Merge branch 'for-next/kexec' into aarch64/for-next/core

Merge in kexec_file_load() support from Akashi Takahiro.

arch/arm64/Kconfig

@@ -905,6 +905,39 @@ config KEXEC
 	  but it is independent of the system firmware.   And like a reboot
 	  you can start any kernel with it, not just Linux.
 
+config KEXEC_FILE
+	bool "kexec file based system call"
+	select KEXEC_CORE
+	help
+	  This is new version of kexec system call. This system call is
+	  file based and takes file descriptors as system call argument
+	  for kernel and initramfs as opposed to list of segments as
+	  accepted by previous system call.
+
+config KEXEC_VERIFY_SIG
+	bool "Verify kernel signature during kexec_file_load() syscall"
+	depends on KEXEC_FILE
+	help
+	  Select this option to verify a signature with loaded kernel
+	  image. If configured, any attempt of loading a image without
+	  valid signature will fail.
+
+	  In addition to that option, you need to enable signature
+	  verification for the corresponding kernel image type being
+	  loaded in order for this to work.
+
+config KEXEC_IMAGE_VERIFY_SIG
+	bool "Enable Image signature verification support"
+	default y
+	depends on KEXEC_VERIFY_SIG
+	depends on EFI && SIGNED_PE_FILE_VERIFICATION
+	help
+	  Enable Image signature verification support.
+
+comment "Support for PE file signature verification disabled"
+	depends on KEXEC_VERIFY_SIG
+	depends on !EFI || !SIGNED_PE_FILE_VERIFICATION
+
 config CRASH_DUMP
 	bool "Build kdump crash kernel"
 	help

arch/arm64/include/asm/cpufeature.h

@@ -489,11 +489,59 @@ static inline bool system_supports_32bit_el0(void)
 	return cpus_have_const_cap(ARM64_HAS_32BIT_EL0);
 }
 
+static inline bool system_supports_4kb_granule(void)
+{
+	u64 mmfr0;
+	u32 val;
+
+	mmfr0 =	read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	val = cpuid_feature_extract_unsigned_field(mmfr0,
+						ID_AA64MMFR0_TGRAN4_SHIFT);
+
+	return val == ID_AA64MMFR0_TGRAN4_SUPPORTED;
+}
+
+static inline bool system_supports_64kb_granule(void)
+{
+	u64 mmfr0;
+	u32 val;
+
+	mmfr0 =	read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	val = cpuid_feature_extract_unsigned_field(mmfr0,
+						ID_AA64MMFR0_TGRAN64_SHIFT);
+
+	return val == ID_AA64MMFR0_TGRAN64_SUPPORTED;
+}
+
+static inline bool system_supports_16kb_granule(void)
+{
+	u64 mmfr0;
+	u32 val;
+
+	mmfr0 =	read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	val = cpuid_feature_extract_unsigned_field(mmfr0,
+						ID_AA64MMFR0_TGRAN16_SHIFT);
+
+	return val == ID_AA64MMFR0_TGRAN16_SUPPORTED;
+}
+
 static inline bool system_supports_mixed_endian_el0(void)
 {
 	return id_aa64mmfr0_mixed_endian_el0(read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1));
 }
 
+static inline bool system_supports_mixed_endian(void)
+{
+	u64 mmfr0;
+	u32 val;
+
+	mmfr0 =	read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+	val = cpuid_feature_extract_unsigned_field(mmfr0,
+						ID_AA64MMFR0_BIGENDEL_SHIFT);
+
+	return val == 0x1;
+}
+
 static inline bool system_supports_fpsimd(void)
 {
 	return !cpus_have_const_cap(ARM64_HAS_NO_FPSIMD);

arch/arm64/include/asm/image.h

+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_IMAGE_H
+#define __ASM_IMAGE_H
+
+#define ARM64_IMAGE_MAGIC	"ARM\x64"
+
+#define ARM64_IMAGE_FLAG_BE_SHIFT		0
+#define ARM64_IMAGE_FLAG_PAGE_SIZE_SHIFT	(ARM64_IMAGE_FLAG_BE_SHIFT + 1)
+#define ARM64_IMAGE_FLAG_PHYS_BASE_SHIFT \
+					(ARM64_IMAGE_FLAG_PAGE_SIZE_SHIFT + 2)
+#define ARM64_IMAGE_FLAG_BE_MASK		0x1
+#define ARM64_IMAGE_FLAG_PAGE_SIZE_MASK		0x3
+#define ARM64_IMAGE_FLAG_PHYS_BASE_MASK		0x1
+
+#define ARM64_IMAGE_FLAG_LE			0
+#define ARM64_IMAGE_FLAG_BE			1
+#define ARM64_IMAGE_FLAG_PAGE_SIZE_4K		1
+#define ARM64_IMAGE_FLAG_PAGE_SIZE_16K		2
+#define ARM64_IMAGE_FLAG_PAGE_SIZE_64K		3
+#define ARM64_IMAGE_FLAG_PHYS_BASE		1
+
+#ifndef __ASSEMBLY__
+
+#define arm64_image_flag_field(flags, field) \
+				(((flags) >> field##_SHIFT) & field##_MASK)
+
+/*
+ * struct arm64_image_header - arm64 kernel image header
+ * See Documentation/arm64/booting.txt for details
+ *
+ * @code0:		Executable code, or
+ *   @mz_header		  alternatively used for part of MZ header
+ * @code1:		Executable code
+ * @text_offset:	Image load offset
+ * @image_size:		Effective Image size
+ * @flags:		kernel flags
+ * @reserved:		reserved
+ * @magic:		Magic number
+ * @reserved5:		reserved, or
+ *   @pe_header:	  alternatively used for PE COFF offset
+ */
+
+struct arm64_image_header {
+	__le32 code0;
+	__le32 code1;
+	__le64 text_offset;
+	__le64 image_size;
+	__le64 flags;
+	__le64 res2;
+	__le64 res3;
+	__le64 res4;
+	__le32 magic;
+	__le32 res5;
+};
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_IMAGE_H */

arch/arm64/include/asm/kexec.h

@@ -93,6 +93,25 @@ static inline void crash_prepare_suspend(void) {}
 static inline void crash_post_resume(void) {}
 #endif
 
+#ifdef CONFIG_KEXEC_FILE
+#define ARCH_HAS_KIMAGE_ARCH
+
+struct kimage_arch {
+	void *dtb;
+	unsigned long dtb_mem;
+};
+
+extern const struct kexec_file_ops kexec_image_ops;
+
+struct kimage;
+
+extern int arch_kimage_file_post_load_cleanup(struct kimage *image);
+extern int load_other_segments(struct kimage *image,
+		unsigned long kernel_load_addr, unsigned long kernel_size,
+		char *initrd, unsigned long initrd_len,
+		char *cmdline);
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif

arch/arm64/kernel/Makefile

@@ -49,8 +49,9 @@ arm64-obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL)	+= acpi_parking_protocol.o
 arm64-obj-$(CONFIG_PARAVIRT)		+= paravirt.o
 arm64-obj-$(CONFIG_RANDOMIZE_BASE)	+= kaslr.o
 arm64-obj-$(CONFIG_HIBERNATION)		+= hibernate.o hibernate-asm.o
-arm64-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o	\
+arm64-obj-$(CONFIG_KEXEC_CORE)		+= machine_kexec.o relocate_kernel.o	\
 					   cpu-reset.o
+arm64-obj-$(CONFIG_KEXEC_FILE)		+= machine_kexec_file.o kexec_image.o
 arm64-obj-$(CONFIG_ARM64_RELOC_TEST)	+= arm64-reloc-test.o
 arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o
 arm64-obj-$(CONFIG_CRASH_DUMP)		+= crash_dump.o

arch/arm64/kernel/cpu-reset.S

@@ -22,11 +22,11 @@
  * __cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2) - Helper for
  * cpu_soft_restart.
  *
- * @el2_switch: Flag to indicate a swich to EL2 is needed.
+ * @el2_switch: Flag to indicate a switch to EL2 is needed.
  * @entry: Location to jump to for soft reset.
- * arg0: First argument passed to @entry.
- * arg1: Second argument passed to @entry.
- * arg2: Third argument passed to @entry.
+ * arg0: First argument passed to @entry. (relocation list)
+ * arg1: Second argument passed to @entry.(physical kernel entry)
+ * arg2: Third argument passed to @entry. (physical dtb address)
  *
  * Put the CPU into the same state as it would be if it had been reset, and
  * branch to what would be the reset vector. It must be executed with the

arch/arm64/kernel/head.S

@@ -31,6 +31,7 @@
 #include <asm/cache.h>
 #include <asm/cputype.h>
 #include <asm/elf.h>
+#include <asm/image.h>
 #include <asm/kernel-pgtable.h>
 #include <asm/kvm_arm.h>
 #include <asm/memory.h>
@@ -91,7 +92,7 @@ _head:
 	.quad	0				// reserved
 	.quad	0				// reserved
 	.quad	0				// reserved
-	.ascii	"ARM\x64"			// Magic number
+	.ascii	ARM64_IMAGE_MAGIC		// Magic number
 #ifdef CONFIG_EFI
 	.long	pe_header - _head		// Offset to the PE header.
 

arch/arm64/kernel/image.h

@@ -15,13 +15,15 @@
  * You should have received a copy of the GNU General Public License
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
-#ifndef __ASM_IMAGE_H
-#define __ASM_IMAGE_H
+#ifndef __ARM64_KERNEL_IMAGE_H
+#define __ARM64_KERNEL_IMAGE_H
 
 #ifndef LINKER_SCRIPT
 #error This file should only be included in vmlinux.lds.S
 #endif
 
+#include <asm/image.h>
+
 /*
  * There aren't any ELF relocations we can use to endian-swap values known only
  * at link time (e.g. the subtraction of two symbol addresses), so we must get
@@ -47,19 +49,22 @@
 	sym##_lo32 = DATA_LE32((data) & 0xffffffff);		\
 	sym##_hi32 = DATA_LE32((data) >> 32)
 
+#define __HEAD_FLAG(field)	(__HEAD_FLAG_##field << \
+					ARM64_IMAGE_FLAG_##field##_SHIFT)
+
 #ifdef CONFIG_CPU_BIG_ENDIAN
-#define __HEAD_FLAG_BE		1
+#define __HEAD_FLAG_BE		ARM64_IMAGE_FLAG_BE
 #else
-#define __HEAD_FLAG_BE		0
+#define __HEAD_FLAG_BE		ARM64_IMAGE_FLAG_LE
 #endif
 
 #define __HEAD_FLAG_PAGE_SIZE	((PAGE_SHIFT - 10) / 2)
 
 #define __HEAD_FLAG_PHYS_BASE	1
 
-#define __HEAD_FLAGS		((__HEAD_FLAG_BE << 0) |	\
-				 (__HEAD_FLAG_PAGE_SIZE << 1) |	\
-				 (__HEAD_FLAG_PHYS_BASE << 3))
+#define __HEAD_FLAGS		(__HEAD_FLAG(BE)	| \
+				 __HEAD_FLAG(PAGE_SIZE) | \
+				 __HEAD_FLAG(PHYS_BASE))
 
 /*
  * These will output as part of the Image header, which should be little-endian
@@ -109,4 +114,4 @@ __efistub_screen_info		= screen_info;
 
 #endif
 
-#endif /* __ASM_IMAGE_H */
+#endif /* __ARM64_KERNEL_IMAGE_H */

arch/arm64/kernel/kexec_image.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Kexec image loader
+
+ * Copyright (C) 2018 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ */
+
+#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 <linux/verification.h>
+#include <asm/byteorder.h>
+#include <asm/cpufeature.h>
+#include <asm/image.h>
+#include <asm/memory.h>
+
+static int image_probe(const char *kernel_buf, unsigned long kernel_len)
+{
+	const struct arm64_image_header *h =
+		(const struct arm64_image_header *)(kernel_buf);
+
+	if (!h || (kernel_len < sizeof(*h)))
+		return -EINVAL;
+
+	if (memcmp(&h->magic, ARM64_IMAGE_MAGIC, sizeof(h->magic)))
+		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 arm64_image_header *h;
+	u64 flags, value;
+	bool be_image, be_kernel;
+	struct kexec_buf kbuf;
+	unsigned long text_offset;
+	struct kexec_segment *kernel_segment;
+	int ret;
+
+	/* We don't support crash kernels yet. */
+	if (image->type == KEXEC_TYPE_CRASH)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	/*
+	 * We require a kernel with an unambiguous Image header. Per
+	 * Documentation/booting.txt, this is the case when image_size
+	 * is non-zero (practically speaking, since v3.17).
+	 */
+	h = (struct arm64_image_header *)kernel;
+	if (!h->image_size)
+		return ERR_PTR(-EINVAL);
+
+	/* Check cpu features */
+	flags = le64_to_cpu(h->flags);
+	be_image = arm64_image_flag_field(flags, ARM64_IMAGE_FLAG_BE);
+	be_kernel = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
+	if ((be_image != be_kernel) && !system_supports_mixed_endian())
+		return ERR_PTR(-EINVAL);
+
+	value = arm64_image_flag_field(flags, ARM64_IMAGE_FLAG_PAGE_SIZE);
+	if (((value == ARM64_IMAGE_FLAG_PAGE_SIZE_4K) &&
+			!system_supports_4kb_granule()) ||
+	    ((value == ARM64_IMAGE_FLAG_PAGE_SIZE_64K) &&
+			!system_supports_64kb_granule()) ||
+	    ((value == ARM64_IMAGE_FLAG_PAGE_SIZE_16K) &&
+			!system_supports_16kb_granule()))
+		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 = 0;
+	kbuf.memsz = le64_to_cpu(h->image_size);
+	text_offset = le64_to_cpu(h->text_offset);
+	kbuf.buf_align = MIN_KIMG_ALIGN;
+
+	/* Adjust kernel segment with TEXT_OFFSET */
+	kbuf.memsz += text_offset;
+
+	ret = kexec_add_buffer(&kbuf);
+	if (ret)
+		return ERR_PTR(ret);
+
+	kernel_segment = &image->segment[image->nr_segments - 1];
+	kernel_segment->mem += text_offset;
+	kernel_segment->memsz -= text_offset;
+	image->start = kernel_segment->mem;
+
+	pr_debug("Loaded kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+				kernel_segment->mem, kbuf.bufsz,
+				kernel_segment->memsz);
+
+	/* Load additional data */
+	ret = load_other_segments(image,
+				kernel_segment->mem, kernel_segment->memsz,
+				initrd, initrd_len, cmdline);
+
+	return ERR_PTR(ret);
+}
+
+#ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG
+static int image_verify_sig(const char *kernel, unsigned long kernel_len)
+{
+	return verify_pefile_signature(kernel, kernel_len, NULL,
+				       VERIFYING_KEXEC_PE_SIGNATURE);
+}
+#endif
+
+const struct kexec_file_ops kexec_image_ops = {
+	.probe = image_probe,
+	.load = image_load,
+#ifdef CONFIG_KEXEC_IMAGE_VERIFY_SIG
+	.verify_sig = image_verify_sig,
+#endif
+};

arch/arm64/kernel/machine_kexec.c

@@ -212,9 +212,17 @@ void machine_kexec(struct kimage *kimage)
 	 * uses physical addressing to relocate the new image to its final
 	 * position and transfers control to the image entry point when the
 	 * relocation is complete.
+	 * In kexec case, kimage->start points to purgatory assuming that
+	 * kernel entry and dtb address are embedded in purgatory by
+	 * userspace (kexec-tools).
+	 * In kexec_file case, the kernel starts directly without purgatory.
 	 */
-
-	cpu_soft_restart(reboot_code_buffer_phys, kimage->head, kimage->start, 0);
+	cpu_soft_restart(reboot_code_buffer_phys, kimage->head, kimage->start,
+#ifdef CONFIG_KEXEC_FILE
+						kimage->arch.dtb_mem);
+#else
+						0);
+#endif
 
 	BUG(); /* Should never get here. */
 }

arch/arm64/kernel/machine_kexec_file.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * kexec_file for arm64
+ *
+ * Copyright (C) 2018 Linaro Limited
+ * Author: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * Most code is derived from arm64 port of kexec-tools
+ */
+
+#define pr_fmt(fmt) "kexec_file: " fmt
+
+#include <linux/ioport.h>
+#include <linux/kernel.h>
+#include <linux/kexec.h>
+#include <linux/libfdt.h>
+#include <linux/memblock.h>
+#include <linux/of_fdt.h>
+#include <linux/random.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+/* relevant device tree properties */
+#define FDT_PROP_INITRD_START	"linux,initrd-start"
+#define FDT_PROP_INITRD_END	"linux,initrd-end"
+#define FDT_PROP_BOOTARGS	"bootargs"
+#define FDT_PROP_KASLR_SEED	"kaslr-seed"
+
+const struct kexec_file_ops * const kexec_file_loaders[] = {
+	&kexec_image_ops,
+	NULL
+};
+
+int arch_kimage_file_post_load_cleanup(struct kimage *image)
+{
+	vfree(image->arch.dtb);
+	image->arch.dtb = NULL;
+
+	return kexec_image_post_load_cleanup_default(image);
+}
+
+static int setup_dtb(struct kimage *image,
+		     unsigned long initrd_load_addr, unsigned long initrd_len,
+		     char *cmdline, void *dtb)
+{
+	int off, ret;
+
+	ret = fdt_path_offset(dtb, "/chosen");
+	if (ret < 0)
+		goto out;
+
+	off = ret;
+
+	/* add bootargs */
+	if (cmdline) {
+		ret = fdt_setprop_string(dtb, off, FDT_PROP_BOOTARGS, cmdline);
+		if (ret)
+			goto out;
+	} else {
+		ret = fdt_delprop(dtb, off, FDT_PROP_BOOTARGS);
+		if (ret && (ret != -FDT_ERR_NOTFOUND))
+			goto out;
+	}
+
+	/* add initrd-* */
+	if (initrd_load_addr) {
+		ret = fdt_setprop_u64(dtb, off, FDT_PROP_INITRD_START,
+				      initrd_load_addr);
+		if (ret)
+			goto out;
+
+		ret = fdt_setprop_u64(dtb, off, FDT_PROP_INITRD_END,
+				      initrd_load_addr + initrd_len);
+		if (ret)
+			goto out;
+	} else {
+		ret = fdt_delprop(dtb, off, FDT_PROP_INITRD_START);
+		if (ret && (ret != -FDT_ERR_NOTFOUND))
+			goto out;
+
+		ret = fdt_delprop(dtb, off, FDT_PROP_INITRD_END);
+		if (ret && (ret != -FDT_ERR_NOTFOUND))
+			goto out;
+	}
+
+	/* add kaslr-seed */
+	ret = fdt_delprop(dtb, off, FDT_PROP_KASLR_SEED);
+	if (ret && (ret != -FDT_ERR_NOTFOUND))
+		goto out;
+
+	if (rng_is_initialized()) {
+		u64 seed = get_random_u64();
+		ret = fdt_setprop_u64(dtb, off, FDT_PROP_KASLR_SEED, seed);
+		if (ret)
+			goto out;
+	} else {
+		pr_notice("RNG is not initialised: omitting \"%s\" property\n",
+				FDT_PROP_KASLR_SEED);
+	}
+
+out:
+	if (ret)
+		return (ret == -FDT_ERR_NOSPACE) ? -ENOMEM : -EINVAL;
+
+	return 0;
+}
+
+/*
+ * More space needed so that we can add initrd, bootargs and kaslr-seed.
+ */
+#define DTB_EXTRA_SPACE 0x1000
+
+static int create_dtb(struct kimage *image,
+		      unsigned long initrd_load_addr, unsigned long initrd_len,
+		      char *cmdline, void **dtb)
+{
+	void *buf;
+	size_t buf_size;
+	int ret;
+
+	buf_size = fdt_totalsize(initial_boot_params)
+			+ strlen(cmdline) + DTB_EXTRA_SPACE;
+
+	for (;;) {
+		buf = vmalloc(buf_size);
+		if (!buf)
+			return -ENOMEM;
+
+		/* duplicate a device tree blob */
+		ret = fdt_open_into(initial_boot_params, buf, buf_size);
+		if (ret)
+			return -EINVAL;
+
+		ret = setup_dtb(image, initrd_load_addr, initrd_len,
+				cmdline, buf);
+		if (ret) {
+			vfree(buf);
+			if (ret == -ENOMEM) {
+				/* unlikely, but just in case */
+				buf_size += DTB_EXTRA_SPACE;
+				continue;
+			} else {
+				return ret;
+			}
+		}
+
+		/* trim it */
+		fdt_pack(buf);
+		*dtb = buf;
+
+		return 0;
+	}
+}
+
+int load_other_segments(struct kimage *image,
+			unsigned long kernel_load_addr,
+			unsigned long kernel_size,
+			char *initrd, unsigned long initrd_len,
+			char *cmdline)
+{
+	struct kexec_buf kbuf;
+	void *dtb = NULL;
+	unsigned long initrd_load_addr = 0, dtb_len;
+	int ret = 0;
+
+	kbuf.image = image;
+	/* not allocate anything below the kernel */
+	kbuf.buf_min = kernel_load_addr + kernel_size;
+
+	/* load initrd */
+	if (initrd) {
+		kbuf.buffer = initrd;
+		kbuf.bufsz = initrd_len;
+		kbuf.mem = 0;
+		kbuf.memsz = initrd_len;
+		kbuf.buf_align = 0;
+		/* within 1GB-aligned window of up to 32GB in size */
+		kbuf.buf_max = round_down(kernel_load_addr, SZ_1G)
+						+ (unsigned long)SZ_1G * 32;
+		kbuf.top_down = false;
+
+		ret = kexec_add_buffer(&kbuf);
+		if (ret)
+			goto out_err;
+		initrd_load_addr = kbuf.mem;
+
+		pr_debug("Loaded initrd at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+				initrd_load_addr, initrd_len, initrd_len);
+	}
+
+	/* load dtb */
+	ret = create_dtb(image, initrd_load_addr, initrd_len, cmdline, &dtb);
+	if (ret) {
+		pr_err("Preparing for new dtb failed\n");
+		goto out_err;
+	}
+
+	dtb_len = fdt_totalsize(dtb);
+	kbuf.buffer = dtb;
+	kbuf.bufsz = dtb_len;
+	kbuf.mem = 0;
+	kbuf.memsz = dtb_len;
+	/* not across 2MB boundary */
+	kbuf.buf_align = SZ_2M;
+	kbuf.buf_max = ULONG_MAX;
+	kbuf.top_down = true;
+
+	ret = kexec_add_buffer(&kbuf);
+	if (ret)
+		goto out_err;
+	image->arch.dtb = dtb;
+	image->arch.dtb_mem = kbuf.mem;
+
+	pr_debug("Loaded dtb at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+			kbuf.mem, dtb_len, dtb_len);
+
+	return 0;
+
+out_err:
+	vfree(dtb);
+	return ret;
+}

arch/arm64/kernel/relocate_kernel.S

@@ -32,6 +32,7 @@
 ENTRY(arm64_relocate_new_kernel)
 
 	/* Setup the list loop variables. */
+	mov	x18, x2				/* x18 = dtb address */
 	mov	x17, x1				/* x17 = kimage_start */
 	mov	x16, x0				/* x16 = kimage_head */
 	raw_dcache_line_size x15, x0		/* x15 = dcache line size */
@@ -107,7 +108,7 @@ ENTRY(arm64_relocate_new_kernel)
 	isb
 
 	/* Start new image. */
-	mov	x0, xzr
+	mov	x0, x18
 	mov	x1, xzr
 	mov	x2, xzr
 	mov	x3, xzr

arch/powerpc/kernel/machine_kexec_file_64.c

@@ -24,7 +24,6 @@
 
 #include <linux/slab.h>
 #include <linux/kexec.h>
-#include <linux/memblock.h>
 #include <linux/of_fdt.h>
 #include <linux/libfdt.h>
 #include <asm/ima.h>
@@ -46,59 +45,6 @@ int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
 	return kexec_image_probe_default(image, buf, buf_len);
 }
 
-/**
- * arch_kexec_walk_mem - call func(data) for each unreserved memory block
- * @kbuf:	Context info for the search. Also passed to @func.
- * @func:	Function to call for each memory block.
- *
- * This function is used by kexec_add_buffer and kexec_locate_mem_hole
- * to find unreserved memory to load kexec segments into.
- *
- * Return: The memory walk will stop when func returns a non-zero value
- * and that value will be returned. If all free regions are visited without
- * func returning non-zero, then zero will be returned.
- */
-int arch_kexec_walk_mem(struct kexec_buf *kbuf,
-			int (*func)(struct resource *, void *))
-{
-	int ret = 0;
-	u64 i;
-	phys_addr_t mstart, mend;
-	struct resource res = { };
-
-	if (kbuf->top_down) {
-		for_each_free_mem_range_reverse(i, NUMA_NO_NODE, 0,
-						&mstart, &mend, NULL) {
-			/*
-			 * In memblock, end points to the first byte after the
-			 * range while in kexec, end points to the last byte
-			 * in the range.
-			 */
-			res.start = mstart;
-			res.end = mend - 1;
-			ret = func(&res, kbuf);
-			if (ret)
-				break;
-		}
-	} else {
-		for_each_free_mem_range(i, NUMA_NO_NODE, 0, &mstart, &mend,
-					NULL) {
-			/*
-			 * In memblock, end points to the first byte after the
-			 * range while in kexec, end points to the last byte
-			 * in the range.
-			 */
-			res.start = mstart;
-			res.end = mend - 1;
-			ret = func(&res, kbuf);
-			if (ret)
-				break;
-		}
-	}
-
-	return ret;
-}
-
 /**
  * setup_purgatory - initialize the purgatory's global variables
  * @image:		kexec image.

arch/s390/kernel/machine_kexec_file.c

@@ -134,16 +134,6 @@ int kexec_file_add_initrd(struct kimage *image, struct s390_load_data *data,
 	return ret;
 }
 
-/*
- * The kernel is loaded to a fixed location. Turn off kexec_locate_mem_hole
- * and provide kbuf->mem by hand.
- */
-int arch_kexec_walk_mem(struct kexec_buf *kbuf,
-			int (*func)(struct resource *, void *))
-{
-	return 1;
-}
-
 int arch_kexec_apply_relocations_add(struct purgatory_info *pi,
 				     Elf_Shdr *section,
 				     const Elf_Shdr *relsec,

include/linux/kexec.h

@@ -143,6 +143,15 @@ extern const struct kexec_file_ops * const kexec_file_loaders[];
 
 int kexec_image_probe_default(struct kimage *image, void *buf,
 			      unsigned long buf_len);
+int kexec_image_post_load_cleanup_default(struct kimage *image);
+
+/*
+ * If kexec_buf.mem is set to this value, kexec_locate_mem_hole()
+ * will try to allocate free memory. Arch may overwrite it.
+ */
+#ifndef KEXEC_BUF_MEM_UNKNOWN
+#define KEXEC_BUF_MEM_UNKNOWN 0
+#endif
 
 /**
  * struct kexec_buf - parameters for finding a place for a buffer in memory
@@ -183,8 +192,6 @@ int __weak arch_kexec_apply_relocations(struct purgatory_info *pi,
 					const Elf_Shdr *relsec,
 					const Elf_Shdr *symtab);
 
-int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf,
-			       int (*func)(struct resource *, void *));
 extern int kexec_add_buffer(struct kexec_buf *kbuf);
 int kexec_locate_mem_hole(struct kexec_buf *kbuf);
 

include/linux/pe.h

@@ -166,7 +166,7 @@ struct mz_hdr {
 	uint16_t oem_info;	/* oem specific */
 	uint16_t reserved1[10];	/* reserved */
 	uint32_t peaddr;	/* address of pe header */
-	char     message[64];	/* message to print */
+	char     message[];	/* message to print */
 };
 
 struct mz_reloc {

include/uapi/asm-generic/unistd.h

@@ -738,9 +738,11 @@ __SYSCALL(__NR_statx,     sys_statx)
 __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
 #define __NR_rseq 293
 __SYSCALL(__NR_rseq, sys_rseq)
+#define __NR_kexec_file_load 294
+__SYSCALL(__NR_kexec_file_load,     sys_kexec_file_load)
 
 #undef __NR_syscalls
-#define __NR_syscalls 294
+#define __NR_syscalls 295
 
 /*
  * 32 bit systems traditionally used different

kernel/kexec_file.c

@@ -16,6 +16,7 @@
 #include <linux/file.h>
 #include <linux/slab.h>
 #include <linux/kexec.h>
+#include <linux/memblock.h>
 #include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/fs.h>
@@ -76,7 +77,7 @@ void * __weak arch_kexec_kernel_image_load(struct kimage *image)
 	return kexec_image_load_default(image);
 }
 
-static int kexec_image_post_load_cleanup_default(struct kimage *image)
+int kexec_image_post_load_cleanup_default(struct kimage *image)
 {
 	if (!image->fops || !image->fops->cleanup)
 		return 0;
@@ -499,8 +500,60 @@ static int locate_mem_hole_callback(struct resource *res, void *arg)
 	return locate_mem_hole_bottom_up(start, end, kbuf);
 }
 
+#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
+static int kexec_walk_memblock(struct kexec_buf *kbuf,
+			       int (*func)(struct resource *, void *))
+{
+	return 0;
+}
+#else
+static int kexec_walk_memblock(struct kexec_buf *kbuf,
+			       int (*func)(struct resource *, void *))
+{
+	int ret = 0;
+	u64 i;
+	phys_addr_t mstart, mend;
+	struct resource res = { };
+
+	if (kbuf->image->type == KEXEC_TYPE_CRASH)
+		return func(&crashk_res, kbuf);
+
+	if (kbuf->top_down) {
+		for_each_free_mem_range_reverse(i, NUMA_NO_NODE, MEMBLOCK_NONE,
+						&mstart, &mend, NULL) {
+			/*
+			 * In memblock, end points to the first byte after the
+			 * range while in kexec, end points to the last byte
+			 * in the range.
+			 */
+			res.start = mstart;
+			res.end = mend - 1;
+			ret = func(&res, kbuf);
+			if (ret)
+				break;
+		}
+	} else {
+		for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE,
+					&mstart, &mend, NULL) {
+			/*
+			 * In memblock, end points to the first byte after the
+			 * range while in kexec, end points to the last byte
+			 * in the range.
+			 */
+			res.start = mstart;
+			res.end = mend - 1;
+			ret = func(&res, kbuf);
+			if (ret)
+				break;
+		}
+	}
+
+	return ret;
+}
+#endif
+
 /**
- * arch_kexec_walk_mem - call func(data) on free memory regions
+ * kexec_walk_resources - call func(data) on free memory regions
  * @kbuf:	Context info for the search. Also passed to @func.
  * @func:	Function to call for each memory region.
  *
@@ -508,7 +561,7 @@ static int locate_mem_hole_callback(struct resource *res, void *arg)
  * and that value will be returned. If all free regions are visited without
  * func returning non-zero, then zero will be returned.
  */
-int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf,
+static int kexec_walk_resources(struct kexec_buf *kbuf,
 				int (*func)(struct resource *, void *))
 {
 	if (kbuf->image->type == KEXEC_TYPE_CRASH)
@@ -532,7 +585,14 @@ int kexec_locate_mem_hole(struct kexec_buf *kbuf)
 {
 	int ret;
 
-	ret = arch_kexec_walk_mem(kbuf, locate_mem_hole_callback);
+	/* Arch knows where to place */
+	if (kbuf->mem != KEXEC_BUF_MEM_UNKNOWN)
+		return 0;
+
+	if (IS_ENABLED(CONFIG_ARCH_DISCARD_MEMBLOCK))
+		ret = kexec_walk_resources(kbuf, locate_mem_hole_callback);
+	else
+		ret = kexec_walk_memblock(kbuf, locate_mem_hole_callback);
 
 	return ret == 1 ? 0 : -EADDRNOTAVAIL;
 }