Merge tag 'x86_urgent_for_v6.9_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

torvalds · torvalds · commit 1aac9cb7e66e · 2024-03-31T10:16:34.000-07:00
Pull x86 fixes from Borislav Petkov:

 - Make sure single object builds in arch/x86/virt/ ala
      make ... arch/x86/virt/vmx/tdx/seamcall.o
   work again

 - Do not do ROM range scans and memory validation when the kernel is
   running as a SEV-SNP guest as those can get problematic and, before
   that, are not really needed in such a guest

 - Exclude the build-time generated vdso-image-x32.o object from objtool
   validation and in particular the return sites in there due to a
   warning which fires when an unpatched return thunk is being used

 - Improve the NMI CPUs stall message to show additional information
   about the state of each CPU wrt the NMI handler

 - Enable gcc named address spaces support only on !KCSAN configs due to
   compiler options incompatibility

 - Revert a change which was trying to use GB pages for mapping regions
   only when the regions would be large enough but that change lead to
   kexec failing

 - A documentation fixlet

* tag 'x86_urgent_for_v6.9_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/build: Use obj-y to descend into arch/x86/virt/
  x86/sev: Skip ROM range scans and validation for SEV-SNP guests
  x86/vdso: Fix rethunk patching for vdso-image-x32.o too
  x86/nmi: Upgrade NMI backtrace stall checks &amp; messages
  x86/percpu: Disable named address spaces for KCSAN
  Revert "x86/mm/ident_map: Use gbpages only where full GB page should be mapped."
  Documentation/x86: Fix title underline length
diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/arch/x86/resctrl.rst
@@ -574,7 +574,7 @@ Memory b/w domain is L3 cache.
 	MB:<cache_id0>=bandwidth0;<cache_id1>=bandwidth1;...
 
 Memory bandwidth Allocation specified in MiBps
----------------------------------------------
+----------------------------------------------
 
 Memory bandwidth domain is L3 cache.
 ::
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild
@@ -28,7 +28,7 @@ obj-y += net/
 
 obj-$(CONFIG_KEXEC_FILE) += purgatory/
 
-obj-y += virt/svm/
+obj-y += virt/
 
 # for cleaning
 subdir- += boot tools
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
@@ -2439,6 +2439,8 @@ config USE_X86_SEG_SUPPORT
 	# with named address spaces - see GCC PR sanitizer/111736.
 	#
 	depends on !KASAN
+	# -fsanitize=thread (KCSAN) is also incompatible.
+	depends on !KCSAN
 
 config CC_HAS_SLS
 	def_bool $(cc-option,-mharden-sls=all)
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
@@ -251,8 +251,6 @@ archheaders:
 
 libs-y  += arch/x86/lib/
 
-core-y += arch/x86/virt/
-
 # drivers-y are linked after core-y
 drivers-$(CONFIG_MATH_EMULATION) += arch/x86/math-emu/
 drivers-$(CONFIG_PCI)            += arch/x86/pci/
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
@@ -41,6 +41,7 @@ obj-$(CONFIG_X86_X32_ABI)			+= vdso-image-x32.o
 obj-$(CONFIG_COMPAT_32)				+= vdso-image-32.o vdso32-setup.o
 
 OBJECT_FILES_NON_STANDARD_vdso-image-32.o	:= n
+OBJECT_FILES_NON_STANDARD_vdso-image-x32.o	:= n
 OBJECT_FILES_NON_STANDARD_vdso-image-64.o	:= n
 OBJECT_FILES_NON_STANDARD_vdso32-setup.o	:= n
 
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
@@ -218,12 +218,12 @@ void early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
 				  unsigned long npages);
 void early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
 				 unsigned long npages);
-void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op);
 void snp_set_memory_shared(unsigned long vaddr, unsigned long npages);
 void snp_set_memory_private(unsigned long vaddr, unsigned long npages);
 void snp_set_wakeup_secondary_cpu(void);
 bool snp_init(struct boot_params *bp);
 void __noreturn snp_abort(void);
+void snp_dmi_setup(void);
 int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio);
 void snp_accept_memory(phys_addr_t start, phys_addr_t end);
 u64 snp_get_unsupported_features(u64 status);
@@ -244,12 +244,12 @@ static inline void __init
 early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned long npages) { }
 static inline void __init
 early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned long npages) { }
-static inline void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op) { }
 static inline void snp_set_memory_shared(unsigned long vaddr, unsigned long npages) { }
 static inline void snp_set_memory_private(unsigned long vaddr, unsigned long npages) { }
 static inline void snp_set_wakeup_secondary_cpu(void) { }
 static inline bool snp_init(struct boot_params *bp) { return false; }
 static inline void snp_abort(void) { }
+static inline void snp_dmi_setup(void) { }
 static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio)
 {
 	return -ENOTTY;
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
@@ -30,12 +30,13 @@ struct x86_init_mpparse {
  * @reserve_resources:		reserve the standard resources for the
  *				platform
  * @memory_setup:		platform specific memory setup
- *
+ * @dmi_setup:			platform specific DMI setup
  */
 struct x86_init_resources {
 	void (*probe_roms)(void);
 	void (*reserve_resources)(void);
 	char *(*memory_setup)(void);
+	void (*dmi_setup)(void);
 };
 
 /**
diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c
@@ -2,6 +2,7 @@
 /*
  * EISA specific code
  */
+#include <linux/cc_platform.h>
 #include <linux/ioport.h>
 #include <linux/eisa.h>
 #include <linux/io.h>
@@ -12,7 +13,7 @@ static __init int eisa_bus_probe(void)
 {
 	void __iomem *p;
 
-	if (xen_pv_domain() && !xen_initial_domain())
+	if ((xen_pv_domain() && !xen_initial_domain()) || cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
 		return 0;
 
 	p = ioremap(0x0FFFD9, 4);
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
@@ -580,7 +580,7 @@ EXPORT_SYMBOL_GPL(asm_exc_nmi_kvm_vmx);
 
 static char *nmi_check_stall_msg[] = {
 /*									*/
-/* +--------- nsp->idt_seq_snap & 0x1: CPU is in NMI handler.		*/
+/* +--------- nmi_seq & 0x1: CPU is currently in NMI handler.		*/
 /* | +------ cpu_is_offline(cpu)					*/
 /* | | +--- nsp->idt_calls_snap != atomic_long_read(&nsp->idt_calls):	*/
 /* | | |	NMI handler has been invoked.				*/
@@ -628,22 +628,26 @@ void nmi_backtrace_stall_check(const struct cpumask *btp)
 		nmi_seq = READ_ONCE(nsp->idt_nmi_seq);
 		if (nsp->idt_nmi_seq_snap + 1 == nmi_seq && (nmi_seq & 0x1)) {
 			msgp = "CPU entered NMI handler function, but has not exited";
-		} else if ((nsp->idt_nmi_seq_snap & 0x1) != (nmi_seq & 0x1)) {
-			msgp = "CPU is handling NMIs";
-		} else {
-			idx = ((nsp->idt_seq_snap & 0x1) << 2) |
+		} else if (nsp->idt_nmi_seq_snap == nmi_seq ||
+			   nsp->idt_nmi_seq_snap + 1 == nmi_seq) {
+			idx = ((nmi_seq & 0x1) << 2) |
 			      (cpu_is_offline(cpu) << 1) |
 			      (nsp->idt_calls_snap != atomic_long_read(&nsp->idt_calls));
 			msgp = nmi_check_stall_msg[idx];
 			if (nsp->idt_ignored_snap != READ_ONCE(nsp->idt_ignored) && (idx & 0x1))
 				modp = ", but OK because ignore_nmis was set";
-			if (nmi_seq & 0x1)
-				msghp = " (CPU currently in NMI handler function)";
-			else if (nsp->idt_nmi_seq_snap + 1 == nmi_seq)
+			if (nsp->idt_nmi_seq_snap + 1 == nmi_seq)
 				msghp = " (CPU exited one NMI handler function)";
+			else if (nmi_seq & 0x1)
+				msghp = " (CPU currently in NMI handler function)";
+			else
+				msghp = " (CPU was never in an NMI handler function)";
+		} else {
+			msgp = "CPU is handling NMIs";
 		}
-		pr_alert("%s: CPU %d: %s%s%s, last activity: %lu jiffies ago.\n",
-			 __func__, cpu, msgp, modp, msghp, j - READ_ONCE(nsp->recv_jiffies));
+		pr_alert("%s: CPU %d: %s%s%s\n", __func__, cpu, msgp, modp, msghp);
+		pr_alert("%s: last activity: %lu jiffies ago.\n",
+			 __func__, j - READ_ONCE(nsp->recv_jiffies));
 	}
 }
 
diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c
@@ -203,16 +203,6 @@ void __init probe_roms(void)
 	unsigned char c;
 	int i;
 
-	/*
-	 * The ROM memory range is not part of the e820 table and is therefore not
-	 * pre-validated by BIOS. The kernel page table maps the ROM region as encrypted
-	 * memory, and SNP requires encrypted memory to be validated before access.
-	 * Do that here.
-	 */
-	snp_prep_memory(video_rom_resource.start,
-			((system_rom_resource.end + 1) - video_rom_resource.start),
-			SNP_PAGE_STATE_PRIVATE);
-
 	/* video rom */
 	upper = adapter_rom_resources[0].start;
 	for (start = video_rom_resource.start; start < upper; start += 2048) {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
@@ -9,7 +9,6 @@
 #include <linux/console.h>
 #include <linux/crash_dump.h>
 #include <linux/dma-map-ops.h>
-#include <linux/dmi.h>
 #include <linux/efi.h>
 #include <linux/ima.h>
 #include <linux/init_ohci1394_dma.h>
@@ -902,7 +901,7 @@ void __init setup_arch(char **cmdline_p)
 		efi_init();
 
 	reserve_ibft_region();
-	dmi_setup();
+	x86_init.resources.dmi_setup();
 
 	/*
 	 * VMware detection requires dmi to be available, so this
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
@@ -23,6 +23,7 @@
 #include <linux/platform_device.h>
 #include <linux/io.h>
 #include <linux/psp-sev.h>
+#include <linux/dmi.h>
 #include <uapi/linux/sev-guest.h>
 
 #include <asm/init.h>
@@ -795,21 +796,6 @@ void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr
 	early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_SHARED);
 }
 
-void __init snp_prep_memory(unsigned long paddr, unsigned int sz, enum psc_op op)
-{
-	unsigned long vaddr, npages;
-
-	vaddr = (unsigned long)__va(paddr);
-	npages = PAGE_ALIGN(sz) >> PAGE_SHIFT;
-
-	if (op == SNP_PAGE_STATE_PRIVATE)
-		early_snp_set_memory_private(vaddr, paddr, npages);
-	else if (op == SNP_PAGE_STATE_SHARED)
-		early_snp_set_memory_shared(vaddr, paddr, npages);
-	else
-		WARN(1, "invalid memory op %d\n", op);
-}
-
 static unsigned long __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr,
 				       unsigned long vaddr_end, int op)
 {
@@ -2136,6 +2122,17 @@ void __head __noreturn snp_abort(void)
 	sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
 }
 
+/*
+ * SEV-SNP guests should only execute dmi_setup() if EFI_CONFIG_TABLES are
+ * enabled, as the alternative (fallback) logic for DMI probing in the legacy
+ * ROM region can cause a crash since this region is not pre-validated.
+ */
+void __init snp_dmi_setup(void)
+{
+	if (efi_enabled(EFI_CONFIG_TABLES))
+		dmi_setup();
+}
+
 static void dump_cpuid_table(void)
 {
 	const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
@@ -3,6 +3,7 @@
  *
  *  For licencing details see kernel-base/COPYING
  */
+#include <linux/dmi.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
 #include <linux/export.h>
@@ -66,6 +67,7 @@ struct x86_init_ops x86_init __initdata = {
 		.probe_roms		= probe_roms,
 		.reserve_resources	= reserve_standard_io_resources,
 		.memory_setup		= e820__memory_setup_default,
+		.dmi_setup		= dmi_setup,
 	},
 
 	.mpparse = {
diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c
@@ -26,31 +26,18 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page,
 	for (; addr < end; addr = next) {
 		pud_t *pud = pud_page + pud_index(addr);
 		pmd_t *pmd;
-		bool use_gbpage;
 
 		next = (addr & PUD_MASK) + PUD_SIZE;
 		if (next > end)
 			next = end;
 
-		/* if this is already a gbpage, this portion is already mapped */
-		if (pud_leaf(*pud))
-			continue;
-
-		/* Is using a gbpage allowed? */
-		use_gbpage = info->direct_gbpages;
-
-		/* Don't use gbpage if it maps more than the requested region. */
-		/* at the begining: */
-		use_gbpage &= ((addr & ~PUD_MASK) == 0);
-		/* ... or at the end: */
-		use_gbpage &= ((next & ~PUD_MASK) == 0);
-
-		/* Never overwrite existing mappings */
-		use_gbpage &= !pud_present(*pud);
-
-		if (use_gbpage) {
+		if (info->direct_gbpages) {
 			pud_t pudval;
 
+			if (pud_present(*pud))
+				continue;
+
+			addr &= PUD_MASK;
 			pudval = __pud((addr - info->offset) | info->page_flag);
 			set_pud(pud, pudval);
 			continue;
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
@@ -492,6 +492,24 @@ void __init sme_early_init(void)
 	 */
 	if (sev_status & MSR_AMD64_SEV_ENABLED)
 		ia32_disable();
+
+	/*
+	 * Override init functions that scan the ROM region in SEV-SNP guests,
+	 * as this memory is not pre-validated and would thus cause a crash.
+	 */
+	if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) {
+		x86_init.mpparse.find_mptable = x86_init_noop;
+		x86_init.pci.init_irq = x86_init_noop;
+		x86_init.resources.probe_roms = x86_init_noop;
+
+		/*
+		 * DMI setup behavior for SEV-SNP guests depends on
+		 * efi_enabled(EFI_CONFIG_TABLES), which hasn't been
+		 * parsed yet. snp_dmi_setup() will run after that
+		 * parsing has happened.
+		 */
+		x86_init.resources.dmi_setup = snp_dmi_setup;
+	}
 }
 
 void __init mem_encrypt_free_decrypted_mem(void)
diff --git a/arch/x86/virt/Makefile b/arch/x86/virt/Makefile
@@ -1,2 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-y	+= vmx/
+obj-y	+= svm/ vmx/

Original file line number	Diff line number	Diff line change
`@@ -2439,6 +2439,8 @@ config USE_X86_SEG_SUPPORT`
`2439`	`2439`	`# with named address spaces - see GCC PR sanitizer/111736.`
`2440`	`2440`	`#`
`2441`	`2441`	`depends on !KASAN`
	`2442`	`+ # -fsanitize=thread (KCSAN) is also incompatible.`
	`2443`	`+ depends on !KCSAN`
`2442`	`2444`
`2443`	`2445`	`config CC_HAS_SLS`
`2444`	`2446`	`def_bool $(cc-option,-mharden-sls=all)`