x86/kexec: carry forward the boot DTB on kexec

Currently, the kexec_file_load syscall on x86 does not support passing a
device tree blob to the new kernel.  Some embedded x86 systems use device
trees.  On these systems, failing to pass a device tree to the new kernel
causes a boot failure.

To add support for this, we copy the behavior of ARM64 and PowerPC and
copy the current boot's device tree blob for use in the new kernel.  We do
this on x86 by passing the device tree blob as a setup_data entry in
accordance with the x86 boot protocol.

This behavior is gated behind the KEXEC_FILE_FORCE_DTB flag.

Link: https://lkml.kernel.org/r/20250805211527.122367-3-makb@juniper.net
Signed-off-by: Brian Mak <makb@juniper.net>
Cc: Alexander Graf <graf@amazon.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Borislav Betkov <bp@alien8.de>
Cc: Dave Young <dyoung@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Saravana Kannan <saravanak@google.com>
Cc: Thomas Gleinxer <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 24a41f0e0cf15f0db5fdbe6033441c3973c4e501..c3244ac680d148496fd2c63affe51096dc4d1394 100644 (file)
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -16,6 +16,8 @@
 #include <linux/kexec.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/libfdt.h>
+#include <linux/of_fdt.h>
 #include <linux/efi.h>
 #include <linux/random.h>
 
@@ -212,6 +214,28 @@ setup_efi_state(struct boot_params *params, unsigned long params_load_addr,
 }
 #endif /* CONFIG_EFI */
 
+#ifdef CONFIG_OF_FLATTREE
+static void setup_dtb(struct boot_params *params,
+                     unsigned long params_load_addr,
+                     unsigned int dtb_setup_data_offset)
+{
+       struct setup_data *sd = (void *)params + dtb_setup_data_offset;
+       unsigned long setup_data_phys, dtb_len;
+
+       dtb_len = fdt_totalsize(initial_boot_params);
+       sd->type = SETUP_DTB;
+       sd->len = dtb_len;
+
+       /* Carry over current boot DTB with setup_data */
+       memcpy(sd->data, initial_boot_params, dtb_len);
+
+       /* Add setup data */
+       setup_data_phys = params_load_addr + dtb_setup_data_offset;
+       sd->next = params->hdr.setup_data;
+       params->hdr.setup_data = setup_data_phys;
+}
+#endif /* CONFIG_OF_FLATTREE */
+
 static void
 setup_ima_state(const struct kimage *image, struct boot_params *params,
                unsigned long params_load_addr,
@@ -336,6 +360,17 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params,
                        sizeof(struct efi_setup_data);
 #endif
 
+#ifdef CONFIG_OF_FLATTREE
+       if (image->force_dtb && initial_boot_params) {
+               setup_dtb(params, params_load_addr, setup_data_offset);
+               setup_data_offset += sizeof(struct setup_data) +
+                                    fdt_totalsize(initial_boot_params);
+       } else {
+               pr_debug("Not carrying over DTB, force_dtb = %d\n",
+                        image->force_dtb);
+       }
+#endif
+
        if (IS_ENABLED(CONFIG_IMA_KEXEC)) {
                /* Setup IMA log buffer state */
                setup_ima_state(image, params, params_load_addr,
@@ -529,6 +564,12 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
                                sizeof(struct setup_data) +
                                RNG_SEED_LENGTH;
 
+#ifdef CONFIG_OF_FLATTREE
+       if (image->force_dtb && initial_boot_params)
+               kbuf.bufsz += sizeof(struct setup_data) +
+                             fdt_totalsize(initial_boot_params);
+#endif
+
        if (IS_ENABLED(CONFIG_IMA_KEXEC))
                kbuf.bufsz += sizeof(struct setup_data) +
                              sizeof(struct ima_setup_data);
@@ -537,7 +578,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
                kbuf.bufsz += sizeof(struct setup_data) +
                              sizeof(struct kho_data);
 
-       params = kzalloc(kbuf.bufsz, GFP_KERNEL);
+       params = kvzalloc(kbuf.bufsz, GFP_KERNEL);
        if (!params)
                return ERR_PTR(-ENOMEM);
        efi_map_offset = params_cmdline_sz;
@@ -647,7 +688,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
        return ldata;
 
 out_free_params:
-       kfree(params);
+       kvfree(params);
        return ERR_PTR(ret);
 }
 
@@ -659,7 +700,7 @@ static int bzImage64_cleanup(void *loader_data)
        if (!ldata)
                return 0;
 
-       kfree(ldata->bootparams_buf);
+       kvfree(ldata->bootparams_buf);
        ldata->bootparams_buf = NULL;
 
        return 0;

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 39fe3e6cd282f8d49d36de4f50f5be5ea3c87070..ff7e231b0485a98b4064639ef0d481f1e7e277b3 100644 (file)
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -395,6 +395,9 @@ struct kimage {
 
        /* Information for loading purgatory */
        struct purgatory_info purgatory_info;
+
+       /* Force carrying over the DTB from the current boot */
+       bool force_dtb;
 #endif
 
 #ifdef CONFIG_CRASH_HOTPLUG
@@ -461,7 +464,7 @@ bool kexec_load_permitted(int kexec_image_type);
 /* List of defined/legal kexec file flags */
 #define KEXEC_FILE_FLAGS       (KEXEC_FILE_UNLOAD | KEXEC_FILE_ON_CRASH | \
                                 KEXEC_FILE_NO_INITRAMFS | KEXEC_FILE_DEBUG | \
-                                KEXEC_FILE_NO_CMA)
+                                KEXEC_FILE_NO_CMA | KEXEC_FILE_FORCE_DTB)
 
 /* flag to track if kexec reboot is in progress */
 extern bool kexec_in_progress;

diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h
index 8958ebfcff9482366c83dc42c6a3776cd8fd4588..55749cb0b81ddee982296982156be9e5c7ca6a6c 100644 (file)
--- a/include/uapi/linux/kexec.h
+++ b/include/uapi/linux/kexec.h
@@ -22,12 +22,16 @@
  * KEXEC_FILE_ON_CRASH : Load/unload operation belongs to kdump image.
  * KEXEC_FILE_NO_INITRAMFS : No initramfs is being loaded. Ignore the initrd
  *                           fd field.
+ * KEXEC_FILE_FORCE_DTB : Force carrying over the current boot's DTB to the new
+ *                        kernel on x86. This is already the default behavior on
+ *                        some other architectures, like ARM64 and PowerPC.
  */
 #define KEXEC_FILE_UNLOAD      0x00000001
 #define KEXEC_FILE_ON_CRASH    0x00000002
 #define KEXEC_FILE_NO_INITRAMFS        0x00000004
 #define KEXEC_FILE_DEBUG       0x00000008
 #define KEXEC_FILE_NO_CMA      0x00000010
+#define KEXEC_FILE_FORCE_DTB   0x00000020
 
 /* These values match the ELF architecture values.
  * Unless there is a good reason that should continue to be the case.

diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 91d46502a8174d3e903eefedde41a3aa9eac363a..eb62a97942428c86005ef35ab063286689584128 100644 (file)
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -255,6 +255,7 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
        }
 
        image->no_cma = !!(flags & KEXEC_FILE_NO_CMA);
+       image->force_dtb = flags & KEXEC_FILE_FORCE_DTB;
 
        if (cmdline_len) {
                image->cmdline_buf = memdup_user(cmdline_ptr, cmdline_len);