Merge tag 'x86-boot-2024-05-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 boot updates from Ingo Molnar:

 - Move the kernel cmdline setup earlier in the boot process (again),
   to address a split_lock_detect= boot parameter bug

 - Ignore relocations in .notes sections

 - Simplify boot stack setup

 - Re-introduce a bootloader quirk wrt CR4 handling

 - Miscellaneous cleanups & fixes

* tag 'x86-boot-2024-05-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/boot/64: Clear most of CR4 in startup_64(), except PAE, MCE and LA57
  x86/boot: Move kernel cmdline setup earlier in the boot process (again)
  x86/build: Clean up arch/x86/tools/relocs.c a bit
  x86/boot: Ignore relocations in .notes sections in walk_relocs() too
  x86: Rename __{start,end}_init_task to __{start,end}_init_stack
  x86/boot: Simplify boot stack setup

arch/x86/boot/compressed/head_64.S

@@ -398,6 +398,11 @@ SYM_CODE_START(startup_64)
 	call	sev_enable
 #endif
 
+	/* Preserve only the CR4 bits that must be preserved, and clear the rest */
+	movq	%cr4, %rax
+	andl	$(X86_CR4_PAE | X86_CR4_MCE | X86_CR4_LA57), %eax
+	movq	%rax, %cr4
+
 	/*
 	 * configure_5level_paging() updates the number of paging levels using
 	 * a trampoline in 32-bit addressable memory if the current number does

arch/x86/include/asm/processor.h

@@ -635,12 +635,10 @@ static __always_inline void prefetchw(const void *x)
 #define KSTK_ESP(task)		(task_pt_regs(task)->sp)
 
 #else
-extern unsigned long __end_init_task[];
+extern unsigned long __top_init_kernel_stack[];
 
 #define INIT_THREAD {							\
-	.sp	= (unsigned long)&__end_init_task -			\
-		  TOP_OF_KERNEL_STACK_PADDING -				\
-		  sizeof(struct pt_regs),				\
+	.sp	= (unsigned long)&__top_init_kernel_stack,		\
 }
 
 extern unsigned long KSTK_ESP(struct task_struct *task);

arch/x86/kernel/head_32.S

@@ -44,9 +44,6 @@
 #define X86_CAPABILITY	new_cpu_data+CPUINFO_x86_capability
 #define X86_VENDOR_ID	new_cpu_data+CPUINFO_x86_vendor_id
 
-
-#define SIZEOF_PTREGS 17*4
-
 /*
  * Worst-case size of the kernel mapping we need to make:
  * a relocatable kernel can live anywhere in lowmem, so we need to be able
@@ -488,13 +485,7 @@ SYM_DATA_END(initial_page_table)
 
 .data
 .balign 4
-/*
- * The SIZEOF_PTREGS gap is a convention which helps the in-kernel unwinder
- * reliably detect the end of the stack.
- */
-SYM_DATA(initial_stack,
-		.long init_thread_union + THREAD_SIZE -
-		SIZEOF_PTREGS - TOP_OF_KERNEL_STACK_PADDING)
+SYM_DATA(initial_stack, .long __top_init_kernel_stack)
 
 __INITRODATA
 int_msg:

arch/x86/kernel/head_64.S

@@ -66,7 +66,7 @@ SYM_CODE_START_NOALIGN(startup_64)
 	mov	%rsi, %r15
 
 	/* Set up the stack for verify_cpu() */
-	leaq	(__end_init_task - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE)(%rip), %rsp
+	leaq	__top_init_kernel_stack(%rip), %rsp
 
 	/* Setup GSBASE to allow stack canary access for C code */
 	movl	$MSR_GS_BASE, %ecx

arch/x86/kernel/setup.c

@@ -753,6 +753,22 @@ void __init setup_arch(char **cmdline_p)
 	boot_cpu_data.x86_phys_bits = MAX_PHYSMEM_BITS;
 #endif
 
+#ifdef CONFIG_CMDLINE_BOOL
+#ifdef CONFIG_CMDLINE_OVERRIDE
+	strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+#else
+	if (builtin_cmdline[0]) {
+		/* append boot loader cmdline to builtin */
+		strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
+		strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
+		strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+	}
+#endif
+#endif
+
+	strscpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
+	*cmdline_p = command_line;
+
 	/*
 	 * If we have OLPC OFW, we might end up relocating the fixmap due to
 	 * reserve_top(), so do this before touching the ioremap area.
@@ -832,22 +848,6 @@ void __init setup_arch(char **cmdline_p)
 	bss_resource.start = __pa_symbol(__bss_start);
 	bss_resource.end = __pa_symbol(__bss_stop)-1;
 
-#ifdef CONFIG_CMDLINE_BOOL
-#ifdef CONFIG_CMDLINE_OVERRIDE
-	strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
-#else
-	if (builtin_cmdline[0]) {
-		/* append boot loader cmdline to builtin */
-		strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
-		strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
-		strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
-	}
-#endif
-#endif
-
-	strscpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
-	*cmdline_p = command_line;
-
 	/*
 	 * x86_configure_nx() is called before parse_early_param() to detect
 	 * whether hardware doesn't support NX (so that the early EHCI debug

arch/x86/kernel/vmlinux.lds.S

@@ -172,6 +172,9 @@ SECTIONS
 		/* init_task */
 		INIT_TASK_DATA(THREAD_SIZE)
 
+		/* equivalent to task_pt_regs(&init_task) */
+		__top_init_kernel_stack = __end_init_stack - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE;
+
 #ifdef CONFIG_X86_32
 		/* 32 bit has nosave before _edata */
 		NOSAVE_DATA

arch/x86/xen/xen-head.S

@@ -49,7 +49,7 @@ SYM_CODE_START(startup_xen)
 	ANNOTATE_NOENDBR
 	cld
 
-	leaq	(__end_init_task - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE)(%rip), %rsp
+	leaq	__top_init_kernel_stack(%rip), %rsp
 
 	/* Set up %gs.
 	 *

include/asm-generic/vmlinux.lds.h

@@ -399,13 +399,13 @@
 
 #define INIT_TASK_DATA(align)						\
 	. = ALIGN(align);						\
-	__start_init_task = .;						\
+	__start_init_stack = .;						\
 	init_thread_union = .;						\
 	init_stack = .;							\
 	KEEP(*(.data..init_task))					\
 	KEEP(*(.data..init_thread_info))				\
-	. = __start_init_task + THREAD_SIZE;				\
-	__end_init_task = .;
+	. = __start_init_stack + THREAD_SIZE;				\
+	__end_init_stack = .;
 
 #define JUMP_TABLE_DATA							\
 	. = ALIGN(8);							\