8 files changed, 161 insertions, 90 deletions
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index c80febc44cd2..6ec103bedcf1 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -16,6 +16,7 @@ KASAN_SANITIZE_pgprot.o		:= n
 KCSAN_SANITIZE := n
 # Avoid recursion by not calling KMSAN hooks for CEA code.
 KMSAN_SANITIZE_cpu_entry_area.o := n
+KMSAN_SANITIZE_mem_encrypt_identity.o := n
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_mem_encrypt.o		= -pg
diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c
index b3ca7d23e4b0..9332b36a1091 100644
--- a/arch/x86/mm/amdtopology.c
+++ b/arch/x86/mm/amdtopology.c
@@ -54,13 +54,11 @@ static __init int find_northbridge(void)
 
 int __init amd_numa_init(void)
 {
-	u64 start = PFN_PHYS(0);
+	unsigned int numnodes, cores, apicid;
+	u64 prevbase, start = PFN_PHYS(0);
 	u64 end = PFN_PHYS(max_pfn);
-	unsigned numnodes;
-	u64 prevbase;
-	int i, j, nb;
 	u32 nodeid, reg;
-	unsigned int bits, cores, apicid_base;
+	int i, j, nb;
 
 	if (!early_pci_allowed())
 		return -EINVAL;
@@ -158,26 +156,18 @@ int __init amd_numa_init(void)
 		return -ENOENT;
 
 	/*
-	 * We seem to have valid NUMA configuration.  Map apicids to nodes
-	 * using the coreid bits from early_identify_cpu.
+	 * We seem to have valid NUMA configuration. Map apicids to nodes
+	 * using the size of the core domain in the APIC space.
 	 */
-	bits = boot_cpu_data.x86_coreid_bits;
-	cores = 1 << bits;
-	apicid_base = 0;
+	cores = topology_get_domain_size(TOPO_CORE_DOMAIN);
 
-	/*
-	 * get boot-time SMP configuration:
-	 */
-	early_get_smp_config();
+	apicid = boot_cpu_physical_apicid;
+	if (apicid > 0)
+		pr_info("BSP APIC ID: %02x\n", apicid);
 
-	if (boot_cpu_physical_apicid > 0) {
-		pr_info("BSP APIC ID: %02x\n", boot_cpu_physical_apicid);
-		apicid_base = boot_cpu_physical_apicid;
+	for_each_node_mask(i, numa_nodes_parsed) {
+		for (j = 0; j < cores; j++, apicid++)
+			set_apicid_to_node(apicid, i);
 	}
-
-	for_each_node_mask(i, numa_nodes_parsed)
-		for (j = apicid_base; j < cores + apicid_base; j++)
-			set_apicid_to_node((i << bits) + j, i);
-
 	return 0;
 }
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 271dcb2deabc..b522933bfa56 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -6,6 +6,7 @@
 #include <xen/xen.h>
 
 #include <asm/fpu/api.h>
+#include <asm/fred.h>
 #include <asm/sev.h>
 #include <asm/traps.h>
 #include <asm/kdebug.h>
@@ -223,6 +224,79 @@ static bool ex_handler_ucopy_len(const struct exception_table_entry *fixup,
 	return ex_handler_uaccess(fixup, regs, trapnr, fault_address);
 }
 
+#ifdef CONFIG_X86_FRED
+static bool ex_handler_eretu(const struct exception_table_entry *fixup,
+			     struct pt_regs *regs, unsigned long error_code)
+{
+	struct pt_regs *uregs = (struct pt_regs *)(regs->sp - offsetof(struct pt_regs, orig_ax));
+	unsigned short ss = uregs->ss;
+	unsigned short cs = uregs->cs;
+
+	/*
+	 * Move the NMI bit from the invalid stack frame, which caused ERETU
+	 * to fault, to the fault handler's stack frame, thus to unblock NMI
+	 * with the fault handler's ERETS instruction ASAP if NMI is blocked.
+	 */
+	regs->fred_ss.nmi = uregs->fred_ss.nmi;
+
+	/*
+	 * Sync event information to uregs, i.e., the ERETU return frame, but
+	 * is it safe to write to the ERETU return frame which is just above
+	 * current event stack frame?
+	 *
+	 * The RSP used by FRED to push a stack frame is not the value in %rsp,
+	 * it is calculated from %rsp with the following 2 steps:
+	 * 1) RSP = %rsp - (IA32_FRED_CONFIG & 0x1c0)	// Reserve N*64 bytes
+	 * 2) RSP = RSP & ~0x3f		// Align to a 64-byte cache line
+	 * when an event delivery doesn't trigger a stack level change.
+	 *
+	 * Here is an example with N*64 (N=1) bytes reserved:
+	 *
+	 *  64-byte cache line ==>  ______________
+	 *                         |___Reserved___|
+	 *                         |__Event_data__|
+	 *                         |_____SS_______|
+	 *                         |_____RSP______|
+	 *                         |_____FLAGS____|
+	 *                         |_____CS_______|
+	 *                         |_____IP_______|
+	 *  64-byte cache line ==> |__Error_code__| <== ERETU return frame
+	 *                         |______________|
+	 *                         |______________|
+	 *                         |______________|
+	 *                         |______________|
+	 *                         |______________|
+	 *                         |______________|
+	 *                         |______________|
+	 *  64-byte cache line ==> |______________| <== RSP after step 1) and 2)
+	 *                         |___Reserved___|
+	 *                         |__Event_data__|
+	 *                         |_____SS_______|
+	 *                         |_____RSP______|
+	 *                         |_____FLAGS____|
+	 *                         |_____CS_______|
+	 *                         |_____IP_______|
+	 *  64-byte cache line ==> |__Error_code__| <== ERETS return frame
+	 *
+	 * Thus a new FRED stack frame will always be pushed below a previous
+	 * FRED stack frame ((N*64) bytes may be reserved between), and it is
+	 * safe to write to a previous FRED stack frame as they never overlap.
+	 */
+	fred_info(uregs)->edata = fred_event_data(regs);
+	uregs->ssx = regs->ssx;
+	uregs->fred_ss.ss = ss;
+	/* The NMI bit was moved away above */
+	uregs->fred_ss.nmi = 0;
+	uregs->csx = regs->csx;
+	uregs->fred_cs.sl = 0;
+	uregs->fred_cs.wfe = 0;
+	uregs->cs = cs;
+	uregs->orig_ax = error_code;
+
+	return ex_handler_default(fixup, regs);
+}
+#endif
+
 int ex_get_fixup_type(unsigned long ip)
 {
 	const struct exception_table_entry *e = search_exception_tables(ip);
@@ -300,6 +374,10 @@ int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code,
 		return ex_handler_ucopy_len(e, regs, trapnr, fault_addr, reg, imm);
 	case EX_TYPE_ZEROPAD:
 		return ex_handler_zeropad(e, regs, fault_addr);
+#ifdef CONFIG_X86_FRED
+	case EX_TYPE_ERETU:
+		return ex_handler_eretu(e, regs, error_code);
+#endif
 	}
 	BUG();
 }
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index d6375b3c633b..cdb5045a0428 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -34,6 +34,8 @@
 #include <asm/kvm_para.h>		/* kvm_handle_async_pf		*/
 #include <asm/vdso.h>			/* fixup_vdso_exception()	*/
 #include <asm/irq_stack.h>
+#include <asm/fred.h>
+#include <asm/sev.h>			/* snp_dump_hva_rmpentry()	*/
 
 #define CREATE_TRACE_POINTS
 #include <asm/trace/exceptions.h>
@@ -547,6 +549,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad
 		 !(error_code & X86_PF_PROT) ? "not-present page" :
 		 (error_code & X86_PF_RSVD)  ? "reserved bit violation" :
 		 (error_code & X86_PF_PK)    ? "protection keys violation" :
+		 (error_code & X86_PF_RMP)   ? "RMP violation" :
 					       "permissions violation");
 
 	if (!(error_code & X86_PF_USER) && user_mode(regs)) {
@@ -579,6 +582,9 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad
 	}
 
 	dump_pagetable(address);
+
+	if (error_code & X86_PF_RMP)
+		snp_dump_hva_rmpentry(address);
 }
 
 static noinline void
@@ -1509,8 +1515,10 @@ handle_page_fault(struct pt_regs *regs, unsigned long error_code,
 
 DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
 {
-	unsigned long address = read_cr2();
 	irqentry_state_t state;
+	unsigned long address;
+
+	address = cpu_feature_enabled(X86_FEATURE_FRED) ? fred_event_data(regs) : read_cr2();
 
 	prefetchw(&current->mm->mmap_lock);
 
diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c
index c290c55b632b..6f3b3e028718 100644
--- a/arch/x86/mm/mem_encrypt.c
+++ b/arch/x86/mm/mem_encrypt.c
@@ -14,6 +14,8 @@
 #include <linux/mem_encrypt.h>
 #include <linux/virtio_anchor.h>
 
+#include <asm/sev.h>
+
 /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */
 bool force_dma_unencrypted(struct device *dev)
 {
@@ -42,38 +44,45 @@ bool force_dma_unencrypted(struct device *dev)
 
 static void print_mem_encrypt_feature_info(void)
 {
-	pr_info("Memory Encryption Features active:");
-
-	if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) {
-		pr_cont(" Intel TDX\n");
-		return;
-	}
+	pr_info("Memory Encryption Features active: ");
 
-	pr_cont(" AMD");
+	switch (cc_vendor) {
+	case CC_VENDOR_INTEL:
+		pr_cont("Intel TDX\n");
+		break;
+	case CC_VENDOR_AMD:
+		pr_cont("AMD");
 
-	/* Secure Memory Encryption */
-	if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) {
+		/* Secure Memory Encryption */
+		if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) {
 		/*
 		 * SME is mutually exclusive with any of the SEV
 		 * features below.
-		 */
-		pr_cont(" SME\n");
-		return;
-	}
+		*/
+			pr_cont(" SME\n");
+			return;
+		}
 
-	/* Secure Encrypted Virtualization */
-	if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
-		pr_cont(" SEV");
+		/* Secure Encrypted Virtualization */
+		if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
+			pr_cont(" SEV");
+
+		/* Encrypted Register State */
+		if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
+			pr_cont(" SEV-ES");
 
-	/* Encrypted Register State */
-	if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
-		pr_cont(" SEV-ES");
+		/* Secure Nested Paging */
+		if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+			pr_cont(" SEV-SNP");
 
-	/* Secure Nested Paging */
-	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
-		pr_cont(" SEV-SNP");
+		pr_cont("\n");
 
-	pr_cont("\n");
+		sev_show_status();
+
+		break;
+	default:
+		pr_cont("Unknown\n");
+	}
 }
 
 /* Architecture __weak replacement functions */
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index d73aeb16417f..0166ab1780cc 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -97,7 +97,6 @@ static char sme_workarea[2 * PMD_SIZE] __section(".init.scratch");
 
 static char sme_cmdline_arg[] __initdata = "mem_encrypt";
 static char sme_cmdline_on[]  __initdata = "on";
-static char sme_cmdline_off[] __initdata = "off";
 
 static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd)
 {
@@ -305,7 +304,8 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
 	 * instrumentation or checking boot_cpu_data in the cc_platform_has()
 	 * function.
 	 */
-	if (!sme_get_me_mask() || sev_status & MSR_AMD64_SEV_ENABLED)
+	if (!sme_get_me_mask() ||
+	    RIP_REL_REF(sev_status) & MSR_AMD64_SEV_ENABLED)
 		return;
 
 	/*
@@ -504,10 +504,9 @@ void __init sme_encrypt_kernel(struct boot_params *bp)
 
 void __init sme_enable(struct boot_params *bp)
 {
-	const char *cmdline_ptr, *cmdline_arg, *cmdline_on, *cmdline_off;
+	const char *cmdline_ptr, *cmdline_arg, *cmdline_on;
 	unsigned int eax, ebx, ecx, edx;
 	unsigned long feature_mask;
-	bool active_by_default;
 	unsigned long me_mask;
 	char buffer[16];
 	bool snp;
@@ -543,11 +542,11 @@ void __init sme_enable(struct boot_params *bp)
 	me_mask = 1UL << (ebx & 0x3f);
 
 	/* Check the SEV MSR whether SEV or SME is enabled */
-	sev_status   = __rdmsr(MSR_AMD64_SEV);
-	feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT;
+	RIP_REL_REF(sev_status) = msr = __rdmsr(MSR_AMD64_SEV);
+	feature_mask = (msr & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT;
 
 	/* The SEV-SNP CC blob should never be present unless SEV-SNP is enabled. */
-	if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
+	if (snp && !(msr & MSR_AMD64_SEV_SNP_ENABLED))
 		snp_abort();
 
 	/* Check if memory encryption is enabled */
@@ -573,7 +572,6 @@ void __init sme_enable(struct boot_params *bp)
 			return;
 	} else {
 		/* SEV state cannot be controlled by a command line option */
-		sme_me_mask = me_mask;
 		goto out;
 	}
 
@@ -588,31 +586,17 @@ void __init sme_enable(struct boot_params *bp)
 	asm ("lea sme_cmdline_on(%%rip), %0"
 	     : "=r" (cmdline_on)
 	     : "p" (sme_cmdline_on));
-	asm ("lea sme_cmdline_off(%%rip), %0"
-	     : "=r" (cmdline_off)
-	     : "p" (sme_cmdline_off));
-
-	if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT_ACTIVE_BY_DEFAULT))
-		active_by_default = true;
-	else
-		active_by_default = false;
 
 	cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr |
 				     ((u64)bp->ext_cmd_line_ptr << 32));
 
-	if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0)
+	if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0 ||
+	    strncmp(buffer, cmdline_on, sizeof(buffer)))
 		return;
 
-	if (!strncmp(buffer, cmdline_on, sizeof(buffer)))
-		sme_me_mask = me_mask;
-	else if (!strncmp(buffer, cmdline_off, sizeof(buffer)))
-		sme_me_mask = 0;
-	else
-		sme_me_mask = active_by_default ? me_mask : 0;
 out:
-	if (sme_me_mask) {
-		physical_mask &= ~sme_me_mask;
-		cc_vendor = CC_VENDOR_AMD;
-		cc_set_mask(sme_me_mask);
-	}
+	RIP_REL_REF(sme_me_mask) = me_mask;
+	physical_mask &= ~me_mask;
+	cc_vendor = CC_VENDOR_AMD;
+	cc_set_mask(me_mask);
 }
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 0904d7e8e126..0d72183b5dd0 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -240,6 +240,8 @@ void pat_cpu_init(void)
 	}
 
 	wrmsrl(MSR_IA32_CR_PAT, pat_msr_val);
+
+	__flush_tlb_all();
 }
 
 /**
@@ -296,13 +298,8 @@ void __init pat_bp_init(void)
 	/*
 	 * Xen PV doesn't allow to set PAT MSR, but all cache modes are
 	 * supported.
-	 * When running as TDX guest setting the PAT MSR won't work either
-	 * due to the requirement to set CR0.CD when doing so. Rely on
-	 * firmware to have set the PAT MSR correctly.
 	 */
-	if (pat_disabled ||
-	    cpu_feature_enabled(X86_FEATURE_XENPV) ||
-	    cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) {
+	if (pat_disabled || cpu_feature_enabled(X86_FEATURE_XENPV)) {
 		init_cache_modes(pat_msr_val);
 		return;
 	}
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index e9b448d1b1b7..102880404046 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -755,10 +755,14 @@ pmd_t *lookup_pmd_address(unsigned long address)
  * areas on 32-bit NUMA systems.  The percpu areas can
  * end up in this kind of memory, for instance.
  *
- * This could be optimized, but it is only intended to be
- * used at initialization time, and keeping it
- * unoptimized should increase the testing coverage for
- * the more obscure platforms.
+ * Note that as long as the PTEs are well-formed with correct PFNs, this
+ * works without checking the PRESENT bit in the leaf PTE.  This is unlike
+ * the similar vmalloc_to_page() and derivatives.  Callers may depend on
+ * this behavior.
+ *
+ * This could be optimized, but it is only used in paths that are not perf
+ * sensitive, and keeping it unoptimized should increase the testing coverage
+ * for the more obscure platforms.
  */
 phys_addr_t slow_virt_to_phys(void *__virt_addr)
 {
@@ -2041,17 +2045,12 @@ int set_mce_nospec(unsigned long pfn)
 	return rc;
 }
 
-static int set_memory_p(unsigned long *addr, int numpages)
-{
-	return change_page_attr_set(addr, numpages, __pgprot(_PAGE_PRESENT), 0);
-}
-
 /* Restore full speculative operation to the pfn. */
 int clear_mce_nospec(unsigned long pfn)
 {
 	unsigned long addr = (unsigned long) pfn_to_kaddr(pfn);
 
-	return set_memory_p(&addr, 1);
+	return set_memory_p(addr, 1);
 }
 EXPORT_SYMBOL_GPL(clear_mce_nospec);
 #endif /* CONFIG_X86_64 */
@@ -2104,6 +2103,11 @@ int set_memory_np_noalias(unsigned long addr, int numpages)
 					CPA_NO_CHECK_ALIAS, NULL);
 }
 
+int set_memory_p(unsigned long addr, int numpages)
+{
+	return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_PRESENT), 0);
+}
+
 int set_memory_4k(unsigned long addr, int numpages)
 {
 	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),