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

Pull x86 boot updates from Ingo Molnar:
 "The main changes were:

   - Extend the boot protocol to allow future extensions without hitting
     the setup_header size limit.

   - Add quirk to devicetree systems to disable the RTC unless it's
     listed as a supported device.

   - Fix ld.lld linker pedantry"

* 'x86-boot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/boot: Introduce setup_indirect
  x86/boot: Introduce kernel_info.setup_type_max
  x86/boot: Introduce kernel_info
  x86/init: Allow DT configured systems to disable RTC at boot time
  x86/realmode: Explicitly set entry point via ENTRY in linker script

Documentation/x86/boot.rst

@@ -68,8 +68,25 @@ Protocol 2.12	(Kernel 3.8) Added the xloadflags field and extension fields
 Protocol 2.13	(Kernel 3.14) Support 32- and 64-bit flags being set in
 		xloadflags to support booting a 64-bit kernel from 32-bit
 		EFI
+
+Protocol 2.14:	BURNT BY INCORRECT COMMIT ae7e1238e68f2a472a125673ab506d49158c1889
+		(x86/boot: Add ACPI RSDP address to setup_header)
+		DO NOT USE!!! ASSUME SAME AS 2.13.
+
+Protocol 2.15:	(Kernel 5.5) Added the kernel_info and kernel_info.setup_type_max.
 =============	============================================================
 
+.. note::
+     The protocol version number should be changed only if the setup header
+     is changed. There is no need to update the version number if boot_params
+     or kernel_info are changed. Additionally, it is recommended to use
+     xloadflags (in this case the protocol version number should not be
+     updated either) or kernel_info to communicate supported Linux kernel
+     features to the boot loader. Due to very limited space available in
+     the original setup header every update to it should be considered
+     with great care. Starting from the protocol 2.15 the primary way to
+     communicate things to the boot loader is the kernel_info.
+
 
 Memory Layout
 =============
@@ -207,6 +224,7 @@ Offset/Size	Proto		Name			Meaning
 0258/8		2.10+		pref_address		Preferred loading address
 0260/4		2.10+		init_size		Linear memory required during initialization
 0264/4		2.11+		handover_offset		Offset of handover entry point
+0268/4		2.15+		kernel_info_offset	Offset of the kernel_info
 ===========	========	=====================	============================================
 
 .. note::
@@ -809,6 +827,47 @@ Protocol:	2.09+
   sure to consider the case where the linked list already contains
   entries.
 
+  The setup_data is a bit awkward to use for extremely large data objects,
+  both because the setup_data header has to be adjacent to the data object
+  and because it has a 32-bit length field. However, it is important that
+  intermediate stages of the boot process have a way to identify which
+  chunks of memory are occupied by kernel data.
+
+  Thus setup_indirect struct and SETUP_INDIRECT type were introduced in
+  protocol 2.15.
+
+  struct setup_indirect {
+    __u32 type;
+    __u32 reserved;  /* Reserved, must be set to zero. */
+    __u64 len;
+    __u64 addr;
+  };
+
+  The type member is a SETUP_INDIRECT | SETUP_* type. However, it cannot be
+  SETUP_INDIRECT itself since making the setup_indirect a tree structure
+  could require a lot of stack space in something that needs to parse it
+  and stack space can be limited in boot contexts.
+
+  Let's give an example how to point to SETUP_E820_EXT data using setup_indirect.
+  In this case setup_data and setup_indirect will look like this:
+
+  struct setup_data {
+    __u64 next = 0 or <addr_of_next_setup_data_struct>;
+    __u32 type = SETUP_INDIRECT;
+    __u32 len = sizeof(setup_data);
+    __u8 data[sizeof(setup_indirect)] = struct setup_indirect {
+      __u32 type = SETUP_INDIRECT | SETUP_E820_EXT;
+      __u32 reserved = 0;
+      __u64 len = <len_of_SETUP_E820_EXT_data>;
+      __u64 addr = <addr_of_SETUP_E820_EXT_data>;
+    }
+  }
+
+.. note::
+     SETUP_INDIRECT | SETUP_NONE objects cannot be properly distinguished
+     from SETUP_INDIRECT itself. So, this kind of objects cannot be provided
+     by the bootloaders.
+
 ============	============
 Field name:	pref_address
 Type:		read (reloc)
@@ -855,6 +914,121 @@ Offset/size:	0x264/4
 
   See EFI HANDOVER PROTOCOL below for more details.
 
+============	==================
+Field name:	kernel_info_offset
+Type:		read
+Offset/size:	0x268/4
+Protocol:	2.15+
+============	==================
+
+  This field is the offset from the beginning of the kernel image to the
+  kernel_info. The kernel_info structure is embedded in the Linux image
+  in the uncompressed protected mode region.
+
+
+The kernel_info
+===============
+
+The relationships between the headers are analogous to the various data
+sections:
+
+  setup_header = .data
+  boot_params/setup_data = .bss
+
+What is missing from the above list? That's right:
+
+  kernel_info = .rodata
+
+We have been (ab)using .data for things that could go into .rodata or .bss for
+a long time, for lack of alternatives and -- especially early on -- inertia.
+Also, the BIOS stub is responsible for creating boot_params, so it isn't
+available to a BIOS-based loader (setup_data is, though).
+
+setup_header is permanently limited to 144 bytes due to the reach of the
+2-byte jump field, which doubles as a length field for the structure, combined
+with the size of the "hole" in struct boot_params that a protected-mode loader
+or the BIOS stub has to copy it into. It is currently 119 bytes long, which
+leaves us with 25 very precious bytes. This isn't something that can be fixed
+without revising the boot protocol entirely, breaking backwards compatibility.
+
+boot_params proper is limited to 4096 bytes, but can be arbitrarily extended
+by adding setup_data entries. It cannot be used to communicate properties of
+the kernel image, because it is .bss and has no image-provided content.
+
+kernel_info solves this by providing an extensible place for information about
+the kernel image. It is readonly, because the kernel cannot rely on a
+bootloader copying its contents anywhere, but that is OK; if it becomes
+necessary it can still contain data items that an enabled bootloader would be
+expected to copy into a setup_data chunk.
+
+All kernel_info data should be part of this structure. Fixed size data have to
+be put before kernel_info_var_len_data label. Variable size data have to be put
+after kernel_info_var_len_data label. Each chunk of variable size data has to
+be prefixed with header/magic and its size, e.g.:
+
+  kernel_info:
+          .ascii  "LToP"          /* Header, Linux top (structure). */
+          .long   kernel_info_var_len_data - kernel_info
+          .long   kernel_info_end - kernel_info
+          .long   0x01234567      /* Some fixed size data for the bootloaders. */
+  kernel_info_var_len_data:
+  example_struct:                 /* Some variable size data for the bootloaders. */
+          .ascii  "0123"          /* Header/Magic. */
+          .long   example_struct_end - example_struct
+          .ascii  "Struct"
+          .long   0x89012345
+  example_struct_end:
+  example_strings:                /* Some variable size data for the bootloaders. */
+          .ascii  "ABCD"          /* Header/Magic. */
+          .long   example_strings_end - example_strings
+          .asciz  "String_0"
+          .asciz  "String_1"
+  example_strings_end:
+  kernel_info_end:
+
+This way the kernel_info is self-contained blob.
+
+.. note::
+     Each variable size data header/magic can be any 4-character string,
+     without \0 at the end of the string, which does not collide with
+     existing variable length data headers/magics.
+
+
+Details of the kernel_info Fields
+=================================
+
+============	========
+Field name:	header
+Offset/size:	0x0000/4
+============	========
+
+  Contains the magic number "LToP" (0x506f544c).
+
+============	========
+Field name:	size
+Offset/size:	0x0004/4
+============	========
+
+  This field contains the size of the kernel_info including kernel_info.header.
+  It does not count kernel_info.kernel_info_var_len_data size. This field should be
+  used by the bootloaders to detect supported fixed size fields in the kernel_info
+  and beginning of kernel_info.kernel_info_var_len_data.
+
+============	========
+Field name:	size_total
+Offset/size:	0x0008/4
+============	========
+
+  This field contains the size of the kernel_info including kernel_info.header
+  and kernel_info.kernel_info_var_len_data.
+
+============	==============
+Field name:	setup_type_max
+Offset/size:	0x000c/4
+============	==============
+
+  This field contains maximal allowed type for setup_data and setup_indirect structs.
+
 
 The Image Checksum
 ==================

arch/x86/boot/Makefile

@@ -87,7 +87,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
 
 SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))
 
-sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p'
 
 quiet_cmd_zoffset = ZOFFSET $@
       cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@

arch/x86/boot/compressed/Makefile

@@ -72,8 +72,8 @@ $(obj)/../voffset.h: vmlinux FORCE
 
 $(obj)/misc.o: $(obj)/../voffset.h
 
-vmlinux-objs-y := $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
-	$(obj)/string.o $(obj)/cmdline.o $(obj)/error.o \
+vmlinux-objs-y := $(obj)/vmlinux.lds $(obj)/kernel_info.o $(obj)/head_$(BITS).o \
+	$(obj)/misc.o $(obj)/string.o $(obj)/cmdline.o $(obj)/error.o \
 	$(obj)/piggy.o $(obj)/cpuflags.o
 
 vmlinux-objs-$(CONFIG_EARLY_PRINTK) += $(obj)/early_serial_console.o

arch/x86/boot/compressed/kaslr.c

@@ -459,6 +459,18 @@ static bool mem_avoid_overlap(struct mem_vector *img,
 			is_overlapping = true;
 		}
 
+		if (ptr->type == SETUP_INDIRECT &&
+		    ((struct setup_indirect *)ptr->data)->type != SETUP_INDIRECT) {
+			avoid.start = ((struct setup_indirect *)ptr->data)->addr;
+			avoid.size = ((struct setup_indirect *)ptr->data)->len;
+
+			if (mem_overlaps(img, &avoid) && (avoid.start < earliest)) {
+				*overlap = avoid;
+				earliest = overlap->start;
+				is_overlapping = true;
+			}
+		}
+
 		ptr = (struct setup_data *)(unsigned long)ptr->next;
 	}
 

arch/x86/boot/compressed/kernel_info.S

+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <asm/bootparam.h>
+
+	.section ".rodata.kernel_info", "a"
+
+	.global kernel_info
+
+kernel_info:
+	/* Header, Linux top (structure). */
+	.ascii	"LToP"
+	/* Size. */
+	.long	kernel_info_var_len_data - kernel_info
+	/* Size total. */
+	.long	kernel_info_end - kernel_info
+
+	/* Maximal allowed type for setup_data and setup_indirect structs. */
+	.long	SETUP_TYPE_MAX
+
+kernel_info_var_len_data:
+	/* Empty for time being... */
+kernel_info_end:

arch/x86/boot/header.S

@@ -300,7 +300,7 @@ _start:
 	# Part 2 of the header, from the old setup.S
 
 		.ascii	"HdrS"		# header signature
-		.word	0x020d		# header version number (>= 0x0105)
+		.word	0x020f		# header version number (>= 0x0105)
 					# or else old loadlin-1.5 will fail)
 		.globl realmode_swtch
 realmode_swtch:	.word	0, 0		# default_switch, SETUPSEG
@@ -567,6 +567,7 @@ pref_address:		.quad LOAD_PHYSICAL_ADDR	# preferred load addr
 
 init_size:		.long INIT_SIZE		# kernel initialization size
 handover_offset:	.long 0			# Filled in by build.c
+kernel_info_offset:	.long 0			# Filled in by build.c
 
 # End of setup header #####################################################
 

arch/x86/boot/tools/build.c

@@ -56,6 +56,7 @@ u8 buf[SETUP_SECT_MAX*512];
 unsigned long efi32_stub_entry;
 unsigned long efi64_stub_entry;
 unsigned long efi_pe_entry;
+unsigned long kernel_info;
 unsigned long startup_64;
 
 /*----------------------------------------------------------------------*/
@@ -321,6 +322,7 @@ static void parse_zoffset(char *fname)
 		PARSE_ZOFS(p, efi32_stub_entry);
 		PARSE_ZOFS(p, efi64_stub_entry);
 		PARSE_ZOFS(p, efi_pe_entry);
+		PARSE_ZOFS(p, kernel_info);
 		PARSE_ZOFS(p, startup_64);
 
 		p = strchr(p, '\n');
@@ -410,6 +412,9 @@ int main(int argc, char ** argv)
 
 	efi_stub_entry_update();
 
+	/* Update kernel_info offset. */
+	put_unaligned_le32(kernel_info, &buf[0x268]);
+
 	crc = partial_crc32(buf, i, crc);
 	if (fwrite(buf, 1, i, dest) != i)
 		die("Writing setup failed");

arch/x86/include/uapi/asm/bootparam.h

@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_BOOTPARAM_H
 #define _ASM_X86_BOOTPARAM_H
 
-/* setup_data types */
+/* setup_data/setup_indirect types */
 #define SETUP_NONE			0
 #define SETUP_E820_EXT			1
 #define SETUP_DTB			2
@@ -11,6 +11,11 @@
 #define SETUP_APPLE_PROPERTIES		5
 #define SETUP_JAILHOUSE			6
 
+#define SETUP_INDIRECT			(1<<31)
+
+/* SETUP_INDIRECT | max(SETUP_*) */
+#define SETUP_TYPE_MAX			(SETUP_INDIRECT | SETUP_JAILHOUSE)
+
 /* ram_size flags */
 #define RAMDISK_IMAGE_START_MASK	0x07FF
 #define RAMDISK_PROMPT_FLAG		0x8000
@@ -49,6 +54,14 @@ struct setup_data {
 	__u8 data[0];
 };
 
+/* extensible setup indirect data node */
+struct setup_indirect {
+	__u32 type;
+	__u32 reserved;  /* Reserved, must be set to zero. */
+	__u64 len;
+	__u64 addr;
+};
+
 struct setup_header {
 	__u8	setup_sects;
 	__u16	root_flags;
@@ -88,6 +101,7 @@ struct setup_header {
 	__u64	pref_address;
 	__u32	init_size;
 	__u32	handover_offset;
+	__u32	kernel_info_offset;
 } __attribute__((packed));
 
 struct sys_desc_table {

arch/x86/kernel/e820.c

@@ -999,6 +999,17 @@ void __init e820__reserve_setup_data(void)
 		data = early_memremap(pa_data, sizeof(*data));
 		e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
 		e820__range_update_kexec(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
+
+		if (data->type == SETUP_INDIRECT &&
+		    ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) {
+			e820__range_update(((struct setup_indirect *)data->data)->addr,
+					   ((struct setup_indirect *)data->data)->len,
+					   E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
+			e820__range_update_kexec(((struct setup_indirect *)data->data)->addr,
+						 ((struct setup_indirect *)data->data)->len,
+						 E820_TYPE_RAM, E820_TYPE_RESERVED_KERN);
+		}
+
 		pa_data = data->next;
 		early_memunmap(data, sizeof(*data));
 	}

arch/x86/kernel/kdebugfs.c

@@ -44,7 +44,12 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf,
 	if (count > node->len - pos)
 		count = node->len - pos;
 
-	pa = node->paddr + sizeof(struct setup_data) + pos;
+	pa = node->paddr + pos;
+
+	/* Is it direct data or invalid indirect one? */
+	if (!(node->type & SETUP_INDIRECT) || node->type == SETUP_INDIRECT)
+		pa += sizeof(struct setup_data);
+
 	p = memremap(pa, count, MEMREMAP_WB);
 	if (!p)
 		return -ENOMEM;
@@ -108,9 +113,17 @@ static int __init create_setup_data_nodes(struct dentry *parent)
 			goto err_dir;
 		}
 
+		if (data->type == SETUP_INDIRECT &&
+		    ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) {
+			node->paddr = ((struct setup_indirect *)data->data)->addr;
+			node->type  = ((struct setup_indirect *)data->data)->type;
+			node->len   = ((struct setup_indirect *)data->data)->len;
+		} else {
 			node->paddr = pa_data;
 			node->type  = data->type;
 			node->len   = data->len;
+		}
+
 		create_setup_data_node(d, no, node);
 		pa_data = data->next;
 

arch/x86/kernel/ksysfs.c

@@ -100,7 +100,12 @@ static int __init get_setup_data_size(int nr, size_t *size)
 		if (!data)
 			return -ENOMEM;
 		if (nr == i) {
+			if (data->type == SETUP_INDIRECT &&
+			    ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT)
+				*size = ((struct setup_indirect *)data->data)->len;
+			else
 				*size = data->len;
+
 			memunmap(data);
 			return 0;
 		}
@@ -130,6 +135,9 @@ static ssize_t type_show(struct kobject *kobj,
 	if (!data)
 		return -ENOMEM;
 
+	if (data->type == SETUP_INDIRECT)
+		ret = sprintf(buf, "0x%x\n", ((struct setup_indirect *)data->data)->type);
+	else
 		ret = sprintf(buf, "0x%x\n", data->type);
 	memunmap(data);
 	return ret;
@@ -142,7 +150,7 @@ static ssize_t setup_data_data_read(struct file *fp,
 				    loff_t off, size_t count)
 {
 	int nr, ret = 0;
-	u64 paddr;
+	u64 paddr, len;
 	struct setup_data *data;
 	void *p;
 
@@ -157,19 +165,28 @@ static ssize_t setup_data_data_read(struct file *fp,
 	if (!data)
 		return -ENOMEM;
 
-	if (off > data->len) {
+	if (data->type == SETUP_INDIRECT &&
+	    ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) {
+		paddr = ((struct setup_indirect *)data->data)->addr;
+		len = ((struct setup_indirect *)data->data)->len;
+	} else {
+		paddr += sizeof(*data);
+		len = data->len;
+	}
+
+	if (off > len) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	if (count > data->len - off)
-		count = data->len - off;
+	if (count > len - off)
+		count = len - off;
 
 	if (!count)
 		goto out;
 
 	ret = count;
-	p = memremap(paddr + sizeof(*data), data->len, MEMREMAP_WB);
+	p = memremap(paddr, len, MEMREMAP_WB);
 	if (!p) {
 		ret = -ENOMEM;
 		goto out;

arch/x86/kernel/setup.c

@@ -438,6 +438,12 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 	while (pa_data) {
 		data = early_memremap(pa_data, sizeof(*data));
 		memblock_reserve(pa_data, sizeof(*data) + data->len);
+
+		if (data->type == SETUP_INDIRECT &&
+		    ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT)
+			memblock_reserve(((struct setup_indirect *)data->data)->addr,
+					 ((struct setup_indirect *)data->data)->len);
+
 		pa_data = data->next;
 		early_memunmap(data, sizeof(*data));
 	}

arch/x86/kernel/x86_init.c

@@ -31,6 +31,28 @@ static int __init iommu_init_noop(void) { return 0; }
 static void iommu_shutdown_noop(void) { }
 bool __init bool_x86_init_noop(void) { return false; }
 void x86_op_int_noop(int cpu) { }
+static __init int set_rtc_noop(const struct timespec64 *now) { return -EINVAL; }
+static __init void get_rtc_noop(struct timespec64 *now) { }
+
+static __initconst const struct of_device_id of_cmos_match[] = {
+	{ .compatible = "motorola,mc146818" },
+	{}
+};
+
+/*
+ * Allow devicetree configured systems to disable the RTC by setting the
+ * corresponding DT node's status property to disabled. Code is optimized
+ * out for CONFIG_OF=n builds.
+ */
+static __init void x86_wallclock_init(void)
+{
+	struct device_node *node = of_find_matching_node(NULL, of_cmos_match);
+
+	if (node && !of_device_is_available(node)) {
+		x86_platform.get_wallclock = get_rtc_noop;
+		x86_platform.set_wallclock = set_rtc_noop;
+	}
+}
 
 /*
  * The platform setup functions are preset with the default functions
@@ -73,7 +95,7 @@ struct x86_init_ops x86_init __initdata = {
 	.timers = {
 		.setup_percpu_clockev	= setup_boot_APIC_clock,
 		.timer_init		= hpet_time_init,
-		.wallclock_init		= x86_init_noop,
+		.wallclock_init		= x86_wallclock_init,
 	},
 
 	.iommu = {

arch/x86/mm/ioremap.c

@@ -626,6 +626,17 @@ static bool memremap_is_setup_data(resource_size_t phys_addr,
 		paddr_next = data->next;
 		len = data->len;
 
+		if ((phys_addr > paddr) && (phys_addr < (paddr + len))) {
+			memunmap(data);
+			return true;
+		}
+
+		if (data->type == SETUP_INDIRECT &&
+		    ((struct setup_indirect *)data->data)->type != SETUP_INDIRECT) {
+			paddr = ((struct setup_indirect *)data->data)->addr;
+			len = ((struct setup_indirect *)data->data)->len;
+		}
+
 		memunmap(data);
 
 		if ((phys_addr > paddr) && (phys_addr < (paddr + len)))

arch/x86/realmode/rm/realmode.lds.S

@@ -11,6 +11,7 @@
 
 OUTPUT_FORMAT("elf32-i386")
 OUTPUT_ARCH(i386)
+ENTRY(pa_text_start)
 
 SECTIONS
 {