x86/boot: Introduce 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.

Do not bump setup_header version in arch/x86/boot/header.S because it
will be followed by additional changes coming into the Linux/x86 boot
protocol.

Suggested-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Signed-off-by: Daniel Kiper <daniel.kiper@oracle.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reviewed-by: Ross Philipson <ross.philipson@oracle.com>
Reviewed-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: ard.biesheuvel@linaro.org
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: dave.hansen@linux.intel.com
Cc: eric.snowberg@oracle.com
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Juergen Gross <jgross@suse.com>
Cc: kanth.ghatraju@oracle.com
Cc: linux-doc@vger.kernel.org
Cc: linux-efi <linux-efi@vger.kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: rdunlap@infradead.org
Cc: ross.philipson@oracle.com
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: x86-ml <x86@kernel.org>
Cc: xen-devel@lists.xenproject.org
Link: https://lkml.kernel.org/r/20191112134640.16035-2-daniel.kiper@oracle.com

5 files changed, 26 insertions, 3 deletions

diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index e2839b5c246c..c30a9b642a86 100644
--- a/arch/x86/boot/Makefile
+++ b/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) > $@
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 6b84afdd7538..fad3b18e2cc3 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/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
diff --git a/arch/x86/boot/compressed/kernel_info.S b/arch/x86/boot/compressed/kernel_info.S
new file mode 100644
index 000000000000..8ea6f6e3feef
--- /dev/null
+++ b/arch/x86/boot/compressed/kernel_info.S
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+	.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
+
+kernel_info_var_len_data:
+	/* Empty for time being... */
+kernel_info_end:
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index 2c11c0f45d49..22dcecaaa898 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -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 #####################################################
 
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index a93d44e58f9c..55e669d29e54 100644
--- a/arch/x86/boot/tools/build.c
+++ b/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");