Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1718948 > unrolled thread

[PATCH 00/14] arm64: kexec: add kexec_file_load support

Back to article view | Back to linux.kernel

Contents

  [PATCH 00/14] arm64: kexec: add kexec_file_load support AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-24 10:20 +0200
    [PATCH 14/14] arm64: kexec_file: add vmlinux format support AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-24 10:20 +0200
      Re: [PATCH 14/14] arm64: kexec_file: add vmlinux format support Mark Rutland <mark.rutland@arm.com> - 2017-08-24 19:40 +0200
        Re: [PATCH 14/14] arm64: kexec_file: add vmlinux format support AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-25 04:10 +0200
          Re: [PATCH 14/14] arm64: kexec_file: add vmlinux format support Dave Young <dyoung@redhat.com> - 2017-08-25 08:20 +0200
    [PATCH 08/14] arm64: kexec_file: create purgatory AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-24 10:20 +0200
      Re: [PATCH 08/14] arm64: kexec_file: create purgatory Ard Biesheuvel <ard.biesheuvel@linaro.org> - 2017-08-24 11:20 +0200
        Re: [PATCH 08/14] arm64: kexec_file: create purgatory AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-25 03:20 +0200
      Re: [PATCH 08/14] arm64: kexec_file: create purgatory Mark Rutland <mark.rutland@arm.com> - 2017-08-24 19:00 +0200
        Re: [PATCH 08/14] arm64: kexec_file: create purgatory AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-25 03:10 +0200
          Re: [PATCH 08/14] arm64: kexec_file: create purgatory Mark Rutland <mark.rutland@arm.com> - 2017-08-25 12:30 +0200
    [PATCH 02/14] include: pe.h: remove message[] from mz header definition AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-24 10:20 +0200
      Re: [PATCH 02/14] include: pe.h: remove message[] from mz header definition Ard Biesheuvel <ard.biesheuvel@linaro.org> - 2017-08-24 11:10 +0200
    [PATCH 01/14] MODSIGN: Export module signature definitions AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-24 10:20 +0200
    [PATCH 09/14] arm64: kexec_file: add sha256 digest check in purgatory AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-24 10:30 +0200
      Re: [PATCH 09/14] arm64: kexec_file: add sha256 digest check in purgatory Ard Biesheuvel <ard.biesheuvel@linaro.org> - 2017-08-24 11:20 +0200
        Re: [PATCH 09/14] arm64: kexec_file: add sha256 digest check in  purgatory AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-25 03:30 +0200
      Re: [PATCH 09/14] arm64: kexec_file: add sha256 digest check in  purgatory Mark Rutland <mark.rutland@arm.com> - 2017-08-24 19:10 +0200
        Re: [PATCH 09/14] arm64: kexec_file: add sha256 digest check in  purgatory AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-25 03:30 +0200
          Re: [PATCH 09/14] arm64: kexec_file: add sha256 digest check in  purgatory Mark Rutland <mark.rutland@arm.com> - 2017-08-25 12:50 +0200
    [PATCH 07/14] asm-generic: add kexec_file_load system call to unistd.h AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-24 10:30 +0200
      Re: [PATCH 07/14] asm-generic: add kexec_file_load system call to unistd.h Arnd Bergmann <arnd@arndb.de> - 2017-08-24 13:00 +0200
    [PATCH 13/14] arm64: kexec_file: add Image format support AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-24 10:30 +0200
      Re: [PATCH 13/14] arm64: kexec_file: add Image format support Mark Rutland <mark.rutland@arm.com> - 2017-08-24 19:30 +0200
        Re: [PATCH 13/14] arm64: kexec_file: add Image format support AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-25 04:00 +0200
    [PATCH 03/14] resource: add walk_system_ram_res_rev() AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-24 10:30 +0200
      Re: [PATCH 03/14] resource: add walk_system_ram_res_rev() Ard Biesheuvel <ard.biesheuvel@linaro.org> - 2017-08-24 11:10 +0200
        Re: [PATCH 03/14] resource: add walk_system_ram_res_rev() AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-25 03:00 +0200
    [PATCH 10/14] arm64: kexec_file: load initrd, device-tree and purgatory segments AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-24 10:30 +0200
      Re: [PATCH 10/14] arm64: kexec_file: load initrd, device-tree and  purgatory segments Mark Rutland <mark.rutland@arm.com> - 2017-08-24 19:20 +0200
        Re: [PATCH 10/14] arm64: kexec_file: load initrd, device-tree and  purgatory segments AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-25 03:40 +0200
    [PATCH 04/14] kexec_file: factor out vmlinux (elf) parser from powerpc AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-24 10:30 +0200
    [PATCH 05/14] kexec_file: factor out crashdump elf header function from x86 AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-24 10:30 +0200
      Re: [PATCH 05/14] kexec_file: factor out crashdump elf header  function from x86 Dave Young <dyoung@redhat.com> - 2017-08-25 07:50 +0200
    [PATCH 06/14] kexec_file: add kexec_add_segment() AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-24 10:30 +0200
    [PATCH 12/14] arm64: enable KEXEC_FILE config AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-24 10:30 +0200
    [PATCH 11/14] arm64: kexec_file: set up for crash dump adding elf core header AKASHI Takahiro <takahiro.akashi@linaro.org> - 2017-08-24 10:30 +0200

Page 2 of 2 — ← Prev page 1 [2]

#1718965 — [PATCH 07/14] asm-generic: add kexec_file_load system call to unistd.h

The initial user of this system call number is arm64.

Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Cc: Arnd Bergmann <arnd@arndb.de>
---
 include/uapi/asm-generic/unistd.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 061185a5eb51..086697fe3917 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -731,9 +731,11 @@ __SYSCALL(__NR_pkey_alloc,    sys_pkey_alloc)
 __SYSCALL(__NR_pkey_free,     sys_pkey_free)
 #define __NR_statx 291
 __SYSCALL(__NR_statx,     sys_statx)
+#define __NR_kexec_file_load 292
+__SYSCALL(__NR_kexec_file_load,     sys_kexec_file_load)
 
 #undef __NR_syscalls
-#define __NR_syscalls 292
+#define __NR_syscalls 293
 
 /*
  * All syscalls below here should go away really,
-- 
2.14.1

[toc] | [prev] | [next] | [standalone]

#1719153 — Re: [PATCH 07/14] asm-generic: add kexec_file_load system call to unistd.h

On Thu, Aug 24, 2017 at 10:18 AM, AKASHI Takahiro
<takahiro.akashi@linaro.org> wrote:
> The initial user of this system call number is arm64.
>
> Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
> Cc: Arnd Bergmann <arnd@arndb.de>

Acked-by:Arnd Bergmann <arnd@arndb.de>

[toc] | [prev] | [next] | [standalone]

#1718967 — [PATCH 13/14] arm64: kexec_file: add Image format support

The "Image" binary will be loaded at the offset of TEXT_OFFSET from
the start of system memory. TEXT_OFFSET is basically determined from
the header of the image.

Regarding kernel verification, it will be done through
verify_pefile_signature() as arm64's "Image" binary can be seen as
in PE format. This approach is consistent with x86 implementation.

we can sign it with sbsign command.

Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/Kconfig                     |  11 ++--
 arch/arm64/include/asm/kexec_file.h    |  83 ++++++++++++++++++++++++
 arch/arm64/kernel/Makefile             |   1 +
 arch/arm64/kernel/kexec_image.c        | 112 +++++++++++++++++++++++++++++++++
 arch/arm64/kernel/machine_kexec_file.c |   6 +-
 5 files changed, 208 insertions(+), 5 deletions(-)
 create mode 100644 arch/arm64/include/asm/kexec_file.h
 create mode 100644 arch/arm64/kernel/kexec_image.c

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index cf10bc720d9e..c8f603700bdd 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -766,18 +766,21 @@ config KEXEC_FILE
 	  for kernel and initramfs as opposed to list of segments as
 	  accepted by previous system call.
 
+config KEXEC_FILE_IMAGE_FMT
+	bool "Enable Image support"
+	depends on KEXEC_FILE
+	---help---
+	  Select this option to enable 'Image' kernel loading.
+
 config KEXEC_VERIFY_SIG
 	bool "Verify kernel signature during kexec_file_load() syscall"
 	depends on KEXEC_FILE
 	select SYSTEM_DATA_VERIFICATION
+	select SIGNED_PE_FILE_VERIFICATION if KEXEC_FILE_IMAGE_FMT
 	---help---
 	  This option makes kernel signature verification mandatory for
 	  the kexec_file_load() syscall.
 
-	  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 CRASH_DUMP
 	bool "Build kdump crash kernel"
 	help
diff --git a/arch/arm64/include/asm/kexec_file.h b/arch/arm64/include/asm/kexec_file.h
new file mode 100644
index 000000000000..5df899aa0d2e
--- /dev/null
+++ b/arch/arm64/include/asm/kexec_file.h
@@ -0,0 +1,83 @@
+#ifndef _ASM_KEXEC_FILE_H
+#define _ASM_KEXEC_FILE_H
+
+extern struct kexec_file_ops kexec_image_ops;
+
+/**
+ * struct arm64_image_header - arm64 kernel image header.
+ *
+ * @pe_sig: Optional PE format 'MZ' signature.
+ * @branch_code: Reserved for instructions to branch to stext.
+ * @text_offset: The image load offset in LSB byte order.
+ * @image_size: An estimated size of the memory image size in LSB byte order.
+ * @flags: Bit flags:
+ *  Bit 7.0: Image byte order, 1=MSB.
+ * @reserved_1: Reserved.
+ * @magic: Magic number, "ARM\x64".
+ * @pe_header: Optional offset to a PE format header.
+ **/
+
+struct arm64_image_header {
+	u8 pe_sig[2];
+	u16 branch_code[3];
+	u64 text_offset;
+	u64 image_size;
+	u8 flags[8];
+	u64 reserved_1[3];
+	u8 magic[4];
+	u32 pe_header;
+};
+
+static const u8 arm64_image_magic[4] = {'A', 'R', 'M', 0x64U};
+static const u8 arm64_image_pe_sig[2] = {'M', 'Z'};
+static const u64 arm64_image_flag_7_be = 0x01U;
+
+/**
+ * arm64_header_check_magic - Helper to check the arm64 image header.
+ *
+ * Returns non-zero if header is OK.
+ */
+
+static inline int arm64_header_check_magic(const struct arm64_image_header *h)
+{
+	if (!h)
+		return 0;
+
+	if (!h->text_offset)
+		return 0;
+
+	return (h->magic[0] == arm64_image_magic[0]
+		&& h->magic[1] == arm64_image_magic[1]
+		&& h->magic[2] == arm64_image_magic[2]
+		&& h->magic[3] == arm64_image_magic[3]);
+}
+
+/**
+ * arm64_header_check_pe_sig - Helper to check the arm64 image header.
+ *
+ * Returns non-zero if 'MZ' signature is found.
+ */
+
+static inline int arm64_header_check_pe_sig(const struct arm64_image_header *h)
+{
+	if (!h)
+		return 0;
+
+	return (h->pe_sig[0] == arm64_image_pe_sig[0]
+		&& h->pe_sig[1] == arm64_image_pe_sig[1]);
+}
+
+/**
+ * arm64_header_check_msb - Helper to check the arm64 image header.
+ *
+ * Returns non-zero if the image was built as big endian.
+ */
+
+static inline int arm64_header_check_msb(const struct arm64_image_header *h)
+{
+	if (!h)
+		return 0;
+
+	return !!(h->flags[7] & arm64_image_flag_7_be);
+}
+#endif  /* _ASM_KEXE_FILE_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 5df003d6157c..a1161bab6810 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -51,6 +51,7 @@ arm64-obj-$(CONFIG_HIBERNATION)		+= hibernate.o hibernate-asm.o
 arm64-obj-$(CONFIG_KEXEC_CORE)		+= machine_kexec.o relocate_kernel.o	\
 					   cpu-reset.o
 arm64-obj-$(CONFIG_KEXEC_FILE)		+= machine_kexec_file.o
+arm64-obj-$(CONFIG_KEXEC_FILE_IMAGE_FMT)	+= 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
diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c
new file mode 100644
index 000000000000..db4aa1379fec
--- /dev/null
+++ b/arch/arm64/kernel/kexec_image.c
@@ -0,0 +1,112 @@
+/*
+ * Kexec image loader
+
+ * Copyright (C) 2017 Linaro Limited
+ * Authors: AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#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/verification.h>
+#include <asm/byteorder.h>
+#include <asm/kexec_file.h>
+#include <asm/memory.h>
+
+static int image_probe(const char *kernel_buf, unsigned long kernel_len)
+{
+	const struct arm64_image_header *h;
+
+	h = (const struct arm64_image_header *)(kernel_buf);
+
+	if ((kernel_len < sizeof(*h)) || !arm64_header_check_magic(h))
+		return -EINVAL;
+
+	pr_debug("%s: PE format: %s\n", __func__,
+		(arm64_header_check_pe_sig(h) ? "yes" : "no"));
+
+	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 kexec_buf kbuf;
+	struct arm64_image_header *h = (struct arm64_image_header *)kernel;
+	unsigned long text_offset, kernel_load_addr;
+	int ret;
+
+	/* Create elf core header segment */
+	ret = load_crashdump_segments(image);
+	if (ret)
+		goto out;
+
+	/* Load the kernel */
+	kbuf.image = image;
+	if (image->type == KEXEC_TYPE_CRASH) {
+		kbuf.buf_min = crashk_res.start;
+		kbuf.buf_max = crashk_res.end + 1;
+	} else {
+		kbuf.buf_min = 0;
+		kbuf.buf_max = ULONG_MAX;
+	}
+	kbuf.top_down = 0;
+
+	kbuf.buffer = kernel;
+	kbuf.bufsz = kernel_len;
+	if (h->image_size) {
+		kbuf.memsz = le64_to_cpu(h->image_size);
+		text_offset = le64_to_cpu(h->text_offset);
+	} else {
+		/* v3.16 or older */
+		kbuf.memsz = kbuf.bufsz; /* NOTE: not including BSS */
+		text_offset = 0x80000;
+	}
+	kbuf.buf_align = SZ_2M;
+
+	/* Adjust kernel segment with TEXT_OFFSET */
+	kbuf.memsz += text_offset;
+
+	ret = kexec_add_buffer(&kbuf);
+	if (ret)
+		goto out;
+
+	image->segment[image->nr_segments - 1].mem += text_offset;
+	image->segment[image->nr_segments - 1].memsz -= text_offset;
+	kernel_load_addr = kbuf.mem + text_offset;
+
+	pr_debug("Loaded kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+		 kernel_load_addr, kbuf.bufsz, kbuf.memsz);
+
+	/* Load additional data */
+	ret = load_other_segments(image, kernel_load_addr,
+			    initrd, initrd_len, cmdline, cmdline_len);
+
+out:
+	return ERR_PTR(ret);
+}
+
+#ifdef CONFIG_KEXEC_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
+
+struct kexec_file_ops kexec_image_ops = {
+	.probe = image_probe,
+	.load = image_load,
+#ifdef CONFIG_KEXEC_VERIFY_SIG
+	.verify_sig = image_verify_sig,
+#endif
+};
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index 012063307001..ab3b19d51727 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -27,7 +27,11 @@
 static int __dt_root_addr_cells;
 static int __dt_root_size_cells;
 
-static struct kexec_file_ops *kexec_file_loaders[0];
+static struct kexec_file_ops *kexec_file_loaders[] = {
+#ifdef CONFIG_KEXEC_FILE_IMAGE_FMT
+	&kexec_image_ops,
+#endif
+};
 
 int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
 				  unsigned long buf_len)
-- 
2.14.1

[toc] | [prev] | [next] | [standalone]

#1719459 — Re: [PATCH 13/14] arm64: kexec_file: add Image format support

On Thu, Aug 24, 2017 at 05:18:10PM +0900, AKASHI Takahiro wrote:
> The "Image" binary will be loaded at the offset of TEXT_OFFSET from
> the start of system memory. TEXT_OFFSET is basically determined from
> the header of the image.

What's the policy for the binary types kexec_file_load() will load, and
how are these identified? AFAICT, there are no flags, so it looks like
we're just checking the magic and hoping.

> Regarding kernel verification, it will be done through
> verify_pefile_signature() as arm64's "Image" binary can be seen as
> in PE format. This approach is consistent with x86 implementation.

This will not work for kernels built without CONFIG_EFI, where we don't
have a PE header.

What happens in that case?

[...]

> +/**
> + * arm64_header_check_msb - Helper to check the arm64 image header.
> + *
> + * Returns non-zero if the image was built as big endian.
> + */
> +
> +static inline int arm64_header_check_msb(const struct arm64_image_header *h)
> +{
> +	if (!h)
> +		return 0;
> +
> +	return !!(h->flags[7] & arm64_image_flag_7_be);
> +}

What are we going to use this for?

In kernel, we use the term "BE" rather than "MSB", and it's unfortunate
to have code with varying naming conventions.

[...]

> +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 kexec_buf kbuf;
> +	struct arm64_image_header *h = (struct arm64_image_header *)kernel;
> +	unsigned long text_offset, kernel_load_addr;
> +	int ret;
> +
> +	/* Create elf core header segment */
> +	ret = load_crashdump_segments(image);
> +	if (ret)
> +		goto out;
> +
> +	/* Load the kernel */
> +	kbuf.image = image;
> +	if (image->type == KEXEC_TYPE_CRASH) {
> +		kbuf.buf_min = crashk_res.start;
> +		kbuf.buf_max = crashk_res.end + 1;
> +	} else {
> +		kbuf.buf_min = 0;
> +		kbuf.buf_max = ULONG_MAX;
> +	}
> +	kbuf.top_down = 0;
> +
> +	kbuf.buffer = kernel;
> +	kbuf.bufsz = kernel_len;
> +	if (h->image_size) {
> +		kbuf.memsz = le64_to_cpu(h->image_size);
> +		text_offset = le64_to_cpu(h->text_offset);
> +	} else {
> +		/* v3.16 or older */
> +		kbuf.memsz = kbuf.bufsz; /* NOTE: not including BSS */

Why bother supporting < 3.16 kernels?

They predate regulate kexec, we know we don't have enough information to
boot such kernels reliably, and arguably attempting to load one would
indicate some kind of rollback attack.

Thanks,
Mark.

[toc] | [prev] | [next] | [standalone]

#1719712 — Re: [PATCH 13/14] arm64: kexec_file: add Image format support

On Thu, Aug 24, 2017 at 06:23:37PM +0100, Mark Rutland wrote:
> On Thu, Aug 24, 2017 at 05:18:10PM +0900, AKASHI Takahiro wrote:
> > The "Image" binary will be loaded at the offset of TEXT_OFFSET from
> > the start of system memory. TEXT_OFFSET is basically determined from
> > the header of the image.
> 
> What's the policy for the binary types kexec_file_load() will load, and
> how are these identified? AFAICT, there are no flags, so it looks like
> we're just checking the magic and hoping.

Yes, please see image_probe().

> > Regarding kernel verification, it will be done through
> > verify_pefile_signature() as arm64's "Image" binary can be seen as
> > in PE format. This approach is consistent with x86 implementation.
> 
> This will not work for kernels built without CONFIG_EFI, where we don't
> have a PE header.

Right.

> What happens in that case?

In this case, we cannot find a signature in the binary when loading,
so kexec just fails.
Signature is a must if the kernel is configured with KEXEC_FILE_VERIFY.

Thanks,
-Takahiro AKASHI

> [...]
> 
> > +/**
> > + * arm64_header_check_msb - Helper to check the arm64 image header.
> > + *
> > + * Returns non-zero if the image was built as big endian.
> > + */
> > +
> > +static inline int arm64_header_check_msb(const struct arm64_image_header *h)
> > +{
> > +	if (!h)
> > +		return 0;
> > +
> > +	return !!(h->flags[7] & arm64_image_flag_7_be);
> > +}
> 
> What are we going to use this for?

Nowhere. I forgot to remove it.

> In kernel, we use the term "BE" rather than "MSB", and it's unfortunate
> to have code with varying naming conventions.
> 
> [...]
> 
> > +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 kexec_buf kbuf;
> > +	struct arm64_image_header *h = (struct arm64_image_header *)kernel;
> > +	unsigned long text_offset, kernel_load_addr;
> > +	int ret;
> > +
> > +	/* Create elf core header segment */
> > +	ret = load_crashdump_segments(image);
> > +	if (ret)
> > +		goto out;
> > +
> > +	/* Load the kernel */
> > +	kbuf.image = image;
> > +	if (image->type == KEXEC_TYPE_CRASH) {
> > +		kbuf.buf_min = crashk_res.start;
> > +		kbuf.buf_max = crashk_res.end + 1;
> > +	} else {
> > +		kbuf.buf_min = 0;
> > +		kbuf.buf_max = ULONG_MAX;
> > +	}
> > +	kbuf.top_down = 0;
> > +
> > +	kbuf.buffer = kernel;
> > +	kbuf.bufsz = kernel_len;
> > +	if (h->image_size) {
> > +		kbuf.memsz = le64_to_cpu(h->image_size);
> > +		text_offset = le64_to_cpu(h->text_offset);
> > +	} else {
> > +		/* v3.16 or older */
> > +		kbuf.memsz = kbuf.bufsz; /* NOTE: not including BSS */
> 
> Why bother supporting < 3.16 kernels?

Because kexec-tools does :)

> They predate regulate kexec, we know we don't have enough information to
> boot such kernels reliably, and arguably attempting to load one would
> indicate some kind of rollback attack.

Around the time when Geoff were originally working on kexec,
there might be some possibility that people might want to boot a bit older
kernel, I guess.

Thanks,
-Takahiro AKASHI

> Thanks,
> Mark.

[toc] | [prev] | [next] | [standalone]

#1718968 — [PATCH 03/14] resource: add walk_system_ram_res_rev()

This function, being a variant of walk_system_ram_res() introduced in
commit 8c86e70acead ("resource: provide new functions to walk through
resources"), walks through a list of all the resources of System RAM
in reversed order, i.e., from higher to lower.

It will be used in kexec_file implementation on arm64.

Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/ioport.h |  3 +++
 kernel/resource.c      | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 51 insertions(+)

diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 6230064d7f95..9a212266299f 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -271,6 +271,9 @@ extern int
 walk_system_ram_res(u64 start, u64 end, void *arg,
 		    int (*func)(u64, u64, void *));
 extern int
+walk_system_ram_res_rev(u64 start, u64 end, void *arg,
+			int (*func)(u64, u64, void *));
+extern int
 walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, u64 end,
 		    void *arg, int (*func)(u64, u64, void *));
 
diff --git a/kernel/resource.c b/kernel/resource.c
index 9b5f04404152..1d6d734c75ac 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -23,6 +23,7 @@
 #include <linux/pfn.h>
 #include <linux/mm.h>
 #include <linux/resource_ext.h>
+#include <linux/vmalloc.h>
 #include <asm/io.h>
 
 
@@ -469,6 +470,53 @@ int walk_system_ram_res(u64 start, u64 end, void *arg,
 	return ret;
 }
 
+int walk_system_ram_res_rev(u64 start, u64 end, void *arg,
+				int (*func)(u64, u64, void *))
+{
+	struct resource res, *rams;
+	u64 orig_end;
+	int count, i;
+	int ret = -1;
+
+	count = 16; /* initial */
+again:
+	/* create a list */
+	rams = vmalloc(sizeof(struct resource) * count);
+	if (!rams)
+		return ret;
+
+	res.start = start;
+	res.end = end;
+	res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+	orig_end = res.end;
+	i = 0;
+	while ((res.start < res.end) &&
+		(!find_next_iomem_res(&res, IORES_DESC_NONE, true))) {
+		if (i >= count) {
+			/* unlikely but */
+			vfree(rams);
+			count += 16;
+			goto again;
+		}
+
+		rams[i].start = res.start;
+		rams[i++].end = res.end;
+
+		res.start = res.end + 1;
+		res.end = orig_end;
+	}
+
+	/* go reverse */
+	for (i--; i >= 0; i--) {
+		ret = (*func)(rams[i].start, rams[i].end, arg);
+		if (ret)
+			break;
+	}
+
+	vfree(rams);
+	return ret;
+}
+
 #if !defined(CONFIG_ARCH_HAS_WALK_MEMORY)
 
 /*
-- 
2.14.1

[toc] | [prev] | [next] | [standalone]

#1719043 — Re: [PATCH 03/14] resource: add walk_system_ram_res_rev()

On 24 August 2017 at 09:18, AKASHI Takahiro <takahiro.akashi@linaro.org> wrote:
> This function, being a variant of walk_system_ram_res() introduced in
> commit 8c86e70acead ("resource: provide new functions to walk through
> resources"), walks through a list of all the resources of System RAM
> in reversed order, i.e., from higher to lower.
>
> It will be used in kexec_file implementation on arm64.
>
> Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
> Cc: Vivek Goyal <vgoyal@redhat.com>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Linus Torvalds <torvalds@linux-foundation.org>
> ---
>  include/linux/ioport.h |  3 +++
>  kernel/resource.c      | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
>  2 files changed, 51 insertions(+)
>
> diff --git a/include/linux/ioport.h b/include/linux/ioport.h
> index 6230064d7f95..9a212266299f 100644
> --- a/include/linux/ioport.h
> +++ b/include/linux/ioport.h
> @@ -271,6 +271,9 @@ extern int
>  walk_system_ram_res(u64 start, u64 end, void *arg,
>                     int (*func)(u64, u64, void *));
>  extern int
> +walk_system_ram_res_rev(u64 start, u64 end, void *arg,
> +                       int (*func)(u64, u64, void *));
> +extern int
>  walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, u64 end,
>                     void *arg, int (*func)(u64, u64, void *));
>
> diff --git a/kernel/resource.c b/kernel/resource.c
> index 9b5f04404152..1d6d734c75ac 100644
> --- a/kernel/resource.c
> +++ b/kernel/resource.c
> @@ -23,6 +23,7 @@
>  #include <linux/pfn.h>
>  #include <linux/mm.h>
>  #include <linux/resource_ext.h>
> +#include <linux/vmalloc.h>
>  #include <asm/io.h>
>
>
> @@ -469,6 +470,53 @@ int walk_system_ram_res(u64 start, u64 end, void *arg,
>         return ret;
>  }
>
> +int walk_system_ram_res_rev(u64 start, u64 end, void *arg,
> +                               int (*func)(u64, u64, void *))
> +{
> +       struct resource res, *rams;
> +       u64 orig_end;
> +       int count, i;
> +       int ret = -1;
> +
> +       count = 16; /* initial */
> +again:
> +       /* create a list */
> +       rams = vmalloc(sizeof(struct resource) * count);
> +       if (!rams)
> +               return ret;
> +
> +       res.start = start;
> +       res.end = end;
> +       res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
> +       orig_end = res.end;
> +       i = 0;
> +       while ((res.start < res.end) &&
> +               (!find_next_iomem_res(&res, IORES_DESC_NONE, true))) {
> +               if (i >= count) {
> +                       /* unlikely but */
> +                       vfree(rams);
> +                       count += 16;

If the count is likely to be < 16, why are we using vmalloc() here?

> +                       goto again;
> +               }
> +
> +               rams[i].start = res.start;
> +               rams[i++].end = res.end;
> +
> +               res.start = res.end + 1;
> +               res.end = orig_end;
> +       }
> +
> +       /* go reverse */
> +       for (i--; i >= 0; i--) {
> +               ret = (*func)(rams[i].start, rams[i].end, arg);
> +               if (ret)
> +                       break;
> +       }
> +
> +       vfree(rams);
> +       return ret;
> +}
> +
>  #if !defined(CONFIG_ARCH_HAS_WALK_MEMORY)
>
>  /*
> --
> 2.14.1
>

[toc] | [prev] | [next] | [standalone]

#1719691 — Re: [PATCH 03/14] resource: add walk_system_ram_res_rev()

On Thu, Aug 24, 2017 at 10:06:28AM +0100, Ard Biesheuvel wrote:
> On 24 August 2017 at 09:18, AKASHI Takahiro <takahiro.akashi@linaro.org> wrote:
> > +       /* create a list */
> > +       rams = vmalloc(sizeof(struct resource) * count);
> > +       if (!rams)
> > +               return ret;
> > +
> > +       res.start = start;
> > +       res.end = end;
> > +       res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
> > +       orig_end = res.end;
> > +       i = 0;
> > +       while ((res.start < res.end) &&
> > +               (!find_next_iomem_res(&res, IORES_DESC_NONE, true))) {
> > +               if (i >= count) {
> > +                       /* unlikely but */
> > +                       vfree(rams);
> > +                       count += 16;
> 
> If the count is likely to be < 16, why are we using vmalloc() here?

Ah, you're right :)

-Takahiro AKASHI

[toc] | [prev] | [next] | [standalone]

#1718969 — [PATCH 10/14] arm64: kexec_file: load initrd, device-tree and purgatory segments

load_other_segments() sets up and adds all the memory segments necessary
other than kernel, including initrd, device-tree blob and purgatory.
Most of the code was borrowed from kexec-tools' counterpart.

In addition, arch_kexec_image_probe(), arch_kexec_image_load() and
arch_kexec_kernel_verify_sig() are stubs for supporting multiple types
of kernel image formats.

Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/kexec.h         |  18 +++
 arch/arm64/kernel/machine_kexec_file.c | 255 +++++++++++++++++++++++++++++++++
 2 files changed, 273 insertions(+)

diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h
index e17f0529a882..ebc4aaa707ae 100644
--- a/arch/arm64/include/asm/kexec.h
+++ b/arch/arm64/include/asm/kexec.h
@@ -93,6 +93,24 @@ 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_buf;
+};
+
+struct kimage;
+extern int setup_dtb(struct kimage *image,
+		unsigned long initrd_load_addr, unsigned long initrd_len,
+		char *cmdline, unsigned long cmdline_len,
+		char **dtb_buf, size_t *dtb_buf_len);
+extern int load_other_segments(struct kimage *image,
+		unsigned long kernel_load_addr,
+		char *initrd, unsigned long initrd_len,
+		char *cmdline, unsigned long cmdline_len);
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index 183f7776d6dd..cd12e451e474 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -16,8 +16,78 @@
 #include <linux/elf.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
+#include <linux/kexec.h>
+#include <linux/libfdt.h>
+#include <linux/memblock.h>
+#include <linux/of_fdt.h>
 #include <linux/types.h>
 #include <asm/byteorder.h>
+#include <asm/kexec_file.h>
+
+static int __dt_root_addr_cells;
+static int __dt_root_size_cells;
+
+static struct kexec_file_ops *kexec_file_loaders[0];
+
+int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
+				  unsigned long buf_len)
+{
+	struct kexec_file_ops *fops;
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(kexec_file_loaders); i++) {
+		fops = kexec_file_loaders[i];
+		if (!fops || !fops->probe)
+			continue;
+
+		ret = fops->probe(buf, buf_len);
+		if (!ret) {
+			image->fops = fops;
+			return 0;
+		}
+	}
+
+	return -ENOEXEC;
+}
+
+void *arch_kexec_kernel_image_load(struct kimage *image)
+{
+	if (!image->fops || !image->fops->load)
+		return ERR_PTR(-ENOEXEC);
+
+	return image->fops->load(image, image->kernel_buf,
+				 image->kernel_buf_len, image->initrd_buf,
+				 image->initrd_buf_len, image->cmdline_buf,
+				 image->cmdline_buf_len);
+}
+
+int arch_kimage_file_post_load_cleanup(struct kimage *image)
+{
+	vfree(image->arch.dtb_buf);
+	image->arch.dtb_buf = NULL;
+
+	vfree(image->arch.elf_headers);
+	image->arch.elf_headers = NULL;
+	image->arch.elf_headers_sz = 0;
+
+	if (!image->fops || !image->fops->cleanup)
+		return 0;
+
+	return image->fops->cleanup(image->image_loader_data);
+}
+
+#ifdef CONFIG_KEXEC_VERIFY_SIG
+int arch_kexec_kernel_verify_sig(struct kimage *image, void *kernel,
+				 unsigned long kernel_len)
+{
+	if (!image->fops || !image->fops->verify_sig) {
+		pr_debug("kernel loader does not support signature verification.\n");
+		return -EKEYREJECTED;
+	}
+
+	return image->fops->verify_sig(kernel, kernel_len);
+}
+#endif
 
 /*
  * Apply purgatory relocations.
@@ -197,3 +267,188 @@ int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr,
 
 	return 0;
 }
+
+int arch_kexec_walk_mem(struct kexec_buf *kbuf, int (*func)(u64, u64, void *))
+{
+	if (kbuf->image->type == KEXEC_TYPE_CRASH)
+		return walk_iomem_res_desc(crashk_res.desc,
+					IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
+					crashk_res.start, crashk_res.end,
+					kbuf, func);
+	else if (kbuf->top_down)
+		return walk_system_ram_res_rev(0, ULONG_MAX, kbuf, func);
+	else
+		return walk_system_ram_res(0, ULONG_MAX, kbuf, func);
+}
+
+int setup_dtb(struct kimage *image,
+		unsigned long initrd_load_addr, unsigned long initrd_len,
+		char *cmdline, unsigned long cmdline_len,
+		char **dtb_buf, size_t *dtb_buf_len)
+{
+	char *buf = NULL;
+	size_t buf_size;
+	int nodeoffset;
+	u64 value;
+	int range_len;
+	int ret;
+
+	/* duplicate dt blob */
+	buf_size = fdt_totalsize(initial_boot_params);
+	range_len = (__dt_root_addr_cells + __dt_root_size_cells) * sizeof(u32);
+
+	if (initrd_load_addr)
+		buf_size += fdt_prop_len("initrd-start", sizeof(u64))
+				+ fdt_prop_len("initrd-end", sizeof(u64));
+
+	if (cmdline)
+		buf_size += fdt_prop_len("bootargs", cmdline_len + 1);
+
+	buf = vmalloc(buf_size);
+	if (!buf) {
+		ret = -ENOMEM;
+		goto out_err;
+	}
+
+	ret = fdt_open_into(initial_boot_params, buf, buf_size);
+	if (ret)
+		goto out_err;
+
+	nodeoffset = fdt_path_offset(buf, "/chosen");
+	if (nodeoffset < 0)
+		goto out_err;
+
+	/* add bootargs */
+	if (cmdline) {
+		ret = fdt_setprop(buf, nodeoffset, "bootargs",
+						cmdline, cmdline_len + 1);
+		if (ret)
+			goto out_err;
+	}
+
+	/* add initrd-* */
+	if (initrd_load_addr) {
+		value = cpu_to_fdt64(initrd_load_addr);
+		ret = fdt_setprop(buf, nodeoffset, "initrd-start",
+				&value, sizeof(value));
+		if (ret)
+			goto out_err;
+
+		value = cpu_to_fdt64(initrd_load_addr + initrd_len);
+		ret = fdt_setprop(buf, nodeoffset, "initrd-end",
+				&value, sizeof(value));
+		if (ret)
+			goto out_err;
+	}
+
+	/* trim a buffer */
+	fdt_pack(buf);
+	*dtb_buf = buf;
+	*dtb_buf_len = fdt_totalsize(buf);
+
+	return 0;
+
+out_err:
+	vfree(buf);
+	return ret;
+}
+
+int load_other_segments(struct kimage *image, unsigned long kernel_load_addr,
+			char *initrd, unsigned long initrd_len,
+			char *cmdline, unsigned long cmdline_len)
+{
+	struct kexec_buf kbuf;
+	unsigned long initrd_load_addr = 0;
+	unsigned long purgatory_load_addr, dtb_load_addr;
+	char *dtb = NULL;
+	unsigned long dtb_len;
+	int ret = 0;
+
+	kbuf.image = image;
+
+	/* Load initrd */
+	if (initrd) {
+		kbuf.buffer = initrd;
+		kbuf.bufsz = initrd_len;
+		kbuf.memsz = initrd_len;
+		kbuf.buf_align = PAGE_SIZE;
+		/* within 1GB-aligned window of up to 32GB in size */
+		kbuf.buf_min = kernel_load_addr;
+		kbuf.buf_max = round_down(kernel_load_addr, SZ_1G)
+						+ (unsigned long)SZ_1G * 31;
+		kbuf.top_down = 0;
+
+		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 blob */
+	ret = setup_dtb(image, initrd_load_addr, initrd_len,
+				cmdline, cmdline_len, &dtb, &dtb_len);
+	if (ret) {
+		pr_err("Preparing for new dtb failed\n");
+		goto out_err;
+	}
+
+	kbuf.buffer = dtb;
+	kbuf.bufsz = dtb_len;
+	kbuf.memsz = dtb_len;
+	/* not across 2MB boundary */
+	kbuf.buf_align = SZ_2M;
+	/*
+	 * Note for backporting:
+	 * On kernel prior to v4.2, fdt must reside within 512MB block
+	 * where the kernel also resides. So
+	 *   kbuf.buf_min = round_down(kernel_load_addr, SZ_512M);
+	 *   kbuf.buf_max = round_up(kernel_load_addr, SZ_512M);
+	 * would be required.
+	 */
+	kbuf.buf_min = kernel_load_addr;
+	kbuf.buf_max = ULONG_MAX;
+	kbuf.top_down = 1;
+
+	ret = kexec_add_buffer(&kbuf);
+	if (ret)
+		goto out_err;
+	dtb_load_addr = kbuf.mem;
+	image->arch.dtb_buf = dtb;
+
+	pr_debug("Loaded dtb at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+			dtb_load_addr, dtb_len, dtb_len);
+
+	/* Load purgatory  */
+	ret = kexec_load_purgatory(image, kernel_load_addr, ULONG_MAX, 1,
+				   &purgatory_load_addr);
+	if (ret) {
+		pr_err("Loading purgatory failed\n");
+		goto out_err;
+	}
+
+	ret = kexec_purgatory_get_set_symbol(image, "arm64_kernel_entry",
+				&kernel_load_addr, sizeof(kernel_load_addr), 0);
+	if (ret) {
+		pr_err("Relocating symbol (arm64_kernel_entry) failed.\n");
+		goto out_err;
+	}
+
+	ret = kexec_purgatory_get_set_symbol(image, "arm64_dtb_addr",
+				&dtb_load_addr, sizeof(dtb_load_addr), 0);
+	if (ret) {
+		pr_err("Relocating symbol (arm64_dtb_addr) failed.\n");
+		goto out_err;
+	}
+
+	pr_debug("Loaded purgatory at 0x%lx\n", purgatory_load_addr);
+
+	return 0;
+
+out_err:
+	vfree(dtb);
+	image->arch.dtb_buf = NULL;
+	return ret;
+}
-- 
2.14.1

[toc] | [prev] | [next] | [standalone]

#1719449 — Re: [PATCH 10/14] arm64: kexec_file: load initrd, device-tree and purgatory segments

On Thu, Aug 24, 2017 at 05:18:07PM +0900, AKASHI Takahiro wrote:
> load_other_segments() sets up and adds all the memory segments necessary
> other than kernel, including initrd, device-tree blob and purgatory.
> Most of the code was borrowed from kexec-tools' counterpart.
> 
> In addition, arch_kexec_image_probe(), arch_kexec_image_load() and
> arch_kexec_kernel_verify_sig() are stubs for supporting multiple types
> of kernel image formats.
> 
> Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
> Cc: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Will Deacon <will.deacon@arm.com>
> ---
>  arch/arm64/include/asm/kexec.h         |  18 +++
>  arch/arm64/kernel/machine_kexec_file.c | 255 +++++++++++++++++++++++++++++++++
>  2 files changed, 273 insertions(+)

> +int load_other_segments(struct kimage *image, unsigned long kernel_load_addr,
> +			char *initrd, unsigned long initrd_len,
> +			char *cmdline, unsigned long cmdline_len)
> +{
> +	struct kexec_buf kbuf;
> +	unsigned long initrd_load_addr = 0;
> +	unsigned long purgatory_load_addr, dtb_load_addr;
> +	char *dtb = NULL;
> +	unsigned long dtb_len;
> +	int ret = 0;
> +
> +	kbuf.image = image;
> +
> +	/* Load initrd */
> +	if (initrd) {
> +		kbuf.buffer = initrd;
> +		kbuf.bufsz = initrd_len;
> +		kbuf.memsz = initrd_len;
> +		kbuf.buf_align = PAGE_SIZE;
> +		/* within 1GB-aligned window of up to 32GB in size */
> +		kbuf.buf_min = kernel_load_addr;
> +		kbuf.buf_max = round_down(kernel_load_addr, SZ_1G)
> +						+ (unsigned long)SZ_1G * 31;
> +		kbuf.top_down = 0;
> +
> +		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 blob */
> +	ret = setup_dtb(image, initrd_load_addr, initrd_len,
> +				cmdline, cmdline_len, &dtb, &dtb_len);
> +	if (ret) {
> +		pr_err("Preparing for new dtb failed\n");
> +		goto out_err;
> +	}
> +
> +	kbuf.buffer = dtb;
> +	kbuf.bufsz = dtb_len;
> +	kbuf.memsz = dtb_len;
> +	/* not across 2MB boundary */
> +	kbuf.buf_align = SZ_2M;
> +	/*
> +	 * Note for backporting:
> +	 * On kernel prior to v4.2, fdt must reside within 512MB block
> +	 * where the kernel also resides. So
> +	 *   kbuf.buf_min = round_down(kernel_load_addr, SZ_512M);
> +	 *   kbuf.buf_max = round_up(kernel_load_addr, SZ_512M);
> +	 * would be required.
> +	 */
> +	kbuf.buf_min = kernel_load_addr;
> +	kbuf.buf_max = ULONG_MAX;
> +	kbuf.top_down = 1;

IIUC, this is trying to load the DTB above the kernel. Is that correct?

Assuming so, shouldn't that kernel_load_addr be kernel_load_addr +
image_size from the kernel header?

Otherwise, if the kernel is loaded close to the end of memory, the DTB
could overlap.

Thanks,
Mark.

[toc] | [prev] | [next] | [standalone]

#1719706 — Re: [PATCH 10/14] arm64: kexec_file: load initrd, device-tree and purgatory segments

On Thu, Aug 24, 2017 at 06:11:31PM +0100, Mark Rutland wrote:
> On Thu, Aug 24, 2017 at 05:18:07PM +0900, AKASHI Takahiro wrote:
> > load_other_segments() sets up and adds all the memory segments necessary
> > other than kernel, including initrd, device-tree blob and purgatory.
> > Most of the code was borrowed from kexec-tools' counterpart.
> > 
> > In addition, arch_kexec_image_probe(), arch_kexec_image_load() and
> > arch_kexec_kernel_verify_sig() are stubs for supporting multiple types
> > of kernel image formats.
> > 
> > Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
> > Cc: Catalin Marinas <catalin.marinas@arm.com>
> > Cc: Will Deacon <will.deacon@arm.com>
> > ---
> >  arch/arm64/include/asm/kexec.h         |  18 +++
> >  arch/arm64/kernel/machine_kexec_file.c | 255 +++++++++++++++++++++++++++++++++
> >  2 files changed, 273 insertions(+)
> 
> > +int load_other_segments(struct kimage *image, unsigned long kernel_load_addr,
> > +			char *initrd, unsigned long initrd_len,
> > +			char *cmdline, unsigned long cmdline_len)
> > +{
> > +	struct kexec_buf kbuf;
> > +	unsigned long initrd_load_addr = 0;
> > +	unsigned long purgatory_load_addr, dtb_load_addr;
> > +	char *dtb = NULL;
> > +	unsigned long dtb_len;
> > +	int ret = 0;
> > +
> > +	kbuf.image = image;
> > +
> > +	/* Load initrd */
> > +	if (initrd) {
> > +		kbuf.buffer = initrd;
> > +		kbuf.bufsz = initrd_len;
> > +		kbuf.memsz = initrd_len;
> > +		kbuf.buf_align = PAGE_SIZE;
> > +		/* within 1GB-aligned window of up to 32GB in size */
> > +		kbuf.buf_min = kernel_load_addr;
> > +		kbuf.buf_max = round_down(kernel_load_addr, SZ_1G)
> > +						+ (unsigned long)SZ_1G * 31;
> > +		kbuf.top_down = 0;
> > +
> > +		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 blob */
> > +	ret = setup_dtb(image, initrd_load_addr, initrd_len,
> > +				cmdline, cmdline_len, &dtb, &dtb_len);
> > +	if (ret) {
> > +		pr_err("Preparing for new dtb failed\n");
> > +		goto out_err;
> > +	}
> > +
> > +	kbuf.buffer = dtb;
> > +	kbuf.bufsz = dtb_len;
> > +	kbuf.memsz = dtb_len;
> > +	/* not across 2MB boundary */
> > +	kbuf.buf_align = SZ_2M;
> > +	/*
> > +	 * Note for backporting:
> > +	 * On kernel prior to v4.2, fdt must reside within 512MB block
> > +	 * where the kernel also resides. So
> > +	 *   kbuf.buf_min = round_down(kernel_load_addr, SZ_512M);
> > +	 *   kbuf.buf_max = round_up(kernel_load_addr, SZ_512M);
> > +	 * would be required.
> > +	 */
> > +	kbuf.buf_min = kernel_load_addr;
> > +	kbuf.buf_max = ULONG_MAX;
> > +	kbuf.top_down = 1;
> 
> IIUC, this is trying to load the DTB above the kernel. Is that correct?

Yes.

> Assuming so, shouldn't that kernel_load_addr be kernel_load_addr +
> image_size from the kernel header?

Okey, it would be much safer.

> Otherwise, if the kernel is loaded close to the end of memory, the DTB
> could overlap.

Right, but we allocate the kernel from "bottom up"(top_down=0)
and such a corruption is very unlikely. If it happens, it means
that system memory is just too small.

Thanks,
-Takahiro AKASHI

> Thanks,
> Mark.

[toc] | [prev] | [next] | [standalone]

#1718971 — [PATCH 04/14] kexec_file: factor out vmlinux (elf) parser from powerpc

build_elf_exec_info() can also be useful for other architectures,
including arm64. So let it factored out.

Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Baoquan He <bhe@redhat.com>
---
 arch/Kconfig                       |   3 +
 arch/powerpc/Kconfig               |   1 +
 arch/powerpc/kernel/kexec_elf_64.c | 464 -------------------------------------
 include/linux/elf.h                |  62 +++++
 include/linux/kexec.h              |  19 ++
 kernel/Makefile                    |   1 +
 kernel/kexec_file_elf.c            | 454 ++++++++++++++++++++++++++++++++++++
 7 files changed, 540 insertions(+), 464 deletions(-)
 create mode 100644 kernel/kexec_file_elf.c

diff --git a/arch/Kconfig b/arch/Kconfig
index 21d0089117fe..e940d16412f4 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -9,6 +9,9 @@ config KEXEC_CORE
 	select CRASH_CORE
 	bool
 
+config KEXEC_FILE_ELF
+	bool
+
 config HAVE_IMA_KEXEC
 	bool
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 36f858c37ca7..f73921bbe29a 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -529,6 +529,7 @@ config KEXEC
 config KEXEC_FILE
 	bool "kexec file based system call"
 	select KEXEC_CORE
+	select KEXEC_FILE_ELF
 	select HAVE_IMA_KEXEC
 	select BUILD_BIN2C
 	depends on PPC64
diff --git a/arch/powerpc/kernel/kexec_elf_64.c b/arch/powerpc/kernel/kexec_elf_64.c
index 9a42309b091a..a0c92bd14259 100644
--- a/arch/powerpc/kernel/kexec_elf_64.c
+++ b/arch/powerpc/kernel/kexec_elf_64.c
@@ -26,475 +26,11 @@
 #include <linux/elf.h>
 #include <linux/kexec.h>
 #include <linux/libfdt.h>
-#include <linux/module.h>
 #include <linux/of_fdt.h>
 #include <linux/slab.h>
-#include <linux/types.h>
 
 #define PURGATORY_STACK_SIZE	(16 * 1024)
 
-#define elf_addr_to_cpu	elf64_to_cpu
-
-#ifndef Elf_Rel
-#define Elf_Rel		Elf64_Rel
-#endif /* Elf_Rel */
-
-struct elf_info {
-	/*
-	 * Where the ELF binary contents are kept.
-	 * Memory managed by the user of the struct.
-	 */
-	const char *buffer;
-
-	const struct elfhdr *ehdr;
-	const struct elf_phdr *proghdrs;
-	struct elf_shdr *sechdrs;
-};
-
-static inline bool elf_is_elf_file(const struct elfhdr *ehdr)
-{
-       return memcmp(ehdr->e_ident, ELFMAG, SELFMAG) == 0;
-}
-
-static uint64_t elf64_to_cpu(const struct elfhdr *ehdr, uint64_t value)
-{
-	if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB)
-		value = le64_to_cpu(value);
-	else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB)
-		value = be64_to_cpu(value);
-
-	return value;
-}
-
-static uint16_t elf16_to_cpu(const struct elfhdr *ehdr, uint16_t value)
-{
-	if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB)
-		value = le16_to_cpu(value);
-	else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB)
-		value = be16_to_cpu(value);
-
-	return value;
-}
-
-static uint32_t elf32_to_cpu(const struct elfhdr *ehdr, uint32_t value)
-{
-	if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB)
-		value = le32_to_cpu(value);
-	else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB)
-		value = be32_to_cpu(value);
-
-	return value;
-}
-
-/**
- * elf_is_ehdr_sane - check that it is safe to use the ELF header
- * @buf_len:	size of the buffer in which the ELF file is loaded.
- */
-static bool elf_is_ehdr_sane(const struct elfhdr *ehdr, size_t buf_len)
-{
-	if (ehdr->e_phnum > 0 && ehdr->e_phentsize != sizeof(struct elf_phdr)) {
-		pr_debug("Bad program header size.\n");
-		return false;
-	} else if (ehdr->e_shnum > 0 &&
-		   ehdr->e_shentsize != sizeof(struct elf_shdr)) {
-		pr_debug("Bad section header size.\n");
-		return false;
-	} else if (ehdr->e_ident[EI_VERSION] != EV_CURRENT ||
-		   ehdr->e_version != EV_CURRENT) {
-		pr_debug("Unknown ELF version.\n");
-		return false;
-	}
-
-	if (ehdr->e_phoff > 0 && ehdr->e_phnum > 0) {
-		size_t phdr_size;
-
-		/*
-		 * e_phnum is at most 65535 so calculating the size of the
-		 * program header cannot overflow.
-		 */
-		phdr_size = sizeof(struct elf_phdr) * ehdr->e_phnum;
-
-		/* Sanity check the program header table location. */
-		if (ehdr->e_phoff + phdr_size < ehdr->e_phoff) {
-			pr_debug("Program headers at invalid location.\n");
-			return false;
-		} else if (ehdr->e_phoff + phdr_size > buf_len) {
-			pr_debug("Program headers truncated.\n");
-			return false;
-		}
-	}
-
-	if (ehdr->e_shoff > 0 && ehdr->e_shnum > 0) {
-		size_t shdr_size;
-
-		/*
-		 * e_shnum is at most 65536 so calculating
-		 * the size of the section header cannot overflow.
-		 */
-		shdr_size = sizeof(struct elf_shdr) * ehdr->e_shnum;
-
-		/* Sanity check the section header table location. */
-		if (ehdr->e_shoff + shdr_size < ehdr->e_shoff) {
-			pr_debug("Section headers at invalid location.\n");
-			return false;
-		} else if (ehdr->e_shoff + shdr_size > buf_len) {
-			pr_debug("Section headers truncated.\n");
-			return false;
-		}
-	}
-
-	return true;
-}
-
-static int elf_read_ehdr(const char *buf, size_t len, struct elfhdr *ehdr)
-{
-	struct elfhdr *buf_ehdr;
-
-	if (len < sizeof(*buf_ehdr)) {
-		pr_debug("Buffer is too small to hold ELF header.\n");
-		return -ENOEXEC;
-	}
-
-	memset(ehdr, 0, sizeof(*ehdr));
-	memcpy(ehdr->e_ident, buf, sizeof(ehdr->e_ident));
-	if (!elf_is_elf_file(ehdr)) {
-		pr_debug("No ELF header magic.\n");
-		return -ENOEXEC;
-	}
-
-	if (ehdr->e_ident[EI_CLASS] != ELF_CLASS) {
-		pr_debug("Not a supported ELF class.\n");
-		return -ENOEXEC;
-	} else  if (ehdr->e_ident[EI_DATA] != ELFDATA2LSB &&
-		ehdr->e_ident[EI_DATA] != ELFDATA2MSB) {
-		pr_debug("Not a supported ELF data format.\n");
-		return -ENOEXEC;
-	}
-
-	buf_ehdr = (struct elfhdr *) buf;
-	if (elf16_to_cpu(ehdr, buf_ehdr->e_ehsize) != sizeof(*buf_ehdr)) {
-		pr_debug("Bad ELF header size.\n");
-		return -ENOEXEC;
-	}
-
-	ehdr->e_type      = elf16_to_cpu(ehdr, buf_ehdr->e_type);
-	ehdr->e_machine   = elf16_to_cpu(ehdr, buf_ehdr->e_machine);
-	ehdr->e_version   = elf32_to_cpu(ehdr, buf_ehdr->e_version);
-	ehdr->e_entry     = elf_addr_to_cpu(ehdr, buf_ehdr->e_entry);
-	ehdr->e_phoff     = elf_addr_to_cpu(ehdr, buf_ehdr->e_phoff);
-	ehdr->e_shoff     = elf_addr_to_cpu(ehdr, buf_ehdr->e_shoff);
-	ehdr->e_flags     = elf32_to_cpu(ehdr, buf_ehdr->e_flags);
-	ehdr->e_phentsize = elf16_to_cpu(ehdr, buf_ehdr->e_phentsize);
-	ehdr->e_phnum     = elf16_to_cpu(ehdr, buf_ehdr->e_phnum);
-	ehdr->e_shentsize = elf16_to_cpu(ehdr, buf_ehdr->e_shentsize);
-	ehdr->e_shnum     = elf16_to_cpu(ehdr, buf_ehdr->e_shnum);
-	ehdr->e_shstrndx  = elf16_to_cpu(ehdr, buf_ehdr->e_shstrndx);
-
-	return elf_is_ehdr_sane(ehdr, len) ? 0 : -ENOEXEC;
-}
-
-/**
- * elf_is_phdr_sane - check that it is safe to use the program header
- * @buf_len:	size of the buffer in which the ELF file is loaded.
- */
-static bool elf_is_phdr_sane(const struct elf_phdr *phdr, size_t buf_len)
-{
-
-	if (phdr->p_offset + phdr->p_filesz < phdr->p_offset) {
-		pr_debug("ELF segment location wraps around.\n");
-		return false;
-	} else if (phdr->p_offset + phdr->p_filesz > buf_len) {
-		pr_debug("ELF segment not in file.\n");
-		return false;
-	} else if (phdr->p_paddr + phdr->p_memsz < phdr->p_paddr) {
-		pr_debug("ELF segment address wraps around.\n");
-		return false;
-	}
-
-	return true;
-}
-
-static int elf_read_phdr(const char *buf, size_t len, struct elf_info *elf_info,
-			 int idx)
-{
-	/* Override the const in proghdrs, we are the ones doing the loading. */
-	struct elf_phdr *phdr = (struct elf_phdr *) &elf_info->proghdrs[idx];
-	const char *pbuf;
-	struct elf_phdr *buf_phdr;
-
-	pbuf = buf + elf_info->ehdr->e_phoff + (idx * sizeof(*buf_phdr));
-	buf_phdr = (struct elf_phdr *) pbuf;
-
-	phdr->p_type   = elf32_to_cpu(elf_info->ehdr, buf_phdr->p_type);
-	phdr->p_offset = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_offset);
-	phdr->p_paddr  = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_paddr);
-	phdr->p_vaddr  = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_vaddr);
-	phdr->p_flags  = elf32_to_cpu(elf_info->ehdr, buf_phdr->p_flags);
-
-	/*
-	 * The following fields have a type equivalent to Elf_Addr
-	 * both in 32 bit and 64 bit ELF.
-	 */
-	phdr->p_filesz = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_filesz);
-	phdr->p_memsz  = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_memsz);
-	phdr->p_align  = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_align);
-
-	return elf_is_phdr_sane(phdr, len) ? 0 : -ENOEXEC;
-}
-
-/**
- * elf_read_phdrs - read the program headers from the buffer
- *
- * This function assumes that the program header table was checked for sanity.
- * Use elf_is_ehdr_sane() if it wasn't.
- */
-static int elf_read_phdrs(const char *buf, size_t len,
-			  struct elf_info *elf_info)
-{
-	size_t phdr_size, i;
-	const struct elfhdr *ehdr = elf_info->ehdr;
-
-	/*
-	 * e_phnum is at most 65535 so calculating the size of the
-	 * program header cannot overflow.
-	 */
-	phdr_size = sizeof(struct elf_phdr) * ehdr->e_phnum;
-
-	elf_info->proghdrs = kzalloc(phdr_size, GFP_KERNEL);
-	if (!elf_info->proghdrs)
-		return -ENOMEM;
-
-	for (i = 0; i < ehdr->e_phnum; i++) {
-		int ret;
-
-		ret = elf_read_phdr(buf, len, elf_info, i);
-		if (ret) {
-			kfree(elf_info->proghdrs);
-			elf_info->proghdrs = NULL;
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
-/**
- * elf_is_shdr_sane - check that it is safe to use the section header
- * @buf_len:	size of the buffer in which the ELF file is loaded.
- */
-static bool elf_is_shdr_sane(const struct elf_shdr *shdr, size_t buf_len)
-{
-	bool size_ok;
-
-	/* SHT_NULL headers have undefined values, so we can't check them. */
-	if (shdr->sh_type == SHT_NULL)
-		return true;
-
-	/* Now verify sh_entsize */
-	switch (shdr->sh_type) {
-	case SHT_SYMTAB:
-		size_ok = shdr->sh_entsize == sizeof(Elf_Sym);
-		break;
-	case SHT_RELA:
-		size_ok = shdr->sh_entsize == sizeof(Elf_Rela);
-		break;
-	case SHT_DYNAMIC:
-		size_ok = shdr->sh_entsize == sizeof(Elf_Dyn);
-		break;
-	case SHT_REL:
-		size_ok = shdr->sh_entsize == sizeof(Elf_Rel);
-		break;
-	case SHT_NOTE:
-	case SHT_PROGBITS:
-	case SHT_HASH:
-	case SHT_NOBITS:
-	default:
-		/*
-		 * This is a section whose entsize requirements
-		 * I don't care about.  If I don't know about
-		 * the section I can't care about it's entsize
-		 * requirements.
-		 */
-		size_ok = true;
-		break;
-	}
-
-	if (!size_ok) {
-		pr_debug("ELF section with wrong entry size.\n");
-		return false;
-	} else if (shdr->sh_addr + shdr->sh_size < shdr->sh_addr) {
-		pr_debug("ELF section address wraps around.\n");
-		return false;
-	}
-
-	if (shdr->sh_type != SHT_NOBITS) {
-		if (shdr->sh_offset + shdr->sh_size < shdr->sh_offset) {
-			pr_debug("ELF section location wraps around.\n");
-			return false;
-		} else if (shdr->sh_offset + shdr->sh_size > buf_len) {
-			pr_debug("ELF section not in file.\n");
-			return false;
-		}
-	}
-
-	return true;
-}
-
-static int elf_read_shdr(const char *buf, size_t len, struct elf_info *elf_info,
-			 int idx)
-{
-	struct elf_shdr *shdr = &elf_info->sechdrs[idx];
-	const struct elfhdr *ehdr = elf_info->ehdr;
-	const char *sbuf;
-	struct elf_shdr *buf_shdr;
-
-	sbuf = buf + ehdr->e_shoff + idx * sizeof(*buf_shdr);
-	buf_shdr = (struct elf_shdr *) sbuf;
-
-	shdr->sh_name      = elf32_to_cpu(ehdr, buf_shdr->sh_name);
-	shdr->sh_type      = elf32_to_cpu(ehdr, buf_shdr->sh_type);
-	shdr->sh_addr      = elf_addr_to_cpu(ehdr, buf_shdr->sh_addr);
-	shdr->sh_offset    = elf_addr_to_cpu(ehdr, buf_shdr->sh_offset);
-	shdr->sh_link      = elf32_to_cpu(ehdr, buf_shdr->sh_link);
-	shdr->sh_info      = elf32_to_cpu(ehdr, buf_shdr->sh_info);
-
-	/*
-	 * The following fields have a type equivalent to Elf_Addr
-	 * both in 32 bit and 64 bit ELF.
-	 */
-	shdr->sh_flags     = elf_addr_to_cpu(ehdr, buf_shdr->sh_flags);
-	shdr->sh_size      = elf_addr_to_cpu(ehdr, buf_shdr->sh_size);
-	shdr->sh_addralign = elf_addr_to_cpu(ehdr, buf_shdr->sh_addralign);
-	shdr->sh_entsize   = elf_addr_to_cpu(ehdr, buf_shdr->sh_entsize);
-
-	return elf_is_shdr_sane(shdr, len) ? 0 : -ENOEXEC;
-}
-
-/**
- * elf_read_shdrs - read the section headers from the buffer
- *
- * This function assumes that the section header table was checked for sanity.
- * Use elf_is_ehdr_sane() if it wasn't.
- */
-static int elf_read_shdrs(const char *buf, size_t len,
-			  struct elf_info *elf_info)
-{
-	size_t shdr_size, i;
-
-	/*
-	 * e_shnum is at most 65536 so calculating
-	 * the size of the section header cannot overflow.
-	 */
-	shdr_size = sizeof(struct elf_shdr) * elf_info->ehdr->e_shnum;
-
-	elf_info->sechdrs = kzalloc(shdr_size, GFP_KERNEL);
-	if (!elf_info->sechdrs)
-		return -ENOMEM;
-
-	for (i = 0; i < elf_info->ehdr->e_shnum; i++) {
-		int ret;
-
-		ret = elf_read_shdr(buf, len, elf_info, i);
-		if (ret) {
-			kfree(elf_info->sechdrs);
-			elf_info->sechdrs = NULL;
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
-/**
- * elf_read_from_buffer - read ELF file and sets up ELF header and ELF info
- * @buf:	Buffer to read ELF file from.
- * @len:	Size of @buf.
- * @ehdr:	Pointer to existing struct which will be populated.
- * @elf_info:	Pointer to existing struct which will be populated.
- *
- * This function allows reading ELF files with different byte order than
- * the kernel, byte-swapping the fields as needed.
- *
- * Return:
- * On success returns 0, and the caller should call elf_free_info(elf_info) to
- * free the memory allocated for the section and program headers.
- */
-int elf_read_from_buffer(const char *buf, size_t len, struct elfhdr *ehdr,
-			 struct elf_info *elf_info)
-{
-	int ret;
-
-	ret = elf_read_ehdr(buf, len, ehdr);
-	if (ret)
-		return ret;
-
-	elf_info->buffer = buf;
-	elf_info->ehdr = ehdr;
-	if (ehdr->e_phoff > 0 && ehdr->e_phnum > 0) {
-		ret = elf_read_phdrs(buf, len, elf_info);
-		if (ret)
-			return ret;
-	}
-	if (ehdr->e_shoff > 0 && ehdr->e_shnum > 0) {
-		ret = elf_read_shdrs(buf, len, elf_info);
-		if (ret) {
-			kfree(elf_info->proghdrs);
-			return ret;
-		}
-	}
-
-	return 0;
-}
-
-/**
- * elf_free_info - free memory allocated by elf_read_from_buffer
- */
-void elf_free_info(struct elf_info *elf_info)
-{
-	kfree(elf_info->proghdrs);
-	kfree(elf_info->sechdrs);
-	memset(elf_info, 0, sizeof(*elf_info));
-}
-/**
- * build_elf_exec_info - read ELF executable and check that we can use it
- */
-static int build_elf_exec_info(const char *buf, size_t len, struct elfhdr *ehdr,
-			       struct elf_info *elf_info)
-{
-	int i;
-	int ret;
-
-	ret = elf_read_from_buffer(buf, len, ehdr, elf_info);
-	if (ret)
-		return ret;
-
-	/* Big endian vmlinux has type ET_DYN. */
-	if (ehdr->e_type != ET_EXEC && ehdr->e_type != ET_DYN) {
-		pr_err("Not an ELF executable.\n");
-		goto error;
-	} else if (!elf_info->proghdrs) {
-		pr_err("No ELF program header.\n");
-		goto error;
-	}
-
-	for (i = 0; i < ehdr->e_phnum; i++) {
-		/*
-		 * Kexec does not support loading interpreters.
-		 * In addition this check keeps us from attempting
-		 * to kexec ordinay executables.
-		 */
-		if (elf_info->proghdrs[i].p_type == PT_INTERP) {
-			pr_err("Requires an ELF interpreter.\n");
-			goto error;
-		}
-	}
-
-	return 0;
-error:
-	elf_free_info(elf_info);
-	return -ENOEXEC;
-}
-
 static int elf64_probe(const char *buf, unsigned long len)
 {
 	struct elfhdr ehdr;
diff --git a/include/linux/elf.h b/include/linux/elf.h
index ba069e8f4f78..e758bb4365c1 100644
--- a/include/linux/elf.h
+++ b/include/linux/elf.h
@@ -1,6 +1,8 @@
 #ifndef _LINUX_ELF_H
 #define _LINUX_ELF_H
 
+#include <linux/types.h>
+#include <asm/byteorder.h>
 #include <asm/elf.h>
 #include <uapi/linux/elf.h>
 
@@ -55,4 +57,64 @@ static inline int elf_coredump_extra_notes_write(struct coredump_params *cprm) {
 extern int elf_coredump_extra_notes_size(void);
 extern int elf_coredump_extra_notes_write(struct coredump_params *cprm);
 #endif
+
+static inline u16 elf16_to_cpu(const struct elfhdr *ehdr, u16 value)
+{
+	if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB)
+		value = le16_to_cpu(value);
+	else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB)
+		value = be16_to_cpu(value);
+
+	return value;
+}
+
+static inline u16 cpu_to_elf16(const struct elfhdr *ehdr, u16 value)
+{
+	if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB)
+		value = cpu_to_le16(value);
+	else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB)
+		value = cpu_to_be16(value);
+
+	return value;
+}
+
+static inline u32 elf32_to_cpu(const struct elfhdr *ehdr, u32 value)
+{
+	if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB)
+		value = le32_to_cpu(value);
+	else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB)
+		value = be32_to_cpu(value);
+
+	return value;
+}
+
+static inline u32 cpu_to_elf32(const struct elfhdr *ehdr, u32 value)
+{
+	if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB)
+		value = cpu_to_le32(value);
+	else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB)
+		value = cpu_to_be32(value);
+
+	return value;
+}
+
+static inline u64 elf64_to_cpu(const struct elfhdr *ehdr, u64 value)
+{
+	if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB)
+		value = le64_to_cpu(value);
+	else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB)
+		value = be64_to_cpu(value);
+
+	return value;
+}
+
+static inline u64 cpu_to_elf64(const struct elfhdr *ehdr, u64 value)
+{
+	if (ehdr->e_ident[EI_DATA] == ELFDATA2LSB)
+		value = cpu_to_le64(value);
+	else if (ehdr->e_ident[EI_DATA] == ELFDATA2MSB)
+		value = cpu_to_be64(value);
+
+	return value;
+}
 #endif /* _LINUX_ELF_H */
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index dd056fab9e35..db98e3459e90 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -22,6 +22,7 @@
 #ifdef CONFIG_KEXEC_CORE
 #include <linux/list.h>
 #include <linux/compat.h>
+#include <linux/elf.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
 #include <asm/kexec.h>
@@ -162,6 +163,24 @@ int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf,
 			       int (*func)(u64, u64, void *));
 extern int kexec_add_buffer(struct kexec_buf *kbuf);
 int kexec_locate_mem_hole(struct kexec_buf *kbuf);
+
+#ifdef CONFIG_KEXEC_FILE_ELF
+struct elf_info {
+	/*
+	 * Where the ELF binary contents are kept.
+	 * Memory managed by the user of the struct.
+	 */
+	const char *buffer;
+
+	const struct elfhdr *ehdr;
+	const struct elf_phdr *proghdrs;
+	struct elf_shdr *sechdrs;
+};
+
+extern void elf_free_info(struct elf_info *elf_info);
+extern int build_elf_exec_info(const char *buf, size_t len, struct elfhdr *ehdr,
+				struct elf_info *elf_info);
+#endif /* CONFIG_KEXEC_FILE_ELF */
 #endif /* CONFIG_KEXEC_FILE */
 
 struct kimage {
diff --git a/kernel/Makefile b/kernel/Makefile
index d5f9748ab19f..d07492eb3804 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -63,6 +63,7 @@ obj-$(CONFIG_CRASH_CORE) += crash_core.o
 obj-$(CONFIG_KEXEC_CORE) += kexec_core.o
 obj-$(CONFIG_KEXEC) += kexec.o
 obj-$(CONFIG_KEXEC_FILE) += kexec_file.o
+obj-$(CONFIG_KEXEC_FILE_ELF) += kexec_file_elf.o
 obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
 obj-$(CONFIG_COMPAT) += compat.o
 obj-$(CONFIG_CGROUPS) += cgroup/
diff --git a/kernel/kexec_file_elf.c b/kernel/kexec_file_elf.c
new file mode 100644
index 000000000000..4fc049e9731b
--- /dev/null
+++ b/kernel/kexec_file_elf.c
@@ -0,0 +1,454 @@
+/*
+ * Load ELF vmlinux file for the kexec_file_load syscall.
+ *
+ * Copyright (C) 2004  Adam Litke (agl@us.ibm.com)
+ * Copyright (C) 2004  IBM Corp.
+ * Copyright (C) 2005  R Sharada (sharada@in.ibm.com)
+ * Copyright (C) 2006  Mohan Kumar M (mohan@in.ibm.com)
+ * Copyright (C) 2016  IBM Corporation
+ *
+ * Based on kexec-tools' kexec-elf-exec.c and kexec-elf-ppc64.c.
+ * Heavily modified for the kernel by
+ * Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>.
+ * Factored out for general use by
+ * AKASHI Takahiro <takahiro.akashi@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation (version 2 of the License).
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"kexec_elf_elf: " fmt
+
+#include <linux/elf.h>
+#include <linux/errno.h>
+#include <linux/kexec.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+#if ELF_CLASS == ELFCLASS32
+#define elf_addr_to_cpu elf32_to_cpu
+#else
+#define elf_addr_to_cpu elf64_to_cpu
+#endif
+
+/**
+ * elf_is_ehdr_sane - check that it is safe to use the ELF header
+ * @buf_len:	size of the buffer in which the ELF file is loaded.
+ */
+static bool elf_is_ehdr_sane(const struct elfhdr *ehdr, size_t buf_len)
+{
+	if (ehdr->e_phnum > 0 && ehdr->e_phentsize != sizeof(struct elf_phdr)) {
+		pr_debug("Bad program header size.\n");
+		return false;
+	} else if (ehdr->e_shnum > 0 &&
+		   ehdr->e_shentsize != sizeof(struct elf_shdr)) {
+		pr_debug("Bad section header size.\n");
+		return false;
+	} else if (ehdr->e_ident[EI_VERSION] != EV_CURRENT ||
+		   ehdr->e_version != EV_CURRENT) {
+		pr_debug("Unknown ELF version.\n");
+		return false;
+	}
+
+	if (ehdr->e_phoff > 0 && ehdr->e_phnum > 0) {
+		size_t phdr_size;
+
+		/*
+		 * e_phnum is at most 65535 so calculating the size of the
+		 * program header cannot overflow.
+		 */
+		phdr_size = sizeof(struct elf_phdr) * ehdr->e_phnum;
+
+		/* Sanity check the program header table location. */
+		if (ehdr->e_phoff + phdr_size < ehdr->e_phoff) {
+			pr_debug("Program headers at invalid location.\n");
+			return false;
+		} else if (ehdr->e_phoff + phdr_size > buf_len) {
+			pr_debug("Program headers truncated.\n");
+			return false;
+		}
+	}
+
+	if (ehdr->e_shoff > 0 && ehdr->e_shnum > 0) {
+		size_t shdr_size;
+
+		/*
+		 * e_shnum is at most 65536 so calculating
+		 * the size of the section header cannot overflow.
+		 */
+		shdr_size = sizeof(struct elf_shdr) * ehdr->e_shnum;
+
+		/* Sanity check the section header table location. */
+		if (ehdr->e_shoff + shdr_size < ehdr->e_shoff) {
+			pr_debug("Section headers at invalid location.\n");
+			return false;
+		} else if (ehdr->e_shoff + shdr_size > buf_len) {
+			pr_debug("Section headers truncated.\n");
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static int elf_read_ehdr(const char *buf, size_t len, struct elfhdr *ehdr)
+{
+	struct elfhdr *buf_ehdr;
+
+	if (len < sizeof(*buf_ehdr)) {
+		pr_debug("Buffer is too small to hold ELF header.\n");
+		return -ENOEXEC;
+	}
+
+	memset(ehdr, 0, sizeof(*ehdr));
+	memcpy(ehdr->e_ident, buf, sizeof(ehdr->e_ident));
+	if (memcmp(ehdr->e_ident, ELFMAG, SELFMAG)) {
+		pr_debug("No ELF header magic.\n");
+		return -ENOEXEC;
+	}
+
+	if (ehdr->e_ident[EI_CLASS] != ELF_CLASS) {
+		pr_debug("Not a supported ELF class.\n");
+		return -ENOEXEC;
+	} else  if (ehdr->e_ident[EI_DATA] != ELFDATA2LSB &&
+		ehdr->e_ident[EI_DATA] != ELFDATA2MSB) {
+		pr_debug("Not a supported ELF data format.\n");
+		return -ENOEXEC;
+	}
+
+	buf_ehdr = (struct elfhdr *) buf;
+	if (elf16_to_cpu(ehdr, buf_ehdr->e_ehsize) != sizeof(*buf_ehdr)) {
+		pr_debug("Bad ELF header size.\n");
+		return -ENOEXEC;
+	}
+
+	ehdr->e_type      = elf16_to_cpu(ehdr, buf_ehdr->e_type);
+	ehdr->e_machine   = elf16_to_cpu(ehdr, buf_ehdr->e_machine);
+	ehdr->e_version   = elf32_to_cpu(ehdr, buf_ehdr->e_version);
+	ehdr->e_entry     = elf_addr_to_cpu(ehdr, buf_ehdr->e_entry);
+	ehdr->e_phoff     = elf_addr_to_cpu(ehdr, buf_ehdr->e_phoff);
+	ehdr->e_shoff     = elf_addr_to_cpu(ehdr, buf_ehdr->e_shoff);
+	ehdr->e_flags     = elf32_to_cpu(ehdr, buf_ehdr->e_flags);
+	ehdr->e_phentsize = elf16_to_cpu(ehdr, buf_ehdr->e_phentsize);
+	ehdr->e_phnum     = elf16_to_cpu(ehdr, buf_ehdr->e_phnum);
+	ehdr->e_shentsize = elf16_to_cpu(ehdr, buf_ehdr->e_shentsize);
+	ehdr->e_shnum     = elf16_to_cpu(ehdr, buf_ehdr->e_shnum);
+	ehdr->e_shstrndx  = elf16_to_cpu(ehdr, buf_ehdr->e_shstrndx);
+
+	return elf_is_ehdr_sane(ehdr, len) ? 0 : -ENOEXEC;
+}
+
+/**
+ * elf_is_phdr_sane - check that it is safe to use the program header
+ * @buf_len:	size of the buffer in which the ELF file is loaded.
+ */
+static bool elf_is_phdr_sane(const struct elf_phdr *phdr, size_t buf_len)
+{
+
+	if (phdr->p_offset + phdr->p_filesz < phdr->p_offset) {
+		pr_debug("ELF segment location wraps around.\n");
+		return false;
+	} else if (phdr->p_offset + phdr->p_filesz > buf_len) {
+		pr_debug("ELF segment not in file.\n");
+		return false;
+	} else if (phdr->p_paddr + phdr->p_memsz < phdr->p_paddr) {
+		pr_debug("ELF segment address wraps around.\n");
+		return false;
+	}
+
+	return true;
+}
+
+static int elf_read_phdr(const char *buf, size_t len, struct elf_info *elf_info,
+			 int idx)
+{
+	/* Override the const in proghdrs, we are the ones doing the loading. */
+	struct elf_phdr *phdr = (struct elf_phdr *) &elf_info->proghdrs[idx];
+	const char *pbuf;
+	struct elf_phdr *buf_phdr;
+
+	pbuf = buf + elf_info->ehdr->e_phoff + (idx * sizeof(*buf_phdr));
+	buf_phdr = (struct elf_phdr *) pbuf;
+
+	phdr->p_type   = elf32_to_cpu(elf_info->ehdr, buf_phdr->p_type);
+	phdr->p_offset = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_offset);
+	phdr->p_paddr  = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_paddr);
+	phdr->p_vaddr  = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_vaddr);
+	phdr->p_flags  = elf32_to_cpu(elf_info->ehdr, buf_phdr->p_flags);
+
+	/*
+	 * The following fields have a type equivalent to Elf_Addr
+	 * both in 32 bit and 64 bit ELF.
+	 */
+	phdr->p_filesz = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_filesz);
+	phdr->p_memsz  = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_memsz);
+	phdr->p_align  = elf_addr_to_cpu(elf_info->ehdr, buf_phdr->p_align);
+
+	return elf_is_phdr_sane(phdr, len) ? 0 : -ENOEXEC;
+}
+
+/**
+ * elf_read_phdrs - read the program headers from the buffer
+ *
+ * This function assumes that the program header table was checked for sanity.
+ * Use elf_is_ehdr_sane() if it wasn't.
+ */
+static int elf_read_phdrs(const char *buf, size_t len,
+			  struct elf_info *elf_info)
+{
+	size_t phdr_size, i;
+	const struct elfhdr *ehdr = elf_info->ehdr;
+
+	/*
+	 * e_phnum is at most 65535 so calculating the size of the
+	 * program header cannot overflow.
+	 */
+	phdr_size = sizeof(struct elf_phdr) * ehdr->e_phnum;
+
+	elf_info->proghdrs = kzalloc(phdr_size, GFP_KERNEL);
+	if (!elf_info->proghdrs)
+		return -ENOMEM;
+
+	for (i = 0; i < ehdr->e_phnum; i++) {
+		int ret;
+
+		ret = elf_read_phdr(buf, len, elf_info, i);
+		if (ret) {
+			kfree(elf_info->proghdrs);
+			elf_info->proghdrs = NULL;
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * elf_is_shdr_sane - check that it is safe to use the section header
+ * @buf_len:	size of the buffer in which the ELF file is loaded.
+ */
+static bool elf_is_shdr_sane(const struct elf_shdr *shdr, size_t buf_len)
+{
+	bool size_ok;
+
+	/* SHT_NULL headers have undefined values, so we can't check them. */
+	if (shdr->sh_type == SHT_NULL)
+		return true;
+
+	/* Now verify sh_entsize */
+	switch (shdr->sh_type) {
+	case SHT_SYMTAB:
+		size_ok = shdr->sh_entsize == sizeof(Elf_Sym);
+		break;
+#ifdef Elf_Rela
+	case SHT_RELA:
+		size_ok = shdr->sh_entsize == sizeof(Elf_Rela);
+		break;
+#endif
+	case SHT_DYNAMIC:
+		size_ok = shdr->sh_entsize == sizeof(Elf_Dyn);
+		break;
+#ifdef Elf_Rel
+	case SHT_REL:
+		size_ok = shdr->sh_entsize == sizeof(Elf_Rel);
+		break;
+#endif
+	case SHT_NOTE:
+	case SHT_PROGBITS:
+	case SHT_HASH:
+	case SHT_NOBITS:
+	default:
+		/*
+		 * This is a section whose entsize requirements
+		 * I don't care about.  If I don't know about
+		 * the section I can't care about it's entsize
+		 * requirements.
+		 */
+		size_ok = true;
+		break;
+	}
+
+	if (!size_ok) {
+		pr_debug("ELF section with wrong entry size.\n");
+		return false;
+	} else if (shdr->sh_addr + shdr->sh_size < shdr->sh_addr) {
+		pr_debug("ELF section address wraps around.\n");
+		return false;
+	}
+
+	if (shdr->sh_type != SHT_NOBITS) {
+		if (shdr->sh_offset + shdr->sh_size < shdr->sh_offset) {
+			pr_debug("ELF section location wraps around.\n");
+			return false;
+		} else if (shdr->sh_offset + shdr->sh_size > buf_len) {
+			pr_debug("ELF section not in file.\n");
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static int elf_read_shdr(const char *buf, size_t len, struct elf_info *elf_info,
+			 int idx)
+{
+	struct elf_shdr *shdr = &elf_info->sechdrs[idx];
+	const struct elfhdr *ehdr = elf_info->ehdr;
+	const char *sbuf;
+	struct elf_shdr *buf_shdr;
+
+	sbuf = buf + ehdr->e_shoff + idx * sizeof(*buf_shdr);
+	buf_shdr = (struct elf_shdr *) sbuf;
+
+	shdr->sh_name      = elf32_to_cpu(ehdr, buf_shdr->sh_name);
+	shdr->sh_type      = elf32_to_cpu(ehdr, buf_shdr->sh_type);
+	shdr->sh_addr      = elf_addr_to_cpu(ehdr, buf_shdr->sh_addr);
+	shdr->sh_offset    = elf_addr_to_cpu(ehdr, buf_shdr->sh_offset);
+	shdr->sh_link      = elf32_to_cpu(ehdr, buf_shdr->sh_link);
+	shdr->sh_info      = elf32_to_cpu(ehdr, buf_shdr->sh_info);
+
+	/*
+	 * The following fields have a type equivalent to Elf_Addr
+	 * both in 32 bit and 64 bit ELF.
+	 */
+	shdr->sh_flags     = elf_addr_to_cpu(ehdr, buf_shdr->sh_flags);
+	shdr->sh_size      = elf_addr_to_cpu(ehdr, buf_shdr->sh_size);
+	shdr->sh_addralign = elf_addr_to_cpu(ehdr, buf_shdr->sh_addralign);
+	shdr->sh_entsize   = elf_addr_to_cpu(ehdr, buf_shdr->sh_entsize);
+
+	return elf_is_shdr_sane(shdr, len) ? 0 : -ENOEXEC;
+}
+
+/**
+ * elf_read_shdrs - read the section headers from the buffer
+ *
+ * This function assumes that the section header table was checked for sanity.
+ * Use elf_is_ehdr_sane() if it wasn't.
+ */
+static int elf_read_shdrs(const char *buf, size_t len,
+			  struct elf_info *elf_info)
+{
+	size_t shdr_size, i;
+
+	/*
+	 * e_shnum is at most 65536 so calculating
+	 * the size of the section header cannot overflow.
+	 */
+	shdr_size = sizeof(struct elf_shdr) * elf_info->ehdr->e_shnum;
+
+	elf_info->sechdrs = kzalloc(shdr_size, GFP_KERNEL);
+	if (!elf_info->sechdrs)
+		return -ENOMEM;
+
+	for (i = 0; i < elf_info->ehdr->e_shnum; i++) {
+		int ret;
+
+		ret = elf_read_shdr(buf, len, elf_info, i);
+		if (ret) {
+			kfree(elf_info->sechdrs);
+			elf_info->sechdrs = NULL;
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * elf_read_from_buffer - read ELF file and sets up ELF header and ELF info
+ * @buf:	Buffer to read ELF file from.
+ * @len:	Size of @buf.
+ * @ehdr:	Pointer to existing struct which will be populated.
+ * @elf_info:	Pointer to existing struct which will be populated.
+ *
+ * This function allows reading ELF files with different byte order than
+ * the kernel, byte-swapping the fields as needed.
+ *
+ * Return:
+ * On success returns 0, and the caller should call elf_free_info(elf_info) to
+ * free the memory allocated for the section and program headers.
+ */
+static int elf_read_from_buffer(const char *buf, size_t len,
+				struct elfhdr *ehdr, struct elf_info *elf_info)
+{
+	int ret;
+
+	ret = elf_read_ehdr(buf, len, ehdr);
+	if (ret)
+		return ret;
+
+	elf_info->buffer = buf;
+	elf_info->ehdr = ehdr;
+	if (ehdr->e_phoff > 0 && ehdr->e_phnum > 0) {
+		ret = elf_read_phdrs(buf, len, elf_info);
+		if (ret)
+			return ret;
+	}
+	if (ehdr->e_shoff > 0 && ehdr->e_shnum > 0) {
+		ret = elf_read_shdrs(buf, len, elf_info);
+		if (ret) {
+			kfree(elf_info->proghdrs);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * elf_free_info - free memory allocated by elf_read_from_buffer
+ */
+void elf_free_info(struct elf_info *elf_info)
+{
+	kfree(elf_info->proghdrs);
+	kfree(elf_info->sechdrs);
+	memset(elf_info, 0, sizeof(*elf_info));
+}
+
+/**
+ * build_elf_exec_info - read ELF executable and check that we can use it
+ */
+int build_elf_exec_info(const char *buf, size_t len, struct elfhdr *ehdr,
+			struct elf_info *elf_info)
+{
+	int i;
+	int ret;
+
+	ret = elf_read_from_buffer(buf, len, ehdr, elf_info);
+	if (ret)
+		return ret;
+
+	/* Big endian vmlinux has type ET_DYN. */
+	if (ehdr->e_type != ET_EXEC && ehdr->e_type != ET_DYN) {
+		pr_err("Not an ELF executable.\n");
+		goto error;
+	} else if (!elf_info->proghdrs) {
+		pr_err("No ELF program header.\n");
+		goto error;
+	}
+
+	for (i = 0; i < ehdr->e_phnum; i++) {
+		/*
+		 * Kexec does not support loading interpreters.
+		 * In addition this check keeps us from attempting
+		 * to kexec ordinary executables.
+		 */
+		if (elf_info->proghdrs[i].p_type == PT_INTERP) {
+			pr_err("Requires an ELF interpreter.\n");
+			goto error;
+		}
+	}
+
+	return 0;
+error:
+	elf_free_info(elf_info);
+	return -ENOEXEC;
+}
-- 
2.14.1

[toc] | [prev] | [next] | [standalone]

#1718975 — [PATCH 05/14] kexec_file: factor out crashdump elf header function from x86

prepare_elf_headers() can also be useful for other architectures,
including arm64. So let it factored out.

Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Cc: Dave Young <dyoung@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Baoquan He <bhe@redhat.com>
---
 arch/x86/kernel/crash.c | 324 ----------------------------------------------
 include/linux/kexec.h   |  19 +++
 kernel/crash_core.c     | 333 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 352 insertions(+), 324 deletions(-)

diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 44404e2307bb..3c6b880f6dbf 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -21,7 +21,6 @@
 #include <linux/elf.h>
 #include <linux/elfcore.h>
 #include <linux/export.h>
-#include <linux/slab.h>
 #include <linux/vmalloc.h>
 
 #include <asm/processor.h>
@@ -41,34 +40,6 @@
 /* Alignment required for elf header segment */
 #define ELF_CORE_HEADER_ALIGN   4096
 
-/* This primarily represents number of split ranges due to exclusion */
-#define CRASH_MAX_RANGES	16
-
-struct crash_mem_range {
-	u64 start, end;
-};
-
-struct crash_mem {
-	unsigned int nr_ranges;
-	struct crash_mem_range ranges[CRASH_MAX_RANGES];
-};
-
-/* Misc data about ram ranges needed to prepare elf headers */
-struct crash_elf_data {
-	struct kimage *image;
-	/*
-	 * Total number of ram ranges we have after various adjustments for
-	 * crash reserved region, etc.
-	 */
-	unsigned int max_nr_ranges;
-
-	/* Pointer to elf header */
-	void *ehdr;
-	/* Pointer to next phdr */
-	void *bufp;
-	struct crash_mem mem;
-};
-
 /* Used while preparing memory map entries for second kernel */
 struct crash_memmap_data {
 	struct boot_params *params;
@@ -209,301 +180,6 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 }
 
 #ifdef CONFIG_KEXEC_FILE
-static int get_nr_ram_ranges_callback(u64 start, u64 end, void *arg)
-{
-	unsigned int *nr_ranges = arg;
-
-	(*nr_ranges)++;
-	return 0;
-}
-
-
-/* Gather all the required information to prepare elf headers for ram regions */
-static void fill_up_crash_elf_data(struct crash_elf_data *ced,
-				   struct kimage *image)
-{
-	unsigned int nr_ranges = 0;
-
-	ced->image = image;
-
-	walk_system_ram_res(0, -1, &nr_ranges,
-				get_nr_ram_ranges_callback);
-
-	ced->max_nr_ranges = nr_ranges;
-
-	/* Exclusion of crash region could split memory ranges */
-	ced->max_nr_ranges++;
-
-	/* If crashk_low_res is not 0, another range split possible */
-	if (crashk_low_res.end)
-		ced->max_nr_ranges++;
-}
-
-static int exclude_mem_range(struct crash_mem *mem,
-		unsigned long long mstart, unsigned long long mend)
-{
-	int i, j;
-	unsigned long long start, end;
-	struct crash_mem_range temp_range = {0, 0};
-
-	for (i = 0; i < mem->nr_ranges; i++) {
-		start = mem->ranges[i].start;
-		end = mem->ranges[i].end;
-
-		if (mstart > end || mend < start)
-			continue;
-
-		/* Truncate any area outside of range */
-		if (mstart < start)
-			mstart = start;
-		if (mend > end)
-			mend = end;
-
-		/* Found completely overlapping range */
-		if (mstart == start && mend == end) {
-			mem->ranges[i].start = 0;
-			mem->ranges[i].end = 0;
-			if (i < mem->nr_ranges - 1) {
-				/* Shift rest of the ranges to left */
-				for (j = i; j < mem->nr_ranges - 1; j++) {
-					mem->ranges[j].start =
-						mem->ranges[j+1].start;
-					mem->ranges[j].end =
-							mem->ranges[j+1].end;
-				}
-			}
-			mem->nr_ranges--;
-			return 0;
-		}
-
-		if (mstart > start && mend < end) {
-			/* Split original range */
-			mem->ranges[i].end = mstart - 1;
-			temp_range.start = mend + 1;
-			temp_range.end = end;
-		} else if (mstart != start)
-			mem->ranges[i].end = mstart - 1;
-		else
-			mem->ranges[i].start = mend + 1;
-		break;
-	}
-
-	/* If a split happend, add the split to array */
-	if (!temp_range.end)
-		return 0;
-
-	/* Split happened */
-	if (i == CRASH_MAX_RANGES - 1) {
-		pr_err("Too many crash ranges after split\n");
-		return -ENOMEM;
-	}
-
-	/* Location where new range should go */
-	j = i + 1;
-	if (j < mem->nr_ranges) {
-		/* Move over all ranges one slot towards the end */
-		for (i = mem->nr_ranges - 1; i >= j; i--)
-			mem->ranges[i + 1] = mem->ranges[i];
-	}
-
-	mem->ranges[j].start = temp_range.start;
-	mem->ranges[j].end = temp_range.end;
-	mem->nr_ranges++;
-	return 0;
-}
-
-/*
- * Look for any unwanted ranges between mstart, mend and remove them. This
- * might lead to split and split ranges are put in ced->mem.ranges[] array
- */
-static int elf_header_exclude_ranges(struct crash_elf_data *ced,
-		unsigned long long mstart, unsigned long long mend)
-{
-	struct crash_mem *cmem = &ced->mem;
-	int ret = 0;
-
-	memset(cmem->ranges, 0, sizeof(cmem->ranges));
-
-	cmem->ranges[0].start = mstart;
-	cmem->ranges[0].end = mend;
-	cmem->nr_ranges = 1;
-
-	/* Exclude crashkernel region */
-	ret = exclude_mem_range(cmem, crashk_res.start, crashk_res.end);
-	if (ret)
-		return ret;
-
-	if (crashk_low_res.end) {
-		ret = exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end);
-		if (ret)
-			return ret;
-	}
-
-	return ret;
-}
-
-static int prepare_elf64_ram_headers_callback(u64 start, u64 end, void *arg)
-{
-	struct crash_elf_data *ced = arg;
-	Elf64_Ehdr *ehdr;
-	Elf64_Phdr *phdr;
-	unsigned long mstart, mend;
-	struct kimage *image = ced->image;
-	struct crash_mem *cmem;
-	int ret, i;
-
-	ehdr = ced->ehdr;
-
-	/* Exclude unwanted mem ranges */
-	ret = elf_header_exclude_ranges(ced, start, end);
-	if (ret)
-		return ret;
-
-	/* Go through all the ranges in ced->mem.ranges[] and prepare phdr */
-	cmem = &ced->mem;
-
-	for (i = 0; i < cmem->nr_ranges; i++) {
-		mstart = cmem->ranges[i].start;
-		mend = cmem->ranges[i].end;
-
-		phdr = ced->bufp;
-		ced->bufp += sizeof(Elf64_Phdr);
-
-		phdr->p_type = PT_LOAD;
-		phdr->p_flags = PF_R|PF_W|PF_X;
-		phdr->p_offset  = mstart;
-
-		/*
-		 * If a range matches backup region, adjust offset to backup
-		 * segment.
-		 */
-		if (mstart == image->arch.backup_src_start &&
-		    (mend - mstart + 1) == image->arch.backup_src_sz)
-			phdr->p_offset = image->arch.backup_load_addr;
-
-		phdr->p_paddr = mstart;
-		phdr->p_vaddr = (unsigned long long) __va(mstart);
-		phdr->p_filesz = phdr->p_memsz = mend - mstart + 1;
-		phdr->p_align = 0;
-		ehdr->e_phnum++;
-		pr_debug("Crash PT_LOAD elf header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
-			phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz,
-			ehdr->e_phnum, phdr->p_offset);
-	}
-
-	return ret;
-}
-
-static int prepare_elf64_headers(struct crash_elf_data *ced,
-		void **addr, unsigned long *sz)
-{
-	Elf64_Ehdr *ehdr;
-	Elf64_Phdr *phdr;
-	unsigned long nr_cpus = num_possible_cpus(), nr_phdr, elf_sz;
-	unsigned char *buf, *bufp;
-	unsigned int cpu;
-	unsigned long long notes_addr;
-	int ret;
-
-	/* extra phdr for vmcoreinfo elf note */
-	nr_phdr = nr_cpus + 1;
-	nr_phdr += ced->max_nr_ranges;
-
-	/*
-	 * kexec-tools creates an extra PT_LOAD phdr for kernel text mapping
-	 * area on x86_64 (ffffffff80000000 - ffffffffa0000000).
-	 * I think this is required by tools like gdb. So same physical
-	 * memory will be mapped in two elf headers. One will contain kernel
-	 * text virtual addresses and other will have __va(physical) addresses.
-	 */
-
-	nr_phdr++;
-	elf_sz = sizeof(Elf64_Ehdr) + nr_phdr * sizeof(Elf64_Phdr);
-	elf_sz = ALIGN(elf_sz, ELF_CORE_HEADER_ALIGN);
-
-	buf = vzalloc(elf_sz);
-	if (!buf)
-		return -ENOMEM;
-
-	bufp = buf;
-	ehdr = (Elf64_Ehdr *)bufp;
-	bufp += sizeof(Elf64_Ehdr);
-	memcpy(ehdr->e_ident, ELFMAG, SELFMAG);
-	ehdr->e_ident[EI_CLASS] = ELFCLASS64;
-	ehdr->e_ident[EI_DATA] = ELFDATA2LSB;
-	ehdr->e_ident[EI_VERSION] = EV_CURRENT;
-	ehdr->e_ident[EI_OSABI] = ELF_OSABI;
-	memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD);
-	ehdr->e_type = ET_CORE;
-	ehdr->e_machine = ELF_ARCH;
-	ehdr->e_version = EV_CURRENT;
-	ehdr->e_phoff = sizeof(Elf64_Ehdr);
-	ehdr->e_ehsize = sizeof(Elf64_Ehdr);
-	ehdr->e_phentsize = sizeof(Elf64_Phdr);
-
-	/* Prepare one phdr of type PT_NOTE for each present cpu */
-	for_each_present_cpu(cpu) {
-		phdr = (Elf64_Phdr *)bufp;
-		bufp += sizeof(Elf64_Phdr);
-		phdr->p_type = PT_NOTE;
-		notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu));
-		phdr->p_offset = phdr->p_paddr = notes_addr;
-		phdr->p_filesz = phdr->p_memsz = sizeof(note_buf_t);
-		(ehdr->e_phnum)++;
-	}
-
-	/* Prepare one PT_NOTE header for vmcoreinfo */
-	phdr = (Elf64_Phdr *)bufp;
-	bufp += sizeof(Elf64_Phdr);
-	phdr->p_type = PT_NOTE;
-	phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
-	phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE;
-	(ehdr->e_phnum)++;
-
-#ifdef CONFIG_X86_64
-	/* Prepare PT_LOAD type program header for kernel text region */
-	phdr = (Elf64_Phdr *)bufp;
-	bufp += sizeof(Elf64_Phdr);
-	phdr->p_type = PT_LOAD;
-	phdr->p_flags = PF_R|PF_W|PF_X;
-	phdr->p_vaddr = (Elf64_Addr)_text;
-	phdr->p_filesz = phdr->p_memsz = _end - _text;
-	phdr->p_offset = phdr->p_paddr = __pa_symbol(_text);
-	(ehdr->e_phnum)++;
-#endif
-
-	/* Prepare PT_LOAD headers for system ram chunks. */
-	ced->ehdr = ehdr;
-	ced->bufp = bufp;
-	ret = walk_system_ram_res(0, -1, ced,
-			prepare_elf64_ram_headers_callback);
-	if (ret < 0)
-		return ret;
-
-	*addr = buf;
-	*sz = elf_sz;
-	return 0;
-}
-
-/* Prepare elf headers. Return addr and size */
-static int prepare_elf_headers(struct kimage *image, void **addr,
-					unsigned long *sz)
-{
-	struct crash_elf_data *ced;
-	int ret;
-
-	ced = kzalloc(sizeof(*ced), GFP_KERNEL);
-	if (!ced)
-		return -ENOMEM;
-
-	fill_up_crash_elf_data(ced, image);
-
-	/* By default prepare 64bit headers */
-	ret =  prepare_elf64_headers(ced, addr, sz);
-	kfree(ced);
-	return ret;
-}
-
 static int add_e820_entry(struct boot_params *params, struct e820_entry *entry)
 {
 	unsigned int nr_e820_entries;
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index db98e3459e90..acaecd72b134 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -163,6 +163,25 @@ int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf,
 			       int (*func)(u64, u64, void *));
 extern int kexec_add_buffer(struct kexec_buf *kbuf);
 int kexec_locate_mem_hole(struct kexec_buf *kbuf);
+#ifdef CONFIG_CRASH_CORE
+extern int prepare_elf_headers(struct kimage *image, void **addr,
+				unsigned long *sz);
+
+/* This primarily represents number of split ranges due to exclusion */
+#define CRASH_MAX_RANGES        16
+
+struct crash_mem_range {
+	u64 start, end;
+};
+
+struct crash_mem {
+	unsigned int nr_ranges;
+	struct crash_mem_range ranges[CRASH_MAX_RANGES];
+};
+
+extern int exclude_mem_range(struct crash_mem *mem,
+		unsigned long long mstart, unsigned long long mend);
+#endif
 
 #ifdef CONFIG_KEXEC_FILE_ELF
 struct elf_info {
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 6db80fc0810b..f2385590e94b 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -7,6 +7,11 @@
  */
 
 #include <linux/crash_core.h>
+#include <linux/elf.h>
+#include <linux/elfcore.h>
+#include <linux/kernel.h>
+#include <linux/kexec.h>
+#include <linux/slab.h>
 #include <linux/utsname.h>
 #include <linux/vmalloc.h>
 
@@ -469,3 +474,331 @@ static int __init crash_save_vmcoreinfo_init(void)
 }
 
 subsys_initcall(crash_save_vmcoreinfo_init);
+
+#ifdef CONFIG_KEXEC_FILE
+/*
+ * The following definitions are for local use only.
+ */
+
+/* Alignment required for elf header segment */
+#define ELF_CORE_HEADER_ALIGN   4096
+
+/* Misc data about ram ranges needed to prepare elf headers */
+struct crash_elf_data {
+	struct kimage *image;
+	/*
+	 * Total number of ram ranges we have after various adjustments for
+	 * crash reserved region, etc.
+	 */
+	unsigned int max_nr_ranges;
+
+	/* Pointer to elf header */
+	void *ehdr;
+	/* Pointer to next phdr */
+	void *bufp;
+	struct crash_mem mem;
+};
+
+static int get_nr_ram_ranges_callback(u64 start, u64 end, void *arg)
+{
+	unsigned int *nr_ranges = arg;
+
+	(*nr_ranges)++;
+	return 0;
+}
+
+
+/* Gather all the required information to prepare elf headers for ram regions */
+static void fill_up_crash_elf_data(struct crash_elf_data *ced,
+				   struct kimage *image)
+{
+	unsigned int nr_ranges = 0;
+
+	ced->image = image;
+
+	walk_system_ram_res(0, -1, &nr_ranges,
+				get_nr_ram_ranges_callback);
+
+	ced->max_nr_ranges = nr_ranges;
+
+	/* Exclusion of crash region could split memory ranges */
+	ced->max_nr_ranges++;
+
+#ifdef CONFIG_X86_64
+	/* If crashk_low_res is not 0, another range split possible */
+	if (crashk_low_res.end)
+		ced->max_nr_ranges++;
+#endif
+}
+
+int exclude_mem_range(struct crash_mem *mem,
+		unsigned long long mstart, unsigned long long mend)
+{
+	int i, j;
+	unsigned long long start, end;
+	struct crash_mem_range temp_range = {0, 0};
+
+	for (i = 0; i < mem->nr_ranges; i++) {
+		start = mem->ranges[i].start;
+		end = mem->ranges[i].end;
+
+		if (mstart > end || mend < start)
+			continue;
+
+		/* Truncate any area outside of range */
+		if (mstart < start)
+			mstart = start;
+		if (mend > end)
+			mend = end;
+
+		/* Found completely overlapping range */
+		if (mstart == start && mend == end) {
+			mem->ranges[i].start = 0;
+			mem->ranges[i].end = 0;
+			if (i < mem->nr_ranges - 1) {
+				/* Shift rest of the ranges to left */
+				for (j = i; j < mem->nr_ranges - 1; j++) {
+					mem->ranges[j].start =
+						mem->ranges[j+1].start;
+					mem->ranges[j].end =
+							mem->ranges[j+1].end;
+				}
+			}
+			mem->nr_ranges--;
+			return 0;
+		}
+
+		if (mstart > start && mend < end) {
+			/* Split original range */
+			mem->ranges[i].end = mstart - 1;
+			temp_range.start = mend + 1;
+			temp_range.end = end;
+		} else if (mstart != start)
+			mem->ranges[i].end = mstart - 1;
+		else
+			mem->ranges[i].start = mend + 1;
+		break;
+	}
+
+	/* If a split happened, add the split to array */
+	if (!temp_range.end)
+		return 0;
+
+	/* Split happened */
+	if (i == CRASH_MAX_RANGES - 1) {
+		pr_err("Too many crash ranges after split\n");
+		return -ENOMEM;
+	}
+
+	/* Location where new range should go */
+	j = i + 1;
+	if (j < mem->nr_ranges) {
+		/* Move over all ranges one slot towards the end */
+		for (i = mem->nr_ranges - 1; i >= j; i--)
+			mem->ranges[i + 1] = mem->ranges[i];
+	}
+
+	mem->ranges[j].start = temp_range.start;
+	mem->ranges[j].end = temp_range.end;
+	mem->nr_ranges++;
+	return 0;
+}
+
+/*
+ * Look for any unwanted ranges between mstart, mend and remove them. This
+ * might lead to split and split ranges are put in ced->mem.ranges[] array
+ */
+static int elf_header_exclude_ranges(struct crash_elf_data *ced,
+		unsigned long long mstart, unsigned long long mend)
+{
+	struct crash_mem *cmem = &ced->mem;
+	int ret = 0;
+
+	memset(cmem->ranges, 0, sizeof(cmem->ranges));
+
+	cmem->ranges[0].start = mstart;
+	cmem->ranges[0].end = mend;
+	cmem->nr_ranges = 1;
+
+	/* Exclude crashkernel region */
+	ret = exclude_mem_range(cmem, crashk_res.start, crashk_res.end);
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_X86_64
+	if (crashk_low_res.end) {
+		ret = exclude_mem_range(cmem, crashk_low_res.start,
+							crashk_low_res.end);
+		if (ret)
+			return ret;
+	}
+#endif
+
+	return ret;
+}
+
+static int prepare_elf64_ram_headers_callback(u64 start, u64 end, void *arg)
+{
+	struct crash_elf_data *ced = arg;
+	Elf64_Ehdr *ehdr;
+	Elf64_Phdr *phdr;
+	unsigned long mstart, mend;
+#ifdef CONFIG_X86_64
+	struct kimage *image = ced->image;
+#endif
+	struct crash_mem *cmem;
+	int ret, i;
+
+	ehdr = ced->ehdr;
+
+	/* Exclude unwanted mem ranges */
+	ret = elf_header_exclude_ranges(ced, start, end);
+	if (ret)
+		return ret;
+
+	/* Go through all the ranges in ced->mem.ranges[] and prepare phdr */
+	cmem = &ced->mem;
+
+	for (i = 0; i < cmem->nr_ranges; i++) {
+		mstart = cmem->ranges[i].start;
+		mend = cmem->ranges[i].end;
+
+		phdr = ced->bufp;
+		ced->bufp += sizeof(Elf64_Phdr);
+
+		phdr->p_type = PT_LOAD;
+		phdr->p_flags = PF_R|PF_W|PF_X;
+		phdr->p_offset  = mstart;
+
+#ifdef CONFIG_X86_64
+		/*
+		 * If a range matches backup region, adjust offset to backup
+		 * segment.
+		 */
+		if (mstart == image->arch.backup_src_start &&
+		    (mend - mstart + 1) == image->arch.backup_src_sz)
+			phdr->p_offset = image->arch.backup_load_addr;
+#endif
+
+		phdr->p_paddr = mstart;
+		phdr->p_vaddr = (unsigned long long) __va(mstart);
+		phdr->p_filesz = phdr->p_memsz = mend - mstart + 1;
+		phdr->p_align = 0;
+		ehdr->e_phnum++;
+		pr_debug("Crash PT_LOAD elf header. phdr=%p vaddr=0x%llx, paddr=0x%llx, sz=0x%llx e_phnum=%d p_offset=0x%llx\n",
+			phdr, phdr->p_vaddr, phdr->p_paddr, phdr->p_filesz,
+			ehdr->e_phnum, phdr->p_offset);
+	}
+
+	return ret;
+}
+
+static int prepare_elf64_headers(struct crash_elf_data *ced,
+		void **addr, unsigned long *sz)
+{
+	Elf64_Ehdr *ehdr;
+	Elf64_Phdr *phdr;
+	unsigned long nr_cpus = num_possible_cpus(), nr_phdr, elf_sz;
+	unsigned char *buf, *bufp;
+	unsigned int cpu;
+	unsigned long long notes_addr;
+	int ret;
+
+	/* extra phdr for vmcoreinfo elf note */
+	nr_phdr = nr_cpus + 1;
+	nr_phdr += ced->max_nr_ranges;
+
+	/*
+	 * kexec-tools creates an extra PT_LOAD phdr for kernel text mapping
+	 * area on x86_64 (ffffffff80000000 - ffffffffa0000000).
+	 * I think this is required by tools like gdb. So same physical
+	 * memory will be mapped in two elf headers. One will contain kernel
+	 * text virtual addresses and other will have __va(physical) addresses.
+	 */
+
+	nr_phdr++;
+	elf_sz = sizeof(Elf64_Ehdr) + nr_phdr * sizeof(Elf64_Phdr);
+	elf_sz = ALIGN(elf_sz, ELF_CORE_HEADER_ALIGN);
+
+	buf = vzalloc(elf_sz);
+	if (!buf)
+		return -ENOMEM;
+
+	bufp = buf;
+	ehdr = (Elf64_Ehdr *)bufp;
+	bufp += sizeof(Elf64_Ehdr);
+	memcpy(ehdr->e_ident, ELFMAG, SELFMAG);
+	ehdr->e_ident[EI_CLASS] = ELFCLASS64;
+	ehdr->e_ident[EI_DATA] = ELFDATA2LSB;
+	ehdr->e_ident[EI_VERSION] = EV_CURRENT;
+	ehdr->e_ident[EI_OSABI] = ELF_OSABI;
+	memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD);
+	ehdr->e_type = ET_CORE;
+	ehdr->e_machine = ELF_ARCH;
+	ehdr->e_version = EV_CURRENT;
+	ehdr->e_phoff = sizeof(Elf64_Ehdr);
+	ehdr->e_ehsize = sizeof(Elf64_Ehdr);
+	ehdr->e_phentsize = sizeof(Elf64_Phdr);
+
+	/* Prepare one phdr of type PT_NOTE for each present cpu */
+	for_each_present_cpu(cpu) {
+		phdr = (Elf64_Phdr *)bufp;
+		bufp += sizeof(Elf64_Phdr);
+		phdr->p_type = PT_NOTE;
+		notes_addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpu));
+		phdr->p_offset = phdr->p_paddr = notes_addr;
+		phdr->p_filesz = phdr->p_memsz = sizeof(note_buf_t);
+		(ehdr->e_phnum)++;
+	}
+
+	/* Prepare one PT_NOTE header for vmcoreinfo */
+	phdr = (Elf64_Phdr *)bufp;
+	bufp += sizeof(Elf64_Phdr);
+	phdr->p_type = PT_NOTE;
+	phdr->p_offset = phdr->p_paddr = paddr_vmcoreinfo_note();
+	phdr->p_filesz = phdr->p_memsz = VMCOREINFO_NOTE_SIZE;
+	(ehdr->e_phnum)++;
+
+#ifdef CONFIG_X86_64
+	/* Prepare PT_LOAD type program header for kernel text region */
+	phdr = (Elf64_Phdr *)bufp;
+	bufp += sizeof(Elf64_Phdr);
+	phdr->p_type = PT_LOAD;
+	phdr->p_flags = PF_R|PF_W|PF_X;
+	phdr->p_vaddr = (Elf64_Addr)_text;
+	phdr->p_filesz = phdr->p_memsz = _end - _text;
+	phdr->p_offset = phdr->p_paddr = __pa_symbol(_text);
+	(ehdr->e_phnum)++;
+#endif
+
+	/* Prepare PT_LOAD headers for system ram chunks. */
+	ced->ehdr = ehdr;
+	ced->bufp = bufp;
+	ret = walk_system_ram_res(0, -1, ced,
+			prepare_elf64_ram_headers_callback);
+	if (ret < 0)
+		return ret;
+
+	*addr = buf;
+	*sz = elf_sz;
+	return 0;
+}
+
+/* Prepare elf headers. Return addr and size */
+int prepare_elf_headers(struct kimage *image, void **addr, unsigned long *sz)
+{
+	struct crash_elf_data *ced;
+	int ret;
+
+	ced = kzalloc(sizeof(*ced), GFP_KERNEL);
+	if (!ced)
+		return -ENOMEM;
+
+	fill_up_crash_elf_data(ced, image);
+
+	/* By default prepare 64bit headers */
+	ret =  prepare_elf64_headers(ced, addr, sz);
+	kfree(ced);
+	return ret;
+}
+#endif /* CONFIG_KEXEC_FILE */
-- 
2.14.1

[toc] | [prev] | [next] | [standalone]

#1719762 — Re: [PATCH 05/14] kexec_file: factor out crashdump elf header function from x86

On 08/24/17 at 05:18pm, AKASHI Takahiro wrote:
> prepare_elf_headers() can also be useful for other architectures,
> including arm64. So let it factored out.
> 
> Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
> Cc: Dave Young <dyoung@redhat.com>
> Cc: Vivek Goyal <vgoyal@redhat.com>
> Cc: Baoquan He <bhe@redhat.com>
> ---
>  arch/x86/kernel/crash.c | 324 ----------------------------------------------
>  include/linux/kexec.h   |  19 +++
>  kernel/crash_core.c     | 333 ++++++++++++++++++++++++++++++++++++++++++++++++

It looks better to add these to kexec_file.c instead.

Thanks
Dave

[toc] | [prev] | [next] | [standalone]

#1718979 — [PATCH 06/14] kexec_file: add kexec_add_segment()

In contrast to kexec_add_buffer(), this function assumes that kbuf->mem
is already assigned by caller. This type of allocation is commonly used
in kexec-tools.

This function will be used on arm64 in loading vmlinux(elf) binary.

Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Cc: Dave Young <dyoung@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Baoquan He <bhe@redhat.com>
---
 include/linux/kexec.h |  1 +
 kernel/kexec_file.c   | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 48 insertions(+)

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index acaecd72b134..be5e99afaf77 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -162,6 +162,7 @@ struct kexec_buf {
 int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf,
 			       int (*func)(u64, u64, void *));
 extern int kexec_add_buffer(struct kexec_buf *kbuf);
+extern int kexec_add_segment(struct kexec_buf *kbuf);
 int kexec_locate_mem_hole(struct kexec_buf *kbuf);
 #ifdef CONFIG_CRASH_CORE
 extern int prepare_elf_headers(struct kimage *image, void **addr,
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 9f48f4412297..d898dec37816 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -519,6 +519,53 @@ int kexec_add_buffer(struct kexec_buf *kbuf)
 	return 0;
 }
 
+/**
+ * kexec_add_segment - place a buffer in a kexec segment
+ * @kbuf:	Buffer contents and memory parameters.
+ *
+ * In contrast to kexec_add_buffer(), this function assumes
+ * that kbuf->mem is already assigned by caller.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int kexec_add_segment(struct kexec_buf *kbuf)
+{
+
+	struct kexec_segment *ksegment;
+
+	/* Currently adding segment this way is allowed only in file mode */
+	if (!kbuf->image->file_mode)
+		return -EINVAL;
+
+	if (kbuf->image->nr_segments >= KEXEC_SEGMENT_MAX)
+		return -EINVAL;
+
+	/*
+	 * Make sure we are not trying to add buffer after allocating
+	 * control pages. All segments need to be placed first before
+	 * any control pages are allocated. As control page allocation
+	 * logic goes through list of segments to make sure there are
+	 * no destination overlaps.
+	 */
+	if (!list_empty(&kbuf->image->control_pages)) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	/* Ensure minimum alignment needed for segments. */
+	kbuf->memsz = ALIGN(kbuf->memsz, PAGE_SIZE);
+
+	/* Found a suitable memory range */
+	ksegment = &kbuf->image->segment[kbuf->image->nr_segments];
+	ksegment->kbuf = kbuf->buffer;
+	ksegment->bufsz = kbuf->bufsz;
+	ksegment->mem = kbuf->mem;
+	ksegment->memsz = kbuf->memsz;
+	kbuf->image->nr_segments++;
+
+	return 0;
+}
+
 /* Calculate and store the digest of segments */
 static int kexec_calculate_store_digests(struct kimage *image)
 {
-- 
2.14.1

[toc] | [prev] | [next] | [standalone]

#1718981 — [PATCH 12/14] arm64: enable KEXEC_FILE config

Modify arm64/Kconfig and Makefile to enable kexec_file_load support.

Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/Kconfig         | 22 ++++++++++++++++++++++
 arch/arm64/kernel/Makefile |  2 +-
 2 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index dfd908630631..cf10bc720d9e 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -756,6 +756,28 @@ 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
+	select BUILD_BIN2C
+	---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
+	select SYSTEM_DATA_VERIFICATION
+	---help---
+	  This option makes kernel signature verification mandatory for
+	  the kexec_file_load() syscall.
+
+	  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 CRASH_DUMP
 	bool "Build kdump crash kernel"
 	help
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 16e9f56b536a..5df003d6157c 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -48,7 +48,7 @@ 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-$(CONFIG_KEXEC_FILE)		+= machine_kexec_file.o
 arm64-obj-$(CONFIG_ARM64_RELOC_TEST)	+= arm64-reloc-test.o
-- 
2.14.1

[toc] | [prev] | [next] | [standalone]

#1718987 — [PATCH 11/14] arm64: kexec_file: set up for crash dump adding elf core header

load_crashdump_segments() creates and loads a memory segment of elf core
header for crash dump.

"linux,usable-memory-range" and "linux,elfcorehdr" will add to the 2nd
kernel's device-tree blob. The logic of this cod is also from kexec-tools.

Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/kexec.h         |   5 ++
 arch/arm64/kernel/machine_kexec_file.c | 145 +++++++++++++++++++++++++++++++++
 2 files changed, 150 insertions(+)

diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h
index ebc4aaa707ae..46b21512efbe 100644
--- a/arch/arm64/include/asm/kexec.h
+++ b/arch/arm64/include/asm/kexec.h
@@ -98,6 +98,10 @@ static inline void crash_post_resume(void) {}
 
 struct kimage_arch {
 	void *dtb_buf;
+	/* Core ELF header buffer */
+	void *elf_headers;
+	unsigned long elf_headers_sz;
+	unsigned long elf_load_addr;
 };
 
 struct kimage;
@@ -109,6 +113,7 @@ extern int load_other_segments(struct kimage *image,
 		unsigned long kernel_load_addr,
 		char *initrd, unsigned long initrd_len,
 		char *cmdline, unsigned long cmdline_len);
+extern int load_crashdump_segments(struct kimage *image);
 #endif
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
index cd12e451e474..012063307001 100644
--- a/arch/arm64/kernel/machine_kexec_file.c
+++ b/arch/arm64/kernel/machine_kexec_file.c
@@ -281,6 +281,77 @@ int arch_kexec_walk_mem(struct kexec_buf *kbuf, int (*func)(u64, u64, void *))
 		return walk_system_ram_res(0, ULONG_MAX, kbuf, func);
 }
 
+static int __init arch_kexec_file_init(void)
+{
+	/* Those values are used later on loading the kernel */
+	__dt_root_addr_cells = dt_root_addr_cells;
+	__dt_root_size_cells = dt_root_size_cells;
+
+	return 0;
+}
+late_initcall(arch_kexec_file_init);
+
+#define FDT_ALIGN(x, a)	(((x) + (a) - 1) & ~((a) - 1))
+#define FDT_TAGALIGN(x)	(FDT_ALIGN((x), FDT_TAGSIZE))
+
+static int fdt_prop_len(const char *prop_name, int len)
+{
+	return (strlen(prop_name) + 1) +
+		sizeof(struct fdt_property) +
+		FDT_TAGALIGN(len);
+}
+
+static bool cells_size_fitted(unsigned long base, unsigned long size)
+{
+	/* if *_cells >= 2, cells can hold 64-bit values anyway */
+	if ((__dt_root_addr_cells == 1) && (base >= (1ULL << 32)))
+		return false;
+
+	if ((__dt_root_size_cells == 1) && (size >= (1ULL << 32)))
+		return false;
+
+	return true;
+}
+
+static void fill_property(void *buf, u64 val64, int cells)
+{
+	u32 val32;
+	int i;
+
+	if (cells == 1) {
+		val32 = cpu_to_fdt32((u32)val64);
+		memcpy(buf, &val32, sizeof(val32));
+	} else {
+		for (i = 0; i < (cells * sizeof(u32) - sizeof(u64)); i++)
+			*(char *)buf++ = 0;
+
+		val64 = cpu_to_fdt64(val64);
+		memcpy(buf, &val64, sizeof(val64));
+	}
+}
+
+static int fdt_setprop_range(void *fdt, int nodeoffset, const char *name,
+				unsigned long addr, unsigned long size)
+{
+	u64 range[2];
+	void *prop;
+	size_t buf_size;
+	int result;
+
+	prop = range;
+	buf_size = (__dt_root_addr_cells + __dt_root_size_cells) * sizeof(u32);
+
+	fill_property(prop, addr, __dt_root_addr_cells);
+	prop += __dt_root_addr_cells * sizeof(u32);
+
+	fill_property(prop, size, __dt_root_size_cells);
+	prop += __dt_root_size_cells * sizeof(u32);
+
+	result = fdt_setprop(fdt, nodeoffset, name, range, buf_size);
+
+	return result;
+}
+
 int setup_dtb(struct kimage *image,
 		unsigned long initrd_load_addr, unsigned long initrd_len,
 		char *cmdline, unsigned long cmdline_len,
@@ -293,10 +364,26 @@ int setup_dtb(struct kimage *image,
 	int range_len;
 	int ret;
 
+	/* check ranges against root's #address-cells and #size-cells */
+	if (image->type == KEXEC_TYPE_CRASH &&
+		(!cells_size_fitted(image->arch.elf_load_addr,
+				image->arch.elf_headers_sz) ||
+		 !cells_size_fitted(crashk_res.start,
+				crashk_res.end - crashk_res.start + 1))) {
+		pr_err("Crash memory region doesn't fit into DT's root cell sizes.\n");
+		ret = -EINVAL;
+		goto out_err;
+	}
+
 	/* duplicate dt blob */
 	buf_size = fdt_totalsize(initial_boot_params);
 	range_len = (__dt_root_addr_cells + __dt_root_size_cells) * sizeof(u32);
 
+	if (image->type == KEXEC_TYPE_CRASH)
+		buf_size += fdt_prop_len("linux,elfcorehdr", range_len)
+				+ fdt_prop_len("linux,usable-memory-range",
+								range_len);
+
 	if (initrd_load_addr)
 		buf_size += fdt_prop_len("initrd-start", sizeof(u64))
 				+ fdt_prop_len("initrd-end", sizeof(u64));
@@ -318,6 +405,23 @@ int setup_dtb(struct kimage *image,
 	if (nodeoffset < 0)
 		goto out_err;
 
+	if (image->type == KEXEC_TYPE_CRASH) {
+		/* add linux,elfcorehdr */
+		ret = fdt_setprop_range(buf, nodeoffset, "linux,elfcorehdr",
+				image->arch.elf_load_addr,
+				image->arch.elf_headers_sz);
+		if (ret)
+			goto out_err;
+
+		/* add linux,usable-memory-range */
+		ret = fdt_setprop_range(buf, nodeoffset,
+				"linux,usable-memory-range",
+				crashk_res.start,
+				crashk_res.end - crashk_res.start + 1);
+		if (ret)
+			goto out_err;
+	}
+
 	/* add bootargs */
 	if (cmdline) {
 		ret = fdt_setprop(buf, nodeoffset, "bootargs",
@@ -452,3 +556,44 @@ int load_other_segments(struct kimage *image, unsigned long kernel_load_addr,
 	image->arch.dtb_buf = NULL;
 	return ret;
 }
+
+int load_crashdump_segments(struct kimage *image)
+{
+	void *elf_addr;
+	unsigned long elf_sz;
+	struct kexec_buf kbuf;
+	int ret;
+
+	if (image->type != KEXEC_TYPE_CRASH)
+		return 0;
+
+	/* Prepare elf headers and add a segment */
+	ret = prepare_elf_headers(image, &elf_addr, &elf_sz);
+	if (ret) {
+		pr_err("Preparing elf core header failed\n");
+		return ret;
+	}
+
+	kbuf.image = image;
+	kbuf.buffer = elf_addr;
+	kbuf.bufsz = elf_sz;
+	kbuf.memsz = elf_sz;
+	kbuf.buf_align = PAGE_SIZE;
+	kbuf.buf_min = crashk_res.start;
+	kbuf.buf_max = crashk_res.end + 1;
+	kbuf.top_down = 1;
+
+	ret = kexec_add_buffer(&kbuf);
+	if (ret) {
+		vfree(elf_addr);
+		return ret;
+	}
+	image->arch.elf_headers = elf_addr;
+	image->arch.elf_headers_sz = elf_sz;
+	image->arch.elf_load_addr = kbuf.mem;
+
+	pr_debug("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+			 image->arch.elf_load_addr, elf_sz, elf_sz);
+
+	return ret;
+}
-- 
2.14.1

[toc] | [prev] | [standalone]

Page 2 of 2 — ← Prev page 1 [2]

Back to top | Article view | linux.kernel

csiph-web