public-mirrors/linux
1
0
Fork 0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2025-08-05 16:54:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
linux/drivers/firmware/efi/libstub/loongarch-stub.c

45 lines
1.1 KiB
C
Raw Permalink Normal View History

efi/loongarch: Add efistub booting support This patch adds efistub booting support, which is the standard UEFI boot protocol for LoongArch to use. We use generic efistub, which means we can pass boot information (i.e., system table, memory map, kernel command line, initrd) via a light FDT and drop a lot of non-standard code. We use a flat mapping to map the efi runtime in the kernel's address space. In efi, VA = PA; in kernel, VA = PA + PAGE_OFFSET. As a result, flat mapping is not identity mapping, SetVirtualAddressMap() is still needed for the efi runtime. Tested-by: Xi Ruoyao <xry111@xry111.site> Signed-off-by: Huacai Chen <chenhuacai@loongson.cn> [ardb: change fpic to fpie as suggested by Xi Ruoyao] Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2022-08-19 18:20:37 +08:00
// SPDX-License-Identifier: GPL-2.0
/*
* Author: Yun Liu <liuyun@loongson.cn>
* Huacai Chen <chenhuacai@loongson.cn>
* Copyright (C) 2020-2022 Loongson Technology Corporation Limited
*/
#include <asm/efi.h>
#include <asm/addrspace.h>
#include "efistub.h"
efi/loongarch: Directly position the loaded image file The use of the 'kernel_offset' variable to position the image file that has been loaded by UEFI or GRUB is unnecessary, because we can directly position the loaded image file through using the image_base field of the efi_loaded_image struct provided by UEFI. Replace kernel_offset with image_base to position the image file that has been loaded by UEFI or GRUB. Signed-off-by: Wang Yao <wangyao@lemote.com> Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2023-12-19 17:14:05 +08:00
#include "loongarch-stub.h"
efi/loongarch: Add efistub booting support This patch adds efistub booting support, which is the standard UEFI boot protocol for LoongArch to use. We use generic efistub, which means we can pass boot information (i.e., system table, memory map, kernel command line, initrd) via a light FDT and drop a lot of non-standard code. We use a flat mapping to map the efi runtime in the kernel's address space. In efi, VA = PA; in kernel, VA = PA + PAGE_OFFSET. As a result, flat mapping is not identity mapping, SetVirtualAddressMap() is still needed for the efi runtime. Tested-by: Xi Ruoyao <xry111@xry111.site> Signed-off-by: Huacai Chen <chenhuacai@loongson.cn> [ardb: change fpic to fpie as suggested by Xi Ruoyao] Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2022-08-19 18:20:37 +08:00
extern int kernel_asize;
extern int kernel_fsize;
efi/loongarch: libstub: Split off kernel image relocation for builtin stub The LoongArch build of the EFI stub is part of the core kernel image, and therefore accesses section markers directly when it needs to figure out the size of the various section. The zboot decompressor does not have access to those symbols, but doesn't really need that either. So let's move handle_kernel_image() into a separate file (or rather, move everything else into a separate file) so that the zboot build does not pull in unused code that links to symbols that it does not define. Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2022-10-13 12:39:37 +02:00
extern int kernel_entry;
efi/loongarch: Add efistub booting support This patch adds efistub booting support, which is the standard UEFI boot protocol for LoongArch to use. We use generic efistub, which means we can pass boot information (i.e., system table, memory map, kernel command line, initrd) via a light FDT and drop a lot of non-standard code. We use a flat mapping to map the efi runtime in the kernel's address space. In efi, VA = PA; in kernel, VA = PA + PAGE_OFFSET. As a result, flat mapping is not identity mapping, SetVirtualAddressMap() is still needed for the efi runtime. Tested-by: Xi Ruoyao <xry111@xry111.site> Signed-off-by: Huacai Chen <chenhuacai@loongson.cn> [ardb: change fpic to fpie as suggested by Xi Ruoyao] Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2022-08-19 18:20:37 +08:00
efi_status_t handle_kernel_image(unsigned long *image_addr,
unsigned long *image_size,
unsigned long *reserve_addr,
unsigned long *reserve_size,
efi_loaded_image_t *image,
efi_handle_t image_handle)
{
efi_status_t status;
efi/loongarch: Reintroduce efi_relocate_kernel() to relocate kernel Since Linux-6.3, LoongArch supports PIE kernel now, so let's reintroduce efi_relocate_kernel() to relocate the core kernel. Signed-off-by: Huacai Chen <chenhuacai@loongson.cn> Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2023-03-01 16:55:45 +08:00
unsigned long kernel_addr = 0;
efi/loongarch: Add efistub booting support This patch adds efistub booting support, which is the standard UEFI boot protocol for LoongArch to use. We use generic efistub, which means we can pass boot information (i.e., system table, memory map, kernel command line, initrd) via a light FDT and drop a lot of non-standard code. We use a flat mapping to map the efi runtime in the kernel's address space. In efi, VA = PA; in kernel, VA = PA + PAGE_OFFSET. As a result, flat mapping is not identity mapping, SetVirtualAddressMap() is still needed for the efi runtime. Tested-by: Xi Ruoyao <xry111@xry111.site> Signed-off-by: Huacai Chen <chenhuacai@loongson.cn> [ardb: change fpic to fpie as suggested by Xi Ruoyao] Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2022-08-19 18:20:37 +08:00
efi/loongarch: Directly position the loaded image file The use of the 'kernel_offset' variable to position the image file that has been loaded by UEFI or GRUB is unnecessary, because we can directly position the loaded image file through using the image_base field of the efi_loaded_image struct provided by UEFI. Replace kernel_offset with image_base to position the image file that has been loaded by UEFI or GRUB. Signed-off-by: Wang Yao <wangyao@lemote.com> Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2023-12-19 17:14:05 +08:00
kernel_addr = (unsigned long)image->image_base;
efi/loongarch: Reintroduce efi_relocate_kernel() to relocate kernel Since Linux-6.3, LoongArch supports PIE kernel now, so let's reintroduce efi_relocate_kernel() to relocate the core kernel. Signed-off-by: Huacai Chen <chenhuacai@loongson.cn> Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2023-03-01 16:55:45 +08:00
status = efi_relocate_kernel(&kernel_addr, kernel_fsize, kernel_asize,
EFI_KIMG_PREFERRED_ADDRESS, efi_get_kimg_min_align(), 0x0);
efi/loongarch: Add efistub booting support This patch adds efistub booting support, which is the standard UEFI boot protocol for LoongArch to use. We use generic efistub, which means we can pass boot information (i.e., system table, memory map, kernel command line, initrd) via a light FDT and drop a lot of non-standard code. We use a flat mapping to map the efi runtime in the kernel's address space. In efi, VA = PA; in kernel, VA = PA + PAGE_OFFSET. As a result, flat mapping is not identity mapping, SetVirtualAddressMap() is still needed for the efi runtime. Tested-by: Xi Ruoyao <xry111@xry111.site> Signed-off-by: Huacai Chen <chenhuacai@loongson.cn> [ardb: change fpic to fpie as suggested by Xi Ruoyao] Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2022-08-19 18:20:37 +08:00
efi/loongarch: Reintroduce efi_relocate_kernel() to relocate kernel Since Linux-6.3, LoongArch supports PIE kernel now, so let's reintroduce efi_relocate_kernel() to relocate the core kernel. Signed-off-by: Huacai Chen <chenhuacai@loongson.cn> Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2023-03-01 16:55:45 +08:00
*image_addr = kernel_addr;
*image_size = kernel_asize;
efi/loongarch: Don't jump to kernel entry via the old image Currently, the EFI entry code for LoongArch is set up to copy the executable image to the preferred offset, but instead of branching directly into that image, it branches to the local copy of kernel_entry, and relies on the logic in that function to switch to the link time address instead. This is a bit sloppy, and not something we can support once we merge the EFI decompressor with the EFI stub. So let's clean this up a bit, by adding a helper that computes the offset of kernel_entry from the start of the image, and simply adding the result to VMLINUX_LOAD_ADDRESS. And considering that we cannot execute from anywhere else anyway, let's avoid efi_relocate_kernel() and just allocate the pages instead. Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2022-10-13 12:07:27 +02:00
efi/loongarch: Add efistub booting support This patch adds efistub booting support, which is the standard UEFI boot protocol for LoongArch to use. We use generic efistub, which means we can pass boot information (i.e., system table, memory map, kernel command line, initrd) via a light FDT and drop a lot of non-standard code. We use a flat mapping to map the efi runtime in the kernel's address space. In efi, VA = PA; in kernel, VA = PA + PAGE_OFFSET. As a result, flat mapping is not identity mapping, SetVirtualAddressMap() is still needed for the efi runtime. Tested-by: Xi Ruoyao <xry111@xry111.site> Signed-off-by: Huacai Chen <chenhuacai@loongson.cn> [ardb: change fpic to fpie as suggested by Xi Ruoyao] Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2022-08-19 18:20:37 +08:00
return status;
}
efi/loongarch: Directly position the loaded image file The use of the 'kernel_offset' variable to position the image file that has been loaded by UEFI or GRUB is unnecessary, because we can directly position the loaded image file through using the image_base field of the efi_loaded_image struct provided by UEFI. Replace kernel_offset with image_base to position the image file that has been loaded by UEFI or GRUB. Signed-off-by: Wang Yao <wangyao@lemote.com> Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2023-12-19 17:14:05 +08:00
unsigned long kernel_entry_address(unsigned long kernel_addr,
efi_loaded_image_t *image)
efi/loongarch: Don't jump to kernel entry via the old image Currently, the EFI entry code for LoongArch is set up to copy the executable image to the preferred offset, but instead of branching directly into that image, it branches to the local copy of kernel_entry, and relies on the logic in that function to switch to the link time address instead. This is a bit sloppy, and not something we can support once we merge the EFI decompressor with the EFI stub. So let's clean this up a bit, by adding a helper that computes the offset of kernel_entry from the start of the image, and simply adding the result to VMLINUX_LOAD_ADDRESS. And considering that we cannot execute from anywhere else anyway, let's avoid efi_relocate_kernel() and just allocate the pages instead. Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2022-10-13 12:07:27 +02:00
{
efi/loongarch: Directly position the loaded image file The use of the 'kernel_offset' variable to position the image file that has been loaded by UEFI or GRUB is unnecessary, because we can directly position the loaded image file through using the image_base field of the efi_loaded_image struct provided by UEFI. Replace kernel_offset with image_base to position the image file that has been loaded by UEFI or GRUB. Signed-off-by: Wang Yao <wangyao@lemote.com> Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2023-12-19 17:14:05 +08:00
unsigned long base = (unsigned long)image->image_base;
efi/loongarch: Don't jump to kernel entry via the old image Currently, the EFI entry code for LoongArch is set up to copy the executable image to the preferred offset, but instead of branching directly into that image, it branches to the local copy of kernel_entry, and relies on the logic in that function to switch to the link time address instead. This is a bit sloppy, and not something we can support once we merge the EFI decompressor with the EFI stub. So let's clean this up a bit, by adding a helper that computes the offset of kernel_entry from the start of the image, and simply adding the result to VMLINUX_LOAD_ADDRESS. And considering that we cannot execute from anywhere else anyway, let's avoid efi_relocate_kernel() and just allocate the pages instead. Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2022-10-13 12:07:27 +02:00
efi/loongarch: Use load address to calculate kernel entry address The efi_relocate_kernel() may load the PIE kernel to anywhere, the loaded address may not be equal to link address or EFI_KIMG_PREFERRED_ADDRESS. Acked-by: Huacai Chen <chenhuacai@loongson.cn> Signed-off-by: Wang Yao <wangyao@lemote.com> Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2023-12-06 08:24:27 +08:00
return (unsigned long)&kernel_entry - base + kernel_addr;
efi/loongarch: Don't jump to kernel entry via the old image Currently, the EFI entry code for LoongArch is set up to copy the executable image to the preferred offset, but instead of branching directly into that image, it branches to the local copy of kernel_entry, and relies on the logic in that function to switch to the link time address instead. This is a bit sloppy, and not something we can support once we merge the EFI decompressor with the EFI stub. So let's clean this up a bit, by adding a helper that computes the offset of kernel_entry from the start of the image, and simply adding the result to VMLINUX_LOAD_ADDRESS. And considering that we cannot execute from anywhere else anyway, let's avoid efi_relocate_kernel() and just allocate the pages instead. Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
2022-10-13 12:07:27 +02:00
}
Reference in a new issue Copy permalink