On Tue, Aug 12, 2025 at 1:09 AM Yao Zi <zi...@disroot.org> wrote:
>
> On Mon, Aug 11, 2025 at 05:26:55PM +0800, Youling Tang wrote:
> > From: Youling Tang <tangyoul...@kylinos.cn>
> >
> > This patch adds support for kexec_file on LoongArch.
> >
> > The image_load() as two parts:
> > - the first part loads the kernel image (vmlinuz.efi or vmlinux.efi)
> > - the second part loads other segments (eg: initrd, cmdline)
> >
> > Currently, pez(vmlinuz.efi) and pei(vmlinux.efi) format images are
> > supported,
> > but ELF format is not supported.
> >
> > Signed-off-by: Youling Tang <tangyoul...@kylinos.cn>
> > ---
> > arch/loongarch/Kconfig | 8 ++
> > arch/loongarch/include/asm/image.h | 18 ++++
> > arch/loongarch/include/asm/kexec.h | 12 +++
> > arch/loongarch/kernel/Makefile | 1 +
> > arch/loongarch/kernel/kexec_image.c | 112 +++++++++++++++++++++
> > arch/loongarch/kernel/machine_kexec.c | 33 ++++--
> > arch/loongarch/kernel/machine_kexec_file.c | 46 +++++++++
> > 7 files changed, 219 insertions(+), 11 deletions(-)
> > create mode 100644 arch/loongarch/kernel/kexec_image.c
> > create mode 100644 arch/loongarch/kernel/machine_kexec_file.c
>
> ...
>
> > diff --git a/arch/loongarch/include/asm/image.h
> > b/arch/loongarch/include/asm/image.h
> > index 1f090736e71d..829e1ecb1f5d 100644
> > --- a/arch/loongarch/include/asm/image.h
> > +++ b/arch/loongarch/include/asm/image.h
> > @@ -36,5 +36,23 @@ struct loongarch_image_header {
> > uint32_t pe_header;
> > };
> >
> > +static const uint8_t loongarch_image_pe_sig[2] = {'M', 'Z'};
> > +static const uint8_t loongarch_pe_machtype[6] = {'P', 'E', 0x0, 0x0, 0x64,
> > 0x62};
>
> loongarch_pe_machtype isn't used at all.
>
> > +
> > +/**
> > + * loongarch_header_check_pe_sig - Helper to check the loongarch image
> > header.
> > + *
> > + * Returns non-zero if 'MZ' signature is found.
> > + */
> > +
> > +static inline int loongarch_header_check_pe_sig(const struct
> > loongarch_image_header *h)
> > +{
> > + if (!h)
> > + return 0;
> > +
> > + return (h->pe_sig[0] == loongarch_image_pe_sig[0]
> > + && h->pe_sig[1] == loongarch_image_pe_sig[1]);
>
> This could be simplified with a memcmp(). Also, this check isn't strict
> enough: PE files for any architectures, and even legacy MS-DOS COM
> executables all start with "MZ".
>
> > +}
> > +
> > #endif /* __ASSEMBLY__ */
> > #endif /* __ASM_IMAGE_H */
>
> ...
>
> > diff --git a/arch/loongarch/kernel/kexec_image.c
> > b/arch/loongarch/kernel/kexec_image.c
> > new file mode 100644
> > index 000000000000..fdd1845b4e2e
> > --- /dev/null
> > +++ b/arch/loongarch/kernel/kexec_image.c
> > @@ -0,0 +1,112 @@
> > +// SPDX-License-Identifier: GPL-2.0
> > +/*
> > + * Kexec image loader for LoongArch
> > +
> > + * Author: Youling Tang <tangyoul...@kylinos.cn>
> > + * Copyright (C) 2025 KylinSoft Corporation.
> > + */
> > +
> > +#define pr_fmt(fmt) "kexec_file(Image): " fmt
> > +
> > +#include <linux/err.h>
> > +#include <linux/errno.h>
> > +#include <linux/kernel.h>
> > +#include <linux/kexec.h>
> > +#include <linux/pe.h>
> > +#include <linux/string.h>
> > +#include <asm/byteorder.h>
> > +#include <asm/cpufeature.h>
> > +#include <asm/image.h>
> > +
> > +static int image_probe(const char *kernel_buf, unsigned long kernel_len)
> > +{
> > + const struct loongarch_image_header *h =
> > + (const struct loongarch_image_header *)(kernel_buf);
>
> Parentheses around "kernel_buf" are unnecessary.
>
> > + if (!h || (kernel_len < sizeof(*h))) {
>
> Comparisons have higher priority than logic operations, so this pair of
> parentheses is redundant, too.
But the kernel coding style suggest to use parentheses in this case.
>
> > + pr_err("No loongarch image header.\n");
> > + return -EINVAL;
> > + }
> > +
> > + if (!loongarch_header_check_pe_sig(h)) {
> > + pr_err("Bad loongarch PE image header.\n");
> > + return -EINVAL;
> > + }
> > +
> > + return 0;
> > +}
> > +
> > +static void *image_load(struct kimage *image,
> > + char *kernel, unsigned long kernel_len,
> > + char *initrd, unsigned long initrd_len,
> > + char *cmdline, unsigned long cmdline_len)
> > +{
> > + struct loongarch_image_header *h;
> > + struct kexec_buf kbuf;
> > + unsigned long text_offset, kernel_segment_number;
> > + struct kexec_segment *kernel_segment;
> > + int ret;
> > +
> > + h = (struct loongarch_image_header *)kernel;
> > + if (!h->image_size)
> > + return ERR_PTR(-EINVAL);
> > +
> > + /* Load the kernel */
> > + kbuf.image = image;
> > + kbuf.buf_min = 0;
> > + kbuf.buf_max = ULONG_MAX;
> > + kbuf.top_down = false;
> > +
> > + kbuf.buffer = kernel;
> > + kbuf.bufsz = kernel_len;
> > + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
> > + kbuf.memsz = le64_to_cpu(h->image_size);
> > + text_offset = le64_to_cpu(h->text_offset);
> > + kbuf.buf_align = SZ_2M;
>
> I think this aligment is unnecessary for relocatable LoongArch kernels:
> it should be enough to align to the page size. See also my comments
> below.
>
> > + kernel_segment_number = image->nr_segments;
> > +
> > + /*
> > + * The location of the kernel segment may make it impossible to
> > satisfy
> > + * the other segment requirements, so we try repeatedly to find a
> > + * location that will work.
> > + */
> > + while ((ret = kexec_add_buffer(&kbuf)) == 0) {
> > + /* Try to load additional data */
> > + kernel_segment = &image->segment[kernel_segment_number];
> > + ret = load_other_segments(image, kernel_segment->mem,
> > + kernel_segment->memsz, initrd,
> > + initrd_len, cmdline, cmdline_len);
> > + if (!ret)
> > + break;
> > +
> > + /*
> > + * We couldn't find space for the other segments; erase the
> > + * kernel segment and try the next available hole.
> > + */
> > + image->nr_segments -= 1;
> > + kbuf.buf_min = kernel_segment->mem + kernel_segment->memsz;
> > + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
> > + }
> > +
> > + if (ret) {
> > + pr_err("Could not find any suitable kernel location!");
> > + return ERR_PTR(ret);
> > + }
> > +
> > + kernel_segment = &image->segment[kernel_segment_number];
> > +
> > + /* Make sure the second kernel jumps to the correct "kernel_entry". */
> > + image->start = kernel_segment->mem + h->kernel_entry - text_offset;
>
> A non-relocatable loongarch kernel cannot be loaded to arbitrary
> address. Thus this loading function seems to only work for relocatable
> kernels, maybe it's better to leave a comment indicating the limitation.
>
> For now, we don't seem to have a way to find out whether the kernel is
> relocatable (for example, a flag in kernel image header), so it's
> impossible to point out whether the loaded kernel boots fine with
> arbitrary loading address...
>
> > + kexec_dprintk("Loaded kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
> > + kernel_segment->mem, kbuf.bufsz,
> > + kernel_segment->memsz);
> > +
> > + return NULL;
> > +}
> > +
> > +const struct kexec_file_ops kexec_image_ops = {
> > + .probe = image_probe,
> > + .load = image_load,
> > +};
> > diff --git a/arch/loongarch/kernel/machine_kexec.c
> > b/arch/loongarch/kernel/machine_kexec.c
> > index f9381800e291..008f43e26120 100644
> > --- a/arch/loongarch/kernel/machine_kexec.c
> > +++ b/arch/loongarch/kernel/machine_kexec.c
> > @@ -70,18 +70,28 @@ int machine_kexec_prepare(struct kimage *kimage)
>
> ...
>
> > - if (!kimage->arch.cmdline_ptr) {
> > - pr_err("Command line not included in the provided image\n");
> > - return -EINVAL;
> > + if (!kimage->arch.cmdline_ptr) {
> > + pr_err("Command line not included in the provided
> > image\n");
> > + return -EINVAL;
> > + }
> > }
> >
> > /* kexec/kdump need a safe page to save reboot_code_buffer */
> > @@ -288,7 +298,8 @@ void machine_kexec(struct kimage *image)
> > local_irq_disable();
> >
> > pr_notice("EFI boot flag 0x%lx\n", efi_boot);
> > - pr_notice("Command line at 0x%lx\n", cmdline_ptr);
> > + pr_notice("Command line addr at 0x%lx\n", cmdline_ptr);
> > + pr_notice("Command line at %s\n", (char *)cmdline_ptr);
>
> The printed message doesn't match meaning of the pointer: you're
> printing the content of cmdline_ptr, instead of its address, thus
> "Command line at" sounds confusing to me.
>
> Furthermore, this chunk isn't related to "support for kexec_file", I
> think it's better to separate it into another patch (or even another
> series).
Separating is not necessary from my point of view, indeed I suggest to
squash patches in this series.
Huacai
>
> > pr_notice("System table at 0x%lx\n", systable_ptr);
> > pr_notice("We will call new kernel at 0x%lx\n", start_addr);
> > pr_notice("Bye ...\n");
>
> Best regards,
> Yao Zi
