Merge tag 'x86-boot-2023-06-26' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 boot updates from Thomas Gleixner:
 "Initialize FPU late.

  Right now FPU is initialized very early during boot. There is no real
  requirement to do so. The only requirement is to have it done before
  alternatives are patched.

  That's done in check_bugs() which does way more than what the function
  name suggests.

  So first rename check_bugs() to arch_cpu_finalize_init() which makes
  it clear what this is about.

  Move the invocation of arch_cpu_finalize_init() earlier in
  start_kernel() as it has to be done before fork_init() which needs to
  know the FPU register buffer size.

  With those prerequisites the FPU initialization can be moved into
  arch_cpu_finalize_init(), which removes it from the early and fragile
  part of the x86 bringup"

* tag 'x86-boot-2023-06-26' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mem_encrypt: Unbreak the AMD_MEM_ENCRYPT=n build
  x86/fpu: Move FPU initialization into arch_cpu_finalize_init()
  x86/fpu: Mark init functions __init
  x86/fpu: Remove cpuinfo argument from init functions
  x86/init: Initialize signal frame size late
  init, x86: Move mem_encrypt_init() into arch_cpu_finalize_init()
  init: Invoke arch_cpu_finalize_init() earlier
  init: Remove check_bugs() leftovers
  um/cpu: Switch to arch_cpu_finalize_init()
  sparc/cpu: Switch to arch_cpu_finalize_init()
  sh/cpu: Switch to arch_cpu_finalize_init()
  mips/cpu: Switch to arch_cpu_finalize_init()
  m68k/cpu: Switch to arch_cpu_finalize_init()
  loongarch/cpu: Switch to arch_cpu_finalize_init()
  ia64/cpu: Switch to arch_cpu_finalize_init()
  ARM: cpu: Switch to arch_cpu_finalize_init()
  x86/cpu: Switch to arch_cpu_finalize_init()
  init: Provide arch_cpu_finalize_init()

10 files changed, 89 insertions, 70 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 53bab123a8ee..e8ebafabd099 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -71,6 +71,7 @@ config X86
 	select ARCH_HAS_ACPI_TABLE_UPGRADE	if ACPI
 	select ARCH_HAS_CACHE_LINE_SIZE
 	select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
+	select ARCH_HAS_CPU_FINALIZE_INIT
 	select ARCH_HAS_CURRENT_STACK_POINTER
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEBUG_VM_PGTABLE	if !X86_PAE
diff --git a/arch/x86/include/asm/bugs.h b/arch/x86/include/asm/bugs.h
index 92ae28389940..f25ca2d709d4 100644
--- a/arch/x86/include/asm/bugs.h
+++ b/arch/x86/include/asm/bugs.h
@@ -4,8 +4,6 @@
 
 #include <asm/processor.h>
 
-extern void check_bugs(void);
-
 #if defined(CONFIG_CPU_SUP_INTEL) && defined(CONFIG_X86_32)
 int ppro_with_ram_bug(void);
 #else
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index 503a577814b2..b475d9a582b8 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -109,7 +109,7 @@ extern void fpu_reset_from_exception_fixup(void);
 
 /* Boot, hotplug and resume */
 extern void fpu__init_cpu(void);
-extern void fpu__init_system(struct cpuinfo_x86 *c);
+extern void fpu__init_system(void);
 extern void fpu__init_check_bugs(void);
 extern void fpu__resume_cpu(void);
 
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index b7126701574c..7f97a8a97e24 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -17,6 +17,12 @@
 
 #include <asm/bootparam.h>
 
+#ifdef CONFIG_X86_MEM_ENCRYPT
+void __init mem_encrypt_init(void);
+#else
+static inline void mem_encrypt_init(void) { }
+#endif
+
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 
 extern u64 sme_me_mask;
@@ -87,9 +93,6 @@ static inline void mem_encrypt_free_decrypted_mem(void) { }
 
 #endif	/* CONFIG_AMD_MEM_ENCRYPT */
 
-/* Architecture __weak replacement functions */
-void __init mem_encrypt_init(void);
-
 void add_encrypt_protection_map(void);
 
 /*
diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h
index 5b1ed650b124..84eab2724875 100644
--- a/arch/x86/include/asm/sigframe.h
+++ b/arch/x86/include/asm/sigframe.h
@@ -85,6 +85,4 @@ struct rt_sigframe_x32 {
 
 #endif /* CONFIG_X86_64 */
 
-void __init init_sigframe_size(void);
-
 #endif /* _ASM_X86_SIGFRAME_H */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 182af64387d0..9e2a91830f72 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -9,7 +9,6 @@
  *	- Andrew D. Balsa (code cleanup).
  */
 #include <linux/init.h>
-#include <linux/utsname.h>
 #include <linux/cpu.h>
 #include <linux/module.h>
 #include <linux/nospec.h>
@@ -27,8 +26,6 @@
 #include <asm/msr.h>
 #include <asm/vmx.h>
 #include <asm/paravirt.h>
-#include <asm/alternative.h>
-#include <asm/set_memory.h>
 #include <asm/intel-family.h>
 #include <asm/e820/api.h>
 #include <asm/hypervisor.h>
@@ -125,21 +122,8 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
 DEFINE_STATIC_KEY_FALSE(mmio_stale_data_clear);
 EXPORT_SYMBOL_GPL(mmio_stale_data_clear);
 
-void __init check_bugs(void)
+void __init cpu_select_mitigations(void)
 {
-	identify_boot_cpu();
-
-	/*
-	 * identify_boot_cpu() initialized SMT support information, let the
-	 * core code know.
-	 */
-	cpu_smt_check_topology();
-
-	if (!IS_ENABLED(CONFIG_SMP)) {
-		pr_info("CPU: ");
-		print_cpu_info(&boot_cpu_data);
-	}
-
 	/*
 	 * Read the SPEC_CTRL MSR to account for reserved bits which may
 	 * have unknown values. AMD64_LS_CFG MSR is cached in the early AMD
@@ -176,39 +160,6 @@ void __init check_bugs(void)
 	md_clear_select_mitigation();
 	srbds_select_mitigation();
 	l1d_flush_select_mitigation();
-
-	arch_smt_update();
-
-#ifdef CONFIG_X86_32
-	/*
-	 * Check whether we are able to run this kernel safely on SMP.
-	 *
-	 * - i386 is no longer supported.
-	 * - In order to run on anything without a TSC, we need to be
-	 *   compiled for a i486.
-	 */
-	if (boot_cpu_data.x86 < 4)
-		panic("Kernel requires i486+ for 'invlpg' and other features");
-
-	init_utsname()->machine[1] =
-		'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
-	alternative_instructions();
-
-	fpu__init_check_bugs();
-#else /* CONFIG_X86_64 */
-	alternative_instructions();
-
-	/*
-	 * Make sure the first 2MB area is not mapped by huge pages
-	 * There are typically fixed size MTRRs in there and overlapping
-	 * MTRRs into large pages causes slow downs.
-	 *
-	 * Right now we don't do that with gbpages because there seems
-	 * very little benefit for that case.
-	 */
-	if (!direct_gbpages)
-		set_memory_4k((unsigned long)__va(0), 1);
-#endif
 }
 
 /*
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 80710a68ef7d..46ebdd60fd96 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -18,12 +18,16 @@
 #include <linux/init.h>
 #include <linux/kprobes.h>
 #include <linux/kgdb.h>
+#include <linux/mem_encrypt.h>
 #include <linux/smp.h>
+#include <linux/cpu.h>
 #include <linux/io.h>
 #include <linux/syscore_ops.h>
 #include <linux/pgtable.h>
 #include <linux/stackprotector.h>
+#include <linux/utsname.h>
 
+#include <asm/alternative.h>
 #include <asm/cmdline.h>
 #include <asm/perf_event.h>
 #include <asm/mmu_context.h>
@@ -59,7 +63,7 @@
 #include <asm/intel-family.h>
 #include <asm/cpu_device_id.h>
 #include <asm/uv/uv.h>
-#include <asm/sigframe.h>
+#include <asm/set_memory.h>
 #include <asm/traps.h>
 #include <asm/sev.h>
 
@@ -1600,10 +1604,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 
 	sld_setup(c);
 
-	fpu__init_system(c);
-
-	init_sigframe_size();
-
 #ifdef CONFIG_X86_32
 	/*
 	 * Regardless of whether PCID is enumerated, the SDM says
@@ -2285,8 +2285,6 @@ void cpu_init(void)
 
 	doublefault_init_cpu_tss();
 
-	fpu__init_cpu();
-
 	if (is_uv_system())
 		uv_cpu_init();
 
@@ -2302,6 +2300,7 @@ void cpu_init_secondary(void)
 	 */
 	cpu_init_exception_handling();
 	cpu_init();
+	fpu__init_cpu();
 }
 #endif
 
@@ -2362,3 +2361,69 @@ void arch_smt_update(void)
 	/* Check whether IPI broadcasting can be enabled */
 	apic_smt_update();
 }
+
+void __init arch_cpu_finalize_init(void)
+{
+	identify_boot_cpu();
+
+	/*
+	 * identify_boot_cpu() initialized SMT support information, let the
+	 * core code know.
+	 */
+	cpu_smt_check_topology();
+
+	if (!IS_ENABLED(CONFIG_SMP)) {
+		pr_info("CPU: ");
+		print_cpu_info(&boot_cpu_data);
+	}
+
+	cpu_select_mitigations();
+
+	arch_smt_update();
+
+	if (IS_ENABLED(CONFIG_X86_32)) {
+		/*
+		 * Check whether this is a real i386 which is not longer
+		 * supported and fixup the utsname.
+		 */
+		if (boot_cpu_data.x86 < 4)
+			panic("Kernel requires i486+ for 'invlpg' and other features");
+
+		init_utsname()->machine[1] =
+			'0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
+	}
+
+	/*
+	 * Must be before alternatives because it might set or clear
+	 * feature bits.
+	 */
+	fpu__init_system();
+	fpu__init_cpu();
+
+	alternative_instructions();
+
+	if (IS_ENABLED(CONFIG_X86_64)) {
+		/*
+		 * Make sure the first 2MB area is not mapped by huge pages
+		 * There are typically fixed size MTRRs in there and overlapping
+		 * MTRRs into large pages causes slow downs.
+		 *
+		 * Right now we don't do that with gbpages because there seems
+		 * very little benefit for that case.
+		 */
+		if (!direct_gbpages)
+			set_memory_4k((unsigned long)__va(0), 1);
+	} else {
+		fpu__init_check_bugs();
+	}
+
+	/*
+	 * This needs to be called before any devices perform DMA
+	 * operations that might use the SWIOTLB bounce buffers. It will
+	 * mark the bounce buffers as decrypted so that their usage will
+	 * not cause "plain-text" data to be decrypted when accessed. It
+	 * must be called after late_time_init() so that Hyper-V x86/x64
+	 * hypercalls work when the SWIOTLB bounce buffers are decrypted.
+	 */
+	mem_encrypt_init();
+}
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index f97b0fe13da8..1c44630d4789 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -79,6 +79,7 @@ extern void detect_ht(struct cpuinfo_x86 *c);
 extern void check_null_seg_clears_base(struct cpuinfo_x86 *c);
 
 unsigned int aperfmperf_get_khz(int cpu);
+void cpu_select_mitigations(void);
 
 extern void x86_spec_ctrl_setup_ap(void);
 extern void update_srbds_msr(void);
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 851eb13edc01..998a08f17e33 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -53,7 +53,7 @@ void fpu__init_cpu(void)
 	fpu__init_cpu_xstate();
 }
 
-static bool fpu__probe_without_cpuid(void)
+static bool __init fpu__probe_without_cpuid(void)
 {
 	unsigned long cr0;
 	u16 fsw, fcw;
@@ -71,7 +71,7 @@ static bool fpu__probe_without_cpuid(void)
 	return fsw == 0 && (fcw & 0x103f) == 0x003f;
 }
 
-static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
+static void __init fpu__init_system_early_generic(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_CPUID) &&
 	    !test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) {
@@ -211,10 +211,10 @@ static void __init fpu__init_system_xstate_size_legacy(void)
  * Called on the boot CPU once per system bootup, to set up the initial
  * FPU state that is later cloned into all processes:
  */
-void __init fpu__init_system(struct cpuinfo_x86 *c)
+void __init fpu__init_system(void)
 {
 	fpstate_reset(&current->thread.fpu);
-	fpu__init_system_early_generic(c);
+	fpu__init_system_early_generic();
 
 	/*
 	 * The FPU has to be operational for some of the
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 004cb30b7419..cfeec3ee877e 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -182,7 +182,7 @@ get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size,
 static unsigned long __ro_after_init max_frame_size;
 static unsigned int __ro_after_init fpu_default_state_size;
 
-void __init init_sigframe_size(void)
+static int __init init_sigframe_size(void)
 {
 	fpu_default_state_size = fpu__get_fpstate_size();
 
@@ -194,7 +194,9 @@ void __init init_sigframe_size(void)
 	max_frame_size = round_up(max_frame_size, FRAME_ALIGNMENT);
 
 	pr_info("max sigframe size: %lu\n", max_frame_size);
+	return 0;
 }
+early_initcall(init_sigframe_size);
 
 unsigned long get_sigframe_size(void)
 {