enable = 0;
+ hv_set_msr(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
}
void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die)
@@ -571,18 +667,18 @@ void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die)
return;
panic_reported = true;
- rdmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id);
+ rdmsrq(HV_X64_MSR_GUEST_OS_ID, guest_id);
- wrmsrl(HV_X64_MSR_CRASH_P0, err);
- wrmsrl(HV_X64_MSR_CRASH_P1, guest_id);
- wrmsrl(HV_X64_MSR_CRASH_P2, regs->ip);
- wrmsrl(HV_X64_MSR_CRASH_P3, regs->ax);
- wrmsrl(HV_X64_MSR_CRASH_P4, regs->sp);
+ wrmsrq(HV_X64_MSR_CRASH_P0, err);
+ wrmsrq(HV_X64_MSR_CRASH_P1, guest_id);
+ wrmsrq(HV_X64_MSR_CRASH_P2, regs->ip);
+ wrmsrq(HV_X64_MSR_CRASH_P3, regs->ax);
+ wrmsrq(HV_X64_MSR_CRASH_P4, regs->sp);
/*
* Let Hyper-V know there is crash data available
*/
- wrmsrl(HV_X64_MSR_CRASH_CTL, HV_CRASH_CTL_CRASH_NOTIFY);
+ wrmsrq(HV_X64_MSR_CRASH_CTL, HV_CRASH_CTL_CRASH_NOTIFY);
}
EXPORT_SYMBOL_GPL(hyperv_report_panic);
@@ -597,13 +693,49 @@ bool hv_is_hyperv_initialized(void)
if (x86_hyper_type != X86_HYPER_MS_HYPERV)
return false;
+ /* A TDX VM with no paravisor uses TDX GHCI call rather than hv_hypercall_pg */
+ if (hv_isolation_type_tdx() && !ms_hyperv.paravisor_present)
+ return true;
/*
* Verify that earlier initialization succeeded by checking
* that the hypercall page is setup
*/
hypercall_msr.as_uint64 = 0;
- rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+ rdmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
return hypercall_msr.enable;
}
EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized);
+
+int hv_apicid_to_vp_index(u32 apic_id)
+{
+ u64 control;
+ u64 status;
+ unsigned long irq_flags;
+ struct hv_get_vp_from_apic_id_in *input;
+ u32 *output, ret;
+
+ local_irq_save(irq_flags);
+
+ input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+ memset(input, 0, sizeof(*input));
+ input->partition_id = HV_PARTITION_ID_SELF;
+ input->apic_ids[0] = apic_id;
+
+ output = *this_cpu_ptr(hyperv_pcpu_output_arg);
+
+ control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_INDEX_FROM_APIC_ID;
+ status = hv_do_hypercall(control, input, output);
+ ret = output[0];
+
+ local_irq_restore(irq_flags);
+
+ if (!hv_result_success(status)) {
+ pr_err("failed to get vp index from apic id %d, status %#llx\n",
+ apic_id, status);
+ return -EINVAL;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(hv_apicid_to_vp_index);
generated by cgit (git 2.34.1) at 2025-12-25 11:23:21 +0000