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/[e-mail]
Signed-off-by: Brian Mak <[e-mail]>
Cc: Alexander Graf <[e-mail]>
Cc: Baoquan He <[e-mail]>
Cc: Borislav Betkov <[e-mail]>
Cc: Dave Young <[e-mail]>
Cc: "H. Peter Anvin" <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: Rob Herring <[e-mail]>
Cc: Saravana Kannan <[e-mail]>
Cc: Thomas Gleinxer <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>

arch/x86/kernel/kexec-bzimage64.c

···
 #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>
 
···
 }
 #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,
···
 			setup_data_offset);
 	setup_data_offset += sizeof(struct setup_data) +
 			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)) {
···
 				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);
···
 		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;
···
 	return ldata;
 
 out_free_params:
-	kfree(params);
+	kvfree(params);
 	return ERR_PTR(ret);
 }
 
···
 	if (!ldata)
 		return 0;
 
-	kfree(ldata->bootparams_buf);
+	kvfree(ldata->bootparams_buf);
 	ldata->bootparams_buf = NULL;
 
 	return 0;

include/linux/kexec.h

···
 
 	/* 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
···
 /* 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;

include/uapi/linux/kexec.h

···
  * 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.

kernel/kexec_file.c

···
 	}
 
 	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);