[PATCH] loader/i386/linux: Prefer entry in long mode when booting via EFI

[Ard Biesheuvel]

The x86_64 Linux kernel can be booted in 32-bit mode, in which case the
startup code creates a set of preliminary page tables that map the first
1GiB of physical memory 1:1, and enables paging. This is a prerequisite
for 64-bit execution, and can therefore only be implemented in 32-bit
code.

The x86_64 Linux kernel can also be booted in 64-bit mode directly: this
implies that paging is already enabled, and it is the responsibility of
the bootloader to ensure that the the active page tables cover the
entire loaded image, including its BSS space, the size of which is
described in the image's setup header.

Given that the EFI spec mandates execution in long mode for x86_64, and
stipulates that all system memory is mapped 1:1, the Linux/x86
requirements for 64-bit entry can be met trivially when booting on
x86_64 via EFI. So enter via the 64-bit entrypoint in this case.

This involves inspecting the xloadflags field in the setup header to
check whether the 64-bit entrypoint is supported. This field was
introduced in Linux version v3.8 (early 2013)

This change ensures that all EFI firmware tables and other assets passed
by the firmware or bootloader in memory remain mapped and accessible
throughout the early startup code. (Note that Linux's 32-bit startup
code creates multiple shadow mappings of the first 1GiB of physical
memory up to the 4 GiB mark so anything that resides there becomes
inaccessible until the 64-bit startup code replaces the preliminary
mappings with more accurate ones)

Avoiding the drop out of long mode will also be needed to support
upcoming CPU designs that no longer implement 32-bit mode at all (as
recently announced by Intel [0])

[0] 
https://www.intel.com/content/www/us/en/developer/articles/technical/envisioning-future-simplified-architecture.html

Cc: Daniel Kiper <daniel.kiper@oracle.com>
Cc: Julian Andres Klode <julian.klode@canonical.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 grub-core/loader/i386/linux.c | 12 ++++++++++++
 include/grub/i386/linux.h     | 15 +++++++++++++--
 2 files changed, 25 insertions(+), 2 deletions(-)

diff --git a/grub-core/loader/i386/linux.c b/grub-core/loader/i386/linux.c
index 997647a33326eeb8..a83cc52a656d587b 100644
--- a/grub-core/loader/i386/linux.c
+++ b/grub-core/loader/i386/linux.c
@@ -624,6 +624,18 @@ grub_linux_boot (void)
   }
 #endif
 
+#if defined (GRUB_MACHINE_EFI) && defined (__x86_64__)
+  if (grub_le_to_cpu16 (ctx.params->version) >= 0x020c &&
+      (linux_params.xloadflags & LINUX_X86_XLF_KERNEL_64) != 0)
+    {
+      struct grub_relocator64_efi_state state64;
+
+      state64.rsi = ctx.real_mode_target;
+      state64.rip = ctx.params->code32_start + LINUX_X86_STARTUP64_OFFSET;
+      return grub_relocator64_efi_boot (relocator, state64);
+    }
+#endif
+
   /* FIXME.  */
   /*  asm volatile ("lidt %0" : : "m" (idt_desc)); */
   state.ebp = state.edi = state.ebx = 0;
diff --git a/include/grub/i386/linux.h b/include/grub/i386/linux.h
index 0fd6e1212fd2fa86..d4b550869534e255 100644
--- a/include/grub/i386/linux.h
+++ b/include/grub/i386/linux.h
@@ -69,6 +69,16 @@
 #define GRUB_LINUX_OFW_SIGNATURE       \
   (' ' << 24 | 'W' << 16 | 'F' << 8 | 'O')
 
+#define LINUX_X86_XLF_KERNEL_64                        (1<<0)
+#define LINUX_X86_XLF_CAN_BE_LOADED_ABOVE_4G   (1<<1)
+#define LINUX_X86_XLF_EFI_HANDOVER_32          (1<<2)
+#define LINUX_X86_XLF_EFI_HANDOVER_64          (1<<3)
+#define LINUX_X86_XLF_EFI_KEXEC                        (1<<4)
+#define LINUX_X86_XLF_5LEVEL                   (1<<5)
+#define LINUX_X86_XLF_5LEVEL_ENABLED           (1<<6)
+
+#define LINUX_X86_STARTUP64_OFFSET             0x200
+
 #ifndef ASM_FILE
 
 #define GRUB_E820_RAM        1
@@ -138,7 +148,7 @@ struct linux_i386_kernel_header
   grub_uint32_t kernel_alignment;
   grub_uint8_t relocatable;
   grub_uint8_t min_alignment;
-  grub_uint8_t pad[2];
+  grub_uint16_t xloadflags;
   grub_uint32_t cmdline_size;
   grub_uint32_t hardware_subarch;
   grub_uint64_t hardware_subarch_data;
@@ -315,7 +325,8 @@ struct linux_kernel_params
   grub_uint32_t initrd_addr_max;       /* Maximum initrd address */
   grub_uint32_t kernel_alignment;      /* Alignment of the kernel */
   grub_uint8_t relocatable_kernel;     /* Is the kernel relocatable */
-  grub_uint8_t pad1[3];
+  grub_uint8_t min_alignment;
+  grub_uint16_t xloadflags;
   grub_uint32_t cmdline_size;          /* Size of the kernel command line */
   grub_uint32_t hardware_subarch;
   grub_uint64_t hardware_subarch_data;
-- 
2.39.2