Merge tag 'x86_urgent_for_v6.2_rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Borislav Petkov:

- Start checking for -mindirect-branch-cs-prefix clang support too now
that LLVM 16 will support it

- Fix a NULL ptr deref when suspending with Xen PV

- Have a SEV-SNP guest check explicitly for features enabled by the
hypervisor and fail gracefully if some are unsupported by the guest
instead of failing in a non-obvious and hard-to-debug way

- Fix a MSI descriptor leakage under Xen

- Mark Xen's MSI domain as supporting MSI-X

- Prevent legacy PIC interrupts from being resent in software by
marking them level triggered, as they should be, which lead to a NULL
ptr deref

* tag 'x86_urgent_for_v6.2_rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/build: Move '-mindirect-branch-cs-prefix' out of GCC-only block
acpi: Fix suspend with Xen PV
x86/sev: Add SEV-SNP guest feature negotiation support
x86/pci/xen: Fixup fallout from the PCI/MSI overhaul
x86/pci/xen: Set MSI_FLAG_PCI_MSIX support in Xen MSI domain
x86/i8259: Mark legacy PIC interrupts with IRQ_LEVEL

Documentation/x86/amd-memory-encryption.rst

···
 not enable SME, then Linux will not be able to activate memory encryption, even
 if configured to do so by default or the mem_encrypt=on command line parameter
 is specified.
+
+Secure Nested Paging (SNP)
+==========================
+
+SEV-SNP introduces new features (SEV_FEATURES[1:63]) which can be enabled
+by the hypervisor for security enhancements. Some of these features need
+guest side implementation to function correctly. The below table lists the
+expected guest behavior with various possible scenarios of guest/hypervisor
+SNP feature support.
+
++-----------------+---------------+---------------+------------------+
+| Feature Enabled | Guest needs   | Guest has     | Guest boot       |
+| by the HV       | implementation| implementation| behaviour        |
++=================+===============+===============+==================+
+|      No         |      No       |      No       |     Boot         |
+|                 |               |               |                  |
++-----------------+---------------+---------------+------------------+
+|      No         |      Yes      |      No       |     Boot         |
+|                 |               |               |                  |
++-----------------+---------------+---------------+------------------+
+|      No         |      Yes      |      Yes      |     Boot         |
+|                 |               |               |                  |
++-----------------+---------------+---------------+------------------+
+|      Yes        |      No       |      No       | Boot with        |
+|                 |               |               | feature enabled  |
++-----------------+---------------+---------------+------------------+
+|      Yes        |      Yes      |      No       | Graceful boot    |
+|                 |               |               | failure          |
++-----------------+---------------+---------------+------------------+
+|      Yes        |      Yes      |      Yes      | Boot with        |
+|                 |               |               | feature enabled  |
++-----------------+---------------+---------------+------------------+
+
+More details in AMD64 APM[1] Vol 2: 15.34.10 SEV_STATUS MSR
+
+[1] https://www.amd.com/system/files/TechDocs/40332.pdf

arch/x86/Makefile

···
 
 ifdef CONFIG_CC_IS_GCC
 RETPOLINE_CFLAGS	:= $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register)
-RETPOLINE_CFLAGS	+= $(call cc-option,-mindirect-branch-cs-prefix)
 RETPOLINE_VDSO_CFLAGS	:= $(call cc-option,-mindirect-branch=thunk-inline -mindirect-branch-register)
 endif
 ifdef CONFIG_CC_IS_CLANG
 RETPOLINE_CFLAGS	:= -mretpoline-external-thunk
 RETPOLINE_VDSO_CFLAGS	:= -mretpoline
 endif
+RETPOLINE_CFLAGS	+= $(call cc-option,-mindirect-branch-cs-prefix)
 
 ifdef CONFIG_RETHUNK
 RETHUNK_CFLAGS		:= -mfunction-return=thunk-extern

arch/x86/boot/compressed/ident_map_64.c

···
 
 	/* Load the new page-table. */
 	write_cr3(top_level_pgt);
+
+	/*
+	 * Now that the required page table mappings are established and a
+	 * GHCB can be used, check for SNP guest/HV feature compatibility.
+	 */
+	snp_check_features();
 }
 
 static pte_t *split_large_pmd(struct x86_mapping_info *info,

arch/x86/boot/compressed/misc.h

···
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 void sev_enable(struct boot_params *bp);
+void snp_check_features(void);
 void sev_es_shutdown_ghcb(void);
 extern bool sev_es_check_ghcb_fault(unsigned long address);
 void snp_set_page_private(unsigned long paddr);
···
 	if (bp)
 		bp->cc_blob_address = 0;
 }
+static inline void snp_check_features(void) { }
 static inline void sev_es_shutdown_ghcb(void) { }
 static inline bool sev_es_check_ghcb_fault(unsigned long address)
 {

arch/x86/boot/compressed/sev.c

···
 		error("Can't unmap GHCB page");
 }
 
+static void __noreturn sev_es_ghcb_terminate(struct ghcb *ghcb, unsigned int set,
+					     unsigned int reason, u64 exit_info_2)
+{
+	u64 exit_info_1 = SVM_VMGEXIT_TERM_REASON(set, reason);
+
+	vc_ghcb_invalidate(ghcb);
+	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_TERM_REQUEST);
+	ghcb_set_sw_exit_info_1(ghcb, exit_info_1);
+	ghcb_set_sw_exit_info_2(ghcb, exit_info_2);
+
+	sev_es_wr_ghcb_msr(__pa(ghcb));
+	VMGEXIT();
+
+	while (true)
+		asm volatile("hlt\n" : : : "memory");
+}
+
 bool sev_es_check_ghcb_fault(unsigned long address)
 {
 	/* Check whether the fault was on the GHCB page */
···
 	attrs = 1;
 	if (rmpadjust((unsigned long)&boot_ghcb_page, RMP_PG_SIZE_4K, attrs))
 		sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_NOT_VMPL0);
+}
+
+/*
+ * SNP_FEATURES_IMPL_REQ is the mask of SNP features that will need
+ * guest side implementation for proper functioning of the guest. If any
+ * of these features are enabled in the hypervisor but are lacking guest
+ * side implementation, the behavior of the guest will be undefined. The
+ * guest could fail in non-obvious way making it difficult to debug.
+ *
+ * As the behavior of reserved feature bits is unknown to be on the
+ * safe side add them to the required features mask.
+ */
+#define SNP_FEATURES_IMPL_REQ	(MSR_AMD64_SNP_VTOM |			\
+				 MSR_AMD64_SNP_REFLECT_VC |		\
+				 MSR_AMD64_SNP_RESTRICTED_INJ |		\
+				 MSR_AMD64_SNP_ALT_INJ |		\
+				 MSR_AMD64_SNP_DEBUG_SWAP |		\
+				 MSR_AMD64_SNP_VMPL_SSS |		\
+				 MSR_AMD64_SNP_SECURE_TSC |		\
+				 MSR_AMD64_SNP_VMGEXIT_PARAM |		\
+				 MSR_AMD64_SNP_VMSA_REG_PROTECTION |	\
+				 MSR_AMD64_SNP_RESERVED_BIT13 |		\
+				 MSR_AMD64_SNP_RESERVED_BIT15 |		\
+				 MSR_AMD64_SNP_RESERVED_MASK)
+
+/*
+ * SNP_FEATURES_PRESENT is the mask of SNP features that are implemented
+ * by the guest kernel. As and when a new feature is implemented in the
+ * guest kernel, a corresponding bit should be added to the mask.
+ */
+#define SNP_FEATURES_PRESENT (0)
+
+void snp_check_features(void)
+{
+	u64 unsupported;
+
+	if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
+		return;
+
+	/*
+	 * Terminate the boot if hypervisor has enabled any feature lacking
+	 * guest side implementation. Pass on the unsupported features mask through
+	 * EXIT_INFO_2 of the GHCB protocol so that those features can be reported
+	 * as part of the guest boot failure.
+	 */
+	unsupported = sev_status & SNP_FEATURES_IMPL_REQ & ~SNP_FEATURES_PRESENT;
+	if (unsupported) {
+		if (ghcb_version < 2 || (!boot_ghcb && !early_setup_ghcb()))
+			sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
+
+		sev_es_ghcb_terminate(boot_ghcb, SEV_TERM_SET_GEN,
+				      GHCB_SNP_UNSUPPORTED, unsupported);
+	}
 }
 
 void sev_enable(struct boot_params *bp)

arch/x86/include/asm/acpi.h

···
 #include <asm/mmu.h>
 #include <asm/mpspec.h>
 #include <asm/x86_init.h>
+#include <asm/cpufeature.h>
 
 #ifdef CONFIG_ACPI_APEI
 # include <asm/pgtable_types.h>
···
 
 /* Physical address to resume after wakeup */
 unsigned long acpi_get_wakeup_address(void);
+
+static inline bool acpi_skip_set_wakeup_address(void)
+{
+	return cpu_feature_enabled(X86_FEATURE_XENPV);
+}
+
+#define acpi_skip_set_wakeup_address acpi_skip_set_wakeup_address
 
 /*
  * Check if the CPU can handle C2 and deeper

arch/x86/include/asm/msr-index.h

···
 #define MSR_AMD64_SEV_ES_ENABLED	BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT)
 #define MSR_AMD64_SEV_SNP_ENABLED	BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT)
 
+/* SNP feature bits enabled by the hypervisor */
+#define MSR_AMD64_SNP_VTOM			BIT_ULL(3)
+#define MSR_AMD64_SNP_REFLECT_VC		BIT_ULL(4)
+#define MSR_AMD64_SNP_RESTRICTED_INJ		BIT_ULL(5)
+#define MSR_AMD64_SNP_ALT_INJ			BIT_ULL(6)
+#define MSR_AMD64_SNP_DEBUG_SWAP		BIT_ULL(7)
+#define MSR_AMD64_SNP_PREVENT_HOST_IBS		BIT_ULL(8)
+#define MSR_AMD64_SNP_BTB_ISOLATION		BIT_ULL(9)
+#define MSR_AMD64_SNP_VMPL_SSS			BIT_ULL(10)
+#define MSR_AMD64_SNP_SECURE_TSC		BIT_ULL(11)
+#define MSR_AMD64_SNP_VMGEXIT_PARAM		BIT_ULL(12)
+#define MSR_AMD64_SNP_IBS_VIRT			BIT_ULL(14)
+#define MSR_AMD64_SNP_VMSA_REG_PROTECTION	BIT_ULL(16)
+#define MSR_AMD64_SNP_SMT_PROTECTION		BIT_ULL(17)
+
+/* SNP feature bits reserved for future use. */
+#define MSR_AMD64_SNP_RESERVED_BIT13		BIT_ULL(13)
+#define MSR_AMD64_SNP_RESERVED_BIT15		BIT_ULL(15)
+#define MSR_AMD64_SNP_RESERVED_MASK		GENMASK_ULL(63, 18)
+
 #define MSR_AMD64_VIRT_SPEC_CTRL	0xc001011f
 
 /* AMD Collaborative Processor Performance Control MSRs */

arch/x86/include/uapi/asm/svm.h

···
 #define SVM_VMGEXIT_AP_CREATE			1
 #define SVM_VMGEXIT_AP_DESTROY			2
 #define SVM_VMGEXIT_HV_FEATURES			0x8000fffd
+#define SVM_VMGEXIT_TERM_REQUEST		0x8000fffe
+#define SVM_VMGEXIT_TERM_REASON(reason_set, reason_code)	\
+	/* SW_EXITINFO1[3:0] */					\
+	(((((u64)reason_set) & 0xf)) |				\
+	/* SW_EXITINFO1[11:4] */				\
+	((((u64)reason_code) & 0xff) << 4))
 #define SVM_VMGEXIT_UNSUPPORTED_EVENT		0x8000ffff
 
 /* Exit code reserved for hypervisor/software use */

arch/x86/kernel/i8259.c

···
 	disable_irq_nosync(irq);
 	io_apic_irqs &= ~(1<<irq);
 	irq_set_chip_and_handler(irq, &i8259A_chip, handle_level_irq);
+	irq_set_status_flags(irq, IRQ_LEVEL);
 	enable_irq(irq);
 	lapic_assign_legacy_vector(irq, true);
 }

arch/x86/kernel/irqinit.c

···
 
 	legacy_pic->init(0);
 
-	for (i = 0; i < nr_legacy_irqs(); i++)
+	for (i = 0; i < nr_legacy_irqs(); i++) {
 		irq_set_chip_and_handler(i, chip, handle_level_irq);
+		irq_set_status_flags(i, IRQ_LEVEL);
+	}
 }
 
 void __init init_IRQ(void)

arch/x86/pci/xen.c

···
 	msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_ASSOCIATED) {
 		for (i = 0; i < msidesc->nvec_used; i++)
 			xen_destroy_irq(msidesc->irq + i);
+		msidesc->irq = 0;
 	}
 }
 
···
 };
 
 static struct msi_domain_info xen_pci_msi_domain_info = {
+	.flags			= MSI_FLAG_PCI_MSIX | MSI_FLAG_FREE_MSI_DESCS | MSI_FLAG_DEV_SYSFS,
 	.ops			= &xen_pci_msi_domain_ops,
 };
 

drivers/acpi/sleep.c

···
 	.priority	= 0,
 };
 
+#ifndef acpi_skip_set_wakeup_address
+#define acpi_skip_set_wakeup_address() false
+#endif
+
 static int acpi_sleep_prepare(u32 acpi_state)
 {
 #ifdef CONFIG_ACPI_SLEEP
 	unsigned long acpi_wakeup_address;
 
 	/* do we have a wakeup address for S2 and S3? */
-	if (acpi_state == ACPI_STATE_S3) {
+	if (acpi_state == ACPI_STATE_S3 && !acpi_skip_set_wakeup_address()) {
 		acpi_wakeup_address = acpi_get_wakeup_address();
 		if (!acpi_wakeup_address)
 			return -EFAULT;