Merge tag 'x86_sev_for_v6.4_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 SEV updates from Borislav Petkov:

 - Add the necessary glue so that the kernel can run as a confidential
   SEV-SNP vTOM guest on Hyper-V. A vTOM guest basically splits the
   address space in two parts: encrypted and unencrypted. The use case
   being running unmodified guests on the Hyper-V confidential computing
   hypervisor

 - Double-buffer messages between the guest and the hardware PSP device
   so that no partial buffers are copied back'n'forth and thus potential
   message integrity and leak attacks are possible

 - Name the return value the sev-guest driver returns when the hw PSP
   device hasn't been called, explicitly

 - Cleanups

* tag 'x86_sev_for_v6.4_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/hyperv: Change vTOM handling to use standard coco mechanisms
  init: Call mem_encrypt_init() after Hyper-V hypercall init is done
  x86/mm: Handle decryption/re-encryption of bss_decrypted consistently
  Drivers: hv: Explicitly request decrypted in vmap_pfn() calls
  x86/hyperv: Reorder code to facilitate future work
  x86/ioremap: Add hypervisor callback for private MMIO mapping in coco VM
  x86/sev: Change snp_guest_issue_request()'s fw_err argument
  virt/coco/sev-guest: Double-buffer messages
  crypto: ccp: Get rid of __sev_platform_init_locked()'s local function pointer
  crypto: ccp - Name -1 return value as SEV_RET_NO_FW_CALL

Author: torvalds

Documentation/virt/coco/sev-guest.rst

@@ -37,11 +37,11 @@ along with a description:
       the return value.  General error numbers (-ENOMEM, -EINVAL)
       are not detailed, but errors with specific meanings are.
 
-The guest ioctl should be issued on a file descriptor of the /dev/sev-guest device.
-The ioctl accepts struct snp_user_guest_request. The input and output structure is
-specified through the req_data and resp_data field respectively. If the ioctl fails
-to execute due to a firmware error, then fw_err code will be set otherwise the
-fw_err will be set to 0x00000000000000ff.
+The guest ioctl should be issued on a file descriptor of the /dev/sev-guest
+device.  The ioctl accepts struct snp_user_guest_request. The input and
+output structure is specified through the req_data and resp_data field
+respectively. If the ioctl fails to execute due to a firmware error, then
+the fw_error code will be set, otherwise fw_error will be set to -1.
 
 The firmware checks that the message sequence counter is one greater than
 the guests message sequence counter. If guest driver fails to increment message
@@ -57,8 +57,14 @@ counter (e.g. counter overflow), then -EIO will be returned.
                 __u64 req_data;
                 __u64 resp_data;
 
-                /* firmware error code on failure (see psp-sev.h) */
-                __u64 fw_err;
+                /* bits[63:32]: VMM error code, bits[31:0] firmware error code (see psp-sev.h) */
+                union {
+                        __u64 exitinfo2;
+                        struct {
+                                __u32 fw_error;
+                                __u32 vmm_error;
+                        };
+                };
         };
 
 2.1 SNP_GET_REPORT

arch/x86/coco/core.c

@@ -29,6 +29,22 @@ static bool intel_cc_platform_has(enum cc_attr attr)
 	}
 }
 
+/*
+ * Handle the SEV-SNP vTOM case where sme_me_mask is zero, and
+ * the other levels of SME/SEV functionality, including C-bit
+ * based SEV-SNP, are not enabled.
+ */
+static __maybe_unused bool amd_cc_platform_vtom(enum cc_attr attr)
+{
+	switch (attr) {
+	case CC_ATTR_GUEST_MEM_ENCRYPT:
+	case CC_ATTR_MEM_ENCRYPT:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /*
  * SME and SEV are very similar but they are not the same, so there are
  * times that the kernel will need to distinguish between SME and SEV. The
@@ -41,9 +57,14 @@ static bool intel_cc_platform_has(enum cc_attr attr)
  * up under SME the trampoline area cannot be encrypted, whereas under SEV
  * the trampoline area must be encrypted.
  */
+
 static bool amd_cc_platform_has(enum cc_attr attr)
 {
 #ifdef CONFIG_AMD_MEM_ENCRYPT
+
+	if (sev_status & MSR_AMD64_SNP_VTOM)
+		return amd_cc_platform_vtom(attr);
+
 	switch (attr) {
 	case CC_ATTR_MEM_ENCRYPT:
 		return sme_me_mask;
@@ -76,20 +97,13 @@ static bool amd_cc_platform_has(enum cc_attr attr)
 #endif
 }
 
-static bool hyperv_cc_platform_has(enum cc_attr attr)
-{
-	return attr == CC_ATTR_GUEST_MEM_ENCRYPT;
-}
-
 bool cc_platform_has(enum cc_attr attr)
 {
 	switch (vendor) {
 	case CC_VENDOR_AMD:
 		return amd_cc_platform_has(attr);
 	case CC_VENDOR_INTEL:
 		return intel_cc_platform_has(attr);
-	case CC_VENDOR_HYPERV:
-		return hyperv_cc_platform_has(attr);
 	default:
 		return false;
 	}
@@ -103,11 +117,14 @@ u64 cc_mkenc(u64 val)
 	 * encryption status of the page.
 	 *
 	 * - for AMD, bit *set* means the page is encrypted
-	 * - for Intel *clear* means encrypted.
+	 * - for AMD with vTOM and for Intel, *clear* means encrypted
 	 */
 	switch (vendor) {
 	case CC_VENDOR_AMD:
-		return val | cc_mask;
+		if (sev_status & MSR_AMD64_SNP_VTOM)
+			return val & ~cc_mask;
+		else
+			return val | cc_mask;
 	case CC_VENDOR_INTEL:
 		return val & ~cc_mask;
 	default:
@@ -120,7 +137,10 @@ u64 cc_mkdec(u64 val)
 	/* See comment in cc_mkenc() */
 	switch (vendor) {
 	case CC_VENDOR_AMD:
-		return val & ~cc_mask;
+		if (sev_status & MSR_AMD64_SNP_VTOM)
+			return val | cc_mask;
+		else
+			return val & ~cc_mask;
 	case CC_VENDOR_INTEL:
 		return val | cc_mask;
 	default:

arch/x86/hyperv/hv_init.c

@@ -29,7 +29,6 @@
 #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;
@@ -504,16 +503,6 @@ void __init hyperv_init(void)
 	/* 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
-
 	return;
 
 clean_guest_os_id:

arch/x86/hyperv/ivm.c

@@ -13,6 +13,8 @@
 #include <asm/svm.h>
 #include <asm/sev.h>
 #include <asm/io.h>
+#include <asm/coco.h>
+#include <asm/mem_encrypt.h>
 #include <asm/mshyperv.h>
 #include <asm/hypervisor.h>
 
@@ -233,41 +235,6 @@ void hv_ghcb_msr_read(u64 msr, u64 *value)
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(hv_ghcb_msr_read);
-#endif
-
-enum hv_isolation_type hv_get_isolation_type(void)
-{
-	if (!(ms_hyperv.priv_high & HV_ISOLATION))
-		return HV_ISOLATION_TYPE_NONE;
-	return FIELD_GET(HV_ISOLATION_TYPE, ms_hyperv.isolation_config_b);
-}
-EXPORT_SYMBOL_GPL(hv_get_isolation_type);
-
-/*
- * hv_is_isolation_supported - Check system runs in the Hyper-V
- * isolation VM.
- */
-bool hv_is_isolation_supported(void)
-{
-	if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR))
-		return false;
-
-	if (!hypervisor_is_type(X86_HYPER_MS_HYPERV))
-		return false;
-
-	return hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE;
-}
-
-DEFINE_STATIC_KEY_FALSE(isolation_type_snp);
-
-/*
- * hv_isolation_type_snp - Check system runs in the AMD SEV-SNP based
- * isolation VM.
- */
-bool hv_isolation_type_snp(void)
-{
-	return static_branch_unlikely(&isolation_type_snp);
-}
 
 /*
  * hv_mark_gpa_visibility - Set pages visible to host via hvcall.
@@ -320,27 +287,25 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[],
 }
 
 /*
- * hv_set_mem_host_visibility - Set specified memory visible to host.
+ * hv_vtom_set_host_visibility - Set specified memory visible to host.
  *
  * In Isolation VM, all guest memory is encrypted from host and guest
  * needs to set memory visible to host via hvcall before sharing memory
  * with host. This function works as wrap of hv_mark_gpa_visibility()
  * with memory base and size.
  */
-int hv_set_mem_host_visibility(unsigned long kbuffer, int pagecount, bool visible)
+static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bool enc)
 {
-	enum hv_mem_host_visibility visibility = visible ?
-			VMBUS_PAGE_VISIBLE_READ_WRITE : VMBUS_PAGE_NOT_VISIBLE;
+	enum hv_mem_host_visibility visibility = enc ?
+			VMBUS_PAGE_NOT_VISIBLE : VMBUS_PAGE_VISIBLE_READ_WRITE;
 	u64 *pfn_array;
 	int ret = 0;
+	bool result = true;
 	int i, pfn;
 
-	if (!hv_is_isolation_supported() || !hv_hypercall_pg)
-		return 0;
-
 	pfn_array = kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
 	if (!pfn_array)
-		return -ENOMEM;
+		return false;
 
 	for (i = 0, pfn = 0; i < pagecount; i++) {
 		pfn_array[pfn] = virt_to_hvpfn((void *)kbuffer + i * HV_HYP_PAGE_SIZE);
@@ -349,17 +314,68 @@ int hv_set_mem_host_visibility(unsigned long kbuffer, int pagecount, bool visibl
 		if (pfn == HV_MAX_MODIFY_GPA_REP_COUNT || i == pagecount - 1) {
 			ret = hv_mark_gpa_visibility(pfn, pfn_array,
 						     visibility);
-			if (ret)
+			if (ret) {
+				result = false;
 				goto err_free_pfn_array;
+			}
 			pfn = 0;
 		}
 	}
 
  err_free_pfn_array:
 	kfree(pfn_array);
-	return ret;
+	return result;
+}
+
+static bool hv_vtom_tlb_flush_required(bool private)
+{
+	return true;
 }
 
+static bool hv_vtom_cache_flush_required(void)
+{
+	return false;
+}
+
+static bool hv_is_private_mmio(u64 addr)
+{
+	/*
+	 * Hyper-V always provides a single IO-APIC in a guest VM.
+	 * When a paravisor is used, it is emulated by the paravisor
+	 * in the guest context and must be mapped private.
+	 */
+	if (addr >= HV_IOAPIC_BASE_ADDRESS &&
+	    addr < (HV_IOAPIC_BASE_ADDRESS + PAGE_SIZE))
+		return true;
+
+	/* Same with a vTPM */
+	if (addr >= VTPM_BASE_ADDRESS &&
+	    addr < (VTPM_BASE_ADDRESS + PAGE_SIZE))
+		return true;
+
+	return false;
+}
+
+void __init hv_vtom_init(void)
+{
+	/*
+	 * By design, a VM using vTOM doesn't see the SEV setting,
+	 * so SEV initialization is bypassed and sev_status isn't set.
+	 * Set it here to indicate a vTOM VM.
+	 */
+	sev_status = MSR_AMD64_SNP_VTOM;
+	cc_set_vendor(CC_VENDOR_AMD);
+	cc_set_mask(ms_hyperv.shared_gpa_boundary);
+	physical_mask &= ms_hyperv.shared_gpa_boundary - 1;
+
+	x86_platform.hyper.is_private_mmio = hv_is_private_mmio;
+	x86_platform.guest.enc_cache_flush_required = hv_vtom_cache_flush_required;
+	x86_platform.guest.enc_tlb_flush_required = hv_vtom_tlb_flush_required;
+	x86_platform.guest.enc_status_change_finish = hv_vtom_set_host_visibility;
+}
+
+#endif /* CONFIG_AMD_MEM_ENCRYPT */
+
 /*
  * hv_map_memory - map memory to extra space in the AMD SEV-SNP Isolation VM.
  */
@@ -377,7 +393,7 @@ void *hv_map_memory(void *addr, unsigned long size)
 		pfns[i] = vmalloc_to_pfn(addr + i * PAGE_SIZE) +
 			(ms_hyperv.shared_gpa_boundary >> PAGE_SHIFT);
 
-	vaddr = vmap_pfn(pfns, size / PAGE_SIZE, PAGE_KERNEL_IO);
+	vaddr = vmap_pfn(pfns, size / PAGE_SIZE, pgprot_decrypted(PAGE_KERNEL));
 	kfree(pfns);
 
 	return vaddr;
@@ -387,3 +403,37 @@ void hv_unmap_memory(void *addr)
 {
 	vunmap(addr);
 }
+
+enum hv_isolation_type hv_get_isolation_type(void)
+{
+	if (!(ms_hyperv.priv_high & HV_ISOLATION))
+		return HV_ISOLATION_TYPE_NONE;
+	return FIELD_GET(HV_ISOLATION_TYPE, ms_hyperv.isolation_config_b);
+}
+EXPORT_SYMBOL_GPL(hv_get_isolation_type);
+
+/*
+ * hv_is_isolation_supported - Check system runs in the Hyper-V
+ * isolation VM.
+ */
+bool hv_is_isolation_supported(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR))
+		return false;
+
+	if (!hypervisor_is_type(X86_HYPER_MS_HYPERV))
+		return false;
+
+	return hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE;
+}
+
+DEFINE_STATIC_KEY_FALSE(isolation_type_snp);
+
+/*
+ * hv_isolation_type_snp - Check system runs in the AMD SEV-SNP based
+ * isolation VM.
+ */
+bool hv_isolation_type_snp(void)
+{
+	return static_branch_unlikely(&isolation_type_snp);
+}

arch/x86/include/asm/coco.h

@@ -7,7 +7,6 @@
 enum cc_vendor {
 	CC_VENDOR_NONE,
 	CC_VENDOR_AMD,
-	CC_VENDOR_HYPERV,
 	CC_VENDOR_INTEL,
 };
 

arch/x86/include/asm/mem_encrypt.h

@@ -56,6 +56,7 @@ void __init sev_es_init_vc_handling(void);
 #else	/* !CONFIG_AMD_MEM_ENCRYPT */
 
 #define sme_me_mask	0ULL
+#define sev_status	0ULL
 
 static inline void __init sme_early_encrypt(resource_size_t paddr,
 					    unsigned long size) { }