Merge tag 'hyperv-next-signed-20230902' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull hyperv updates from Wei Liu:

 - Support for SEV-SNP guests on Hyper-V (Tianyu Lan)

 - Support for TDX guests on Hyper-V (Dexuan Cui)

 - Use SBRM API in Hyper-V balloon driver (Mitchell Levy)

 - Avoid dereferencing ACPI root object handle in VMBus driver (Maciej
   Szmigiero)

 - A few misecllaneous fixes (Jiapeng Chong, Nathan Chancellor, Saurabh
   Sengar)

* tag 'hyperv-next-signed-20230902' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux: (24 commits)
  x86/hyperv: Remove duplicate include
  x86/hyperv: Move the code in ivm.c around to avoid unnecessary ifdef's
  x86/hyperv: Remove hv_isolation_type_en_snp
  x86/hyperv: Use TDX GHCI to access some MSRs in a TDX VM with the paravisor
  Drivers: hv: vmbus: Bring the post_msg_page back for TDX VMs with the paravisor
  x86/hyperv: Introduce a global variable hyperv_paravisor_present
  Drivers: hv: vmbus: Support >64 VPs for a fully enlightened TDX/SNP VM
  x86/hyperv: Fix serial console interrupts for fully enlightened TDX guests
  Drivers: hv: vmbus: Support fully enlightened TDX guests
  x86/hyperv: Support hypercalls for fully enlightened TDX guests
  x86/hyperv: Add hv_isolation_type_tdx() to detect TDX guests
  x86/hyperv: Fix undefined reference to isolation_type_en_snp without CONFIG_HYPERV
  x86/hyperv: Add missing 'inline' to hv_snp_boot_ap() stub
  hv: hyperv.h: Replace one-element array with flexible-array member
  Drivers: hv: vmbus: Don't dereference ACPI root object handle
  x86/hyperv: Add hyperv-specific handling for VMMCALL under SEV-ES
  x86/hyperv: Add smp support for SEV-SNP guest
  clocksource: hyper-v: Mark hyperv tsc page unencrypted in sev-snp enlightened guest
  x86/hyperv: Use vmmcall to implement Hyper-V hypercall in sev-snp enlightened guest
  drivers: hv: Mark percpu hvcall input arg page unencrypted in SEV-SNP enlightened guest
  ...

1 files changed, 117 insertions, 14 deletions

diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index de6708dbe0df..51e5018ac9b2 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -20,6 +20,7 @@
 #include <linux/interrupt.h>
 #include <clocksource/hyperv_timer.h>
 #include <asm/mshyperv.h>
+#include <linux/set_memory.h>
 #include "hyperv_vmbus.h"
 
 /* The one and only */
@@ -56,20 +57,37 @@ int hv_post_message(union hv_connection_id connection_id,
 
 	local_irq_save(flags);
 
-	aligned_msg = *this_cpu_ptr(hyperv_pcpu_input_arg);
+	/*
+	 * A TDX VM with the paravisor must use the decrypted post_msg_page: see
+	 * the comment in struct hv_per_cpu_context. A SNP VM with the paravisor
+	 * can use the encrypted hyperv_pcpu_input_arg because it copies the
+	 * input into the GHCB page, which has been decrypted by the paravisor.
+	 */
+	if (hv_isolation_type_tdx() && ms_hyperv.paravisor_present)
+		aligned_msg = this_cpu_ptr(hv_context.cpu_context)->post_msg_page;
+	else
+		aligned_msg = *this_cpu_ptr(hyperv_pcpu_input_arg);
+
 	aligned_msg->connectionid = connection_id;
 	aligned_msg->reserved = 0;
 	aligned_msg->message_type = message_type;
 	aligned_msg->payload_size = payload_size;
 	memcpy((void *)aligned_msg->payload, payload, payload_size);
 
-	if (hv_isolation_type_snp())
-		status = hv_ghcb_hypercall(HVCALL_POST_MESSAGE,
-				(void *)aligned_msg, NULL,
-				sizeof(*aligned_msg));
-	else
+	if (ms_hyperv.paravisor_present) {
+		if (hv_isolation_type_tdx())
+			status = hv_tdx_hypercall(HVCALL_POST_MESSAGE,
+						  virt_to_phys(aligned_msg), 0);
+		else if (hv_isolation_type_snp())
+			status = hv_ghcb_hypercall(HVCALL_POST_MESSAGE,
+						   aligned_msg, NULL,
+						   sizeof(*aligned_msg));
+		else
+			status = HV_STATUS_INVALID_PARAMETER;
+	} else {
 		status = hv_do_hypercall(HVCALL_POST_MESSAGE,
 				aligned_msg, NULL);
+	}
 
 	local_irq_restore(flags);
 
@@ -78,7 +96,7 @@ int hv_post_message(union hv_connection_id connection_id,
 
 int hv_synic_alloc(void)
 {
-	int cpu;
+	int cpu, ret = -ENOMEM;
 	struct hv_per_cpu_context *hv_cpu;
 
 	/*
@@ -104,11 +122,29 @@ int hv_synic_alloc(void)
 		tasklet_init(&hv_cpu->msg_dpc,
 			     vmbus_on_msg_dpc, (unsigned long) hv_cpu);
 
+		if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) {
+			hv_cpu->post_msg_page = (void *)get_zeroed_page(GFP_ATOMIC);
+			if (hv_cpu->post_msg_page == NULL) {
+				pr_err("Unable to allocate post msg page\n");
+				goto err;
+			}
+
+			ret = set_memory_decrypted((unsigned long)hv_cpu->post_msg_page, 1);
+			if (ret) {
+				pr_err("Failed to decrypt post msg page: %d\n", ret);
+				/* Just leak the page, as it's unsafe to free the page. */
+				hv_cpu->post_msg_page = NULL;
+				goto err;
+			}
+
+			memset(hv_cpu->post_msg_page, 0, PAGE_SIZE);
+		}
+
 		/*
 		 * Synic message and event pages are allocated by paravisor.
 		 * Skip these pages allocation here.
 		 */
-		if (!hv_isolation_type_snp() && !hv_root_partition) {
+		if (!ms_hyperv.paravisor_present && !hv_root_partition) {
 			hv_cpu->synic_message_page =
 				(void *)get_zeroed_page(GFP_ATOMIC);
 			if (hv_cpu->synic_message_page == NULL) {
@@ -120,29 +156,96 @@ int hv_synic_alloc(void)
 				(void *)get_zeroed_page(GFP_ATOMIC);
 			if (hv_cpu->synic_event_page == NULL) {
 				pr_err("Unable to allocate SYNIC event page\n");
+
+				free_page((unsigned long)hv_cpu->synic_message_page);
+				hv_cpu->synic_message_page = NULL;
 				goto err;
 			}
 		}
+
+		if (!ms_hyperv.paravisor_present &&
+		    (hv_isolation_type_snp() || hv_isolation_type_tdx())) {
+			ret = set_memory_decrypted((unsigned long)
+				hv_cpu->synic_message_page, 1);
+			if (ret) {
+				pr_err("Failed to decrypt SYNIC msg page: %d\n", ret);
+				hv_cpu->synic_message_page = NULL;
+
+				/*
+				 * Free the event page here so that hv_synic_free()
+				 * won't later try to re-encrypt it.
+				 */
+				free_page((unsigned long)hv_cpu->synic_event_page);
+				hv_cpu->synic_event_page = NULL;
+				goto err;
+			}
+
+			ret = set_memory_decrypted((unsigned long)
+				hv_cpu->synic_event_page, 1);
+			if (ret) {
+				pr_err("Failed to decrypt SYNIC event page: %d\n", ret);
+				hv_cpu->synic_event_page = NULL;
+				goto err;
+			}
+
+			memset(hv_cpu->synic_message_page, 0, PAGE_SIZE);
+			memset(hv_cpu->synic_event_page, 0, PAGE_SIZE);
+		}
 	}
 
 	return 0;
+
 err:
 	/*
 	 * Any memory allocations that succeeded will be freed when
 	 * the caller cleans up by calling hv_synic_free()
 	 */
-	return -ENOMEM;
+	return ret;
 }
 
 
 void hv_synic_free(void)
 {
-	int cpu;
+	int cpu, ret;
 
 	for_each_present_cpu(cpu) {
 		struct hv_per_cpu_context *hv_cpu
 			= per_cpu_ptr(hv_context.cpu_context, cpu);
 
+		/* It's better to leak the page if the encryption fails. */
+		if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) {
+			if (hv_cpu->post_msg_page) {
+				ret = set_memory_encrypted((unsigned long)
+					hv_cpu->post_msg_page, 1);
+				if (ret) {
+					pr_err("Failed to encrypt post msg page: %d\n", ret);
+					hv_cpu->post_msg_page = NULL;
+				}
+			}
+		}
+
+		if (!ms_hyperv.paravisor_present &&
+		    (hv_isolation_type_snp() || hv_isolation_type_tdx())) {
+			if (hv_cpu->synic_message_page) {
+				ret = set_memory_encrypted((unsigned long)
+					hv_cpu->synic_message_page, 1);
+				if (ret) {
+					pr_err("Failed to encrypt SYNIC msg page: %d\n", ret);
+					hv_cpu->synic_message_page = NULL;
+				}
+			}
+
+			if (hv_cpu->synic_event_page) {
+				ret = set_memory_encrypted((unsigned long)
+					hv_cpu->synic_event_page, 1);
+				if (ret) {
+					pr_err("Failed to encrypt SYNIC event page: %d\n", ret);
+					hv_cpu->synic_event_page = NULL;
+				}
+			}
+		}
+
+		free_page((unsigned long)hv_cpu->post_msg_page);
 		free_page((unsigned long)hv_cpu->synic_event_page);
 		free_page((unsigned long)hv_cpu->synic_message_page);
 	}
@@ -170,7 +273,7 @@ void hv_synic_enable_regs(unsigned int cpu)
 	simp.as_uint64 = hv_get_register(HV_REGISTER_SIMP);
 	simp.simp_enabled = 1;
 
-	if (hv_isolation_type_snp() || hv_root_partition) {
+	if (ms_hyperv.paravisor_present || hv_root_partition) {
 		/* Mask out vTOM bit. ioremap_cache() maps decrypted */
 		u64 base = (simp.base_simp_gpa << HV_HYP_PAGE_SHIFT) &
 				~ms_hyperv.shared_gpa_boundary;
@@ -189,7 +292,7 @@ void hv_synic_enable_regs(unsigned int cpu)
 	siefp.as_uint64 = hv_get_register(HV_REGISTER_SIEFP);
 	siefp.siefp_enabled = 1;
 
-	if (hv_isolation_type_snp() || hv_root_partition) {
+	if (ms_hyperv.paravisor_present || hv_root_partition) {
 		/* Mask out vTOM bit. ioremap_cache() maps decrypted */
 		u64 base = (siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT) &
 				~ms_hyperv.shared_gpa_boundary;
@@ -272,7 +375,7 @@ void hv_synic_disable_regs(unsigned int cpu)
 	 * addresses.
 	 */
 	simp.simp_enabled = 0;
-	if (hv_isolation_type_snp() || hv_root_partition) {
+	if (ms_hyperv.paravisor_present || hv_root_partition) {
 		iounmap(hv_cpu->synic_message_page);
 		hv_cpu->synic_message_page = NULL;
 	} else {
@@ -284,7 +387,7 @@ void hv_synic_disable_regs(unsigned int cpu)
 	siefp.as_uint64 = hv_get_register(HV_REGISTER_SIEFP);
 	siefp.siefp_enabled = 0;
 
-	if (hv_isolation_type_snp() || hv_root_partition) {
+	if (ms_hyperv.paravisor_present || hv_root_partition) {
 		iounmap(hv_cpu->synic_event_page);
 		hv_cpu->synic_event_page = NULL;
 	} else {