Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Ingo Molnar:
 "Misc fixes:

   - fix the s2ram regression related to confusion around segment
     register restoration, plus related cleanups that make the code more
     robust

   - a guess-unwinder Kconfig dependency fix

   - an isoimage build target fix for certain tool chain combinations

   - instruction decoder opcode map fixes+updates, and the syncing of
     the kernel decoder headers to the objtool headers

   - a kmmio tracing fix

   - two 5-level paging related fixes

   - a topology enumeration fix on certain SMP systems"

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  objtool: Resync objtool's instruction decoder source code copy with the kernel's latest version
  x86/decoder: Fix and update the opcodes map
  x86/power: Make restore_processor_context() sane
  x86/power/32: Move SYSENTER MSR restoration to fix_processor_context()
  x86/power/64: Use struct desc_ptr for the IDT in struct saved_context
  x86/unwinder/guess: Prevent using CONFIG_UNWINDER_GUESS=y with CONFIG_STACKDEPOT=y
  x86/build: Don't verify mtools configuration file for isoimage
  x86/mm/kmmio: Fix mmiotrace for page unaligned addresses
  x86/boot/compressed/64: Print error if 5-level paging is not supported
  x86/boot/compressed/64: Detect and handle 5-level paging at boot-time
  x86/smpboot: Do not use smp_num_siblings in __max_logical_packages calculation

arch/x86/Kconfig.debug

@@ -400,6 +400,7 @@ config UNWINDER_FRAME_POINTER
 config UNWINDER_GUESS
 	bool "Guess unwinder"
 	depends on EXPERT
+	depends on !STACKDEPOT
 	---help---
 	  This option enables the "guess" unwinder for unwinding kernel stack
 	  traces.  It scans the stack and reports every kernel text address it

arch/x86/boot/compressed/Makefile

@@ -80,6 +80,7 @@ vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o
 ifdef CONFIG_X86_64
 	vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/pagetable.o
 	vmlinux-objs-y += $(obj)/mem_encrypt.o
+	vmlinux-objs-y += $(obj)/pgtable_64.o
 endif
 
 $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone

arch/x86/boot/compressed/head_64.S

@@ -305,10 +305,18 @@ ENTRY(startup_64)
 	leaq	boot_stack_end(%rbx), %rsp
 
 #ifdef CONFIG_X86_5LEVEL
-	/* Check if 5-level paging has already enabled */
-	movq	%cr4, %rax
-	testl	$X86_CR4_LA57, %eax
-	jnz	lvl5
+	/*
+	 * Check if we need to enable 5-level paging.
+	 * RSI holds real mode data and need to be preserved across
+	 * a function call.
+	 */
+	pushq	%rsi
+	call	l5_paging_required
+	popq	%rsi
+
+	/* If l5_paging_required() returned zero, we're done here. */
+	cmpq	$0, %rax
+	je	lvl5
 
 	/*
 	 * At this point we are in long mode with 4-level paging enabled,

arch/x86/boot/compressed/misc.c

@@ -169,6 +169,16 @@ void __puthex(unsigned long value)
 	}
 }
 
+static bool l5_supported(void)
+{
+	/* Check if leaf 7 is supported. */
+	if (native_cpuid_eax(0) < 7)
+		return 0;
+
+	/* Check if la57 is supported. */
+	return native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31));
+}
+
 #if CONFIG_X86_NEED_RELOCS
 static void handle_relocations(void *output, unsigned long output_len,
 			       unsigned long virt_addr)
@@ -362,6 +372,12 @@ asmlinkage __visible void *extract_kernel(void *rmode, memptr heap,
 	console_init();
 	debug_putstr("early console in extract_kernel\n");
 
+	if (IS_ENABLED(CONFIG_X86_5LEVEL) && !l5_supported()) {
+		error("This linux kernel as configured requires 5-level paging\n"
+			"This CPU does not support the required 'cr4.la57' feature\n"
+			"Unable to boot - please use a kernel appropriate for your CPU\n");
+	}
+
 	free_mem_ptr     = heap;	/* Heap */
 	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
 

arch/x86/boot/compressed/pgtable_64.c

+#include <asm/processor.h>
+
+/*
+ * __force_order is used by special_insns.h asm code to force instruction
+ * serialization.
+ *
+ * It is not referenced from the code, but GCC < 5 with -fPIE would fail
+ * due to an undefined symbol. Define it to make these ancient GCCs work.
+ */
+unsigned long __force_order;
+
+int l5_paging_required(void)
+{
+	/* Check if leaf 7 is supported. */
+
+	if (native_cpuid_eax(0) < 7)
+		return 0;
+
+	/* Check if la57 is supported. */
+	if (!(native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31))))
+		return 0;
+
+	/* Check if 5-level paging has already been enabled. */
+	if (native_read_cr4() & X86_CR4_LA57)
+		return 0;
+
+	return 1;
+}

arch/x86/boot/genimage.sh

@@ -44,9 +44,9 @@ FDINITRD=$6
 
 # Make sure the files actually exist
 verify "$FBZIMAGE"
-verify "$MTOOLSRC"
 
 genbzdisk() {
+	verify "$MTOOLSRC"
 	mformat a:
 	syslinux $FIMAGE
 	echo "$KCMDLINE" | mcopy - a:syslinux.cfg
@@ -57,6 +57,7 @@ genbzdisk() {
 }
 
 genfdimage144() {
+	verify "$MTOOLSRC"
 	dd if=/dev/zero of=$FIMAGE bs=1024 count=1440 2> /dev/null
 	mformat v:
 	syslinux $FIMAGE
@@ -68,6 +69,7 @@ genfdimage144() {
 }
 
 genfdimage288() {
+	verify "$MTOOLSRC"
 	dd if=/dev/zero of=$FIMAGE bs=1024 count=2880 2> /dev/null
 	mformat w:
 	syslinux $FIMAGE

arch/x86/include/asm/suspend_32.h

@@ -12,7 +12,13 @@
 
 /* image of the saved processor state */
 struct saved_context {
-	u16 es, fs, gs, ss;
+	/*
+	 * On x86_32, all segment registers, with the possible exception of
+	 * gs, are saved at kernel entry in pt_regs.
+	 */
+#ifdef CONFIG_X86_32_LAZY_GS
+	u16 gs;
+#endif
 	unsigned long cr0, cr2, cr3, cr4;
 	u64 misc_enable;
 	bool misc_enable_saved;

arch/x86/include/asm/suspend_64.h

@@ -20,8 +20,20 @@
  */
 struct saved_context {
 	struct pt_regs regs;
-	u16 ds, es, fs, gs, ss;
-	unsigned long gs_base, gs_kernel_base, fs_base;
+
+	/*
+	 * User CS and SS are saved in current_pt_regs().  The rest of the
+	 * segment selectors need to be saved and restored here.
+	 */
+	u16 ds, es, fs, gs;
+
+	/*
+	 * Usermode FSBASE and GSBASE may not match the fs and gs selectors,
+	 * so we save them separately.  We save the kernelmode GSBASE to
+	 * restore percpu access after resume.
+	 */
+	unsigned long kernelmode_gs_base, usermode_gs_base, fs_base;
+
 	unsigned long cr0, cr2, cr3, cr4, cr8;
 	u64 misc_enable;
 	bool misc_enable_saved;
@@ -30,8 +42,7 @@ struct saved_context {
 	u16 gdt_pad; /* Unused */
 	struct desc_ptr gdt_desc;
 	u16 idt_pad;
-	u16 idt_limit;
-	unsigned long idt_base;
+	struct desc_ptr idt;
 	u16 ldt;
 	u16 tss;
 	unsigned long tr;

arch/x86/kernel/smpboot.c

@@ -106,7 +106,7 @@ EXPORT_SYMBOL(__max_logical_packages);
 static unsigned int logical_packages __read_mostly;
 
 /* Maximum number of SMT threads on any online core */
-int __max_smt_threads __read_mostly;
+int __read_mostly __max_smt_threads = 1;
 
 /* Flag to indicate if a complete sched domain rebuild is required */
 bool x86_topology_update;
@@ -1304,7 +1304,7 @@ void __init native_smp_cpus_done(unsigned int max_cpus)
 	 * Today neither Intel nor AMD support heterogenous systems so
 	 * extrapolate the boot cpu's data to all packages.
 	 */
-	ncpus = cpu_data(0).booted_cores * smp_num_siblings;
+	ncpus = cpu_data(0).booted_cores * topology_max_smt_threads();
 	__max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus);
 	pr_info("Max logical packages: %u\n", __max_logical_packages);
 

arch/x86/lib/x86-opcode-map.txt

@@ -607,7 +607,7 @@ fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1)
 fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1)
 fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1)
 fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1)
-ff:
+ff: UD0
 EndTable
 
 Table: 3-byte opcode 1 (0x0f 0x38)
@@ -717,7 +717,7 @@ AVXcode: 2
 7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
 7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
 80: INVEPT Gy,Mdq (66)
-81: INVPID Gy,Mdq (66)
+81: INVVPID Gy,Mdq (66)
 82: INVPCID Gy,Mdq (66)
 83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
 88: vexpandps/d Vpd,Wpd (66),(ev)
@@ -970,6 +970,15 @@ GrpTable: Grp9
 EndTable
 
 GrpTable: Grp10
+# all are UD1
+0: UD1
+1: UD1
+2: UD1
+3: UD1
+4: UD1
+5: UD1
+6: UD1
+7: UD1
 EndTable
 
 # Grp11A and Grp11B are expressed as Grp11 in Intel SDM

arch/x86/mm/ioremap.c

@@ -404,11 +404,11 @@ void iounmap(volatile void __iomem *addr)
 		return;
 	}
 
+	mmiotrace_iounmap(addr);
+
 	addr = (volatile void __iomem *)
 		(PAGE_MASK & (unsigned long __force)addr);
 
-	mmiotrace_iounmap(addr);
-
 	/* Use the vm area unlocked, assuming the caller
 	   ensures there isn't another iounmap for the same address
 	   in parallel. Reuse of the virtual address is prevented by

arch/x86/mm/kmmio.c

@@ -435,17 +435,18 @@ int register_kmmio_probe(struct kmmio_probe *p)
 	unsigned long flags;
 	int ret = 0;
 	unsigned long size = 0;
+	unsigned long addr = p->addr & PAGE_MASK;
 	const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
 	unsigned int l;
 	pte_t *pte;
 
 	spin_lock_irqsave(&kmmio_lock, flags);
-	if (get_kmmio_probe(p->addr)) {
+	if (get_kmmio_probe(addr)) {
 		ret = -EEXIST;
 		goto out;
 	}
 
-	pte = lookup_address(p->addr, &l);
+	pte = lookup_address(addr, &l);
 	if (!pte) {
 		ret = -EINVAL;
 		goto out;
@@ -454,7 +455,7 @@ int register_kmmio_probe(struct kmmio_probe *p)
 	kmmio_count++;
 	list_add_rcu(&p->list, &kmmio_probes);
 	while (size < size_lim) {
-		if (add_kmmio_fault_page(p->addr + size))
+		if (add_kmmio_fault_page(addr + size))
 			pr_err("Unable to set page fault.\n");
 		size += page_level_size(l);
 	}
@@ -528,19 +529,20 @@ void unregister_kmmio_probe(struct kmmio_probe *p)
 {
 	unsigned long flags;
 	unsigned long size = 0;
+	unsigned long addr = p->addr & PAGE_MASK;
 	const unsigned long size_lim = p->len + (p->addr & ~PAGE_MASK);
 	struct kmmio_fault_page *release_list = NULL;
 	struct kmmio_delayed_release *drelease;
 	unsigned int l;
 	pte_t *pte;
 
-	pte = lookup_address(p->addr, &l);
+	pte = lookup_address(addr, &l);
 	if (!pte)
 		return;
 
 	spin_lock_irqsave(&kmmio_lock, flags);
 	while (size < size_lim) {
-		release_kmmio_fault_page(p->addr + size, &release_list);
+		release_kmmio_fault_page(addr + size, &release_list);
 		size += page_level_size(l);
 	}
 	list_del_rcu(&p->list);

arch/x86/power/cpu.c

@@ -82,12 +82,8 @@ static void __save_processor_state(struct saved_context *ctxt)
 	/*
 	 * descriptor tables
 	 */
-#ifdef CONFIG_X86_32
 	store_idt(&ctxt->idt);
-#else
-/* CONFIG_X86_64 */
-	store_idt((struct desc_ptr *)&ctxt->idt_limit);
-#endif
+
 	/*
 	 * We save it here, but restore it only in the hibernate case.
 	 * For ACPI S3 resume, this is loaded via 'early_gdt_desc' in 64-bit
@@ -103,22 +99,18 @@ static void __save_processor_state(struct saved_context *ctxt)
 	/*
 	 * segment registers
 	 */
-#ifdef CONFIG_X86_32
-	savesegment(es, ctxt->es);
-	savesegment(fs, ctxt->fs);
+#ifdef CONFIG_X86_32_LAZY_GS
 	savesegment(gs, ctxt->gs);
-	savesegment(ss, ctxt->ss);
-#else
-/* CONFIG_X86_64 */
-	asm volatile ("movw %%ds, %0" : "=m" (ctxt->ds));
-	asm volatile ("movw %%es, %0" : "=m" (ctxt->es));
-	asm volatile ("movw %%fs, %0" : "=m" (ctxt->fs));
-	asm volatile ("movw %%gs, %0" : "=m" (ctxt->gs));
-	asm volatile ("movw %%ss, %0" : "=m" (ctxt->ss));
+#endif
+#ifdef CONFIG_X86_64
+	savesegment(gs, ctxt->gs);
+	savesegment(fs, ctxt->fs);
+	savesegment(ds, ctxt->ds);
+	savesegment(es, ctxt->es);
 
 	rdmsrl(MSR_FS_BASE, ctxt->fs_base);
-	rdmsrl(MSR_GS_BASE, ctxt->gs_base);
-	rdmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
+	rdmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base);
+	rdmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base);
 	mtrr_save_fixed_ranges(NULL);
 
 	rdmsrl(MSR_EFER, ctxt->efer);
@@ -178,6 +170,9 @@ static void fix_processor_context(void)
 	write_gdt_entry(desc, GDT_ENTRY_TSS, &tss, DESC_TSS);
 
 	syscall_init();				/* This sets MSR_*STAR and related */
+#else
+	if (boot_cpu_has(X86_FEATURE_SEP))
+		enable_sep_cpu();
 #endif
 	load_TR_desc();				/* This does ltr */
 	load_mm_ldt(current->active_mm);	/* This does lldt */
@@ -190,9 +185,12 @@ static void fix_processor_context(void)
 }
 
 /**
- *	__restore_processor_state - restore the contents of CPU registers saved
- *		by __save_processor_state()
- *	@ctxt - structure to load the registers contents from
+ * __restore_processor_state - restore the contents of CPU registers saved
+ *                             by __save_processor_state()
+ * @ctxt - structure to load the registers contents from
+ *
+ * The asm code that gets us here will have restored a usable GDT, although
+ * it will be pointing to the wrong alias.
  */
 static void notrace __restore_processor_state(struct saved_context *ctxt)
 {
@@ -215,57 +213,50 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	write_cr2(ctxt->cr2);
 	write_cr0(ctxt->cr0);
 
+	/* Restore the IDT. */
+	load_idt(&ctxt->idt);
+
 	/*
-	 * now restore the descriptor tables to their proper values
-	 * ltr is done i fix_processor_context().
+	 * Just in case the asm code got us here with the SS, DS, or ES
+	 * out of sync with the GDT, update them.
 	 */
-#ifdef CONFIG_X86_32
-	load_idt(&ctxt->idt);
-#else
-/* CONFIG_X86_64 */
-	load_idt((const struct desc_ptr *)&ctxt->idt_limit);
-#endif
+	loadsegment(ss, __KERNEL_DS);
+	loadsegment(ds, __USER_DS);
+	loadsegment(es, __USER_DS);
 
-#ifdef CONFIG_X86_64
 	/*
-	 * We need GSBASE restored before percpu access can work.
-	 * percpu access can happen in exception handlers or in complicated
-	 * helpers like load_gs_index().
+	 * Restore percpu access.  Percpu access can happen in exception
+	 * handlers or in complicated helpers like load_gs_index().
 	 */
-	wrmsrl(MSR_GS_BASE, ctxt->gs_base);
+#ifdef CONFIG_X86_64
+	wrmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base);
+#else
+	loadsegment(fs, __KERNEL_PERCPU);
+	loadsegment(gs, __KERNEL_STACK_CANARY);
 #endif
 
+	/* Restore the TSS, RO GDT, LDT, and usermode-relevant MSRs. */
 	fix_processor_context();
 
 	/*
-	 * Restore segment registers.  This happens after restoring the GDT
-	 * and LDT, which happen in fix_processor_context().
+	 * Now that we have descriptor tables fully restored and working
+	 * exception handling, restore the usermode segments.
 	 */
-#ifdef CONFIG_X86_32
+#ifdef CONFIG_X86_64
+	loadsegment(ds, ctxt->es);
 	loadsegment(es, ctxt->es);
 	loadsegment(fs, ctxt->fs);
-	loadsegment(gs, ctxt->gs);
-	loadsegment(ss, ctxt->ss);
-
-	/*
-	 * sysenter MSRs
-	 */
-	if (boot_cpu_has(X86_FEATURE_SEP))
-		enable_sep_cpu();
-#else
-/* CONFIG_X86_64 */
-	asm volatile ("movw %0, %%ds" :: "r" (ctxt->ds));
-	asm volatile ("movw %0, %%es" :: "r" (ctxt->es));
-	asm volatile ("movw %0, %%fs" :: "r" (ctxt->fs));
 	load_gs_index(ctxt->gs);
-	asm volatile ("movw %0, %%ss" :: "r" (ctxt->ss));
 
 	/*
-	 * Restore FSBASE and user GSBASE after reloading the respective
-	 * segment selectors.
+	 * Restore FSBASE and GSBASE after restoring the selectors, since
+	 * restoring the selectors clobbers the bases.  Keep in mind
+	 * that MSR_KERNEL_GS_BASE is horribly misnamed.
 	 */
 	wrmsrl(MSR_FS_BASE, ctxt->fs_base);
-	wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
+	wrmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base);
+#elif defined(CONFIG_X86_32_LAZY_GS)
+	loadsegment(gs, ctxt->gs);
 #endif
 
 	do_fpu_end();

tools/objtool/arch/x86/lib/x86-opcode-map.txt

@@ -607,7 +607,7 @@ fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1)
 fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1)
 fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1)
 fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1)
-ff:
+ff: UD0
 EndTable
 
 Table: 3-byte opcode 1 (0x0f 0x38)
@@ -717,7 +717,7 @@ AVXcode: 2
 7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
 7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
 80: INVEPT Gy,Mdq (66)
-81: INVPID Gy,Mdq (66)
+81: INVVPID Gy,Mdq (66)
 82: INVPCID Gy,Mdq (66)
 83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
 88: vexpandps/d Vpd,Wpd (66),(ev)
@@ -896,7 +896,7 @@ EndTable
 
 GrpTable: Grp3_1
 0: TEST Eb,Ib
-1:
+1: TEST Eb,Ib
 2: NOT Eb
 3: NEG Eb
 4: MUL AL,Eb
@@ -970,6 +970,15 @@ GrpTable: Grp9
 EndTable
 
 GrpTable: Grp10
+# all are UD1
+0: UD1
+1: UD1
+2: UD1
+3: UD1
+4: UD1
+5: UD1
+6: UD1
+7: UD1
 EndTable
 
 # Grp11A and Grp11B are expressed as Grp11 in Intel SDM

tools/perf/util/intel-pt-decoder/x86-opcode-map.txt

@@ -607,7 +607,7 @@ fb: psubq Pq,Qq | vpsubq Vx,Hx,Wx (66),(v1)
 fc: paddb Pq,Qq | vpaddb Vx,Hx,Wx (66),(v1)
 fd: paddw Pq,Qq | vpaddw Vx,Hx,Wx (66),(v1)
 fe: paddd Pq,Qq | vpaddd Vx,Hx,Wx (66),(v1)
-ff:
+ff: UD0
 EndTable
 
 Table: 3-byte opcode 1 (0x0f 0x38)
@@ -717,7 +717,7 @@ AVXcode: 2
 7e: vpermt2d/q Vx,Hx,Wx (66),(ev)
 7f: vpermt2ps/d Vx,Hx,Wx (66),(ev)
 80: INVEPT Gy,Mdq (66)
-81: INVPID Gy,Mdq (66)
+81: INVVPID Gy,Mdq (66)
 82: INVPCID Gy,Mdq (66)
 83: vpmultishiftqb Vx,Hx,Wx (66),(ev)
 88: vexpandps/d Vpd,Wpd (66),(ev)
@@ -970,6 +970,15 @@ GrpTable: Grp9
 EndTable
 
 GrpTable: Grp10
+# all are UD1
+0: UD1
+1: UD1
+2: UD1
+3: UD1
+4: UD1
+5: UD1
+6: UD1
+7: UD1
 EndTable
 
 # Grp11A and Grp11B are expressed as Grp11 in Intel SDM