Merge tag 'x86-urgent-2025-05-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull misc x86 fixes from Ingo Molnar:

 - Fix SEV-SNP kdump bugs

 - Update the email address of Alexey Makhalov in MAINTAINERS

 - Add the CPU feature flag for the Zen6 microarchitecture

 - Fix typo in system message

* tag 'x86-urgent-2025-05-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm: Remove duplicated word in warning message
  x86/CPU/AMD: Add X86_FEATURE_ZEN6
  x86/sev: Make sure pages are not skipped during kdump
  x86/sev: Do not touch VMSA pages during SNP guest memory kdump
  MAINTAINERS: Update Alexey Makhalov's email address
  x86/sev: Fix operator precedence in GHCB_MSR_VMPL_REQ_LEVEL macro

Author: torvalds

MAINTAINERS

@@ -18439,7 +18439,7 @@ F:	include/uapi/linux/ppdev.h
 PARAVIRT_OPS INTERFACE
 M:	Juergen Gross <jgross@suse.com>
 R:	Ajay Kaher <ajay.kaher@broadcom.com>
-R:	Alexey Makhalov <alexey.amakhalov@broadcom.com>
+R:	Alexey Makhalov <alexey.makhalov@broadcom.com>
 R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	virtualization@lists.linux.dev
 L:	x86@kernel.org
@@ -25924,7 +25924,7 @@ F:	drivers/misc/vmw_balloon.c
 
 VMWARE HYPERVISOR INTERFACE
 M:	Ajay Kaher <ajay.kaher@broadcom.com>
-M:	Alexey Makhalov <alexey.amakhalov@broadcom.com>
+M:	Alexey Makhalov <alexey.makhalov@broadcom.com>
 R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	virtualization@lists.linux.dev
 L:	x86@kernel.org
@@ -25952,7 +25952,7 @@ F:	drivers/scsi/vmw_pvscsi.h
 VMWARE VIRTUAL PTP CLOCK DRIVER
 M:	Nick Shi <nick.shi@broadcom.com>
 R:	Ajay Kaher <ajay.kaher@broadcom.com>
-R:	Alexey Makhalov <alexey.amakhalov@broadcom.com>
+R:	Alexey Makhalov <alexey.makhalov@broadcom.com>
 R:	Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com>
 L:	netdev@vger.kernel.org
 S:	Supported

arch/x86/coco/sev/core.c

@@ -959,6 +959,102 @@ void snp_accept_memory(phys_addr_t start, phys_addr_t end)
 	set_pages_state(vaddr, npages, SNP_PAGE_STATE_PRIVATE);
 }
 
+static int vmgexit_ap_control(u64 event, struct sev_es_save_area *vmsa, u32 apic_id)
+{
+	bool create = event != SVM_VMGEXIT_AP_DESTROY;
+	struct ghcb_state state;
+	unsigned long flags;
+	struct ghcb *ghcb;
+	int ret = 0;
+
+	local_irq_save(flags);
+
+	ghcb = __sev_get_ghcb(&state);
+
+	vc_ghcb_invalidate(ghcb);
+
+	if (create)
+		ghcb_set_rax(ghcb, vmsa->sev_features);
+
+	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION);
+	ghcb_set_sw_exit_info_1(ghcb,
+				((u64)apic_id << 32)	|
+				((u64)snp_vmpl << 16)	|
+				event);
+	ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa));
+
+	sev_es_wr_ghcb_msr(__pa(ghcb));
+	VMGEXIT();
+
+	if (!ghcb_sw_exit_info_1_is_valid(ghcb) ||
+	    lower_32_bits(ghcb->save.sw_exit_info_1)) {
+		pr_err("SNP AP %s error\n", (create ? "CREATE" : "DESTROY"));
+		ret = -EINVAL;
+	}
+
+	__sev_put_ghcb(&state);
+
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+static int snp_set_vmsa(void *va, void *caa, int apic_id, bool make_vmsa)
+{
+	int ret;
+
+	if (snp_vmpl) {
+		struct svsm_call call = {};
+		unsigned long flags;
+
+		local_irq_save(flags);
+
+		call.caa = this_cpu_read(svsm_caa);
+		call.rcx = __pa(va);
+
+		if (make_vmsa) {
+			/* Protocol 0, Call ID 2 */
+			call.rax = SVSM_CORE_CALL(SVSM_CORE_CREATE_VCPU);
+			call.rdx = __pa(caa);
+			call.r8  = apic_id;
+		} else {
+			/* Protocol 0, Call ID 3 */
+			call.rax = SVSM_CORE_CALL(SVSM_CORE_DELETE_VCPU);
+		}
+
+		ret = svsm_perform_call_protocol(&call);
+
+		local_irq_restore(flags);
+	} else {
+		/*
+		 * If the kernel runs at VMPL0, it can change the VMSA
+		 * bit for a page using the RMPADJUST instruction.
+		 * However, for the instruction to succeed it must
+		 * target the permissions of a lesser privileged (higher
+		 * numbered) VMPL level, so use VMPL1.
+		 */
+		u64 attrs = 1;
+
+		if (make_vmsa)
+			attrs |= RMPADJUST_VMSA_PAGE_BIT;
+
+		ret = rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs);
+	}
+
+	return ret;
+}
+
+static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa, int apic_id)
+{
+	int err;
+
+	err = snp_set_vmsa(vmsa, NULL, apic_id, false);
+	if (err)
+		pr_err("clear VMSA page failed (%u), leaking page\n", err);
+	else
+		free_page((unsigned long)vmsa);
+}
+
 static void set_pte_enc(pte_t *kpte, int level, void *va)
 {
 	struct pte_enc_desc d = {
@@ -1005,7 +1101,8 @@ static void unshare_all_memory(void)
 			data = per_cpu(runtime_data, cpu);
 			ghcb = (unsigned long)&data->ghcb_page;
 
-			if (addr <= ghcb && ghcb <= addr + size) {
+			/* Handle the case of a huge page containing the GHCB page */
+			if (addr <= ghcb && ghcb < addr + size) {
 				skipped_addr = true;
 				break;
 			}
@@ -1055,11 +1152,70 @@ void snp_kexec_begin(void)
 		pr_warn("Failed to stop shared<->private conversions\n");
 }
 
+/*
+ * Shutdown all APs except the one handling kexec/kdump and clearing
+ * the VMSA tag on AP's VMSA pages as they are not being used as
+ * VMSA page anymore.
+ */
+static void shutdown_all_aps(void)
+{
+	struct sev_es_save_area *vmsa;
+	int apic_id, this_cpu, cpu;
+
+	this_cpu = get_cpu();
+
+	/*
+	 * APs are already in HLT loop when enc_kexec_finish() callback
+	 * is invoked.
+	 */
+	for_each_present_cpu(cpu) {
+		vmsa = per_cpu(sev_vmsa, cpu);
+
+		/*
+		 * The BSP or offlined APs do not have guest allocated VMSA
+		 * and there is no need  to clear the VMSA tag for this page.
+		 */
+		if (!vmsa)
+			continue;
+
+		/*
+		 * Cannot clear the VMSA tag for the currently running vCPU.
+		 */
+		if (this_cpu == cpu) {
+			unsigned long pa;
+			struct page *p;
+
+			pa = __pa(vmsa);
+			/*
+			 * Mark the VMSA page of the running vCPU as offline
+			 * so that is excluded and not touched by makedumpfile
+			 * while generating vmcore during kdump.
+			 */
+			p = pfn_to_online_page(pa >> PAGE_SHIFT);
+			if (p)
+				__SetPageOffline(p);
+			continue;
+		}
+
+		apic_id = cpuid_to_apicid[cpu];
+
+		/*
+		 * Issue AP destroy to ensure AP gets kicked out of guest mode
+		 * to allow using RMPADJUST to remove the VMSA tag on it's
+		 * VMSA page.
+		 */
+		vmgexit_ap_control(SVM_VMGEXIT_AP_DESTROY, vmsa, apic_id);
+		snp_cleanup_vmsa(vmsa, apic_id);
+	}
+
+	put_cpu();
+}
+
 void snp_kexec_finish(void)
 {
 	struct sev_es_runtime_data *data;
+	unsigned long size, addr;
 	unsigned int level, cpu;
-	unsigned long size;
 	struct ghcb *ghcb;
 	pte_t *pte;
 
@@ -1069,6 +1225,8 @@ void snp_kexec_finish(void)
 	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
 		return;
 
+	shutdown_all_aps();
+
 	unshare_all_memory();
 
 	/*
@@ -1085,54 +1243,11 @@ void snp_kexec_finish(void)
 		ghcb = &data->ghcb_page;
 		pte = lookup_address((unsigned long)ghcb, &level);
 		size = page_level_size(level);
-		set_pte_enc(pte, level, (void *)ghcb);
-		snp_set_memory_private((unsigned long)ghcb, (size / PAGE_SIZE));
-	}
-}
-
-static int snp_set_vmsa(void *va, void *caa, int apic_id, bool make_vmsa)
-{
-	int ret;
-
-	if (snp_vmpl) {
-		struct svsm_call call = {};
-		unsigned long flags;
-
-		local_irq_save(flags);
-
-		call.caa = this_cpu_read(svsm_caa);
-		call.rcx = __pa(va);
-
-		if (make_vmsa) {
-			/* Protocol 0, Call ID 2 */
-			call.rax = SVSM_CORE_CALL(SVSM_CORE_CREATE_VCPU);
-			call.rdx = __pa(caa);
-			call.r8  = apic_id;
-		} else {
-			/* Protocol 0, Call ID 3 */
-			call.rax = SVSM_CORE_CALL(SVSM_CORE_DELETE_VCPU);
-		}
-
-		ret = svsm_perform_call_protocol(&call);
-
-		local_irq_restore(flags);
-	} else {
-		/*
-		 * If the kernel runs at VMPL0, it can change the VMSA
-		 * bit for a page using the RMPADJUST instruction.
-		 * However, for the instruction to succeed it must
-		 * target the permissions of a lesser privileged (higher
-		 * numbered) VMPL level, so use VMPL1.
-		 */
-		u64 attrs = 1;
-
-		if (make_vmsa)
-			attrs |= RMPADJUST_VMSA_PAGE_BIT;
-
-		ret = rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs);
+		/* Handle the case of a huge page containing the GHCB page */
+		addr = (unsigned long)ghcb & page_level_mask(level);
+		set_pte_enc(pte, level, (void *)addr);
+		snp_set_memory_private(addr, (size / PAGE_SIZE));
 	}
-
-	return ret;
 }
 
 #define __ATTR_BASE		(SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK)
@@ -1166,24 +1281,10 @@ static void *snp_alloc_vmsa_page(int cpu)
 	return page_address(p + 1);
 }
 
-static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa, int apic_id)
-{
-	int err;
-
-	err = snp_set_vmsa(vmsa, NULL, apic_id, false);
-	if (err)
-		pr_err("clear VMSA page failed (%u), leaking page\n", err);
-	else
-		free_page((unsigned long)vmsa);
-}
-
 static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
 {
 	struct sev_es_save_area *cur_vmsa, *vmsa;
-	struct ghcb_state state;
 	struct svsm_ca *caa;
-	unsigned long flags;
-	struct ghcb *ghcb;
 	u8 sipi_vector;
 	int cpu, ret;
 	u64 cr4;
@@ -1297,33 +1398,7 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
 	}
 
 	/* Issue VMGEXIT AP Creation NAE event */
-	local_irq_save(flags);
-
-	ghcb = __sev_get_ghcb(&state);
-
-	vc_ghcb_invalidate(ghcb);
-	ghcb_set_rax(ghcb, vmsa->sev_features);
-	ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION);
-	ghcb_set_sw_exit_info_1(ghcb,
-				((u64)apic_id << 32)	|
-				((u64)snp_vmpl << 16)	|
-				SVM_VMGEXIT_AP_CREATE);
-	ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa));
-
-	sev_es_wr_ghcb_msr(__pa(ghcb));
-	VMGEXIT();
-
-	if (!ghcb_sw_exit_info_1_is_valid(ghcb) ||
-	    lower_32_bits(ghcb->save.sw_exit_info_1)) {
-		pr_err("SNP AP Creation error\n");
-		ret = -EINVAL;
-	}
-
-	__sev_put_ghcb(&state);
-
-	local_irq_restore(flags);
-
-	/* Perform cleanup if there was an error */
+	ret = vmgexit_ap_control(SVM_VMGEXIT_AP_CREATE, vmsa, apic_id);
 	if (ret) {
 		snp_cleanup_vmsa(vmsa, apic_id);
 		vmsa = NULL;

arch/x86/include/asm/cpufeatures.h

@@ -75,7 +75,7 @@
 #define X86_FEATURE_CENTAUR_MCR		( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */
 #define X86_FEATURE_K8			( 3*32+ 4) /* Opteron, Athlon64 */
 #define X86_FEATURE_ZEN5		( 3*32+ 5) /* CPU based on Zen5 microarchitecture */
-/* Free                                 ( 3*32+ 6) */
+#define X86_FEATURE_ZEN6		( 3*32+ 6) /* CPU based on Zen6 microarchitecture */
 /* Free                                 ( 3*32+ 7) */
 #define X86_FEATURE_CONSTANT_TSC	( 3*32+ 8) /* "constant_tsc" TSC ticks at a constant rate */
 #define X86_FEATURE_UP			( 3*32+ 9) /* "up" SMP kernel running on UP */

arch/x86/include/asm/sev-common.h

@@ -116,7 +116,7 @@ enum psc_op {
 #define GHCB_MSR_VMPL_REQ		0x016
 #define GHCB_MSR_VMPL_REQ_LEVEL(v)			\
 	/* GHCBData[39:32] */				\
-	(((u64)(v) & GENMASK_ULL(7, 0) << 32) |		\
+	((((u64)(v) & GENMASK_ULL(7, 0)) << 32) |	\
 	/* GHCBDdata[11:0] */				\
 	GHCB_MSR_VMPL_REQ)
 

arch/x86/kernel/cpu/amd.c

@@ -472,6 +472,11 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		case 0x60 ... 0x7f:
 			setup_force_cpu_cap(X86_FEATURE_ZEN5);
 			break;
+		case 0x50 ... 0x5f:
+		case 0x90 ... 0xaf:
+		case 0xc0 ... 0xcf:
+			setup_force_cpu_cap(X86_FEATURE_ZEN6);
+			break;
 		default:
 			goto warn;
 		}

arch/x86/mm/init_32.c

@@ -566,7 +566,7 @@ static void __init lowmem_pfn_init(void)
 	"only %luMB highmem pages available, ignoring highmem size of %luMB!\n"
 
 #define MSG_HIGHMEM_TRIMMED \
-	"Warning: only 4GB will be used. Support for for CONFIG_HIGHMEM64G was removed!\n"
+	"Warning: only 4GB will be used. Support for CONFIG_HIGHMEM64G was removed!\n"
 /*
  * We have more RAM than fits into lowmem - we try to put it into
  * highmem, also taking the highmem=x boot parameter into account: