linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH v2 0/9] kexec_file_load implementation for PowerPC
@ 2016-06-14 14:59 Thiago Jung Bauermann
  2016-06-14 14:59 ` [PATCH v2 1/9] kexec_file: Remove unused members from struct kexec_buf Thiago Jung Bauermann
                   ` (9 more replies)
  0 siblings, 10 replies; 20+ messages in thread
From: Thiago Jung Bauermann @ 2016-06-14 14:59 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: kexec, linux-kernel, Thiago Jung Bauermann

Hello,

This patch series implements the kexec_file_load system call on PowerPC.

It starts by removing an x86 assumption from kexec_file: kexec_add_buffer uses
iomem to find reserved memory ranges, but PowerPC uses the memblock subsystem.
A hook is added so that each arch can specify how memory ranges can be found.

Also, the memory-walking logic in kexec_add_buffer is useful in this
implementation to find a free area for the purgatory's stack, so the next
patch moves that logic to kexec_locate_mem_hole.

The kexec_file_load system call needs to apply relocations to the purgatory
but adding code for that would duplicate functionality with the module loading
mechanism, which also needs to apply relocations to the kernel modules.
Therefore, this patch series factors out the module relocation code so that it
can be shared.

One thing that is still missing is crashkernel support, which I intend to
submit shortly. For now, arch_kexec_kernel_image_probe rejects crash kernels.

This code is based on kexec-tools, but with many modifications to adapt it to
the kernel environment and facilities. Except the purgatory, which only has
minimal changes.

Changes for v2:

- All patches: forgot to add Signed-off-by lines in v1, so added them now.
- Patch "kexec_file: Generalize kexec_add_buffer.": broke in two, one
  adding arch_kexec_walk_mem and the other adding kexec_locate_mem_hole.
- Patch "powerpc: Implement kexec_file_load.":
    - Moved relocation changes and the arch_kexec_walk_mem implementation to
      the next patch in the series.
    - Removed pr_fmt from machine_kexec_64.c, since the patch doesn't add
      any call to pr_debug in that file.
    - Changed arch_kexec_kernel_image_probe to reject crash kernels.

Thiago Jung Bauermann (9):
  kexec_file: Remove unused members from struct kexec_buf.
  kexec_file: Generalize kexec_add_buffer.
  kexec_file: Factor out kexec_locate_mem_hole from kexec_add_buffer.
  powerpc: Factor out relocation code from module_64.c to elf_util_64.c.
  powerpc: Generalize elf64_apply_relocate_add.
  powerpc: Add functions to read ELF files of any endianness.
  powerpc: Implement kexec_file_load.
  powerpc: Add support for loading ELF kernels with kexec_file_load.
  powerpc: Add purgatory for kexec_file_load implementation.

 arch/powerpc/Kconfig                      |  13 +
 arch/powerpc/Makefile                     |   4 +
 arch/powerpc/include/asm/elf_util.h       |  92 +++++
 arch/powerpc/include/asm/kexec_elf_64.h   |  10 +
 arch/powerpc/include/asm/module.h         |  14 +-
 arch/powerpc/include/asm/systbl.h         |   1 +
 arch/powerpc/include/asm/unistd.h         |   2 +-
 arch/powerpc/include/uapi/asm/unistd.h    |   1 +
 arch/powerpc/kernel/Makefile              |   7 +
 arch/powerpc/kernel/elf_util.c            | 476 +++++++++++++++++++++++++
 arch/powerpc/kernel/elf_util_64.c         | 372 ++++++++++++++++++++
 arch/powerpc/kernel/kexec_elf_64.c        | 564 ++++++++++++++++++++++++++++++
 arch/powerpc/kernel/machine_kexec_64.c    | 151 ++++++++
 arch/powerpc/kernel/module_64.c           | 328 +++--------------
 arch/powerpc/purgatory/.gitignore         |   2 +
 arch/powerpc/purgatory/Makefile           |  36 ++
 arch/powerpc/purgatory/console-ppc64.c    |  43 +++
 arch/powerpc/purgatory/crashdump-ppc64.h  |  42 +++
 arch/powerpc/purgatory/crashdump_backup.c |  40 +++
 arch/powerpc/purgatory/crtsavres.S        |   5 +
 arch/powerpc/purgatory/hvCall.S           |  27 ++
 arch/powerpc/purgatory/hvCall.h           |   8 +
 arch/powerpc/purgatory/kexec-sha256.h     |  11 +
 arch/powerpc/purgatory/ppc64_asm.h        |  18 +
 arch/powerpc/purgatory/printf.c           | 171 +++++++++
 arch/powerpc/purgatory/purgatory-ppc64.c  |  46 +++
 arch/powerpc/purgatory/purgatory-ppc64.h  |   6 +
 arch/powerpc/purgatory/purgatory.c        |  66 ++++
 arch/powerpc/purgatory/purgatory.h        |  11 +
 arch/powerpc/purgatory/sha256.c           |   6 +
 arch/powerpc/purgatory/sha256.h           |   1 +
 arch/powerpc/purgatory/string.S           |   1 +
 arch/powerpc/purgatory/v2wrap.S           | 139 ++++++++
 include/linux/kexec.h                     |   7 +
 kernel/kexec_file.c                       | 116 ++++--
 kernel/kexec_internal.h                   |   2 -
 36 files changed, 2523 insertions(+), 316 deletions(-)
 create mode 100644 arch/powerpc/include/asm/elf_util.h
 create mode 100644 arch/powerpc/include/asm/kexec_elf_64.h
 create mode 100644 arch/powerpc/kernel/elf_util.c
 create mode 100644 arch/powerpc/kernel/elf_util_64.c
 create mode 100644 arch/powerpc/kernel/kexec_elf_64.c
 create mode 100644 arch/powerpc/purgatory/.gitignore
 create mode 100644 arch/powerpc/purgatory/Makefile
 create mode 100644 arch/powerpc/purgatory/console-ppc64.c
 create mode 100644 arch/powerpc/purgatory/crashdump-ppc64.h
 create mode 100644 arch/powerpc/purgatory/crashdump_backup.c
 create mode 100644 arch/powerpc/purgatory/crtsavres.S
 create mode 100644 arch/powerpc/purgatory/hvCall.S
 create mode 100644 arch/powerpc/purgatory/hvCall.h
 create mode 100644 arch/powerpc/purgatory/kexec-sha256.h
 create mode 100644 arch/powerpc/purgatory/ppc64_asm.h
 create mode 100644 arch/powerpc/purgatory/printf.c
 create mode 100644 arch/powerpc/purgatory/purgatory-ppc64.c
 create mode 100644 arch/powerpc/purgatory/purgatory-ppc64.h
 create mode 100644 arch/powerpc/purgatory/purgatory.c
 create mode 100644 arch/powerpc/purgatory/purgatory.h
 create mode 100644 arch/powerpc/purgatory/sha256.c
 create mode 100644 arch/powerpc/purgatory/sha256.h
 create mode 100644 arch/powerpc/purgatory/string.S
 create mode 100644 arch/powerpc/purgatory/v2wrap.S

-- 
1.9.1

^ permalink raw reply	[flat|nested] 20+ messages in thread

* [PATCH v2 1/9] kexec_file: Remove unused members from struct kexec_buf.
  2016-06-14 14:59 [PATCH v2 0/9] kexec_file_load implementation for PowerPC Thiago Jung Bauermann
@ 2016-06-14 14:59 ` Thiago Jung Bauermann
  2016-06-14 14:59 ` [PATCH v2 2/9] kexec_file: Generalize kexec_add_buffer Thiago Jung Bauermann
                   ` (8 subsequent siblings)
  9 siblings, 0 replies; 20+ messages in thread
From: Thiago Jung Bauermann @ 2016-06-14 14:59 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: kexec, linux-kernel, Thiago Jung Bauermann, Eric Biederman

kexec_add_buffer uses kexec_buf.buffer and kexec_buf.bufsz to pass along
its own arguments buffer and bufsz, but since they aren't used anywhere
else, it's pointless.

Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: kexec@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
Acked-by: Dave Young <dyoung@redhat.com>
---
 kernel/kexec_file.c     | 6 ++----
 kernel/kexec_internal.h | 2 --
 2 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 01ab82a40d22..b6eec7527e9f 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -464,8 +464,6 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
 	memset(&buf, 0, sizeof(struct kexec_buf));
 	kbuf = &buf;
 	kbuf->image = image;
-	kbuf->buffer = buffer;
-	kbuf->bufsz = bufsz;
 
 	kbuf->memsz = ALIGN(memsz, PAGE_SIZE);
 	kbuf->buf_align = max(buf_align, PAGE_SIZE);
@@ -489,8 +487,8 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
 
 	/* Found a suitable memory range */
 	ksegment = &image->segment[image->nr_segments];
-	ksegment->kbuf = kbuf->buffer;
-	ksegment->bufsz = kbuf->bufsz;
+	ksegment->kbuf = buffer;
+	ksegment->bufsz = bufsz;
 	ksegment->mem = kbuf->mem;
 	ksegment->memsz = kbuf->memsz;
 	image->nr_segments++;
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index 0a52315d9c62..eefd5bf960c2 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -26,8 +26,6 @@ struct kexec_sha_region {
  */
 struct kexec_buf {
 	struct kimage *image;
-	char *buffer;
-	unsigned long bufsz;
 	unsigned long mem;
 	unsigned long memsz;
 	unsigned long buf_align;
-- 
1.9.1

^ permalink raw reply	[flat|nested] 20+ messages in thread

* [PATCH v2 2/9] kexec_file: Generalize kexec_add_buffer.
  2016-06-14 14:59 [PATCH v2 0/9] kexec_file_load implementation for PowerPC Thiago Jung Bauermann
  2016-06-14 14:59 ` [PATCH v2 1/9] kexec_file: Remove unused members from struct kexec_buf Thiago Jung Bauermann
@ 2016-06-14 14:59 ` Thiago Jung Bauermann
  2016-06-15  7:33   ` Dave Young
  2016-06-14 14:59 ` [PATCH v2 3/9] kexec_file: Factor out kexec_locate_mem_hole from kexec_add_buffer Thiago Jung Bauermann
                   ` (7 subsequent siblings)
  9 siblings, 1 reply; 20+ messages in thread
From: Thiago Jung Bauermann @ 2016-06-14 14:59 UTC (permalink / raw)
  To: linuxppc-dev
  Cc: kexec, linux-kernel, Thiago Jung Bauermann, Eric Biederman, Dave Young

Allow architectures to specify different memory walking functions for
kexec_add_buffer. Intel uses iomem to track reserved memory ranges,
but PowerPC uses the memblock subsystem.

Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: kexec@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
 include/linux/kexec.h |  3 +++
 kernel/kexec_file.c   | 44 ++++++++++++++++++++++++++++++++++++--------
 2 files changed, 39 insertions(+), 8 deletions(-)

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index e8acb2b43dd9..7321043aa65a 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -315,6 +315,9 @@ int __weak arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr,
 					Elf_Shdr *sechdrs, unsigned int relsec);
 int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 					unsigned int relsec);
+int __weak arch_kexec_walk_mem(unsigned int image_type, unsigned long start,
+			       unsigned long end, bool top_down, void *data,
+			       int (*func)(u64, u64, void *));
 void arch_kexec_protect_crashkres(void);
 void arch_kexec_unprotect_crashkres(void);
 
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index b6eec7527e9f..a3ca7cfe070e 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -428,6 +428,31 @@ static int locate_mem_hole_callback(u64 start, u64 end, void *arg)
 	return locate_mem_hole_bottom_up(start, end, kbuf);
 }
 
+/**
+ * arch_kexec_walk_mem - call func(data) on free memory regions
+ * @image_type:	kimage.type
+ * @start:	Don't visit memory regions below this address.
+ * @end:	Don't visit memory regions above this address.
+ * @top_down:	Start from the highest address?
+ * @data:	Argument to pass to @func.
+ * @func:	Function to call for each memory region.
+ *
+ * Return: The memory walk will stop when func returns a non-zero value
+ * and that value will be returned. If all free regions are visited without
+ * func returning non-zero, then zero will be returned.
+ */
+int __weak arch_kexec_walk_mem(unsigned int image_type, unsigned long start,
+			       unsigned long end, bool top_down, void *data,
+			       int (*func)(u64, u64, void *))
+{
+	if (image_type == KEXEC_TYPE_CRASH)
+		return walk_iomem_res_desc(crashk_res.desc,
+					   IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
+					   start, end, data, func);
+	else
+		return walk_system_ram_res(start, end, data, func);
+}
+
 /*
  * Helper function for placing a buffer in a kexec segment. This assumes
  * that kexec_mutex is held.
@@ -441,6 +466,7 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
 	struct kexec_segment *ksegment;
 	struct kexec_buf buf, *kbuf;
 	int ret;
+	unsigned long start, end;
 
 	/* Currently adding segment this way is allowed only in file mode */
 	if (!image->file_mode)
@@ -472,14 +498,16 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
 	kbuf->top_down = top_down;
 
 	/* Walk the RAM ranges and allocate a suitable range for the buffer */
-	if (image->type == KEXEC_TYPE_CRASH)
-		ret = walk_iomem_res_desc(crashk_res.desc,
-				IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
-				crashk_res.start, crashk_res.end, kbuf,
-				locate_mem_hole_callback);
-	else
-		ret = walk_system_ram_res(0, -1, kbuf,
-					  locate_mem_hole_callback);
+	if (image->type == KEXEC_TYPE_CRASH) {
+		start = crashk_res.start;
+		end = crashk_res.end;
+	} else {
+		start = 0;
+		end = ULONG_MAX;
+	}
+
+	ret = arch_kexec_walk_mem(image->type, start, end, top_down, kbuf,
+				   locate_mem_hole_callback);
 	if (ret != 1) {
 		/* A suitable memory range could not be found for buffer */
 		return -EADDRNOTAVAIL;
-- 
1.9.1

^ permalink raw reply	[flat|nested] 20+ messages in thread

* [PATCH v2 3/9] kexec_file: Factor out kexec_locate_mem_hole from kexec_add_buffer.
  2016-06-14 14:59 [PATCH v2 0/9] kexec_file_load implementation for PowerPC Thiago Jung Bauermann
  2016-06-14 14:59 ` [PATCH v2 1/9] kexec_file: Remove unused members from struct kexec_buf Thiago Jung Bauermann
  2016-06-14 14:59 ` [PATCH v2 2/9] kexec_file: Generalize kexec_add_buffer Thiago Jung Bauermann
@ 2016-06-14 14:59 ` Thiago Jung Bauermann
  2016-06-14 14:59 ` [PATCH v2 4/9] powerpc: Factor out relocation code from module_64.c to elf_util_64.c Thiago Jung Bauermann
                   ` (6 subsequent siblings)
  9 siblings, 0 replies; 20+ messages in thread
From: Thiago Jung Bauermann @ 2016-06-14 14:59 UTC (permalink / raw)
  To: linuxppc-dev
  Cc: kexec, linux-kernel, Thiago Jung Bauermann, Eric Biederman, Dave Young

kexec_locate_mem_hole will be used by the PowerPC kexec_file_load
implementation to find free memory for the purgatory stack.

Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: kexec@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
 include/linux/kexec.h |  4 +++
 kernel/kexec_file.c   | 88 +++++++++++++++++++++++++++++++++++----------------
 2 files changed, 64 insertions(+), 28 deletions(-)

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 7321043aa65a..a08cd986b5a1 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -210,6 +210,10 @@ extern asmlinkage long sys_kexec_load(unsigned long entry,
 					struct kexec_segment __user *segments,
 					unsigned long flags);
 extern int kernel_kexec(void);
+int kexec_locate_mem_hole(struct kimage *image, unsigned long size,
+			  unsigned long align, unsigned long min_addr,
+			  unsigned long max_addr, bool top_down,
+			  unsigned long *addr);
 extern int kexec_add_buffer(struct kimage *image, char *buffer,
 			    unsigned long bufsz, unsigned long memsz,
 			    unsigned long buf_align, unsigned long buf_min,
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index a3ca7cfe070e..3e494261d32a 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -453,6 +453,57 @@ int __weak arch_kexec_walk_mem(unsigned int image_type, unsigned long start,
 		return walk_system_ram_res(start, end, data, func);
 }
 
+/**
+ * kexec_locate_mem_hole - find free memory to load segment or use in purgatory
+ * @image:	kexec image being updated.
+ * @size:	Memory size.
+ * @align:	Minimum alignment needed.
+ * @min_addr:	Minimum starting address.
+ * @max_addr:	Maximum end address.
+ * @top_down	Find the highest free memory region?
+ * @addr	On success, will have start address of the memory region found.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int kexec_locate_mem_hole(struct kimage *image, unsigned long size,
+			  unsigned long align, unsigned long min_addr,
+			  unsigned long max_addr, bool top_down,
+			  unsigned long *addr)
+{
+	int ret;
+	struct kexec_buf buf;
+	unsigned long start, end;
+
+	memset(&buf, 0, sizeof(struct kexec_buf));
+	buf.image = image;
+
+	buf.memsz = size;
+	buf.buf_align = align;
+	buf.buf_min = min_addr;
+	buf.buf_max = max_addr;
+	buf.top_down = top_down;
+
+	/* Walk the RAM ranges and allocate a suitable range for the buffer */
+	if (image->type == KEXEC_TYPE_CRASH) {
+		start = crashk_res.start;
+		end = crashk_res.end;
+	} else {
+		start = 0;
+		end = ULONG_MAX;
+	}
+
+	ret = arch_kexec_walk_mem(image->type, start, end, top_down, &buf,
+				  locate_mem_hole_callback);
+	if (ret != 1) {
+		/* A suitable memory range could not be found for buffer */
+		return -EADDRNOTAVAIL;
+	}
+
+	*addr = buf.mem;
+
+	return 0;
+}
+
 /*
  * Helper function for placing a buffer in a kexec segment. This assumes
  * that kexec_mutex is held.
@@ -464,9 +515,8 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
 {
 
 	struct kexec_segment *ksegment;
-	struct kexec_buf buf, *kbuf;
 	int ret;
-	unsigned long start, end;
+	unsigned long addr, align, size;
 
 	/* Currently adding segment this way is allowed only in file mode */
 	if (!image->file_mode)
@@ -487,38 +537,20 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
 		return -EINVAL;
 	}
 
-	memset(&buf, 0, sizeof(struct kexec_buf));
-	kbuf = &buf;
-	kbuf->image = image;
-
-	kbuf->memsz = ALIGN(memsz, PAGE_SIZE);
-	kbuf->buf_align = max(buf_align, PAGE_SIZE);
-	kbuf->buf_min = buf_min;
-	kbuf->buf_max = buf_max;
-	kbuf->top_down = top_down;
+	size = ALIGN(memsz, PAGE_SIZE);
+	align = max(buf_align, PAGE_SIZE);
 
-	/* Walk the RAM ranges and allocate a suitable range for the buffer */
-	if (image->type == KEXEC_TYPE_CRASH) {
-		start = crashk_res.start;
-		end = crashk_res.end;
-	} else {
-		start = 0;
-		end = ULONG_MAX;
-	}
-
-	ret = arch_kexec_walk_mem(image->type, start, end, top_down, kbuf,
-				   locate_mem_hole_callback);
-	if (ret != 1) {
-		/* A suitable memory range could not be found for buffer */
-		return -EADDRNOTAVAIL;
-	}
+	ret = kexec_locate_mem_hole(image, size, align, buf_min, buf_max,
+				    top_down, &addr);
+	if (ret)
+		return ret;
 
 	/* Found a suitable memory range */
 	ksegment = &image->segment[image->nr_segments];
 	ksegment->kbuf = buffer;
 	ksegment->bufsz = bufsz;
-	ksegment->mem = kbuf->mem;
-	ksegment->memsz = kbuf->memsz;
+	ksegment->mem = addr;
+	ksegment->memsz = size;
 	image->nr_segments++;
 	*load_addr = ksegment->mem;
 	return 0;
-- 
1.9.1

^ permalink raw reply	[flat|nested] 20+ messages in thread

* [PATCH v2 4/9] powerpc: Factor out relocation code from module_64.c to elf_util_64.c.
  2016-06-14 14:59 [PATCH v2 0/9] kexec_file_load implementation for PowerPC Thiago Jung Bauermann
                   ` (2 preceding siblings ...)
  2016-06-14 14:59 ` [PATCH v2 3/9] kexec_file: Factor out kexec_locate_mem_hole from kexec_add_buffer Thiago Jung Bauermann
@ 2016-06-14 14:59 ` Thiago Jung Bauermann
  2016-06-14 14:59 ` [PATCH v2 5/9] powerpc: Generalize elf64_apply_relocate_add Thiago Jung Bauermann
                   ` (5 subsequent siblings)
  9 siblings, 0 replies; 20+ messages in thread
From: Thiago Jung Bauermann @ 2016-06-14 14:59 UTC (permalink / raw)
  To: linuxppc-dev
  Cc: kexec, linux-kernel, Thiago Jung Bauermann,
	Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
	Torsten Duwe

The kexec_file_load system call needs to relocate the purgatory, so
factor out the module relocation code so that it can be shared.

This patch's purpose is to move the ELF relocation logic from
apply_relocate_add to elf_util_64.c with as few changes as
possible. The following changes were needed:

To avoid having module-specific code in a general purpose utility
function, struct elf_info was created to contain the information
needed for ELF binaries manipulation.

my_r2, stub_for_addr and create_stub were changed to use it instead of
having to receive a struct module, since they are called from
elf64_apply_relocate_add.

local_entry_offset and squash_toc_save_inst were only used by
apply_rellocate_add, so they were moved to elf_util_64.c as well.

Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Torsten Duwe <duwe@suse.de>
Cc: kexec@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
 arch/powerpc/include/asm/elf_util.h |  70 ++++++++
 arch/powerpc/include/asm/module.h   |  14 +-
 arch/powerpc/kernel/Makefile        |   4 +
 arch/powerpc/kernel/elf_util_64.c   | 269 +++++++++++++++++++++++++++++++
 arch/powerpc/kernel/module_64.c     | 312 ++++--------------------------------
 5 files changed, 386 insertions(+), 283 deletions(-)

diff --git a/arch/powerpc/include/asm/elf_util.h b/arch/powerpc/include/asm/elf_util.h
new file mode 100644
index 000000000000..13d3ca113299
--- /dev/null
+++ b/arch/powerpc/include/asm/elf_util.h
@@ -0,0 +1,70 @@
+/*
+ * Utility functions to work with ELF files.
+ *
+ * Copyright (C) 2016, IBM Corporation
+ *
+ * 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; either version 2, or (at your option)
+ * any later version.
+ *
+ * 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.
+ */
+
+#ifndef _ASM_POWERPC_ELF_UTIL_H
+#define _ASM_POWERPC_ELF_UTIL_H
+
+#include <linux/elf.h>
+
+struct elf_info {
+	struct elf_shdr *sechdrs;
+
+	/* Index of stubs section. */
+	unsigned int stubs_section;
+	/* Index of TOC section. */
+	unsigned int toc_section;
+};
+
+#ifdef __powerpc64__
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+
+/* An address is simply the address of the function. */
+typedef unsigned long func_desc_t;
+#else
+
+/* An address is address of the OPD entry, which contains address of fn. */
+typedef struct ppc64_opd_entry func_desc_t;
+#endif
+
+/* Like PPC32, we need little trampolines to do > 24-bit jumps (into
+   the kernel itself).  But on PPC64, these need to be used for every
+   jump, actually, to reset r2 (TOC+0x8000). */
+struct ppc64_stub_entry
+{
+	/* 28 byte jump instruction sequence (7 instructions). We only
+	 * need 6 instructions on ABIv2 but we always allocate 7 so
+	 * so we don't have to modify the trampoline load instruction. */
+	u32 jump[7];
+	/* Used by ftrace to identify stubs */
+	u32 magic;
+	/* Data for the above code */
+	func_desc_t funcdata;
+};
+#endif
+
+/* r2 is the TOC pointer: it actually points 0x8000 into the TOC (this
+   gives the value maximum span in an instruction which uses a signed
+   offset) */
+static inline unsigned long my_r2(const struct elf_info *elf_info)
+{
+	return elf_info->sechdrs[elf_info->toc_section].sh_addr + 0x8000;
+}
+
+int elf64_apply_relocate_add(const struct elf_info *elf_info,
+			     const char *strtab, unsigned int symindex,
+			     unsigned int relsec, const char *obj_name);
+
+#endif /* _ASM_POWERPC_ELF_UTIL_H */
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index cd4ffd86765f..f2073115d518 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -12,7 +12,14 @@
 #include <linux/list.h>
 #include <asm/bug.h>
 #include <asm-generic/module.h>
+#include <asm/elf_util.h>
 
+/* Both low and high 16 bits are added as SIGNED additions, so if low
+   16 bits has high bit set, high 16 bits must be adjusted.  These
+   macros do that (stolen from binutils). */
+#define PPC_LO(v) ((v) & 0xffff)
+#define PPC_HI(v) (((v) >> 16) & 0xffff)
+#define PPC_HA(v) PPC_HI ((v) + 0x8000)
 
 #ifndef __powerpc64__
 /*
@@ -33,8 +40,7 @@ struct ppc_plt_entry {
 
 struct mod_arch_specific {
 #ifdef __powerpc64__
-	unsigned int stubs_section;	/* Index of stubs section in module */
-	unsigned int toc_section;	/* What section is the TOC? */
+	struct elf_info elf_info;
 	bool toc_fixed;			/* Have we fixed up .TOC.? */
 #ifdef CONFIG_DYNAMIC_FTRACE
 	unsigned long toc;
@@ -90,6 +96,10 @@ static inline int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sec
 }
 #endif
 
+unsigned long stub_for_addr(const struct elf_info *elf_info, unsigned long addr,
+			    const char *obj_name);
+int restore_r2(u32 *instruction, const char *obj_name);
+
 struct exception_table_entry;
 void sort_ex_table(struct exception_table_entry *start,
 		   struct exception_table_entry *finish);
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 2da380fcc34c..e99f626acc85 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -124,6 +124,10 @@ ifneq ($(CONFIG_PPC_INDIRECT_PIO),y)
 obj-y				+= iomap.o
 endif
 
+ifeq ($(CONFIG_MODULES)$(CONFIG_WORD_SIZE),y64)
+obj-y				+= elf_util_64.o
+endif
+
 obj64-$(CONFIG_PPC_TRANSACTIONAL_MEM)	+= tm.o
 
 obj-$(CONFIG_PPC64)		+= $(obj64-y)
diff --git a/arch/powerpc/kernel/elf_util_64.c b/arch/powerpc/kernel/elf_util_64.c
new file mode 100644
index 000000000000..b53b3959a605
--- /dev/null
+++ b/arch/powerpc/kernel/elf_util_64.c
@@ -0,0 +1,269 @@
+/*
+ * Utility functions to work with ELF files.
+ *
+ * Copyright (C) 2016, IBM Corporation
+ *
+ * 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; either version 2, or (at your option)
+ * any later version.
+ *
+ * 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.
+ */
+
+#include <asm/ppc-opcode.h>
+#include <asm/elf_util.h>
+
+/*
+ * We just need to use the functions defined in <asm/module.h>, so just declare
+ * struct module here and avoid having to import <linux/module.h>.
+ */
+struct module;
+#include <asm/module.h>
+
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+/* PowerPC64 specific values for the Elf64_Sym st_other field.  */
+#define STO_PPC64_LOCAL_BIT	5
+#define STO_PPC64_LOCAL_MASK	(7 << STO_PPC64_LOCAL_BIT)
+#define PPC64_LOCAL_ENTRY_OFFSET(other)					\
+ (((1 << (((other) & STO_PPC64_LOCAL_MASK) >> STO_PPC64_LOCAL_BIT)) >> 2) << 2)
+
+static unsigned int local_entry_offset(const Elf64_Sym *sym)
+{
+	/* sym->st_other indicates offset to local entry point
+	 * (otherwise it will assume r12 is the address of the start
+	 * of function and try to derive r2 from it). */
+	return PPC64_LOCAL_ENTRY_OFFSET(sym->st_other);
+}
+#else
+static unsigned int local_entry_offset(const Elf64_Sym *sym)
+{
+	return 0;
+}
+#endif
+
+#ifdef CC_USING_MPROFILE_KERNEL
+/*
+ * In case of _mcount calls, do not save the current callee's TOC (in r2) into
+ * the original caller's stack frame. If we did we would clobber the saved TOC
+ * value of the original caller.
+ */
+static void squash_toc_save_inst(const char *name, unsigned long addr)
+{
+	struct ppc64_stub_entry *stub = (struct ppc64_stub_entry *)addr;
+
+	/* Only for calls to _mcount */
+	if (strcmp("_mcount", name) != 0)
+		return;
+
+	stub->jump[2] = PPC_INST_NOP;
+}
+#else
+static void squash_toc_save_inst(const char *name, unsigned long addr) { }
+#endif
+
+/**
+ * elf64_apply_relocate_add - apply 64 bit RELA relocations
+ * @elf_info:		Support information for the ELF binary being relocated.
+ * @strtab:		String table for the associated symbol table.
+ * @symindex:		Section header index for the associated symbol table.
+ * @relsec:		Section header index for the relocations to apply.
+ * @obj_name:		The name of the ELF binary, for information messages.
+ */
+int elf64_apply_relocate_add(const struct elf_info *elf_info,
+			     const char *strtab, unsigned int symindex,
+			     unsigned int relsec, const char *obj_name)
+{
+	unsigned int i;
+	Elf64_Shdr *sechdrs = elf_info->sechdrs;
+	Elf64_Rela *rela = (void *)sechdrs[relsec].sh_addr;
+	Elf64_Sym *sym;
+	unsigned long *location;
+	unsigned long value;
+
+
+	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) {
+		/* This is where to make the change */
+		location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
+			+ rela[i].r_offset;
+		/* This is the symbol it is referring to */
+		sym = (Elf64_Sym *)sechdrs[symindex].sh_addr
+			+ ELF64_R_SYM(rela[i].r_info);
+
+		pr_debug("RELOC at %p: %li-type as %s (0x%lx) + %li\n",
+		       location, (long)ELF64_R_TYPE(rela[i].r_info),
+		       strtab + sym->st_name, (unsigned long)sym->st_value,
+		       (long)rela[i].r_addend);
+
+		/* `Everything is relative'. */
+		value = sym->st_value + rela[i].r_addend;
+
+		switch (ELF64_R_TYPE(rela[i].r_info)) {
+		case R_PPC64_ADDR32:
+			/* Simply set it */
+			*(u32 *)location = value;
+			break;
+
+		case R_PPC64_ADDR64:
+			/* Simply set it */
+			*(unsigned long *)location = value;
+			break;
+
+		case R_PPC64_TOC:
+			*(unsigned long *)location = my_r2(elf_info);
+			break;
+
+		case R_PPC64_TOC16:
+			/* Subtract TOC pointer */
+			value -= my_r2(elf_info);
+			if (value + 0x8000 > 0xffff) {
+				pr_err("%s: bad TOC16 relocation (0x%lx)\n",
+				       obj_name, value);
+				return -ENOEXEC;
+			}
+			*((uint16_t *) location)
+				= (*((uint16_t *) location) & ~0xffff)
+				| (value & 0xffff);
+			break;
+
+		case R_PPC64_TOC16_LO:
+			/* Subtract TOC pointer */
+			value -= my_r2(elf_info);
+			*((uint16_t *) location)
+				= (*((uint16_t *) location) & ~0xffff)
+				| (value & 0xffff);
+			break;
+
+		case R_PPC64_TOC16_DS:
+			/* Subtract TOC pointer */
+			value -= my_r2(elf_info);
+			if ((value & 3) != 0 || value + 0x8000 > 0xffff) {
+				pr_err("%s: bad TOC16_DS relocation (0x%lx)\n",
+				       obj_name, value);
+				return -ENOEXEC;
+			}
+			*((uint16_t *) location)
+				= (*((uint16_t *) location) & ~0xfffc)
+				| (value & 0xfffc);
+			break;
+
+		case R_PPC64_TOC16_LO_DS:
+			/* Subtract TOC pointer */
+			value -= my_r2(elf_info);
+			if ((value & 3) != 0) {
+				pr_err("%s: bad TOC16_LO_DS relocation (0x%lx)\n",
+				       obj_name, value);
+				return -ENOEXEC;
+			}
+			*((uint16_t *) location)
+				= (*((uint16_t *) location) & ~0xfffc)
+				| (value & 0xfffc);
+			break;
+
+		case R_PPC64_TOC16_HA:
+			/* Subtract TOC pointer */
+			value -= my_r2(elf_info);
+			value = ((value + 0x8000) >> 16);
+			*((uint16_t *) location)
+				= (*((uint16_t *) location) & ~0xffff)
+				| (value & 0xffff);
+			break;
+
+		case R_PPC_REL24:
+			/* FIXME: Handle weak symbols here --RR */
+			if (sym->st_shndx == SHN_UNDEF) {
+				/* External: go via stub */
+				value = stub_for_addr(elf_info, value, obj_name);
+				if (!value)
+					return -ENOENT;
+				if (!restore_r2((u32 *)location + 1, obj_name))
+					return -ENOEXEC;
+
+				squash_toc_save_inst(strtab + sym->st_name, value);
+			} else
+				value += local_entry_offset(sym);
+
+			/* Convert value to relative */
+			value -= (unsigned long)location;
+			if (value + 0x2000000 > 0x3ffffff || (value & 3) != 0){
+				pr_err("%s: REL24 %li out of range!\n",
+				       obj_name, (long int)value);
+				return -ENOEXEC;
+			}
+
+			/* Only replace bits 2 through 26 */
+			*(uint32_t *)location
+				= (*(uint32_t *)location & ~0x03fffffc)
+				| (value & 0x03fffffc);
+			break;
+
+		case R_PPC64_REL64:
+			/* 64 bits relative (used by features fixups) */
+			*location = value - (unsigned long)location;
+			break;
+
+		case R_PPC64_TOCSAVE:
+			/*
+			 * Marker reloc indicates we don't have to save r2.
+			 * That would only save us one instruction, so ignore
+			 * it.
+			 */
+			break;
+
+		case R_PPC64_ENTRY:
+			/*
+			 * Optimize ELFv2 large code model entry point if
+			 * the TOC is within 2GB range of current location.
+			 */
+			value = my_r2(elf_info) - (unsigned long)location;
+			if (value + 0x80008000 > 0xffffffff)
+				break;
+			/*
+			 * Check for the large code model prolog sequence:
+			 *	ld r2, ...(r12)
+			 *	add r2, r2, r12
+			 */
+			if ((((uint32_t *)location)[0] & ~0xfffc)
+			    != 0xe84c0000)
+				break;
+			if (((uint32_t *)location)[1] != 0x7c426214)
+				break;
+			/*
+			 * If found, replace it with:
+			 *	addis r2, r12, (.TOC.-func)@ha
+			 *	addi r2, r12, (.TOC.-func)@l
+			 */
+			((uint32_t *)location)[0] = 0x3c4c0000 + PPC_HA(value);
+			((uint32_t *)location)[1] = 0x38420000 + PPC_LO(value);
+			break;
+
+		case R_PPC64_REL16_HA:
+			/* Subtract location pointer */
+			value -= (unsigned long)location;
+			value = ((value + 0x8000) >> 16);
+			*((uint16_t *) location)
+				= (*((uint16_t *) location) & ~0xffff)
+				| (value & 0xffff);
+			break;
+
+		case R_PPC64_REL16_LO:
+			/* Subtract location pointer */
+			value -= (unsigned long)location;
+			*((uint16_t *) location)
+				= (*((uint16_t *) location) & ~0xffff)
+				| (value & 0xffff);
+			break;
+
+		default:
+			pr_err("%s: Unknown ADD relocation: %lu\n",
+			       obj_name,
+			       (unsigned long)ELF64_R_TYPE(rela[i].r_info));
+			return -ENOEXEC;
+		}
+	}
+
+	return 0;
+}
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 9ce9a25f58b5..5f2eeab93651 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -19,7 +19,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/module.h>
-#include <linux/elf.h>
+#include <asm/elf_util.h>
 #include <linux/moduleloader.h>
 #include <linux/err.h>
 #include <linux/vmalloc.h>
@@ -43,9 +43,6 @@
 
 #if defined(_CALL_ELF) && _CALL_ELF == 2
 
-/* An address is simply the address of the function. */
-typedef unsigned long func_desc_t;
-
 static func_desc_t func_desc(unsigned long addr)
 {
 	return addr;
@@ -58,25 +55,8 @@ static unsigned long stub_func_addr(func_desc_t func)
 {
 	return func;
 }
-
-/* PowerPC64 specific values for the Elf64_Sym st_other field.  */
-#define STO_PPC64_LOCAL_BIT	5
-#define STO_PPC64_LOCAL_MASK	(7 << STO_PPC64_LOCAL_BIT)
-#define PPC64_LOCAL_ENTRY_OFFSET(other)					\
- (((1 << (((other) & STO_PPC64_LOCAL_MASK) >> STO_PPC64_LOCAL_BIT)) >> 2) << 2)
-
-static unsigned int local_entry_offset(const Elf64_Sym *sym)
-{
-	/* sym->st_other indicates offset to local entry point
-	 * (otherwise it will assume r12 is the address of the start
-	 * of function and try to derive r2 from it). */
-	return PPC64_LOCAL_ENTRY_OFFSET(sym->st_other);
-}
 #else
 
-/* An address is address of the OPD entry, which contains address of fn. */
-typedef struct ppc64_opd_entry func_desc_t;
-
 static func_desc_t func_desc(unsigned long addr)
 {
 	return *(struct ppc64_opd_entry *)addr;
@@ -89,29 +69,10 @@ static unsigned long stub_func_addr(func_desc_t func)
 {
 	return func.funcaddr;
 }
-static unsigned int local_entry_offset(const Elf64_Sym *sym)
-{
-	return 0;
-}
 #endif
 
 #define STUB_MAGIC 0x73747562 /* stub */
 
-/* Like PPC32, we need little trampolines to do > 24-bit jumps (into
-   the kernel itself).  But on PPC64, these need to be used for every
-   jump, actually, to reset r2 (TOC+0x8000). */
-struct ppc64_stub_entry
-{
-	/* 28 byte jump instruction sequence (7 instructions). We only
-	 * need 6 instructions on ABIv2 but we always allocate 7 so
-	 * so we don't have to modify the trampoline load instruction. */
-	u32 jump[7];
-	/* Used by ftrace to identify stubs */
-	u32 magic;
-	/* Data for the above code */
-	func_desc_t funcdata;
-};
-
 /*
  * PPC64 uses 24 bit jumps, but we need to jump into other modules or
  * the kernel which may be further.  So we jump to a stub.
@@ -346,9 +307,9 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr,
 	for (i = 1; i < hdr->e_shnum; i++) {
 		char *p;
 		if (strcmp(secstrings + sechdrs[i].sh_name, ".stubs") == 0)
-			me->arch.stubs_section = i;
+			me->arch.elf_info.stubs_section = i;
 		else if (strcmp(secstrings + sechdrs[i].sh_name, ".toc") == 0)
-			me->arch.toc_section = i;
+			me->arch.elf_info.toc_section = i;
 		else if (strcmp(secstrings+sechdrs[i].sh_name,"__versions")==0)
 			dedotify_versions((void *)hdr + sechdrs[i].sh_offset,
 					  sechdrs[i].sh_size);
@@ -364,7 +325,7 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr,
 				 + sechdrs[sechdrs[i].sh_link].sh_offset);
 	}
 
-	if (!me->arch.stubs_section) {
+	if (!me->arch.elf_info.stubs_section) {
 		pr_err("%s: doesn't contain .stubs.\n", me->name);
 		return -ENOEXEC;
 	}
@@ -373,44 +334,32 @@ int module_frob_arch_sections(Elf64_Ehdr *hdr,
 	   to some reasonable value in case the module calls out to
 	   other functions via a stub, or if a function pointer escapes
 	   the module by some means.  */
-	if (!me->arch.toc_section)
-		me->arch.toc_section = me->arch.stubs_section;
+	if (!me->arch.elf_info.toc_section)
+		me->arch.elf_info.toc_section = me->arch.elf_info.stubs_section;
 
 	/* Override the stubs size */
-	sechdrs[me->arch.stubs_section].sh_size = get_stubs_size(hdr, sechdrs);
-	return 0;
-}
+	sechdrs[me->arch.elf_info.stubs_section].sh_size = get_stubs_size(hdr, sechdrs);
 
-/* r2 is the TOC pointer: it actually points 0x8000 into the TOC (this
-   gives the value maximum span in an instruction which uses a signed
-   offset) */
-static inline unsigned long my_r2(const Elf64_Shdr *sechdrs, struct module *me)
-{
-	return sechdrs[me->arch.toc_section].sh_addr + 0x8000;
-}
+	/* For the elf_util functions. */
+	me->arch.elf_info.sechdrs = sechdrs;
 
-/* Both low and high 16 bits are added as SIGNED additions, so if low
-   16 bits has high bit set, high 16 bits must be adjusted.  These
-   macros do that (stolen from binutils). */
-#define PPC_LO(v) ((v) & 0xffff)
-#define PPC_HI(v) (((v) >> 16) & 0xffff)
-#define PPC_HA(v) PPC_HI ((v) + 0x8000)
+	return 0;
+}
 
 /* Patch stub to reference function and correct r2 value. */
-static inline int create_stub(const Elf64_Shdr *sechdrs,
+static inline int create_stub(const struct elf_info *elf_info,
 			      struct ppc64_stub_entry *entry,
-			      unsigned long addr,
-			      struct module *me)
+			      unsigned long addr, const char *obj_name)
 {
 	long reladdr;
 
 	memcpy(entry->jump, ppc64_stub_insns, sizeof(ppc64_stub_insns));
 
 	/* Stub uses address relative to r2. */
-	reladdr = (unsigned long)entry - my_r2(sechdrs, me);
+	reladdr = (unsigned long)entry - my_r2(elf_info);
 	if (reladdr > 0x7FFFFFFF || reladdr < -(0x80000000L)) {
 		pr_err("%s: Address %p of stub out of range of %p.\n",
-		       me->name, (void *)reladdr, (void *)my_r2);
+		       obj_name, (void *)reladdr, (void *)my_r2);
 		return 0;
 	}
 	pr_debug("Stub %p get data from reladdr %li\n", entry, reladdr);
@@ -425,17 +374,17 @@ static inline int create_stub(const Elf64_Shdr *sechdrs,
 
 /* Create stub to jump to function described in this OPD/ptr: we need the
    stub to set up the TOC ptr (r2) for the function. */
-static unsigned long stub_for_addr(const Elf64_Shdr *sechdrs,
-				   unsigned long addr,
-				   struct module *me)
+unsigned long stub_for_addr(const struct elf_info *elf_info, unsigned long addr,
+			    const char *obj_name)
 {
+	struct elf_shdr *stubs_sec = &elf_info->sechdrs[elf_info->stubs_section];
 	struct ppc64_stub_entry *stubs;
 	unsigned int i, num_stubs;
 
-	num_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*stubs);
+	num_stubs = stubs_sec->sh_size / sizeof(*stubs);
 
 	/* Find this stub, or if that fails, the next avail. entry */
-	stubs = (void *)sechdrs[me->arch.stubs_section].sh_addr;
+	stubs = (void *) stubs_sec->sh_addr;
 	for (i = 0; stub_func_addr(stubs[i].funcdata); i++) {
 		BUG_ON(i >= num_stubs);
 
@@ -443,7 +392,7 @@ static unsigned long stub_for_addr(const Elf64_Shdr *sechdrs,
 			return (unsigned long)&stubs[i];
 	}
 
-	if (!create_stub(sechdrs, &stubs[i], addr, me))
+	if (!create_stub(elf_info, &stubs[i], addr, obj_name))
 		return 0;
 
 	return (unsigned long)&stubs[i];
@@ -465,24 +414,7 @@ static bool is_early_mcount_callsite(u32 *instruction)
 	return false;
 }
 
-/*
- * In case of _mcount calls, do not save the current callee's TOC (in r2) into
- * the original caller's stack frame. If we did we would clobber the saved TOC
- * value of the original caller.
- */
-static void squash_toc_save_inst(const char *name, unsigned long addr)
-{
-	struct ppc64_stub_entry *stub = (struct ppc64_stub_entry *)addr;
-
-	/* Only for calls to _mcount */
-	if (strcmp("_mcount", name) != 0)
-		return;
-
-	stub->jump[2] = PPC_INST_NOP;
-}
 #else
-static void squash_toc_save_inst(const char *name, unsigned long addr) { }
-
 /* without -mprofile-kernel, mcount calls are never early */
 static bool is_early_mcount_callsite(u32 *instruction)
 {
@@ -492,13 +424,13 @@ static bool is_early_mcount_callsite(u32 *instruction)
 
 /* We expect a noop next: if it is, replace it with instruction to
    restore r2. */
-static int restore_r2(u32 *instruction, struct module *me)
+int restore_r2(u32 *instruction, const char *obj_name)
 {
 	if (*instruction != PPC_INST_NOP) {
 		if (is_early_mcount_callsite(instruction - 1))
 			return 1;
 		pr_err("%s: Expect noop after relocate, got %08x\n",
-		       me->name, *instruction);
+		       obj_name, *instruction);
 		return 0;
 	}
 	/* ld r2,R2_STACK_OFFSET(r1) */
@@ -512,11 +444,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		       unsigned int relsec,
 		       struct module *me)
 {
-	unsigned int i;
-	Elf64_Rela *rela = (void *)sechdrs[relsec].sh_addr;
 	Elf64_Sym *sym;
-	unsigned long *location;
-	unsigned long value;
 
 	pr_debug("Applying ADD relocate section %u to %u\n", relsec,
 	       sechdrs[relsec].sh_info);
@@ -527,191 +455,12 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		/* It's theoretically possible that a module doesn't want a
 		 * .TOC. so don't fail it just for that. */
 		if (sym)
-			sym->st_value = my_r2(sechdrs, me);
+			sym->st_value = my_r2(&me->arch.elf_info);
 		me->arch.toc_fixed = true;
 	}
 
-	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) {
-		/* This is where to make the change */
-		location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
-			+ rela[i].r_offset;
-		/* This is the symbol it is referring to */
-		sym = (Elf64_Sym *)sechdrs[symindex].sh_addr
-			+ ELF64_R_SYM(rela[i].r_info);
-
-		pr_debug("RELOC at %p: %li-type as %s (0x%lx) + %li\n",
-		       location, (long)ELF64_R_TYPE(rela[i].r_info),
-		       strtab + sym->st_name, (unsigned long)sym->st_value,
-		       (long)rela[i].r_addend);
-
-		/* `Everything is relative'. */
-		value = sym->st_value + rela[i].r_addend;
-
-		switch (ELF64_R_TYPE(rela[i].r_info)) {
-		case R_PPC64_ADDR32:
-			/* Simply set it */
-			*(u32 *)location = value;
-			break;
-
-		case R_PPC64_ADDR64:
-			/* Simply set it */
-			*(unsigned long *)location = value;
-			break;
-
-		case R_PPC64_TOC:
-			*(unsigned long *)location = my_r2(sechdrs, me);
-			break;
-
-		case R_PPC64_TOC16:
-			/* Subtract TOC pointer */
-			value -= my_r2(sechdrs, me);
-			if (value + 0x8000 > 0xffff) {
-				pr_err("%s: bad TOC16 relocation (0x%lx)\n",
-				       me->name, value);
-				return -ENOEXEC;
-			}
-			*((uint16_t *) location)
-				= (*((uint16_t *) location) & ~0xffff)
-				| (value & 0xffff);
-			break;
-
-		case R_PPC64_TOC16_LO:
-			/* Subtract TOC pointer */
-			value -= my_r2(sechdrs, me);
-			*((uint16_t *) location)
-				= (*((uint16_t *) location) & ~0xffff)
-				| (value & 0xffff);
-			break;
-
-		case R_PPC64_TOC16_DS:
-			/* Subtract TOC pointer */
-			value -= my_r2(sechdrs, me);
-			if ((value & 3) != 0 || value + 0x8000 > 0xffff) {
-				pr_err("%s: bad TOC16_DS relocation (0x%lx)\n",
-				       me->name, value);
-				return -ENOEXEC;
-			}
-			*((uint16_t *) location)
-				= (*((uint16_t *) location) & ~0xfffc)
-				| (value & 0xfffc);
-			break;
-
-		case R_PPC64_TOC16_LO_DS:
-			/* Subtract TOC pointer */
-			value -= my_r2(sechdrs, me);
-			if ((value & 3) != 0) {
-				pr_err("%s: bad TOC16_LO_DS relocation (0x%lx)\n",
-				       me->name, value);
-				return -ENOEXEC;
-			}
-			*((uint16_t *) location)
-				= (*((uint16_t *) location) & ~0xfffc)
-				| (value & 0xfffc);
-			break;
-
-		case R_PPC64_TOC16_HA:
-			/* Subtract TOC pointer */
-			value -= my_r2(sechdrs, me);
-			value = ((value + 0x8000) >> 16);
-			*((uint16_t *) location)
-				= (*((uint16_t *) location) & ~0xffff)
-				| (value & 0xffff);
-			break;
-
-		case R_PPC_REL24:
-			/* FIXME: Handle weak symbols here --RR */
-			if (sym->st_shndx == SHN_UNDEF) {
-				/* External: go via stub */
-				value = stub_for_addr(sechdrs, value, me);
-				if (!value)
-					return -ENOENT;
-				if (!restore_r2((u32 *)location + 1, me))
-					return -ENOEXEC;
-
-				squash_toc_save_inst(strtab + sym->st_name, value);
-			} else
-				value += local_entry_offset(sym);
-
-			/* Convert value to relative */
-			value -= (unsigned long)location;
-			if (value + 0x2000000 > 0x3ffffff || (value & 3) != 0){
-				pr_err("%s: REL24 %li out of range!\n",
-				       me->name, (long int)value);
-				return -ENOEXEC;
-			}
-
-			/* Only replace bits 2 through 26 */
-			*(uint32_t *)location
-				= (*(uint32_t *)location & ~0x03fffffc)
-				| (value & 0x03fffffc);
-			break;
-
-		case R_PPC64_REL64:
-			/* 64 bits relative (used by features fixups) */
-			*location = value - (unsigned long)location;
-			break;
-
-		case R_PPC64_TOCSAVE:
-			/*
-			 * Marker reloc indicates we don't have to save r2.
-			 * That would only save us one instruction, so ignore
-			 * it.
-			 */
-			break;
-
-		case R_PPC64_ENTRY:
-			/*
-			 * Optimize ELFv2 large code model entry point if
-			 * the TOC is within 2GB range of current location.
-			 */
-			value = my_r2(sechdrs, me) - (unsigned long)location;
-			if (value + 0x80008000 > 0xffffffff)
-				break;
-			/*
-			 * Check for the large code model prolog sequence:
-		         *	ld r2, ...(r12)
-			 *	add r2, r2, r12
-			 */
-			if ((((uint32_t *)location)[0] & ~0xfffc)
-			    != 0xe84c0000)
-				break;
-			if (((uint32_t *)location)[1] != 0x7c426214)
-				break;
-			/*
-			 * If found, replace it with:
-			 *	addis r2, r12, (.TOC.-func)@ha
-			 *	addi r2, r12, (.TOC.-func)@l
-			 */
-			((uint32_t *)location)[0] = 0x3c4c0000 + PPC_HA(value);
-			((uint32_t *)location)[1] = 0x38420000 + PPC_LO(value);
-			break;
-
-		case R_PPC64_REL16_HA:
-			/* Subtract location pointer */
-			value -= (unsigned long)location;
-			value = ((value + 0x8000) >> 16);
-			*((uint16_t *) location)
-				= (*((uint16_t *) location) & ~0xffff)
-				| (value & 0xffff);
-			break;
-
-		case R_PPC64_REL16_LO:
-			/* Subtract location pointer */
-			value -= (unsigned long)location;
-			*((uint16_t *) location)
-				= (*((uint16_t *) location) & ~0xffff)
-				| (value & 0xffff);
-			break;
-
-		default:
-			pr_err("%s: Unknown ADD relocation: %lu\n",
-			       me->name,
-			       (unsigned long)ELF64_R_TYPE(rela[i].r_info));
-			return -ENOEXEC;
-		}
-	}
-
-	return 0;
+	return elf64_apply_relocate_add(&me->arch.elf_info, strtab, symindex,
+					relsec, me->name);
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -745,10 +494,10 @@ static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module
 	};
 	long reladdr;
 
-	num_stubs = sechdrs[me->arch.stubs_section].sh_size / sizeof(*entry);
+	num_stubs = sechdrs[me->arch.elf_info.stubs_section].sh_size / sizeof(*entry);
 
 	/* Find the next available stub entry */
-	entry = (void *)sechdrs[me->arch.stubs_section].sh_addr;
+	entry = (void *)sechdrs[me->arch.elf_info.stubs_section].sh_addr;
 	for (i = 0; i < num_stubs && stub_func_addr(entry->funcdata); i++, entry++);
 
 	if (i >= num_stubs) {
@@ -777,13 +526,14 @@ static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module
 #else
 static unsigned long create_ftrace_stub(const Elf64_Shdr *sechdrs, struct module *me)
 {
-	return stub_for_addr(sechdrs, (unsigned long)ftrace_caller, me);
+	return stub_for_addr(&me->arch.elf_info, (unsigned long)ftrace_caller,
+			     me->name);
 }
 #endif
 
 int module_finalize_ftrace(struct module *mod, const Elf_Shdr *sechdrs)
 {
-	mod->arch.toc = my_r2(sechdrs, mod);
+	mod->arch.toc = my_r2(&mod->arch.elf_info);
 	mod->arch.tramp = create_ftrace_stub(sechdrs, mod);
 
 	if (!mod->arch.tramp)
-- 
1.9.1

^ permalink raw reply	[flat|nested] 20+ messages in thread

* [PATCH v2 5/9] powerpc: Generalize elf64_apply_relocate_add.
  2016-06-14 14:59 [PATCH v2 0/9] kexec_file_load implementation for PowerPC Thiago Jung Bauermann
                   ` (3 preceding siblings ...)
  2016-06-14 14:59 ` [PATCH v2 4/9] powerpc: Factor out relocation code from module_64.c to elf_util_64.c Thiago Jung Bauermann
@ 2016-06-14 14:59 ` Thiago Jung Bauermann
  2016-06-14 14:59 ` [PATCH v2 6/9] powerpc: Add functions to read ELF files of any endianness Thiago Jung Bauermann
                   ` (4 subsequent siblings)
  9 siblings, 0 replies; 20+ messages in thread
From: Thiago Jung Bauermann @ 2016-06-14 14:59 UTC (permalink / raw)
  To: linuxppc-dev
  Cc: kexec, linux-kernel, Thiago Jung Bauermann,
	Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
	Torsten Duwe

When apply_relocate_add is called, modules are already loaded at their
final location in memory so Elf64_Shdr.sh_addr can be used for accessing
the section contents as well as the base address for relocations.

This is not the case for kexec's purgatory, because it will only be
copied to its final location right before being executed. Therefore,
it needs to be relocated while it is still in a temporary buffer. In
this case, Elf64_Shdr.sh_addr can't be used to access the sections'
contents.

This patch allows elf64_apply_relocate_add to be used when the ELF
binary is not yet at its final location by adding an addr_base argument
to specify the address at which the section will be loaded, and rela,
loc_base and syms_base to point to the sections' contents.

Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Torsten Duwe <duwe@suse.de>
Cc: kexec@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
 arch/powerpc/include/asm/elf_util.h |  6 ++--
 arch/powerpc/kernel/elf_util_64.c   | 63 +++++++++++++++++++++++++------------
 arch/powerpc/kernel/module_64.c     | 17 ++++++++--
 3 files changed, 61 insertions(+), 25 deletions(-)

diff --git a/arch/powerpc/include/asm/elf_util.h b/arch/powerpc/include/asm/elf_util.h
index 13d3ca113299..19ff3335d17d 100644
--- a/arch/powerpc/include/asm/elf_util.h
+++ b/arch/powerpc/include/asm/elf_util.h
@@ -64,7 +64,9 @@ static inline unsigned long my_r2(const struct elf_info *elf_info)
 }
 
 int elf64_apply_relocate_add(const struct elf_info *elf_info,
-			     const char *strtab, unsigned int symindex,
-			     unsigned int relsec, const char *obj_name);
+			     const char *strtab, const Elf64_Rela *rela,
+			     unsigned int num_rela, void *syms_base,
+			     void *loc_base, Elf64_Addr addr_base,
+			     const char *obj_name);
 
 #endif /* _ASM_POWERPC_ELF_UTIL_H */
diff --git a/arch/powerpc/kernel/elf_util_64.c b/arch/powerpc/kernel/elf_util_64.c
index b53b3959a605..cde0420add9e 100644
--- a/arch/powerpc/kernel/elf_util_64.c
+++ b/arch/powerpc/kernel/elf_util_64.c
@@ -69,33 +69,56 @@ static void squash_toc_save_inst(const char *name, unsigned long addr) { }
  * elf64_apply_relocate_add - apply 64 bit RELA relocations
  * @elf_info:		Support information for the ELF binary being relocated.
  * @strtab:		String table for the associated symbol table.
- * @symindex:		Section header index for the associated symbol table.
- * @relsec:		Section header index for the relocations to apply.
+ * @rela:		Contents of the section with the relocations to apply.
+ * @num_rela:		Number of relocation entries in the section.
+ * @syms_base:		Contents of the associated symbol table.
+ * @loc_base:		Contents of the section to which relocations apply.
+ * @addr_base:		The address where the section will be loaded in memory.
  * @obj_name:		The name of the ELF binary, for information messages.
+ *
+ * Applies RELA relocations to an ELF file already at its final location
+ * in memory (in which case loc_base == addr_base), or still in a temporary
+ * buffer.
  */
 int elf64_apply_relocate_add(const struct elf_info *elf_info,
-			     const char *strtab, unsigned int symindex,
-			     unsigned int relsec, const char *obj_name)
+			     const char *strtab, const Elf64_Rela *rela,
+			     unsigned int num_rela, void *syms_base,
+			     void *loc_base, Elf64_Addr addr_base,
+			     const char *obj_name)
 {
 	unsigned int i;
-	Elf64_Shdr *sechdrs = elf_info->sechdrs;
-	Elf64_Rela *rela = (void *)sechdrs[relsec].sh_addr;
-	Elf64_Sym *sym;
 	unsigned long *location;
+	unsigned long address;
 	unsigned long value;
+	const char *name;
+	Elf64_Sym *sym;
+
+	for (i = 0; i < num_rela; i++) {
+		/*
+		 * rels[i].r_offset contains the byte offset from the beginning
+		 * of section to the storage unit affected.
+		 *
+		 * This is the location to update in the temporary buffer where
+		 * the section is currently loaded. The section will finally
+		 * be loaded to a different address later, pointed to by
+		 * addr_base.
+		 */
+		location = loc_base + rela[i].r_offset;
+
+		/* Final address of the location. */
+		address = addr_base + rela[i].r_offset;
 
+		/* This is the symbol the relocation is referring to. */
+		sym = (Elf64_Sym *) syms_base + ELF64_R_SYM(rela[i].r_info);
 
-	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rela); i++) {
-		/* This is where to make the change */
-		location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr
-			+ rela[i].r_offset;
-		/* This is the symbol it is referring to */
-		sym = (Elf64_Sym *)sechdrs[symindex].sh_addr
-			+ ELF64_R_SYM(rela[i].r_info);
+		if (sym->st_name)
+			name = strtab + sym->st_name;
+		else
+			name = "<unnamed symbol>";
 
 		pr_debug("RELOC at %p: %li-type as %s (0x%lx) + %li\n",
 		       location, (long)ELF64_R_TYPE(rela[i].r_info),
-		       strtab + sym->st_name, (unsigned long)sym->st_value,
+		       name, (unsigned long)sym->st_value,
 		       (long)rela[i].r_addend);
 
 		/* `Everything is relative'. */
@@ -187,7 +210,7 @@ int elf64_apply_relocate_add(const struct elf_info *elf_info,
 				value += local_entry_offset(sym);
 
 			/* Convert value to relative */
-			value -= (unsigned long)location;
+			value -= address;
 			if (value + 0x2000000 > 0x3ffffff || (value & 3) != 0){
 				pr_err("%s: REL24 %li out of range!\n",
 				       obj_name, (long int)value);
@@ -202,7 +225,7 @@ int elf64_apply_relocate_add(const struct elf_info *elf_info,
 
 		case R_PPC64_REL64:
 			/* 64 bits relative (used by features fixups) */
-			*location = value - (unsigned long)location;
+			*location = value - address;
 			break;
 
 		case R_PPC64_TOCSAVE:
@@ -218,7 +241,7 @@ int elf64_apply_relocate_add(const struct elf_info *elf_info,
 			 * Optimize ELFv2 large code model entry point if
 			 * the TOC is within 2GB range of current location.
 			 */
-			value = my_r2(elf_info) - (unsigned long)location;
+			value = my_r2(elf_info) - address;
 			if (value + 0x80008000 > 0xffffffff)
 				break;
 			/*
@@ -242,7 +265,7 @@ int elf64_apply_relocate_add(const struct elf_info *elf_info,
 
 		case R_PPC64_REL16_HA:
 			/* Subtract location pointer */
-			value -= (unsigned long)location;
+			value -= address;
 			value = ((value + 0x8000) >> 16);
 			*((uint16_t *) location)
 				= (*((uint16_t *) location) & ~0xffff)
@@ -251,7 +274,7 @@ int elf64_apply_relocate_add(const struct elf_info *elf_info,
 
 		case R_PPC64_REL16_LO:
 			/* Subtract location pointer */
-			value -= (unsigned long)location;
+			value -= address;
 			*((uint16_t *) location)
 				= (*((uint16_t *) location) & ~0xffff)
 				| (value & 0xffff);
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index 5f2eeab93651..a3cb0f6e83bb 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -438,16 +438,26 @@ int restore_r2(u32 *instruction, const char *obj_name)
 	return 1;
 }
 
+/*
+ * When this function is called, the module is already at its final location in
+ * memory, so Elf64_Shdr.sh_addr can be used for accessing the section
+ * contents as well as the base address for relocations.
+ */
 int apply_relocate_add(Elf64_Shdr *sechdrs,
 		       const char *strtab,
 		       unsigned int symindex,
 		       unsigned int relsec,
 		       struct module *me)
 {
+	Elf64_Shdr *rel_section = &sechdrs[relsec];
+	void *syms_base = (void *) sechdrs[symindex].sh_addr;
+	Elf64_Addr addr_base = sechdrs[rel_section->sh_info].sh_addr;
+	const Elf64_Rela *rela = (const Elf64_Rela *) rel_section->sh_addr;
+	unsigned int num_rela = rel_section->sh_size / sizeof(Elf64_Rela);
 	Elf64_Sym *sym;
 
 	pr_debug("Applying ADD relocate section %u to %u\n", relsec,
-	       sechdrs[relsec].sh_info);
+		 rel_section->sh_info);
 
 	/* First time we're called, we can fix up .TOC. */
 	if (!me->arch.toc_fixed) {
@@ -459,8 +469,9 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		me->arch.toc_fixed = true;
 	}
 
-	return elf64_apply_relocate_add(&me->arch.elf_info, strtab, symindex,
-					relsec, me->name);
+	return elf64_apply_relocate_add(&me->arch.elf_info, strtab, rela,
+					num_rela, syms_base, (void *) addr_base,
+					addr_base, me->name);
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-- 
1.9.1

^ permalink raw reply	[flat|nested] 20+ messages in thread

* [PATCH v2 6/9] powerpc: Add functions to read ELF files of any endianness.
  2016-06-14 14:59 [PATCH v2 0/9] kexec_file_load implementation for PowerPC Thiago Jung Bauermann
                   ` (4 preceding siblings ...)
  2016-06-14 14:59 ` [PATCH v2 5/9] powerpc: Generalize elf64_apply_relocate_add Thiago Jung Bauermann
@ 2016-06-14 14:59 ` Thiago Jung Bauermann
  2016-06-14 14:59 ` [PATCH v2 7/9] powerpc: Implement kexec_file_load Thiago Jung Bauermann
                   ` (3 subsequent siblings)
  9 siblings, 0 replies; 20+ messages in thread
From: Thiago Jung Bauermann @ 2016-06-14 14:59 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: kexec, linux-kernel, Thiago Jung Bauermann

A little endian kernel might need to kexec a big endian kernel (the
opposite is less likely but could happen as well), so we can't just cast
the buffer with the binary to ELF structs and use them as is done
elsewhere.

This patch adds functions which do byte-swapping as necessary when
populating the ELF structs. These functions will be used in the next
patch in the series.

Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
Cc: kexec@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
 arch/powerpc/include/asm/elf_util.h |  19 ++
 arch/powerpc/kernel/Makefile        |   2 +-
 arch/powerpc/kernel/elf_util.c      | 476 ++++++++++++++++++++++++++++++++++++
 3 files changed, 496 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/elf_util.h b/arch/powerpc/include/asm/elf_util.h
index 19ff3335d17d..9cd24bc528b1 100644
--- a/arch/powerpc/include/asm/elf_util.h
+++ b/arch/powerpc/include/asm/elf_util.h
@@ -20,6 +20,14 @@
 #include <linux/elf.h>
 
 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;
 
 	/* Index of stubs section. */
@@ -63,6 +71,17 @@ static inline unsigned long my_r2(const struct elf_info *elf_info)
 	return elf_info->sechdrs[elf_info->toc_section].sh_addr + 0x8000;
 }
 
+static inline bool elf_is_elf_file(const struct elfhdr *ehdr)
+{
+       return memcmp(ehdr->e_ident, ELFMAG, SELFMAG) == 0;
+}
+
+int elf_read_from_buffer(const char *buf, size_t len, struct elfhdr *ehdr,
+			 struct elf_info *elf_info);
+void elf_init_elf_info(const struct elfhdr *ehdr, struct elf_shdr *sechdrs,
+		       struct elf_info *elf_info);
+void elf_free_info(struct elf_info *elf_info);
+
 int elf64_apply_relocate_add(const struct elf_info *elf_info,
 			     const char *strtab, const Elf64_Rela *rela,
 			     unsigned int num_rela, void *syms_base,
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index e99f626acc85..8a53fccaa053 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -125,7 +125,7 @@ obj-y				+= iomap.o
 endif
 
 ifeq ($(CONFIG_MODULES)$(CONFIG_WORD_SIZE),y64)
-obj-y				+= elf_util_64.o
+obj-y				+= elf_util.o elf_util_64.o
 endif
 
 obj64-$(CONFIG_PPC_TRANSACTIONAL_MEM)	+= tm.o
diff --git a/arch/powerpc/kernel/elf_util.c b/arch/powerpc/kernel/elf_util.c
new file mode 100644
index 000000000000..760be6a5c393
--- /dev/null
+++ b/arch/powerpc/kernel/elf_util.c
@@ -0,0 +1,476 @@
+/*
+ * Utility functions to work with ELF files.
+ *
+ * Copyright (C) 2016, IBM Corporation
+ *
+ * Based on kexec-tools' kexec-elf.c. Heavily modified for the
+ * kernel by Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>.
+ *
+ * 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) KBUILD_MODNAME ": " fmt
+
+#include <linux/slab.h>
+#include <asm/elf_util.h>
+#include <asm-generic/module.h>
+
+#if ELF_CLASS == ELFCLASS32
+#define elf_addr_to_cpu	elf32_to_cpu
+
+#ifndef Elf_Rel
+#define Elf_Rel		Elf32_Rel
+#endif /* Elf_Rel */
+#else /* ELF_CLASS == ELFCLASS32 */
+#define elf_addr_to_cpu	elf64_to_cpu
+
+#ifndef Elf_Rel
+#define Elf_Rel		Elf64_Rel
+#endif /* Elf_Rel */
+
+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;
+}
+#endif /* ELF_CLASS == ELFCLASS32 */
+
+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 -1;
+	} 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_init_elf_info - initialize elf_info from existing information
+ * @ehdr:	Pointer to already loaded ELF header.
+ * @sechdrs:	Pointer to already loaded section headers contents.
+ * @elf_info:	Pointer to existing struct which will be populated.
+ *
+ * If the ELF binary was not loaded using elf_read_from_buffer, this function
+ * can be used to obtain a struct elf_info for use with other ELF utility
+ * functions.
+ *
+ * The caller is responsible for managing @sechdrs memory, users of this
+ * function don't need to call elf_free_info() if they free this memory
+ * separately.
+ */
+void elf_init_elf_info(const struct elfhdr *ehdr, struct elf_shdr *sechdrs,
+		       struct elf_info *elf_info)
+{
+	int i;
+	const char *shstrtab;
+
+	memset(elf_info, 0, sizeof(*elf_info));
+
+	/* Section header string table. */
+	shstrtab = (const char *) sechdrs[ehdr->e_shstrndx].sh_offset;
+
+	for (i = 0; i < ehdr->e_shnum; i++) {
+		if (sechdrs[i].sh_size == 0)
+			continue;
+
+		if (!strcmp(&shstrtab[sechdrs[i].sh_name], ".stubs"))
+			elf_info->stubs_section = i;
+		else if (!strcmp(&shstrtab[sechdrs[i].sh_name], ".toc"))
+			elf_info->toc_section = i;
+	}
+
+	elf_info->ehdr = ehdr;
+	elf_info->sechdrs = sechdrs;
+}
+
+/**
+ * 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));
+}
-- 
1.9.1

^ permalink raw reply	[flat|nested] 20+ messages in thread

* [PATCH v2 7/9] powerpc: Implement kexec_file_load.
  2016-06-14 14:59 [PATCH v2 0/9] kexec_file_load implementation for PowerPC Thiago Jung Bauermann
                   ` (5 preceding siblings ...)
  2016-06-14 14:59 ` [PATCH v2 6/9] powerpc: Add functions to read ELF files of any endianness Thiago Jung Bauermann
@ 2016-06-14 14:59 ` Thiago Jung Bauermann
  2016-06-14 14:59 ` [PATCH v2 8/9] powerpc: Add support for loading ELF kernels with kexec_file_load Thiago Jung Bauermann
                   ` (2 subsequent siblings)
  9 siblings, 0 replies; 20+ messages in thread
From: Thiago Jung Bauermann @ 2016-06-14 14:59 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: kexec, linux-kernel, Thiago Jung Bauermann, Josh Sklar

Adds the basic machinery needed by kexec_file_load.

Signed-off-by: Josh Sklar <sklar@linux.vnet.ibm.com>
Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
Cc: kexec@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
 arch/powerpc/Kconfig                   | 13 +++++++++
 arch/powerpc/include/asm/systbl.h      |  1 +
 arch/powerpc/include/asm/unistd.h      |  2 +-
 arch/powerpc/include/uapi/asm/unistd.h |  1 +
 arch/powerpc/kernel/machine_kexec_64.c | 51 ++++++++++++++++++++++++++++++++++
 5 files changed, 67 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 01f7464d9fea..3ed5770b89e4 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -457,6 +457,19 @@ config KEXEC
 	  interface is strongly in flux, so no good recommendation can be
 	  made.
 
+config KEXEC_FILE
+	bool "kexec file based system call"
+	select KEXEC_CORE
+	select BUILD_BIN2C
+	depends on PPC64
+	depends on CRYPTO=y
+	depends on CRYPTO_SHA256=y
+	help
+	  This is a new version of the kexec system call. This call is
+	  file based and takes in file descriptors as system call arguments
+	  for kernel and initramfs as opposed to a list of segments as is the
+	  case for the older kexec call.
+
 config CRASH_DUMP
 	bool "Build a kdump crash kernel"
 	depends on PPC64 || 6xx || FSL_BOOKE || (44x && !SMP)
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 2fc5d4db503c..4b369d83fe9c 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -386,3 +386,4 @@ SYSCALL(mlock2)
 SYSCALL(copy_file_range)
 COMPAT_SYS_SPU(preadv2)
 COMPAT_SYS_SPU(pwritev2)
+SYSCALL(kexec_file_load)
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index cf12c580f6b2..a01e97d3f305 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -12,7 +12,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls		382
+#define NR_syscalls		383
 
 #define __NR__exit __NR_exit
 
diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h
index e9f5f41aa55a..2f26335a3c42 100644
--- a/arch/powerpc/include/uapi/asm/unistd.h
+++ b/arch/powerpc/include/uapi/asm/unistd.h
@@ -392,5 +392,6 @@
 #define __NR_copy_file_range	379
 #define __NR_preadv2		380
 #define __NR_pwritev2		381
+#define __NR_kexec_file_load	382
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index b8c202d63ecb..4042d66939b8 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -30,6 +30,10 @@
 #include <asm/smp.h>
 #include <asm/hw_breakpoint.h>
 
+#ifdef CONFIG_KEXEC_FILE
+static struct kexec_file_ops *kexec_file_loaders[] = { };
+#endif
+
 #ifdef CONFIG_PPC_BOOK3E
 int default_machine_kexec_prepare(struct kimage *image)
 {
@@ -426,3 +430,50 @@ static int __init export_htab_values(void)
 }
 late_initcall(export_htab_values);
 #endif /* CONFIG_PPC_STD_MMU_64 */
+
+/* arch-dependent functionality required for implementing kexec_file_load() syscall */
+#ifdef CONFIG_KEXEC_FILE
+int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
+				  unsigned long buf_len)
+{
+	int i, ret = -ENOEXEC;
+	struct kexec_file_ops *fops;
+
+	/* We don't support crash kernels yet. */
+	if (image->type == KEXEC_TYPE_CRASH)
+		return -ENOTSUPP;
+
+	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 ret;
+		}
+	}
+
+	return ret;
+}
+
+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)
+{
+	if (!image->fops || !image->fops->cleanup)
+		return 0;
+
+	return image->fops->cleanup(image->image_loader_data);
+}
+#endif /* CONFIG_KEXEC_FILE */
-- 
1.9.1

^ permalink raw reply	[flat|nested] 20+ messages in thread

* [PATCH v2 8/9] powerpc: Add support for loading ELF kernels with kexec_file_load.
  2016-06-14 14:59 [PATCH v2 0/9] kexec_file_load implementation for PowerPC Thiago Jung Bauermann
                   ` (6 preceding siblings ...)
  2016-06-14 14:59 ` [PATCH v2 7/9] powerpc: Implement kexec_file_load Thiago Jung Bauermann
@ 2016-06-14 14:59 ` Thiago Jung Bauermann
  2016-06-14 14:59 ` [PATCH v2 9/9] powerpc: Add purgatory for kexec_file_load implementation Thiago Jung Bauermann
  2016-06-16  5:48 ` [PATCH v2 0/9] kexec_file_load implementation for PowerPC Michael Ellerman
  9 siblings, 0 replies; 20+ messages in thread
From: Thiago Jung Bauermann @ 2016-06-14 14:59 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: kexec, linux-kernel, Thiago Jung Bauermann

This uses all the infrastructure built up by the previous patches
in the series to load an ELF vmlinux file and an initrd. It uses the
flattened device tree at initial_boot_params as a base and adjusts memory
reservations and its /chosen node for the next kernel.

elf64_apply_relocate_add was extended to support relative symbols. This
is necessary because before relocation, the module loading mechanism
adjusts Elf64_Sym.st_value to point to the absolute memory address
while the kexec purgatory relocation code does that during relocation.

The patch also adds relocation types used by the purgatory.

Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
Cc: kexec@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
 arch/powerpc/include/asm/elf_util.h     |   1 +
 arch/powerpc/include/asm/kexec_elf_64.h |  10 +
 arch/powerpc/kernel/Makefile            |   5 +-
 arch/powerpc/kernel/elf_util_64.c       |  82 ++++-
 arch/powerpc/kernel/kexec_elf_64.c      | 564 ++++++++++++++++++++++++++++++++
 arch/powerpc/kernel/machine_kexec_64.c  | 102 +++++-
 arch/powerpc/kernel/module_64.c         |   5 +-
 7 files changed, 765 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/include/asm/elf_util.h b/arch/powerpc/include/asm/elf_util.h
index 9cd24bc528b1..41a172077f9e 100644
--- a/arch/powerpc/include/asm/elf_util.h
+++ b/arch/powerpc/include/asm/elf_util.h
@@ -86,6 +86,7 @@ int elf64_apply_relocate_add(const struct elf_info *elf_info,
 			     const char *strtab, const Elf64_Rela *rela,
 			     unsigned int num_rela, void *syms_base,
 			     void *loc_base, Elf64_Addr addr_base,
+			     bool relative_symbols, bool check_symbols,
 			     const char *obj_name);
 
 #endif /* _ASM_POWERPC_ELF_UTIL_H */
diff --git a/arch/powerpc/include/asm/kexec_elf_64.h b/arch/powerpc/include/asm/kexec_elf_64.h
new file mode 100644
index 000000000000..30da6bc0ccf8
--- /dev/null
+++ b/arch/powerpc/include/asm/kexec_elf_64.h
@@ -0,0 +1,10 @@
+#ifndef __POWERPC_KEXEC_ELF_64_H__
+#define __POWERPC_KEXEC_ELF_64_H__
+
+#ifdef CONFIG_KEXEC_FILE
+
+extern struct kexec_file_ops kexec_elf64_ops;
+
+#endif /* CONFIG_KEXEC_FILE */
+
+#endif /* __POWERPC_KEXEC_ELF_64_H__ */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 8a53fccaa053..b89a2ae1b2a0 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -110,6 +110,7 @@ obj-$(CONFIG_PCI)		+= pci_$(CONFIG_WORD_SIZE).o $(pci64-y) \
 obj-$(CONFIG_PCI_MSI)		+= msi.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o crash.o \
 				   machine_kexec_$(CONFIG_WORD_SIZE).o
+obj-$(CONFIG_KEXEC_FILE)	+= kexec_elf_$(CONFIG_WORD_SIZE).o
 obj-$(CONFIG_AUDIT)		+= audit.o
 obj64-$(CONFIG_AUDIT)		+= compat_audit.o
 
@@ -124,9 +125,11 @@ ifneq ($(CONFIG_PPC_INDIRECT_PIO),y)
 obj-y				+= iomap.o
 endif
 
-ifeq ($(CONFIG_MODULES)$(CONFIG_WORD_SIZE),y64)
+ifneq ($(CONFIG_MODULES)$(CONFIG_KEXEC_FILE),)
+ifeq ($(CONFIG_WORD_SIZE),64)
 obj-y				+= elf_util.o elf_util_64.o
 endif
+endif
 
 obj64-$(CONFIG_PPC_TRANSACTIONAL_MEM)	+= tm.o
 
diff --git a/arch/powerpc/kernel/elf_util_64.c b/arch/powerpc/kernel/elf_util_64.c
index cde0420add9e..4ad85086b31b 100644
--- a/arch/powerpc/kernel/elf_util_64.c
+++ b/arch/powerpc/kernel/elf_util_64.c
@@ -74,6 +74,8 @@ static void squash_toc_save_inst(const char *name, unsigned long addr) { }
  * @syms_base:		Contents of the associated symbol table.
  * @loc_base:		Contents of the section to which relocations apply.
  * @addr_base:		The address where the section will be loaded in memory.
+ * @relative_symbols:	Are the symbols' st_value members relative?
+ * @check_symbols:	Fail if an unexpected symbol is found?
  * @obj_name:		The name of the ELF binary, for information messages.
  *
  * Applies RELA relocations to an ELF file already at its final location
@@ -84,11 +86,13 @@ int elf64_apply_relocate_add(const struct elf_info *elf_info,
 			     const char *strtab, const Elf64_Rela *rela,
 			     unsigned int num_rela, void *syms_base,
 			     void *loc_base, Elf64_Addr addr_base,
+			     bool relative_symbols, bool check_symbols,
 			     const char *obj_name)
 {
 	unsigned int i;
 	unsigned long *location;
 	unsigned long address;
+	unsigned long sec_base;
 	unsigned long value;
 	const char *name;
 	Elf64_Sym *sym;
@@ -121,8 +125,34 @@ int elf64_apply_relocate_add(const struct elf_info *elf_info,
 		       name, (unsigned long)sym->st_value,
 		       (long)rela[i].r_addend);
 
+		if (check_symbols) {
+			/* TOC symbols appear as undefined but should be
+			 * resolved as well, so allow them to be processed. */
+			if (sym->st_shndx == SHN_UNDEF &&
+					strcmp(name, ".TOC.") != 0) {
+				pr_err("Undefined symbol: %s\n", name);
+				return -ENOEXEC;
+			} else if (sym->st_shndx == SHN_COMMON) {
+				pr_err("Symbol '%s' in common section.\n", name);
+				return -ENOEXEC;
+			}
+		}
+
+		if (relative_symbols && sym->st_shndx != SHN_ABS) {
+			if (sym->st_shndx >= elf_info->ehdr->e_shnum) {
+				pr_err("Invalid section %d for symbol %s\n",
+				       sym->st_shndx, name);
+				return -ENOEXEC;
+			} else {
+				struct elf_shdr *sechdrs = elf_info->sechdrs;
+
+				sec_base = sechdrs[sym->st_shndx].sh_addr;
+			}
+		} else
+			sec_base = 0;
+
 		/* `Everything is relative'. */
-		value = sym->st_value + rela[i].r_addend;
+		value = sym->st_value + sec_base + rela[i].r_addend;
 
 		switch (ELF64_R_TYPE(rela[i].r_info)) {
 		case R_PPC64_ADDR32:
@@ -135,6 +165,10 @@ int elf64_apply_relocate_add(const struct elf_info *elf_info,
 			*(unsigned long *)location = value;
 			break;
 
+		case R_PPC64_REL32:
+			*(uint32_t *)location = value - (uint32_t)(uint64_t)location;
+			break;
+
 		case R_PPC64_TOC:
 			*(unsigned long *)location = my_r2(elf_info);
 			break;
@@ -186,6 +220,14 @@ int elf64_apply_relocate_add(const struct elf_info *elf_info,
 				| (value & 0xfffc);
 			break;
 
+		case R_PPC64_TOC16_HI:
+			/* Subtract TOC pointer */
+			value -= my_r2(elf_info);
+			value = value >> 16;
+			*((uint16_t *) location)
+				= (*((uint16_t *) location) & ~0xffff)
+				| (value & 0xffff);
+
 		case R_PPC64_TOC16_HA:
 			/* Subtract TOC pointer */
 			value -= my_r2(elf_info);
@@ -195,6 +237,21 @@ int elf64_apply_relocate_add(const struct elf_info *elf_info,
 				| (value & 0xffff);
 			break;
 
+		case R_PPC64_REL14:
+			/* Convert value to relative */
+			value -= address;
+			if (value + 0x8000 > 0xffff || (value & 3) != 0) {
+				pr_err("%s: REL14 %li out of range!\n", obj_name,
+				       (long int)value);
+				return -ENOEXEC;
+			}
+
+			/* Only replace bits 2 through 16 */
+			*(uint32_t *)location
+				= (*(uint32_t *)location & ~0xfffc)
+				| (value & 0xfffc);
+			break;
+
 		case R_PPC_REL24:
 			/* FIXME: Handle weak symbols here --RR */
 			if (sym->st_shndx == SHN_UNDEF) {
@@ -263,6 +320,29 @@ int elf64_apply_relocate_add(const struct elf_info *elf_info,
 			((uint32_t *)location)[1] = 0x38420000 + PPC_LO(value);
 			break;
 
+		case R_PPC64_ADDR16_LO:
+			*(uint16_t *)location = value & 0xffff;
+			break;
+
+		case R_PPC64_ADDR16_HI:
+			*(uint16_t *)location = (value >> 16) & 0xffff;
+			break;
+
+		case R_PPC64_ADDR16_HA:
+			*(uint16_t *)location = (((value + 0x8000) >> 16) &
+							0xffff);
+			break;
+
+		case R_PPC64_ADDR16_HIGHER:
+			*(uint16_t *)location = (((uint64_t)value >> 32) &
+							0xffff);
+			break;
+
+		case R_PPC64_ADDR16_HIGHEST:
+			*(uint16_t *)location = (((uint64_t)value >> 48) &
+							0xffff);
+			break;
+
 		case R_PPC64_REL16_HA:
 			/* Subtract location pointer */
 			value -= address;
diff --git a/arch/powerpc/kernel/kexec_elf_64.c b/arch/powerpc/kernel/kexec_elf_64.c
new file mode 100644
index 000000000000..4e71595300ed
--- /dev/null
+++ b/arch/powerpc/kernel/kexec_elf_64.c
@@ -0,0 +1,564 @@
+/*
+ * 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>.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#define pr_fmt(fmt)	"kexec_elf: " fmt
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/kexec.h>
+#include <linux/elf.h>
+#include <linux/kexec.h>
+#include <linux/of_fdt.h>
+#include <linux/libfdt.h>
+#include <linux/memblock.h>
+#include <asm/elf_util.h>
+
+extern size_t kexec_purgatory_size;
+
+#define PURGATORY_STACK_SIZE	(16 * 1024)
+#define SLAVE_CODE_SIZE		256
+
+/**
+ * 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;
+
+	if (ehdr->e_type != ET_EXEC) {
+		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;
+	struct elf_info elf_info;
+	int ret;
+
+	ret = build_elf_exec_info(buf, len, &ehdr, &elf_info);
+	if (ret)
+		return ret;
+
+	elf_free_info(&elf_info);
+
+	return elf_check_arch(&ehdr)? 0 : -ENOEXEC;
+}
+
+static bool find_debug_console(void *fdt, int chosen_node)
+{
+	int len;
+	int console_node;
+	const void *prop, *colon;
+
+	prop = fdt_getprop(fdt, chosen_node, "stdout-path", &len);
+	if (prop == NULL) {
+		if (len == -FDT_ERR_NOTFOUND) {
+			prop = fdt_getprop(fdt, chosen_node, "linux,stdout-path",
+					   &len);
+			if (prop == NULL) {
+				pr_debug("Unable to find [linux,]stdout-path.\n");
+				return false;
+			}
+		} else {
+			pr_debug("Error finding console: %s\n",
+				 fdt_strerror(len));
+			return false;
+		}
+	}
+
+	/*
+	 * stdout-path can have a ':' separating the path from device-specific
+	 * information, so we should only consider what's before it.
+	 */
+	colon = strchr(prop, ':');
+	if (colon != NULL)
+		len = colon - prop;
+	else
+		len -= 1;	/* Ignore the terminating NUL. */
+
+	console_node = fdt_path_offset_namelen(fdt, prop, len);
+	if (console_node < 0) {
+		pr_debug("Error finding console: %s\n",
+			 fdt_strerror(console_node));
+		return false;
+	}
+
+	if (fdt_node_check_compatible(fdt, console_node, "hvterm1") == 0)
+		return true;
+	else if (fdt_node_check_compatible(fdt, console_node,
+					   "hvterm-protocol") == 0)
+		return true;
+
+	return false;
+}
+
+static int setup_purgatory(struct kimage *image, struct elf_info *kernel_info,
+			   void *fdt, unsigned long kernel_load_addr,
+			   unsigned long fdt_load_addr, unsigned long stack_top,
+			   int debug)
+{
+	int ret, tree_node;
+	const void *prop;
+	unsigned long opal_base, opal_entry;
+	uint64_t toc;
+	unsigned int *slave_code, master_entry;
+	struct elf_info purg_info;
+
+	/* Get the slave code from the new kernel and put it in purgatory. */
+	slave_code = kmalloc(SLAVE_CODE_SIZE, GFP_KERNEL);
+	if (!slave_code)
+		return -ENOMEM;
+	ret = kexec_purgatory_get_set_symbol(image, "purgatory_start",
+					     slave_code, SLAVE_CODE_SIZE, true);
+	if (ret) {
+		kfree(slave_code);
+		return ret;
+	}
+	master_entry = slave_code[0];
+	memcpy(slave_code,
+	       kernel_info->buffer + kernel_info->proghdrs[0].p_offset,
+	       SLAVE_CODE_SIZE);
+	slave_code[0] = master_entry;
+	ret = kexec_purgatory_get_set_symbol(image, "purgatory_start",
+					     slave_code, SLAVE_CODE_SIZE,
+					     false);
+	kfree(slave_code);
+
+	ret = kexec_purgatory_get_set_symbol(image, "kernel", &kernel_load_addr,
+					     sizeof(kernel_load_addr), false);
+	if (ret)
+		return ret;
+	ret = kexec_purgatory_get_set_symbol(image, "dt_offset", &fdt_load_addr,
+					     sizeof(fdt_load_addr), false);
+	if (ret)
+		return ret;
+
+	tree_node = fdt_path_offset(fdt, "/ibm,opal");
+	if (tree_node >= 0) {
+		prop = fdt_getprop(fdt, tree_node, "opal-base-address", NULL);
+		if (!prop) {
+			pr_err("OPAL address not found in the device tree.\n");
+			return -EINVAL;
+		}
+		opal_base = fdt64_to_cpu((const fdt64_t *) prop);
+
+		prop = fdt_getprop(fdt, tree_node, "opal-entry-address", NULL);
+		if (!prop) {
+			pr_err("OPAL address not found in the device tree.\n");
+			return -EINVAL;
+		}
+		opal_entry = fdt64_to_cpu((const fdt64_t *) prop);
+
+		ret = kexec_purgatory_get_set_symbol(image, "opal_base",
+						     &opal_base,
+						     sizeof(opal_base), false);
+		if (ret)
+			return ret;
+		ret = kexec_purgatory_get_set_symbol(image, "opal_entry",
+						     &opal_entry,
+						     sizeof(opal_entry), false);
+		if (ret)
+			return ret;
+	}
+
+	ret = kexec_purgatory_get_set_symbol(image, "stack", &stack_top,
+					     sizeof(stack_top), false);
+	if (ret)
+		return ret;
+
+	elf_init_elf_info(image->purgatory_info.ehdr,
+			  image->purgatory_info.sechdrs, &purg_info);
+	toc = my_r2(&purg_info);
+	ret = kexec_purgatory_get_set_symbol(image, "my_toc", &toc, sizeof(toc),
+					     false);
+	if (ret)
+		return ret;
+	pr_debug("Purgatory TOC is at 0x%llx\n", toc);
+
+	ret = kexec_purgatory_get_set_symbol(image, "debug", &debug,
+					     sizeof(debug), false);
+	if (ret)
+		return ret;
+	if (!debug)
+		pr_debug("Disabling purgatory output.\n");
+
+	return 0;
+}
+
+/**
+ * elf_exec_load - load ELF executable image
+ * @lowest_load_addr:	On return, will be the address where the first PT_LOAD
+ *			section will be loaded in memory.
+ *
+ * Return:
+ * 0 on success, negative value on failure.
+ */
+static int elf_exec_load(struct kimage *image, struct elfhdr *ehdr,
+			 struct elf_info *elf_info,
+			 unsigned long *lowest_load_addr)
+{
+	unsigned long base = 0, lowest_addr = UINT_MAX;
+	int ret;
+	size_t i;
+
+	/* Read in the PT_LOAD segments. */
+	for(i = 0; i < ehdr->e_phnum; i++) {
+		unsigned long load_addr;
+		size_t size;
+		const struct elf_phdr *phdr;
+
+		phdr = &elf_info->proghdrs[i];
+		if (phdr->p_type != PT_LOAD)
+			continue;
+
+		size = phdr->p_filesz;
+		if (size > phdr->p_memsz)
+			size = phdr->p_memsz;
+
+		ret = kexec_add_buffer(image,
+				       (char *) elf_info->buffer + phdr->p_offset,
+				       size, phdr->p_memsz, phdr->p_align,
+				       phdr->p_paddr + base, ppc64_rma_size,
+				       false, &load_addr);
+		if (ret)
+			goto out;
+
+		if (load_addr < lowest_addr)
+			lowest_addr = load_addr;
+	}
+
+	/* Update entry point to reflect new load address. */
+	ehdr->e_entry += base;
+
+	*lowest_load_addr = lowest_addr;
+	ret = 0;
+ out:
+	return ret;
+}
+
+void *elf64_load(struct kimage *image, char *kernel_buf,
+		 unsigned long kernel_len, char *initrd,
+		 unsigned long initrd_len, char *cmdline,
+		 unsigned long cmdline_len)
+{
+	int i;
+	int ret = 0, chosen_node;
+	unsigned int fdt_size;
+	unsigned long kernel_load_addr, purgatory_load_addr;
+	unsigned long initrd_load_addr, fdt_load_addr, stack_top;
+	uint64_t oldfdt_addr;
+	void *fdt;
+	const void *prop;
+	struct elfhdr ehdr;
+	struct elf_info elf_info;
+	struct fdt_reserve_entry *rsvmap;
+
+	ret = build_elf_exec_info(kernel_buf, kernel_len, &ehdr, &elf_info);
+	if (ret)
+		goto out;
+
+	ret = elf_exec_load(image, &ehdr, &elf_info, &kernel_load_addr);
+	if (ret)
+		goto out;
+
+	pr_debug("Loaded the kernel at 0x%lx\n", kernel_load_addr);
+
+	ret = kexec_load_purgatory(image, 0, ppc64_rma_size, true,
+				   &purgatory_load_addr);
+	if (ret) {
+		pr_err("Loading purgatory failed.\n");
+		goto out;
+	}
+
+	pr_debug("Loaded purgatory at 0x%lx\n", purgatory_load_addr);
+
+	fdt_size = fdt_totalsize(initial_boot_params) * 2;
+	fdt = kmalloc(fdt_size, GFP_KERNEL);
+	if (!fdt) {
+		pr_err("Not enough memory for the device tree.\n");
+		ret = -ENOMEM;
+		goto out;
+	}
+	ret = fdt_open_into(initial_boot_params, fdt, fdt_size);
+	if (ret < 0) {
+		pr_err("Error setting up the new device tree.\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* Remove memory reservation for the current device tree. */
+	oldfdt_addr = __pa(initial_boot_params);
+	for (i = 0; i < fdt_num_mem_rsv(fdt); i++) {
+		uint64_t rsv_start, rsv_size;
+
+		ret = fdt_get_mem_rsv(fdt, i, &rsv_start, &rsv_size);
+		if (ret) {
+			pr_err("Malformed device tree.\n");
+			ret = -EINVAL;
+			goto out;
+		}
+
+		if (rsv_start == oldfdt_addr &&
+		    rsv_size == fdt_totalsize(initial_boot_params)) {
+			ret = fdt_del_mem_rsv(fdt, i);
+			if (ret) {
+				pr_err("Error deleting fdt reservation.\n");
+				ret = -EINVAL;
+				goto out;
+			}
+			pr_debug("Removed old device tree reservation.\n");
+
+			break;
+		}
+	}
+
+	chosen_node = fdt_path_offset(fdt, "/chosen");
+	if (chosen_node < 0) {
+		pr_err("Malformed device tree: /chosen not found.\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/* Did we boot using an initrd? */
+	prop = fdt_getprop(fdt, chosen_node, "linux,initrd-start", NULL);
+	if (prop) {
+		uint64_t tmp_start, tmp_end, tmp_size, tmp_sizepg;
+
+		tmp_start = fdt64_to_cpu(*((const fdt64_t *) prop));
+
+		prop = fdt_getprop(fdt, chosen_node, "linux,initrd-end", NULL);
+		if (!prop) {
+			pr_err("Malformed device tree.\n");
+			ret = -EINVAL;
+			goto out;
+		}
+		tmp_end = fdt64_to_cpu(*((const fdt64_t *) prop));
+
+		/*
+		 * kexec reserves exact initrd size, while firmware may
+		 * reserve a multiple of PAGE_SIZE, so check for both.
+		 */
+		tmp_size = tmp_end - tmp_start;
+		tmp_sizepg = round_up(tmp_size, PAGE_SIZE);
+
+		/* Remove memory reservation for the current initrd. */
+		for (i = 0; i < fdt_num_mem_rsv(fdt); i++) {
+			uint64_t rsv_start, rsv_size;
+
+			ret = fdt_get_mem_rsv(fdt, i, &rsv_start, &rsv_size);
+			if (ret) {
+				pr_err("Malformed device tree.\n");
+				ret = -EINVAL;
+				goto out;
+			}
+
+			if (rsv_start == tmp_start &&
+			    (rsv_size == tmp_size || rsv_size == tmp_sizepg)) {
+				ret = fdt_del_mem_rsv(fdt, i);
+				if (ret) {
+					pr_err("Error deleting fdt reservation.\n");
+					ret = -EINVAL;
+					goto out;
+				}
+				pr_debug("Removed old initrd reservation.\n");
+
+				/* fdt was modified, offsets may have changed. */
+				chosen_node = fdt_path_offset(fdt, "/chosen");
+				if (chosen_node < 0) {
+					pr_err("Malformed device tree.\n");
+					ret = -EINVAL;
+					goto out;
+				}
+
+				break;
+			}
+		}
+
+		/* If there's no new initrd, delete the old initrd's info. */
+		if (initrd == NULL) {
+			ret = fdt_delprop(fdt, chosen_node, "linux,initrd-start");
+			if (ret) {
+				pr_err("Error deleting linux,initrd-start.\n");
+				ret = -EINVAL;
+				goto out;
+			}
+
+			ret = fdt_delprop(fdt, chosen_node, "linux,initrd-end");
+			if (ret) {
+				pr_err("Error deleting linux,initrd-end.\n");
+				ret = -EINVAL;
+				goto out;
+			}
+		}
+	}
+
+	if (initrd != NULL) {
+		ret = kexec_add_buffer(image, initrd, initrd_len, initrd_len,
+				       PAGE_SIZE, 0, ppc64_rma_size, false,
+				       &initrd_load_addr);
+		if (ret)
+			goto out;
+
+		pr_debug("Loaded initrd at 0x%lx\n", initrd_load_addr);
+
+		ret = fdt_setprop_u64(fdt, chosen_node, "linux,initrd-start",
+				      initrd_load_addr);
+		if (ret < 0) {
+			pr_err("Error setting up the new device tree.\n");
+			ret = -EINVAL;
+			goto out;
+		}
+		/* initrd-end is the first address after the initrd image. */
+		ret = fdt_setprop_u64(fdt, chosen_node, "linux,initrd-end",
+				      initrd_load_addr + initrd_len);
+		if (ret < 0) {
+			pr_err("Error setting up the new device tree.\n");
+			ret = -EINVAL;
+			goto out;
+		}
+
+		ret = fdt_add_mem_rsv(fdt, initrd_load_addr, initrd_len);
+		if (ret) {
+			pr_err("Error reserving initrd memory: %s\n",
+			       fdt_strerror(ret));
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	if (cmdline_len) {
+		ret = fdt_setprop_string(fdt, chosen_node, "bootargs", cmdline);
+		if (ret < 0) {
+			pr_err("Error setting up the new device tree.\n");
+			ret = -EINVAL;
+			goto out;
+		}
+	} else {
+		ret = fdt_delprop(fdt, chosen_node, "bootargs");
+		if (ret && ret != -FDT_ERR_NOTFOUND) {
+			pr_err("Error deleting bootargs.\n");
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	ret = fdt_setprop(fdt, chosen_node, "linux,booted-from-kexec", NULL, 0);
+	if (ret) {
+		pr_err("Error setting up the new device tree.\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * Documentation/devicetree/booting-without-of.txt says we need to
+	 * add a reservation entry for the device tree block, but
+	 * early_init_fdt_reserve_self reserves the memory even if there's no
+	 * such entry. We'll add a reservation entry anyway, to be safe and
+	 * compliant.
+	 *
+	 * Use dummy values, we will correct them in a moment.
+	 */
+	ret = fdt_add_mem_rsv(fdt, 1, 1);
+	if (ret) {
+		pr_err("Error reserving device tree memory: %s\n",
+		       fdt_strerror(ret));
+		ret = -EINVAL;
+		goto out;
+	}
+	fdt_pack(fdt);
+
+	ret = kexec_add_buffer(image, fdt, fdt_size, fdt_size, PAGE_SIZE, 0,
+			       ppc64_rma_size, true, &fdt_load_addr);
+	if (ret)
+		goto out;
+
+	/*
+	 * Fix fdt reservation, now that we now where it will be loaded
+	 * and how big it is.
+	 */
+	rsvmap = fdt + fdt_off_mem_rsvmap(fdt);
+	i = fdt_num_mem_rsv(fdt) - 1;
+	rsvmap[i].address = cpu_to_fdt64(fdt_load_addr);
+	rsvmap[i].size = cpu_to_fdt64(fdt_totalsize(fdt));
+
+	pr_debug("Loaded device tree at 0x%lx\n", fdt_load_addr);
+
+	ret = kexec_locate_mem_hole(image, PURGATORY_STACK_SIZE, PAGE_SIZE, 0,
+				    ppc64_rma_size, true, &stack_top);
+	if (ret) {
+		pr_err("Couldn't find free memory for the purgatory stack.\n");
+		ret = -ENOMEM;
+		goto out;
+	}
+	stack_top = stack_top + PURGATORY_STACK_SIZE - 1;
+	pr_debug("Purgatory stack is at 0x%lx\n", stack_top);
+
+	ret = setup_purgatory(image, &elf_info, fdt, kernel_load_addr,
+			      fdt_load_addr, stack_top,
+			      find_debug_console(fdt, chosen_node));
+	if (ret)
+		pr_err("Error setting up the purgatory.\n");
+
+out:
+	elf_free_info(&elf_info);
+
+	/* Make kimage_file_post_load_cleanup free the fdt buffer for us. */
+	return ret? ERR_PTR(ret) : fdt;
+}
+
+struct kexec_file_ops kexec_elf64_ops = {
+	.probe = elf64_probe,
+	.load = elf64_load,
+};
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index 4042d66939b8..43e8185ab6f7 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -18,6 +18,7 @@
 #include <linux/kernel.h>
 #include <linux/cpu.h>
 #include <linux/hardirq.h>
+#include <linux/memblock.h>
 
 #include <asm/page.h>
 #include <asm/current.h>
@@ -29,9 +30,12 @@
 #include <asm/prom.h>
 #include <asm/smp.h>
 #include <asm/hw_breakpoint.h>
+#include <asm/kexec_elf_64.h>
 
 #ifdef CONFIG_KEXEC_FILE
-static struct kexec_file_ops *kexec_file_loaders[] = { };
+static struct kexec_file_ops *kexec_file_loaders[] = {
+	&kexec_elf64_ops,
+};
 #endif
 
 #ifdef CONFIG_PPC_BOOK3E
@@ -476,4 +480,100 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image)
 
 	return image->fops->cleanup(image->image_loader_data);
 }
+
+/**
+ * arch_kexec_walk_mem - call func(data) for each unreserved memory block
+ * @image_type:	kimage.type
+ * @start:	Minimum address.
+ * @end:	Maximum address.
+ * @top_down:	Start from the highest address?
+ * @data:	Argument to pass to @func.
+ * @func:	Function to call for each memory block.
+ *
+ * This function is used by kexec_add_buffer and kexec_locate_mem_hole
+ * to find unreserved memory to load kexec segments into.
+ *
+ * Return: The memory walk will stop when func returns a non-zero value
+ * and that value will be returned. If all free regions are visited without
+ * func returning non-zero, then zero will be returned.
+ */
+int arch_kexec_walk_mem(unsigned int image_type, unsigned long start,
+			unsigned long end, bool top_down, void *data,
+			int (*func)(u64, u64, void *))
+{
+	int ret = 0;
+	u64 i;
+	phys_addr_t mstart, mend;
+
+	if (top_down) {
+		for_each_free_mem_range_reverse(i, NUMA_NO_NODE, 0,
+						&mstart, &mend, NULL) {
+			if (end < mstart)
+				continue;
+			else if (start > mend)
+				break;
+
+			ret = func(mstart, mend, data);
+			if (ret)
+				break;
+		}
+	} else {
+		for_each_free_mem_range(i, NUMA_NO_NODE, 0, &mstart, &mend,
+					NULL) {
+			if (end < mstart)
+				break;
+			else if (start > mend)
+				continue;
+
+			ret = func(mstart, mend, data);
+			if (ret)
+				break;
+		}
+	}
+
+	return ret;
+}
+
+/**
+ * arch_kexec_apply_relocations_add - apply purgatory relocations
+ * @ehdr:	Pointer to ELF headers.
+ * @sechdrs:	Pointer to section headers.
+ * @relsec:	Section index of SHT_RELA section.
+ *
+ * Elf64_Shdr.sh_offset has been modified to keep the pointer to the section
+ * contents, while Elf64_Shdr.sh_addr points to the final adress of the
+ * section in memory.
+ */
+int arch_kexec_apply_relocations_add(const Elf64_Ehdr *ehdr,
+				     Elf64_Shdr *sechdrs, unsigned int relsec)
+{
+	/* Section containing the relocation entries. */
+	Elf64_Shdr *rel_section = &sechdrs[relsec];
+	const Elf64_Rela *rela = (const Elf64_Rela *) rel_section->sh_offset;
+	unsigned int num_rela = rel_section->sh_size / sizeof(Elf64_Rela);
+	/* Section to which relocations apply. */
+	Elf64_Shdr *target_section = &sechdrs[rel_section->sh_info];
+	/* Associated symbol table. */
+	Elf64_Shdr *symtabsec = &sechdrs[rel_section->sh_link];
+	void *syms_base = (void *) symtabsec->sh_offset;
+	void *loc_base = (void *) target_section->sh_offset;
+	Elf64_Addr addr_base = target_section->sh_addr;
+	struct elf_info elf_info;
+	const char *strtab;
+
+	if (symtabsec->sh_link >= ehdr->e_shnum) {
+		/* Invalid strtab section number */
+		pr_err("Invalid string table section index %d\n",
+		       symtabsec->sh_link);
+		return -ENOEXEC;
+	}
+	/* String table for the associated symbol table. */
+	strtab = (const char *) sechdrs[symtabsec->sh_link].sh_offset;
+
+	elf_init_elf_info(ehdr, sechdrs, &elf_info);
+
+	return elf64_apply_relocate_add(&elf_info, strtab, rela, num_rela,
+					syms_base, loc_base, addr_base,
+					true, true, "kexec purgatory");
+}
 #endif /* CONFIG_KEXEC_FILE */
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index a3cb0f6e83bb..15b822867f8d 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -442,6 +442,9 @@ int restore_r2(u32 *instruction, const char *obj_name)
  * When this function is called, the module is already at its final location in
  * memory, so Elf64_Shdr.sh_addr can be used for accessing the section
  * contents as well as the base address for relocations.
+ *
+ * Also, simplify_symbols already changed all symbols' st_value members
+ * to absolute addresses.
  */
 int apply_relocate_add(Elf64_Shdr *sechdrs,
 		       const char *strtab,
@@ -471,7 +474,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 
 	return elf64_apply_relocate_add(&me->arch.elf_info, strtab, rela,
 					num_rela, syms_base, (void *) addr_base,
-					addr_base, me->name);
+					addr_base, false, false, me->name);
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-- 
1.9.1

^ permalink raw reply	[flat|nested] 20+ messages in thread

* [PATCH v2 9/9] powerpc: Add purgatory for kexec_file_load implementation.
  2016-06-14 14:59 [PATCH v2 0/9] kexec_file_load implementation for PowerPC Thiago Jung Bauermann
                   ` (7 preceding siblings ...)
  2016-06-14 14:59 ` [PATCH v2 8/9] powerpc: Add support for loading ELF kernels with kexec_file_load Thiago Jung Bauermann
@ 2016-06-14 14:59 ` Thiago Jung Bauermann
  2016-06-16  5:48 ` [PATCH v2 0/9] kexec_file_load implementation for PowerPC Michael Ellerman
  9 siblings, 0 replies; 20+ messages in thread
From: Thiago Jung Bauermann @ 2016-06-14 14:59 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: kexec, linux-kernel, Thiago Jung Bauermann

This purgatory implementation comes from kexec-tools, almost unchanged.

The only changes were that the sha256_regions global variable was
renamed to sha_regions to match what kexec_file_load expects, and to
use the sha256.c file from x86's purgatory to avoid adding yet another
SHA-256 implementation.

Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
Cc: kexec@lists.infradead.org
Cc: linux-kernel@vger.kernel.org
---
 arch/powerpc/Makefile                     |   4 +
 arch/powerpc/purgatory/.gitignore         |   2 +
 arch/powerpc/purgatory/Makefile           |  36 +++++++
 arch/powerpc/purgatory/console-ppc64.c    |  43 ++++++++
 arch/powerpc/purgatory/crashdump-ppc64.h  |  42 ++++++++
 arch/powerpc/purgatory/crashdump_backup.c |  40 +++++++
 arch/powerpc/purgatory/crtsavres.S        |   5 +
 arch/powerpc/purgatory/hvCall.S           |  27 +++++
 arch/powerpc/purgatory/hvCall.h           |   8 ++
 arch/powerpc/purgatory/kexec-sha256.h     |  11 ++
 arch/powerpc/purgatory/ppc64_asm.h        |  18 ++++
 arch/powerpc/purgatory/printf.c           | 171 ++++++++++++++++++++++++++++++
 arch/powerpc/purgatory/purgatory-ppc64.c  |  46 ++++++++
 arch/powerpc/purgatory/purgatory-ppc64.h  |   6 ++
 arch/powerpc/purgatory/purgatory.c        |  66 ++++++++++++
 arch/powerpc/purgatory/purgatory.h        |  11 ++
 arch/powerpc/purgatory/sha256.c           |   6 ++
 arch/powerpc/purgatory/sha256.h           |   1 +
 arch/powerpc/purgatory/string.S           |   1 +
 arch/powerpc/purgatory/v2wrap.S           | 139 ++++++++++++++++++++++++
 20 files changed, 683 insertions(+)

diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 709a22a3e824..293322855cce 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -249,6 +249,7 @@ core-y				+= arch/powerpc/kernel/ \
 core-$(CONFIG_XMON)		+= arch/powerpc/xmon/
 core-$(CONFIG_KVM) 		+= arch/powerpc/kvm/
 core-$(CONFIG_PERF_EVENTS)	+= arch/powerpc/perf/
+core-$(CONFIG_KEXEC_FILE)	+= arch/powerpc/purgatory/
 
 drivers-$(CONFIG_OPROFILE)	+= arch/powerpc/oprofile/
 
@@ -370,6 +371,9 @@ archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
 
 archprepare: checkbin
+ifeq ($(CONFIG_KEXEC_FILE),y)
+	$(Q)$(MAKE) $(build)=arch/powerpc/purgatory arch/powerpc/purgatory/kexec-purgatory.c
+endif
 
 # Use the file '.tmp_gas_check' for binutils tests, as gas won't output
 # to stdout and these checks are run even on install targets.
diff --git a/arch/powerpc/purgatory/.gitignore b/arch/powerpc/purgatory/.gitignore
new file mode 100644
index 000000000000..e9e66f178a6d
--- /dev/null
+++ b/arch/powerpc/purgatory/.gitignore
@@ -0,0 +1,2 @@
+kexec-purgatory.c
+purgatory.ro
diff --git a/arch/powerpc/purgatory/Makefile b/arch/powerpc/purgatory/Makefile
new file mode 100644
index 000000000000..63daf95e5703
--- /dev/null
+++ b/arch/powerpc/purgatory/Makefile
@@ -0,0 +1,36 @@
+purgatory-y := purgatory.o printf.o string.o v2wrap.o hvCall.o \
+		purgatory-ppc64.o console-ppc64.o crashdump_backup.o \
+		crtsavres.o sha256.o
+
+targets += $(purgatory-y)
+PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
+
+LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostartfiles \
+			-nostdlib -nodefaultlibs
+targets += purgatory.ro
+
+# Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
+# in turn leaves some undefined symbols like __fentry__ in purgatory and not
+# sure how to relocate those. Like kexec-tools, use custom flags.
+
+KBUILD_CFLAGS := -Wall -Wstrict-prototypes -fno-strict-aliasing \
+		-fno-zero-initialized-in-bss -fno-builtin -ffreestanding \
+		-fno-PIC -fno-PIE -fno-stack-protector  -fno-exceptions \
+		-msoft-float -MD -Os
+KBUILD_CFLAGS += -m$(CONFIG_WORD_SIZE)
+
+$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
+		$(call if_changed,ld)
+
+targets += kexec-purgatory.c
+
+CMD_BIN2C = $(objtree)/scripts/basic/bin2c
+quiet_cmd_bin2c = BIN2C   $@
+      cmd_bin2c = $(CMD_BIN2C) kexec_purgatory < $< > $@
+
+$(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE
+	$(call if_changed,bin2c)
+	@:
+
+
+obj-$(CONFIG_KEXEC_FILE)	+= kexec-purgatory.o
diff --git a/arch/powerpc/purgatory/console-ppc64.c b/arch/powerpc/purgatory/console-ppc64.c
new file mode 100644
index 000000000000..a52e043b4813
--- /dev/null
+++ b/arch/powerpc/purgatory/console-ppc64.c
@@ -0,0 +1,43 @@
+/*
+ * kexec: Linux boots Linux
+ *
+ * Created by: Mohan Kumar M (mohan@in.ibm.com)
+ *
+ * Copyright (C) IBM Corporation, 2005. All rights reserved
+ *
+ * Code taken from kexec-tools.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include "hvCall.h"
+#include <asm/byteorder.h>
+
+extern int debug;
+
+void putchar(int c)
+{
+	char buff[8];
+	unsigned long *lbuf = (unsigned long *)buff;
+
+	if (!debug) /* running on non pseries */
+		return;
+
+	if (c == '\n')
+		putchar('\r');
+
+	buff[0] = c;
+	plpar_hcall_norets(H_PUT_TERM_CHAR, 0, 1, __cpu_to_be64(*lbuf), 0);
+	return;
+}
diff --git a/arch/powerpc/purgatory/crashdump-ppc64.h b/arch/powerpc/purgatory/crashdump-ppc64.h
new file mode 100644
index 000000000000..90064b49ebfe
--- /dev/null
+++ b/arch/powerpc/purgatory/crashdump-ppc64.h
@@ -0,0 +1,42 @@
+#ifndef CRASHDUMP_PPC64_H
+#define CRASHDUMP_PPC64_H
+
+#include <linux/types.h>
+
+struct kexec_info;
+int load_crashdump_segments(struct kexec_info *info, char *mod_cmdline,
+				uint64_t max_addr, unsigned long min_base);
+void add_usable_mem_rgns(unsigned long long base, unsigned long long size);
+
+#define PAGE_OFFSET     0xC000000000000000ULL
+#define KERNELBASE      PAGE_OFFSET
+#define VMALLOCBASE     0xD000000000000000ULL
+
+#define __pa(x)         ((unsigned long)(x)-PAGE_OFFSET)
+#define MAXMEM          (-KERNELBASE-VMALLOCBASE)
+
+#define COMMAND_LINE_SIZE       512 /* from kernel */
+/* Backup Region, First 64K of System RAM. */
+#define BACKUP_SRC_START    0x0000
+#define BACKUP_SRC_END      0xffff
+#define BACKUP_SRC_SIZE     (BACKUP_SRC_END - BACKUP_SRC_START + 1)
+
+#define KDUMP_BACKUP_LIMIT	BACKUP_SRC_SIZE
+
+#define KERNEL_RUN_AT_ZERO_MAGIC 0x72756e30	/* "run0" */
+
+extern uint64_t crash_base;
+extern uint64_t crash_size;
+extern uint64_t memory_limit;
+extern unsigned int rtas_base;
+extern unsigned int rtas_size;
+extern uint64_t opal_base;
+extern uint64_t opal_size;
+
+uint64_t lmb_size;
+unsigned int num_of_lmbs;
+
+#define DRCONF_ADDR	0
+#define DRCONF_FLAGS	20
+
+#endif /* CRASHDUMP_PPC64_H */
diff --git a/arch/powerpc/purgatory/crashdump_backup.c b/arch/powerpc/purgatory/crashdump_backup.c
new file mode 100644
index 000000000000..e8491617527a
--- /dev/null
+++ b/arch/powerpc/purgatory/crashdump_backup.c
@@ -0,0 +1,40 @@
+/*
+ * kexec: Linux boots Linux
+ *
+ * Created by: Mohan Kumar M (mohan@in.ibm.com)
+ *
+ * Copyright (C) IBM Corporation, 2005. All rights reserved
+ *
+ * Code taken from kexec-tools.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include "../boot/string.h"
+#include "crashdump-ppc64.h"
+
+extern unsigned long backup_start;
+
+/* Backup first 32KB of memory to backup region reserved by kexec */
+void crashdump_backup_memory(void)
+{
+	void *dest, *src;
+
+	src = (void *)BACKUP_SRC_START;
+
+	if (backup_start) {
+		dest = (void *)(backup_start);
+		memcpy(dest, src, BACKUP_SRC_SIZE);
+	}
+}
diff --git a/arch/powerpc/purgatory/crtsavres.S b/arch/powerpc/purgatory/crtsavres.S
new file mode 100644
index 000000000000..5d17e1c0d575
--- /dev/null
+++ b/arch/powerpc/purgatory/crtsavres.S
@@ -0,0 +1,5 @@
+#ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
+#define CONFIG_CC_OPTIMIZE_FOR_SIZE 1
+#endif
+
+#include "../lib/crtsavres.S"
diff --git a/arch/powerpc/purgatory/hvCall.S b/arch/powerpc/purgatory/hvCall.S
new file mode 100644
index 000000000000..a96c4898f1d8
--- /dev/null
+++ b/arch/powerpc/purgatory/hvCall.S
@@ -0,0 +1,27 @@
+/*
+ * This file contains the generic function to perform a call to the
+ * pSeries LPAR hypervisor.
+ *
+ * Taken from linux/arch/powerpc/platforms/pseries/hvCall.S
+ *
+ * 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; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include "ppc64_asm.h"
+
+#define HVSC	.long 0x44000022
+.text
+	.machine ppc64
+.globl DOTSYM(plpar_hcall_norets)
+DOTSYM(plpar_hcall_norets):
+	or	6,6,6			# medium low priority
+        mfcr	0
+        stw	0,8(1)
+
+        HVSC 				/* invoke the hypervisor */
+
+        lwz	0,8(1)
+        mtcrf	0xff,0
+        blr                             /* return r3 = status */
diff --git a/arch/powerpc/purgatory/hvCall.h b/arch/powerpc/purgatory/hvCall.h
new file mode 100644
index 000000000000..187e24d8b964
--- /dev/null
+++ b/arch/powerpc/purgatory/hvCall.h
@@ -0,0 +1,8 @@
+#ifndef HVCALL_H
+#define HVCALL_H
+
+#define H_PUT_TERM_CHAR	0x58
+
+long plpar_hcall_norets(unsigned long opcode, ...);
+
+#endif
diff --git a/arch/powerpc/purgatory/kexec-sha256.h b/arch/powerpc/purgatory/kexec-sha256.h
new file mode 100644
index 000000000000..4418ed02c052
--- /dev/null
+++ b/arch/powerpc/purgatory/kexec-sha256.h
@@ -0,0 +1,11 @@
+#ifndef KEXEC_SHA256_H
+#define KEXEC_SHA256_H
+
+struct kexec_sha_region {
+	unsigned long start;
+	unsigned long len;
+};
+
+#define SHA256_REGIONS 16
+
+#endif /* KEXEC_SHA256_H */
diff --git a/arch/powerpc/purgatory/ppc64_asm.h b/arch/powerpc/purgatory/ppc64_asm.h
new file mode 100644
index 000000000000..3410cf66ae35
--- /dev/null
+++ b/arch/powerpc/purgatory/ppc64_asm.h
@@ -0,0 +1,18 @@
+/*
+ * ppc64_asm.h - common defines for PPC64 assembly parts
+ *
+ * Code taken from kexec-tools.
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ */
+
+/*
+ * ABIv1 requires dot symbol while ABIv2 does not.
+ */
+#if defined(_CALL_ELF) && _CALL_ELF == 2
+#define DOTSYM(a)	a
+#else
+#define GLUE(a,b)	a##b
+#define DOTSYM(a)	GLUE(.,a)
+#endif
diff --git a/arch/powerpc/purgatory/printf.c b/arch/powerpc/purgatory/printf.c
new file mode 100644
index 000000000000..73c85f251ae6
--- /dev/null
+++ b/arch/powerpc/purgatory/printf.c
@@ -0,0 +1,171 @@
+/*
+ * Code taken from kexec-tools.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include <stdarg.h>
+#include "purgatory.h"
+#include "../boot/string.h"
+
+#define CHAR_BIT 8
+
+/*
+ * Output
+ * =============================================================================
+ */
+
+#define LONG_LONG_SHIFT  ((int)((sizeof(unsigned long long)*CHAR_BIT) - 4))
+#define LONG_SHIFT  ((int)((sizeof(unsigned long)*CHAR_BIT) - 4))
+#define INT_SHIFT   ((int)((sizeof(unsigned int)*CHAR_BIT) - 4))
+#define SHRT_SHIFT  ((int)((sizeof(unsigned short)*CHAR_BIT) - 4))
+#define CHAR_SHIFT  ((int)((sizeof(unsigned char)*CHAR_BIT) - 4))
+
+/**************************************************************************
+PRINTF and friends
+
+	Formats:
+		%x	- 4 bytes int (8 hex digits, lower case)
+		%X	- 4 bytes int (8 hex digits, upper case)
+		%lx     - 8 bytes long (16 hex digits, lower case)
+		%lX     - 8 bytes long (16 hex digits, upper case)
+		%hx	- 2 bytes int (4 hex digits, lower case)
+		%hX	- 2 bytes int (4 hex digits, upper case)
+		%hhx	- 1 byte int (2 hex digits, lower case)
+		%hhX	- 1 byte int (2 hex digits, upper case)
+			- optional # prefixes 0x or 0X
+		%d	- decimal int
+		%c	- char
+		%s	- string
+	Note: width specification not supported
+**************************************************************************/
+void vsprintf(char *buffer, const char *fmt, va_list args)
+{
+	char *p;
+	for ( ; *fmt != '\0'; ++fmt) {
+		if (*fmt != '%') {
+			if (buffer)
+				*buffer++ = *fmt;
+			else
+				putchar(*fmt);
+			continue;
+		}
+		if (*++fmt == 's') {
+			for(p = va_arg(args, char *); *p != '\0'; p++)
+				if (buffer)
+					*buffer++ = *p;
+				else
+					putchar(*p);
+		}
+		else {	/* Length of item is bounded */
+			char tmp[40], *q = tmp;
+			int shift = INT_SHIFT;
+			if (*fmt == 'L') {
+				shift = LONG_LONG_SHIFT;
+				fmt++;
+			}
+			else if (*fmt == 'l') {
+				shift = LONG_SHIFT;
+				fmt++;
+			}
+			else if (*fmt == 'h') {
+				shift = SHRT_SHIFT;
+				fmt++;
+				if (*fmt == 'h') {
+					shift = CHAR_SHIFT;
+					fmt++;
+				}
+			}
+
+			/*
+			 * Before each format q points to tmp buffer
+			 * After each format q points past end of item
+			 */
+			if ((*fmt | 0x20) == 'x') {
+				/* With x86 gcc, sizeof(long) == sizeof(int) */
+				unsigned long long h;
+				int ncase;
+				if (shift > LONG_SHIFT) {
+					h = va_arg(args, unsigned long long);
+				}
+				else if (shift > INT_SHIFT) {
+					h = va_arg(args, unsigned long);
+				} else {
+					h = va_arg(args, unsigned int);
+				}
+				ncase = (*fmt & 0x20);
+				for ( ; shift >= 0; shift -= 4)
+					*q++ = "0123456789ABCDEF"[(h >> shift) & 0xF] | ncase;
+			}
+			else if (*fmt == 'd') {
+				char *r;
+				long i;
+				if (shift > LONG_SHIFT) {
+					i = va_arg(args, long long);
+				}
+				else if (shift > INT_SHIFT) {
+					i = va_arg(args, long);
+				} else {
+					i = va_arg(args, int);
+				}
+				if (i < 0) {
+					*q++ = '-';
+					i = -i;
+				}
+				p = q;		/* save beginning of digits */
+				do {
+					*q++ = '0' + (i % 10);
+					i /= 10;
+				} while (i);
+				/* reverse digits, stop in middle */
+				r = q;		/* don't alter q */
+				while (--r > p) {
+					i = *r;
+					*r = *p;
+					*p++ = i;
+				}
+			}
+			else if (*fmt == 'c')
+				*q++ = va_arg(args, int);
+			else
+				*q++ = *fmt;
+			/* now output the saved string */
+			for (p = tmp; p < q; ++p)
+				if (buffer)
+					*buffer++ = *p;
+				else
+					putchar(*p);
+		}
+	}
+	if (buffer)
+		*buffer = '\0';
+}
+
+void sprintf(char *buffer, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	vsprintf(buffer, fmt, args);
+	va_end(args);
+}
+
+void printf(const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	vsprintf(0, fmt, args);
+	va_end(args);
+}
diff --git a/arch/powerpc/purgatory/purgatory-ppc64.c b/arch/powerpc/purgatory/purgatory-ppc64.c
new file mode 100644
index 000000000000..01145d9ff4c1
--- /dev/null
+++ b/arch/powerpc/purgatory/purgatory-ppc64.c
@@ -0,0 +1,46 @@
+/*
+ * kexec: Linux boots Linux
+ *
+ * Created by: Mohan Kumar M (mohan@in.ibm.com)
+ *
+ * Copyright (C) IBM Corporation, 2005. All rights reserved
+ *
+ * Code taken from kexec-tools.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include "purgatory.h"
+#include "purgatory-ppc64.h"
+
+unsigned int panic_kernel = 0;
+unsigned long backup_start = 0;
+unsigned long stack = 0;
+unsigned long dt_offset = 0;
+unsigned long my_toc = 0;
+unsigned long kernel = 0;
+unsigned int debug = 0;
+unsigned long opal_base = 0;
+unsigned long opal_entry = 0;
+
+void setup_arch(void)
+{
+	return;
+}
+
+void post_verification_setup_arch(void)
+{
+	if (panic_kernel)
+		crashdump_backup_memory();
+}
diff --git a/arch/powerpc/purgatory/purgatory-ppc64.h b/arch/powerpc/purgatory/purgatory-ppc64.h
new file mode 100644
index 000000000000..52eaf4394c48
--- /dev/null
+++ b/arch/powerpc/purgatory/purgatory-ppc64.h
@@ -0,0 +1,6 @@
+#ifndef PURGATORY_PPC64_H
+#define PURGATORY_PPC64_H
+
+void crashdump_backup_memory(void);
+
+#endif /* PURGATORY_PPC64_H */
diff --git a/arch/powerpc/purgatory/purgatory.c b/arch/powerpc/purgatory/purgatory.c
new file mode 100644
index 000000000000..7d2d83466e4c
--- /dev/null
+++ b/arch/powerpc/purgatory/purgatory.c
@@ -0,0 +1,66 @@
+/*
+ * Code taken from kexec-tools.
+ *
+ * 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.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#include "purgatory.h"
+#include "sha256.h"
+#include "../boot/string.h"
+#include "kexec-sha256.h"
+
+struct kexec_sha_region sha_regions[SHA256_REGIONS] = {};
+u8 sha256_digest[SHA256_DIGEST_SIZE] = { 0 };
+
+int verify_sha256_digest(void)
+{
+	struct kexec_sha_region *ptr, *end;
+	u8 digest[SHA256_DIGEST_SIZE];
+	size_t i;
+	struct sha256_state sctx;
+
+	sha256_init(&sctx);
+	end = &sha_regions[sizeof(sha_regions)/sizeof(sha_regions[0])];
+	for (ptr = sha_regions; ptr < end; ptr++)
+		sha256_update(&sctx, (uint8_t *)(ptr->start), ptr->len);
+	sha256_final(&sctx, digest);
+
+	if (memcmp(digest, sha256_digest, sizeof(digest)) != 0) {
+		printf("sha256 digests do not match :(\n");
+		printf("       digest: ");
+		for(i = 0; i < sizeof(digest); i++)
+			printf("%hhx ", digest[i]);
+		printf("\n");
+
+		printf("sha256_digest: ");
+		for(i = 0; i < sizeof(sha256_digest); i++)
+			printf("%hhx ", sha256_digest[i]);
+
+		printf("\n");
+		return 1;
+	}
+	return 0;
+}
+
+void purgatory(void)
+{
+	printf("I'm in purgatory\n");
+	setup_arch();
+	if (verify_sha256_digest()) {
+		/* loop forever */
+		for(;;)
+			;
+	}
+	post_verification_setup_arch();
+}
diff --git a/arch/powerpc/purgatory/purgatory.h b/arch/powerpc/purgatory/purgatory.h
new file mode 100644
index 000000000000..788ce4930a30
--- /dev/null
+++ b/arch/powerpc/purgatory/purgatory.h
@@ -0,0 +1,11 @@
+#ifndef PURGATORY_H
+#define PURGATORY_H
+
+void putchar(int ch);
+void sprintf(char *buffer, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
+void printf(const char *fmt, ...) __attribute__ ((format (printf, 1, 2)));
+void setup_arch(void);
+void post_verification_setup_arch(void);
+
+#endif /* PURGATORY_H */
diff --git a/arch/powerpc/purgatory/sha256.c b/arch/powerpc/purgatory/sha256.c
new file mode 100644
index 000000000000..6abee1877d56
--- /dev/null
+++ b/arch/powerpc/purgatory/sha256.c
@@ -0,0 +1,6 @@
+#include "../boot/string.h"
+
+/* Avoid including x86's boot/string.h in sha256.c. */
+#define BOOT_STRING_H
+
+#include "../../x86/purgatory/sha256.c"
diff --git a/arch/powerpc/purgatory/sha256.h b/arch/powerpc/purgatory/sha256.h
new file mode 100644
index 000000000000..72818f3a207e
--- /dev/null
+++ b/arch/powerpc/purgatory/sha256.h
@@ -0,0 +1 @@
+#include "../../x86/purgatory/sha256.h"
diff --git a/arch/powerpc/purgatory/string.S b/arch/powerpc/purgatory/string.S
new file mode 100644
index 000000000000..3a1e23ff4017
--- /dev/null
+++ b/arch/powerpc/purgatory/string.S
@@ -0,0 +1 @@
+#include "../boot/string.S"
diff --git a/arch/powerpc/purgatory/v2wrap.S b/arch/powerpc/purgatory/v2wrap.S
new file mode 100644
index 000000000000..c7791819c0c6
--- /dev/null
+++ b/arch/powerpc/purgatory/v2wrap.S
@@ -0,0 +1,139 @@
+#
+#  kexec: Linux boots Linux
+#
+#  Copyright (C) 2004 - 2005, Milton D Miller II, IBM Corporation
+#  Copyright (C) 2006, Mohan Kumar M (mohan@in.ibm.com), IBM Corporation
+#
+# Code taken from kexec-tools.
+#
+#  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.
+#
+#  You should have received a copy of the GNU General Public License
+#  along with this program; if not, write to the Free Software
+#  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+#
+
+#include "ppc64_asm.h"
+
+# v2wrap.S
+# a wrapper to call purgatory code to backup first
+# 32kB of first kernel into the backup region
+# reserved by kexec-tools.
+# Invokes ppc64 kernel with the expected arguments
+# of kernel(device-tree, phys-offset, 0)
+
+#
+# calling convention:
+#   r3 = physical number of this cpu (all cpus)
+#   r4 = address of this chunk (master only)
+# master enters at purgatory_start (aka first byte of this chunk)
+# slaves (additional cpus), if any, enter a copy of the
+# first 0x100 bytes of this code relocated to 0x0
+#
+# in other words,
+#   a copy of the first 0x100 bytes of this code is copied to 0
+#   and the slaves are sent to address 0x60
+#   with r3 = their physical cpu number.
+
+#define LOADADDR(rn,name) \
+	lis     rn,name##@highest;      \
+	ori     rn,rn,name##@higher;    \
+	rldicr  rn,rn,32,31;            \
+	oris    rn,rn,name##@h;         \
+	ori     rn,rn,name##@l
+
+	.machine ppc64
+	.align 8
+	.globl purgatory_start
+purgatory_start:	b	master
+	.org purgatory_start + 0x5c     # ABI: possible run_at_load flag at 0x5c
+	.globl run_at_load
+run_at_load:
+	.long 0
+	.size run_at_load, . - run_at_load
+	.org purgatory_start + 0x60     # ABI: slaves start at 60 with r3=phys
+slave:	b $
+	.org purgatory_start + 0x100    # ABI: end of copied region
+	.size purgatory_start, . - purgatory_start
+
+#
+# The above 0x100 bytes at purgatory_start are replaced with the
+# code from the kernel (or next stage) by kexec/arch/ppc64/kexec-elf-ppc64.c
+#
+
+master:
+	or	1,1,1		# low priority to let other threads catchup
+	isync
+	mr      17,3            # save cpu id to r17
+	mr      15,4            # save physical address in reg15
+
+	LOADADDR(6,my_toc)
+	ld      2,0(6)          #setup toc
+
+	LOADADDR(6,stack)
+	ld      1,0(6)          #setup stack
+
+	subi    1,1,112
+	bl      DOTSYM(purgatory)
+	nop
+
+	or	3,3,3		# ok now to high priority, lets boot
+	lis	6,0x1
+	mtctr	6		# delay a bit for slaves to catch up
+83:	bdnz	83b		# before we overwrite 0-100 again
+
+	LOADADDR(16, dt_offset)
+	ld      3,0(16)         # load device-tree address
+	mr      16,3            # save dt address in reg16
+#ifdef __BIG_ENDIAN__
+	lwz     6,20(3)         # fetch version number
+#else
+	li	4,20
+	lwbrx	6,3,4		# fetch BE version number
+#endif
+	cmpwi   0,6,2           # v2 ?
+	blt     80f
+#ifdef __BIG_ENDIAN__
+	stw     17,28(3)        # save my cpu number as boot_cpu_phys
+#else
+	li	4,28
+	stwbrx	17,3,4		# Store my cpu as BE value
+#endif
+80:
+	LOADADDR(6,opal_base)	# For OPAL early debug
+	ld      8,0(6)          # load the OPAL base address in r8
+	LOADADDR(6,opal_entry)	# For OPAL early debug
+	ld      9,0(6)          # load the OPAL entry address in r9
+	LOADADDR(6,kernel)
+	ld      4,0(6)          # load the kernel address
+	LOADADDR(6,run_at_load) # the load flag
+	lwz	7,0(6)		# possibly patched by kexec-elf-ppc64
+	stw	7,0x5c(4)	# and patch it into the kernel
+	mr      3,16            # restore dt address
+
+	mfmsr	5
+	andi.	10,5,1		# test MSR_LE
+	bne	little_endian
+
+	li	5,0		# r5 will be 0 for kernel
+	mtctr	4		# prepare branch to
+	bctr			# start kernel
+
+little_endian:			# book3s-only
+	mtsrr0	4		# prepare branch to
+
+	clrrdi	5,5,1		# clear MSR_LE
+	mtsrr1	5
+
+	li	5,0		# r5 will be 0 for kernel
+
+				# skip cache flush, do we care?
+
+	rfid			# update MSR and start kernel
-- 
1.9.1

^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [PATCH v2 2/9] kexec_file: Generalize kexec_add_buffer.
  2016-06-14 14:59 ` [PATCH v2 2/9] kexec_file: Generalize kexec_add_buffer Thiago Jung Bauermann
@ 2016-06-15  7:33   ` Dave Young
  2016-06-15 16:21     ` Thiago Jung Bauermann
  0 siblings, 1 reply; 20+ messages in thread
From: Dave Young @ 2016-06-15  7:33 UTC (permalink / raw)
  To: Thiago Jung Bauermann; +Cc: linuxppc-dev, kexec, linux-kernel, Eric Biederman

Hi, Thiago

On 06/14/16 at 11:59am, Thiago Jung Bauermann wrote:
> Allow architectures to specify different memory walking functions for
> kexec_add_buffer. Intel uses iomem to track reserved memory ranges,
> but PowerPC uses the memblock subsystem.
> 
> Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
> Cc: Eric Biederman <ebiederm@xmission.com>
> Cc: Dave Young <dyoung@redhat.com>
> Cc: kexec@lists.infradead.org
> Cc: linux-kernel@vger.kernel.org
> ---
>  include/linux/kexec.h |  3 +++
>  kernel/kexec_file.c   | 44 ++++++++++++++++++++++++++++++++++++--------
>  2 files changed, 39 insertions(+), 8 deletions(-)
> 
> diff --git a/include/linux/kexec.h b/include/linux/kexec.h
> index e8acb2b43dd9..7321043aa65a 100644
> --- a/include/linux/kexec.h
> +++ b/include/linux/kexec.h
> @@ -315,6 +315,9 @@ int __weak arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr,
>  					Elf_Shdr *sechdrs, unsigned int relsec);
>  int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
>  					unsigned int relsec);
> +int __weak arch_kexec_walk_mem(unsigned int image_type, unsigned long start,
> +			       unsigned long end, bool top_down, void *data,
> +			       int (*func)(u64, u64, void *));
>  void arch_kexec_protect_crashkres(void);
>  void arch_kexec_unprotect_crashkres(void);
>  
> diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
> index b6eec7527e9f..a3ca7cfe070e 100644
> --- a/kernel/kexec_file.c
> +++ b/kernel/kexec_file.c
> @@ -428,6 +428,31 @@ static int locate_mem_hole_callback(u64 start, u64 end, void *arg)
>  	return locate_mem_hole_bottom_up(start, end, kbuf);
>  }
>  
> +/**
> + * arch_kexec_walk_mem - call func(data) on free memory regions
> + * @image_type:	kimage.type
> + * @start:	Don't visit memory regions below this address.
> + * @end:	Don't visit memory regions above this address.
> + * @top_down:	Start from the highest address?
> + * @data:	Argument to pass to @func.
> + * @func:	Function to call for each memory region.
> + *
> + * Return: The memory walk will stop when func returns a non-zero value
> + * and that value will be returned. If all free regions are visited without
> + * func returning non-zero, then zero will be returned.
> + */
> +int __weak arch_kexec_walk_mem(unsigned int image_type, unsigned long start,
> +			       unsigned long end, bool top_down, void *data,
> +			       int (*func)(u64, u64, void *))
> +{
> +	if (image_type == KEXEC_TYPE_CRASH)
> +		return walk_iomem_res_desc(crashk_res.desc,
> +					   IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
> +					   start, end, data, func);
> +	else
> +		return walk_system_ram_res(start, end, data, func);
> +}
> +
>  /*
>   * Helper function for placing a buffer in a kexec segment. This assumes
>   * that kexec_mutex is held.
> @@ -441,6 +466,7 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
>  	struct kexec_segment *ksegment;
>  	struct kexec_buf buf, *kbuf;
>  	int ret;
> +	unsigned long start, end;
>  
>  	/* Currently adding segment this way is allowed only in file mode */
>  	if (!image->file_mode)
> @@ -472,14 +498,16 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
>  	kbuf->top_down = top_down;
>  
>  	/* Walk the RAM ranges and allocate a suitable range for the buffer */
> -	if (image->type == KEXEC_TYPE_CRASH)
> -		ret = walk_iomem_res_desc(crashk_res.desc,
> -				IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
> -				crashk_res.start, crashk_res.end, kbuf,
> -				locate_mem_hole_callback);
> -	else
> -		ret = walk_system_ram_res(0, -1, kbuf,
> -					  locate_mem_hole_callback);
> +	if (image->type == KEXEC_TYPE_CRASH) {
> +		start = crashk_res.start;
> +		end = crashk_res.end;
> +	} else {
> +		start = 0;
> +		end = ULONG_MAX;
> +	}

For crashk_res, start and end is global, the non-crash values are
hard coded, thus it is not necessary to pass these two in arguments.

Moving above to arch_kexec_walk_mem will make it cleaner.

> +
> +	ret = arch_kexec_walk_mem(image->type, start, end, top_down, kbuf,
> +				   locate_mem_hole_callback);
>  	if (ret != 1) {
>  		/* A suitable memory range could not be found for buffer */
>  		return -EADDRNOTAVAIL;
> -- 
> 1.9.1
> 
> 
> _______________________________________________
> kexec mailing list
> kexec@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/kexec

Thanks
Dave

^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [PATCH v2 2/9] kexec_file: Generalize kexec_add_buffer.
  2016-06-15  7:33   ` Dave Young
@ 2016-06-15 16:21     ` Thiago Jung Bauermann
  2016-06-16  1:58       ` Dave Young
  0 siblings, 1 reply; 20+ messages in thread
From: Thiago Jung Bauermann @ 2016-06-15 16:21 UTC (permalink / raw)
  To: Dave Young; +Cc: linuxppc-dev, kexec, linux-kernel, Eric Biederman

Hello Dave,

Am Mittwoch, 15 Juni 2016, 15:33:02 schrieb Dave Young:
> > @@ -472,14 +498,16 @@ int kexec_add_buffer(struct kimage *image, char
> > *buffer, unsigned long bufsz,> 
> >  	kbuf->top_down = top_down;
> >  	
> >  	/* Walk the RAM ranges and allocate a suitable range for the buffer */
> > 
> > -	if (image->type == KEXEC_TYPE_CRASH)
> > -		ret = walk_iomem_res_desc(crashk_res.desc,
> > -				IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
> > -				crashk_res.start, crashk_res.end, kbuf,
> > -				locate_mem_hole_callback);
> > -	else
> > -		ret = walk_system_ram_res(0, -1, kbuf,
> > -					  locate_mem_hole_callback);
> > +	if (image->type == KEXEC_TYPE_CRASH) {
> > +		start = crashk_res.start;
> > +		end = crashk_res.end;
> > +	} else {
> > +		start = 0;
> > +		end = ULONG_MAX;
> > +	}
> 
> For crashk_res, start and end is global, the non-crash values are
> hard coded, thus it is not necessary to pass these two in arguments.
> 
> Moving above to arch_kexec_walk_mem will make it cleaner.

That's true. What about this version?

[]'s
Thiago Jung Bauermann
IBM Linux Technology Center


    kexec_file: Generalize kexec_add_buffer.
    
    Allow architectures to specify different memory walking functions for
    kexec_add_buffer. Intel uses iomem to track reserved memory ranges,
    but PowerPC uses the memblock subsystem.
    
    Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
    Cc: Eric Biederman <ebiederm@xmission.com>
    Cc: Dave Young <dyoung@redhat.com>
    Cc: kexec@lists.infradead.org
    Cc: linux-kernel@vger.kernel.org

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index e8acb2b43dd9..9b02f907b40a 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -315,6 +315,8 @@ int __weak arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr,
 					Elf_Shdr *sechdrs, unsigned int relsec);
 int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 					unsigned int relsec);
+int __weak arch_kexec_walk_mem(unsigned int image_type, bool top_down,
+			       void *data, int (*func)(u64, u64, void *));
 void arch_kexec_protect_crashkres(void);
 void arch_kexec_unprotect_crashkres(void);
 
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index b6eec7527e9f..2d066c458222 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -428,6 +428,29 @@ static int locate_mem_hole_callback(u64 start, u64 end, void *arg)
 	return locate_mem_hole_bottom_up(start, end, kbuf);
 }
 
+/**
+ * arch_kexec_walk_mem - call func(data) on free memory regions
+ * @image_type:	kimage.type
+ * @top_down:	Start from the highest address?
+ * @data:	Argument to pass to @func.
+ * @func:	Function to call for each memory region.
+ *
+ * Return: The memory walk will stop when func returns a non-zero value
+ * and that value will be returned. If all free regions are visited without
+ * func returning non-zero, then zero will be returned.
+ */
+int __weak arch_kexec_walk_mem(unsigned int image_type, bool top_down,
+			       void *data, int (*func)(u64, u64, void *))
+{
+	if (image_type == KEXEC_TYPE_CRASH)
+		return walk_iomem_res_desc(crashk_res.desc,
+					   IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
+					   crashk_res.start, crashk_res.end,
+					   data, func);
+	else
+		return walk_system_ram_res(0, ULONG_MAX, data, func);
+}
+
 /*
  * Helper function for placing a buffer in a kexec segment. This assumes
  * that kexec_mutex is held.
@@ -472,14 +495,8 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
 	kbuf->top_down = top_down;
 
 	/* Walk the RAM ranges and allocate a suitable range for the buffer */
-	if (image->type == KEXEC_TYPE_CRASH)
-		ret = walk_iomem_res_desc(crashk_res.desc,
-				IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
-				crashk_res.start, crashk_res.end, kbuf,
-				locate_mem_hole_callback);
-	else
-		ret = walk_system_ram_res(0, -1, kbuf,
-					  locate_mem_hole_callback);
+	ret = arch_kexec_walk_mem(image->type, top_down, kbuf,
+				   locate_mem_hole_callback);
 	if (ret != 1) {
 		/* A suitable memory range could not be found for buffer */
 		return -EADDRNOTAVAIL;

^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [PATCH v2 2/9] kexec_file: Generalize kexec_add_buffer.
  2016-06-15 16:21     ` Thiago Jung Bauermann
@ 2016-06-16  1:58       ` Dave Young
  2016-06-16 20:39         ` Thiago Jung Bauermann
  0 siblings, 1 reply; 20+ messages in thread
From: Dave Young @ 2016-06-16  1:58 UTC (permalink / raw)
  To: Thiago Jung Bauermann; +Cc: linuxppc-dev, kexec, linux-kernel, Eric Biederman

On 06/15/16 at 01:21pm, Thiago Jung Bauermann wrote:
> Hello Dave,
> 
> Am Mittwoch, 15 Juni 2016, 15:33:02 schrieb Dave Young:
> > > @@ -472,14 +498,16 @@ int kexec_add_buffer(struct kimage *image, char
> > > *buffer, unsigned long bufsz,> 
> > >  	kbuf->top_down = top_down;
> > >  	
> > >  	/* Walk the RAM ranges and allocate a suitable range for the buffer */
> > > 
> > > -	if (image->type == KEXEC_TYPE_CRASH)
> > > -		ret = walk_iomem_res_desc(crashk_res.desc,
> > > -				IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
> > > -				crashk_res.start, crashk_res.end, kbuf,
> > > -				locate_mem_hole_callback);
> > > -	else
> > > -		ret = walk_system_ram_res(0, -1, kbuf,
> > > -					  locate_mem_hole_callback);
> > > +	if (image->type == KEXEC_TYPE_CRASH) {
> > > +		start = crashk_res.start;
> > > +		end = crashk_res.end;
> > > +	} else {
> > > +		start = 0;
> > > +		end = ULONG_MAX;
> > > +	}
> > 
> > For crashk_res, start and end is global, the non-crash values are
> > hard coded, thus it is not necessary to pass these two in arguments.
> > 
> > Moving above to arch_kexec_walk_mem will make it cleaner.
> 
> That's true. What about this version?
> 
> []'s
> Thiago Jung Bauermann
> IBM Linux Technology Center
> 
> 
>     kexec_file: Generalize kexec_add_buffer.
>     
>     Allow architectures to specify different memory walking functions for
>     kexec_add_buffer. Intel uses iomem to track reserved memory ranges,
>     but PowerPC uses the memblock subsystem.
>     
>     Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
>     Cc: Eric Biederman <ebiederm@xmission.com>
>     Cc: Dave Young <dyoung@redhat.com>
>     Cc: kexec@lists.infradead.org
>     Cc: linux-kernel@vger.kernel.org
> 
> diff --git a/include/linux/kexec.h b/include/linux/kexec.h
> index e8acb2b43dd9..9b02f907b40a 100644
> --- a/include/linux/kexec.h
> +++ b/include/linux/kexec.h
> @@ -315,6 +315,8 @@ int __weak arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr,
>  					Elf_Shdr *sechdrs, unsigned int relsec);
>  int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
>  					unsigned int relsec);
> +int __weak arch_kexec_walk_mem(unsigned int image_type, bool top_down,
> +			       void *data, int (*func)(u64, u64, void *));
>  void arch_kexec_protect_crashkres(void);
>  void arch_kexec_unprotect_crashkres(void);
>  
> diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
> index b6eec7527e9f..2d066c458222 100644
> --- a/kernel/kexec_file.c
> +++ b/kernel/kexec_file.c
> @@ -428,6 +428,29 @@ static int locate_mem_hole_callback(u64 start, u64 end, void *arg)
>  	return locate_mem_hole_bottom_up(start, end, kbuf);
>  }
>  
> +/**
> + * arch_kexec_walk_mem - call func(data) on free memory regions
> + * @image_type:	kimage.type
> + * @top_down:	Start from the highest address?
> + * @data:	Argument to pass to @func.
> + * @func:	Function to call for each memory region.
> + *
> + * Return: The memory walk will stop when func returns a non-zero value
> + * and that value will be returned. If all free regions are visited without
> + * func returning non-zero, then zero will be returned.
> + */
> +int __weak arch_kexec_walk_mem(unsigned int image_type, bool top_down,
> +			       void *data, int (*func)(u64, u64, void *))
> +{

top_down is also not used?

Rethink about the argument name type should be better than image_type,
it is obvious in the comments and the code and simpler.

> +	if (image_type == KEXEC_TYPE_CRASH)
> +		return walk_iomem_res_desc(crashk_res.desc,
> +					   IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
> +					   crashk_res.start, crashk_res.end,
> +					   data, func);
> +	else
> +		return walk_system_ram_res(0, ULONG_MAX, data, func);
> +}
> +
>  /*
>   * Helper function for placing a buffer in a kexec segment. This assumes
>   * that kexec_mutex is held.
> @@ -472,14 +495,8 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
>  	kbuf->top_down = top_down;
>  
>  	/* Walk the RAM ranges and allocate a suitable range for the buffer */
> -	if (image->type == KEXEC_TYPE_CRASH)
> -		ret = walk_iomem_res_desc(crashk_res.desc,
> -				IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
> -				crashk_res.start, crashk_res.end, kbuf,
> -				locate_mem_hole_callback);
> -	else
> -		ret = walk_system_ram_res(0, -1, kbuf,
> -					  locate_mem_hole_callback);
> +	ret = arch_kexec_walk_mem(image->type, top_down, kbuf,
> +				   locate_mem_hole_callback);
>  	if (ret != 1) {
>  		/* A suitable memory range could not be found for buffer */
>  		return -EADDRNOTAVAIL;
> 

^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [PATCH v2 0/9] kexec_file_load implementation for PowerPC
  2016-06-14 14:59 [PATCH v2 0/9] kexec_file_load implementation for PowerPC Thiago Jung Bauermann
                   ` (8 preceding siblings ...)
  2016-06-14 14:59 ` [PATCH v2 9/9] powerpc: Add purgatory for kexec_file_load implementation Thiago Jung Bauermann
@ 2016-06-16  5:48 ` Michael Ellerman
  2016-06-16 19:55   ` Thiago Jung Bauermann
  9 siblings, 1 reply; 20+ messages in thread
From: Michael Ellerman @ 2016-06-16  5:48 UTC (permalink / raw)
  To: Thiago Jung Bauermann, linuxppc-dev; +Cc: kexec, linux-kernel

On Tue, 2016-06-14 at 11:59 -0300, Thiago Jung Bauermann wrote:

> Hello,
> 
> This patch series implements the kexec_file_load system call on PowerPC.

Can you tell me what this syscall does and why I would want it?

cheers

^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [PATCH v2 0/9] kexec_file_load implementation for PowerPC
  2016-06-16  5:48 ` [PATCH v2 0/9] kexec_file_load implementation for PowerPC Michael Ellerman
@ 2016-06-16 19:55   ` Thiago Jung Bauermann
  0 siblings, 0 replies; 20+ messages in thread
From: Thiago Jung Bauermann @ 2016-06-16 19:55 UTC (permalink / raw)
  To: Michael Ellerman; +Cc: linuxppc-dev, kexec, linux-kernel

Am Donnerstag, 16 Juni 2016, 15:48:30 schrieb Michael Ellerman:
> On Tue, 2016-06-14 at 11:59 -0300, Thiago Jung Bauermann wrote:
> > Hello,
> > 
> > This patch series implements the kexec_file_load system call on PowerPC.
> 
> Can you tell me what this syscall does and why I would want it?

Sorry, should have provided the motivation when I posted the patches.

This system call moves the reading of the kernel, initrd and the device tree 
from the userspace kexec tool to the kernel. This is needed if you want to 
do one or both of the following:

1. only allow loading of signed kernels.
2. "measure" (i.e., record the hashes of) the kernel, initrd, kernel command 
line and other boot inputs for the  Integrity Measurement Architecture 
subsystem.

The above are the functions kexec already has built into kexec_file_load. I 
will soon post a set of patches which will allow a third feature:

3. have IMA pass-on its event log (where integrity measurements are 
registered) accross kexec to the second kernel, so that the event history is 
preserved.

Because OpenPower uses an intermediary Linux instance as a boot loader 
(skiroot), feature 1 is needed to implement secure boot for the platform, 
while features 2 and 3 are needed to implement trusted boot.

There's an LWN article giving more context on the origins of the system 
call, if you are interested:

https://lwn.net/Articles/603116/

-- 
[]'s
Thiago Jung Bauermann
IBM Linux Technology Center

^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [PATCH v2 2/9] kexec_file: Generalize kexec_add_buffer.
  2016-06-16  1:58       ` Dave Young
@ 2016-06-16 20:39         ` Thiago Jung Bauermann
  2016-06-17  7:35           ` Dave Young
  0 siblings, 1 reply; 20+ messages in thread
From: Thiago Jung Bauermann @ 2016-06-16 20:39 UTC (permalink / raw)
  To: Dave Young; +Cc: linuxppc-dev, kexec, linux-kernel, Eric Biederman

Am Donnerstag, 16 Juni 2016, 09:58:53 schrieb Dave Young:
> On 06/15/16 at 01:21pm, Thiago Jung Bauermann wrote:
> > +/**
> > + * arch_kexec_walk_mem - call func(data) on free memory regions
> > + * @image_type:	kimage.type
> > + * @top_down:	Start from the highest address?
> > + * @data:	Argument to pass to @func.
> > + * @func:	Function to call for each memory region.
> > + *
> > + * Return: The memory walk will stop when func returns a non-zero value
> > + * and that value will be returned. If all free regions are visited
> > without + * func returning non-zero, then zero will be returned.
> > + */
> > +int __weak arch_kexec_walk_mem(unsigned int image_type, bool top_down,
> > +			       void *data, int (*func)(u64, u64, void *))
> > +{
> 
> top_down is also not used?

It's unused in the default implementation, but the powerpc implementation in patch 8 uses it:

int arch_kexec_walk_mem(unsigned int type, bool top_down, void *data,
			int (*func)(u64, u64, void *))
{
	int ret = 0;
	u64 i;
	phys_addr_t mstart, mend;

	if (top_down) {
		for_each_free_mem_range_reverse(i, NUMA_NO_NODE, 0,
						&mstart, &mend, NULL) {
			ret = func(mstart, mend, data);
			if (ret)
				break;
		}
	} else {
		for_each_free_mem_range(i, NUMA_NO_NODE, 0, &mstart, &mend,
					NULL) {
			ret = func(mstart, mend, data);
			if (ret)
				break;
		}
	}

	return ret;
}

> Rethink about the argument name type should be better than image_type,
> it is obvious in the comments and the code and simpler.

Ok, renamed in the patch below.

[]'s
Thiago Jung Bauermann
IBM Linux Technology Center


    kexec_file: Generalize kexec_add_buffer.
    
    Allow architectures to specify different memory walking functions for
    kexec_add_buffer. Intel uses iomem to track reserved memory ranges,
    but PowerPC uses the memblock subsystem.
    
    Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
    Cc: Eric Biederman <ebiederm@xmission.com>
    Cc: Dave Young <dyoung@redhat.com>
    Cc: kexec@lists.infradead.org
    Cc: linux-kernel@vger.kernel.org

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index e8acb2b43dd9..42b31f2e1d88 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -315,6 +315,8 @@ int __weak arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr,
 					Elf_Shdr *sechdrs, unsigned int relsec);
 int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 					unsigned int relsec);
+int __weak arch_kexec_walk_mem(unsigned int type, bool top_down, void *data,
+			       int (*func)(u64, u64, void *));
 void arch_kexec_protect_crashkres(void);
 void arch_kexec_unprotect_crashkres(void);
 
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index b6eec7527e9f..989647a324f2 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -428,6 +428,29 @@ static int locate_mem_hole_callback(u64 start, u64 end, void *arg)
 	return locate_mem_hole_bottom_up(start, end, kbuf);
 }
 
+/**
+ * arch_kexec_walk_mem - call func(data) on free memory regions
+ * @type:	kimage.type
+ * @top_down:	Start from the highest address?
+ * @data:	Argument to pass to @func.
+ * @func:	Function to call for each memory region.
+ *
+ * Return: The memory walk will stop when func returns a non-zero value
+ * and that value will be returned. If all free regions are visited without
+ * func returning non-zero, then zero will be returned.
+ */
+int __weak arch_kexec_walk_mem(unsigned int type, bool top_down, void *data,
+			       int (*func)(u64, u64, void *))
+{
+	if (type == KEXEC_TYPE_CRASH)
+		return walk_iomem_res_desc(crashk_res.desc,
+					   IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
+					   crashk_res.start, crashk_res.end,
+					   data, func);
+	else
+		return walk_system_ram_res(0, ULONG_MAX, data, func);
+}
+
 /*
  * Helper function for placing a buffer in a kexec segment. This assumes
  * that kexec_mutex is held.
@@ -472,14 +495,8 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
 	kbuf->top_down = top_down;
 
 	/* Walk the RAM ranges and allocate a suitable range for the buffer */
-	if (image->type == KEXEC_TYPE_CRASH)
-		ret = walk_iomem_res_desc(crashk_res.desc,
-				IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
-				crashk_res.start, crashk_res.end, kbuf,
-				locate_mem_hole_callback);
-	else
-		ret = walk_system_ram_res(0, -1, kbuf,
-					  locate_mem_hole_callback);
+	ret = arch_kexec_walk_mem(image->type, top_down, kbuf,
+				   locate_mem_hole_callback);
 	if (ret != 1) {
 		/* A suitable memory range could not be found for buffer */
 		return -EADDRNOTAVAIL;

^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [PATCH v2 2/9] kexec_file: Generalize kexec_add_buffer.
  2016-06-16 20:39         ` Thiago Jung Bauermann
@ 2016-06-17  7:35           ` Dave Young
  2016-06-17 20:51             ` Thiago Jung Bauermann
  0 siblings, 1 reply; 20+ messages in thread
From: Dave Young @ 2016-06-17  7:35 UTC (permalink / raw)
  To: Thiago Jung Bauermann; +Cc: kexec, linuxppc-dev, linux-kernel, Eric Biederman

On 06/16/16 at 05:39pm, Thiago Jung Bauermann wrote:
> Am Donnerstag, 16 Juni 2016, 09:58:53 schrieb Dave Young:
> > On 06/15/16 at 01:21pm, Thiago Jung Bauermann wrote:
> > > +/**
> > > + * arch_kexec_walk_mem - call func(data) on free memory regions
> > > + * @image_type:	kimage.type
> > > + * @top_down:	Start from the highest address?
> > > + * @data:	Argument to pass to @func.
> > > + * @func:	Function to call for each memory region.
> > > + *
> > > + * Return: The memory walk will stop when func returns a non-zero value
> > > + * and that value will be returned. If all free regions are visited
> > > without + * func returning non-zero, then zero will be returned.
> > > + */
> > > +int __weak arch_kexec_walk_mem(unsigned int image_type, bool top_down,
> > > +			       void *data, int (*func)(u64, u64, void *))
> > > +{
> > 
> > top_down is also not used?
> 
> It's unused in the default implementation, but the powerpc implementation in patch 8 uses it:

Well, arch_kexec_walk_mem use kbuf as "data", you can even drop
"image_type" since kbuf has all you want kbuf->image->type, and
kbuf->top_down 

int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf,
			       int (*func)(u64, u64, void *))
> 
> int arch_kexec_walk_mem(unsigned int type, bool top_down, void *data,
> 			int (*func)(u64, u64, void *))
> {
> 	int ret = 0;
> 	u64 i;
> 	phys_addr_t mstart, mend;
> 
> 	if (top_down) {
> 		for_each_free_mem_range_reverse(i, NUMA_NO_NODE, 0,
> 						&mstart, &mend, NULL) {
> 			ret = func(mstart, mend, data);
> 			if (ret)
> 				break;
> 		}
> 	} else {
> 		for_each_free_mem_range(i, NUMA_NO_NODE, 0, &mstart, &mend,
> 					NULL) {
> 			ret = func(mstart, mend, data);
> 			if (ret)
> 				break;
> 		}
> 	}
> 
> 	return ret;
> }
> 
> > Rethink about the argument name type should be better than image_type,
> > it is obvious in the comments and the code and simpler.
> 
> Ok, renamed in the patch below.
> 
> []'s
> Thiago Jung Bauermann
> IBM Linux Technology Center
> 
> 
>     kexec_file: Generalize kexec_add_buffer.
>     
>     Allow architectures to specify different memory walking functions for
>     kexec_add_buffer. Intel uses iomem to track reserved memory ranges,
>     but PowerPC uses the memblock subsystem.
>     
>     Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
>     Cc: Eric Biederman <ebiederm@xmission.com>
>     Cc: Dave Young <dyoung@redhat.com>
>     Cc: kexec@lists.infradead.org
>     Cc: linux-kernel@vger.kernel.org
> 
> diff --git a/include/linux/kexec.h b/include/linux/kexec.h
> index e8acb2b43dd9..42b31f2e1d88 100644
> --- a/include/linux/kexec.h
> +++ b/include/linux/kexec.h
> @@ -315,6 +315,8 @@ int __weak arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr,
>  					Elf_Shdr *sechdrs, unsigned int relsec);
>  int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
>  					unsigned int relsec);
> +int __weak arch_kexec_walk_mem(unsigned int type, bool top_down, void *data,
> +			       int (*func)(u64, u64, void *));
>  void arch_kexec_protect_crashkres(void);
>  void arch_kexec_unprotect_crashkres(void);
>  
> diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
> index b6eec7527e9f..989647a324f2 100644
> --- a/kernel/kexec_file.c
> +++ b/kernel/kexec_file.c
> @@ -428,6 +428,29 @@ static int locate_mem_hole_callback(u64 start, u64 end, void *arg)
>  	return locate_mem_hole_bottom_up(start, end, kbuf);
>  }
>  
> +/**
> + * arch_kexec_walk_mem - call func(data) on free memory regions
> + * @type:	kimage.type
> + * @top_down:	Start from the highest address?
> + * @data:	Argument to pass to @func.
> + * @func:	Function to call for each memory region.
> + *
> + * Return: The memory walk will stop when func returns a non-zero value
> + * and that value will be returned. If all free regions are visited without
> + * func returning non-zero, then zero will be returned.
> + */
> +int __weak arch_kexec_walk_mem(unsigned int type, bool top_down, void *data,
> +			       int (*func)(u64, u64, void *))
> +{
> +	if (type == KEXEC_TYPE_CRASH)
> +		return walk_iomem_res_desc(crashk_res.desc,
> +					   IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
> +					   crashk_res.start, crashk_res.end,
> +					   data, func);
> +	else
> +		return walk_system_ram_res(0, ULONG_MAX, data, func);
> +}
> +
>  /*
>   * Helper function for placing a buffer in a kexec segment. This assumes
>   * that kexec_mutex is held.
> @@ -472,14 +495,8 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
>  	kbuf->top_down = top_down;
>  
>  	/* Walk the RAM ranges and allocate a suitable range for the buffer */
> -	if (image->type == KEXEC_TYPE_CRASH)
> -		ret = walk_iomem_res_desc(crashk_res.desc,
> -				IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
> -				crashk_res.start, crashk_res.end, kbuf,
> -				locate_mem_hole_callback);
> -	else
> -		ret = walk_system_ram_res(0, -1, kbuf,
> -					  locate_mem_hole_callback);
> +	ret = arch_kexec_walk_mem(image->type, top_down, kbuf,
> +				   locate_mem_hole_callback);
>  	if (ret != 1) {
>  		/* A suitable memory range could not be found for buffer */
>  		return -EADDRNOTAVAIL;
> 
> 
> _______________________________________________
> kexec mailing list
> kexec@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/kexec

Thanks
Dave

^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [PATCH v2 2/9] kexec_file: Generalize kexec_add_buffer.
  2016-06-17  7:35           ` Dave Young
@ 2016-06-17 20:51             ` Thiago Jung Bauermann
  2016-06-20  2:26               ` Dave Young
  0 siblings, 1 reply; 20+ messages in thread
From: Thiago Jung Bauermann @ 2016-06-17 20:51 UTC (permalink / raw)
  To: Dave Young; +Cc: kexec, linuxppc-dev, linux-kernel, Eric Biederman

Am Freitag, 17 Juni 2016, 15:35:23 schrieb Dave Young:
> On 06/16/16 at 05:39pm, Thiago Jung Bauermann wrote:
> > Am Donnerstag, 16 Juni 2016, 09:58:53 schrieb Dave Young:
> > > On 06/15/16 at 01:21pm, Thiago Jung Bauermann wrote:
> > > > +int __weak arch_kexec_walk_mem(unsigned int image_type, bool
> > > > top_down,
> > > > +			       void *data, int (*func)(u64, u64, void *))
> > > > +{
> > > 
> > > top_down is also not used?
> > 
> > It's unused in the default implementation, but the powerpc implementation
> > in patch 8 uses it:
> Well, arch_kexec_walk_mem use kbuf as "data", you can even drop
> "image_type" since kbuf has all you want kbuf->image->type, and
> kbuf->top_down
> 
> int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf,
> 			       int (*func)(u64, u64, void *))

Sounds good to me, but I had to move struct kexec_buf from
kernel/kexec_internal.h to include/linux/kexec.h.

Here's the updated patch. What do you think?

[]'s
Thiago Jung Bauermann
IBM Linux Technology Center


    kexec_file: Generalize kexec_add_buffer.
    
    Allow architectures to specify different memory walking functions for
    kexec_add_buffer. Intel uses iomem to track reserved memory ranges,
    but PowerPC uses the memblock subsystem.
    
    Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
    Cc: Eric Biederman <ebiederm@xmission.com>
    Cc: Dave Young <dyoung@redhat.com>
    Cc: kexec@lists.infradead.org
    Cc: linux-kernel@vger.kernel.org

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index e8acb2b43dd9..d8df01107ae2 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -201,6 +201,20 @@ struct kimage {
 #endif
 };
 
+/*
+ * Keeps track of buffer parameters as provided by caller for requesting
+ * memory placement of buffer.
+ */
+struct kexec_buf {
+	struct kimage *image;
+	unsigned long mem;
+	unsigned long memsz;
+	unsigned long buf_align;
+	unsigned long buf_min;
+	unsigned long buf_max;
+	bool top_down;		/* allocate from top of memory hole */
+};
+
 /* kexec interface functions */
 extern void machine_kexec(struct kimage *image);
 extern int machine_kexec_prepare(struct kimage *image);
@@ -315,6 +329,8 @@ int __weak arch_kexec_apply_relocations_add(const Elf_Ehdr *ehdr,
 					Elf_Shdr *sechdrs, unsigned int relsec);
 int __weak arch_kexec_apply_relocations(const Elf_Ehdr *ehdr, Elf_Shdr *sechdrs,
 					unsigned int relsec);
+int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf,
+			       int (*func)(u64, u64, void *));
 void arch_kexec_protect_crashkres(void);
 void arch_kexec_unprotect_crashkres(void);
 
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index b6eec7527e9f..b1f1f6402518 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -428,6 +428,27 @@ static int locate_mem_hole_callback(u64 start, u64 end, void *arg)
 	return locate_mem_hole_bottom_up(start, end, kbuf);
 }
 
+/**
+ * arch_kexec_walk_mem - call func(data) on free memory regions
+ * @kbuf:	Context info for the search. Also passed to @func.
+ * @func:	Function to call for each memory region.
+ *
+ * Return: The memory walk will stop when func returns a non-zero value
+ * and that value will be returned. If all free regions are visited without
+ * func returning non-zero, then zero will be returned.
+ */
+int __weak 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
+		return walk_system_ram_res(0, ULONG_MAX, kbuf, func);
+}
+
 /*
  * Helper function for placing a buffer in a kexec segment. This assumes
  * that kexec_mutex is held.
@@ -472,14 +493,7 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
 	kbuf->top_down = top_down;
 
 	/* Walk the RAM ranges and allocate a suitable range for the buffer */
-	if (image->type == KEXEC_TYPE_CRASH)
-		ret = walk_iomem_res_desc(crashk_res.desc,
-				IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
-				crashk_res.start, crashk_res.end, kbuf,
-				locate_mem_hole_callback);
-	else
-		ret = walk_system_ram_res(0, -1, kbuf,
-					  locate_mem_hole_callback);
+	ret = arch_kexec_walk_mem(kbuf, locate_mem_hole_callback);
 	if (ret != 1) {
 		/* A suitable memory range could not be found for buffer */
 		return -EADDRNOTAVAIL;
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index eefd5bf960c2..4cef7e4706b0 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -20,20 +20,6 @@ struct kexec_sha_region {
 	unsigned long len;
 };
 
-/*
- * Keeps track of buffer parameters as provided by caller for requesting
- * memory placement of buffer.
- */
-struct kexec_buf {
-	struct kimage *image;
-	unsigned long mem;
-	unsigned long memsz;
-	unsigned long buf_align;
-	unsigned long buf_min;
-	unsigned long buf_max;
-	bool top_down;		/* allocate from top of memory hole */
-};
-
 void kimage_file_post_load_cleanup(struct kimage *image);
 #else /* CONFIG_KEXEC_FILE */
 static inline void kimage_file_post_load_cleanup(struct kimage *image) { }

^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [PATCH v2 2/9] kexec_file: Generalize kexec_add_buffer.
  2016-06-17 20:51             ` Thiago Jung Bauermann
@ 2016-06-20  2:26               ` Dave Young
  2016-06-20 16:01                 ` Thiago Jung Bauermann
  0 siblings, 1 reply; 20+ messages in thread
From: Dave Young @ 2016-06-20  2:26 UTC (permalink / raw)
  To: Thiago Jung Bauermann; +Cc: kexec, linuxppc-dev, linux-kernel, Eric Biederman

On 06/17/16 at 05:51pm, Thiago Jung Bauermann wrote:
> Am Freitag, 17 Juni 2016, 15:35:23 schrieb Dave Young:
> > On 06/16/16 at 05:39pm, Thiago Jung Bauermann wrote:
> > > Am Donnerstag, 16 Juni 2016, 09:58:53 schrieb Dave Young:
> > > > On 06/15/16 at 01:21pm, Thiago Jung Bauermann wrote:
> > > > > +int __weak arch_kexec_walk_mem(unsigned int image_type, bool
> > > > > top_down,
> > > > > +			       void *data, int (*func)(u64, u64, void *))
> > > > > +{
> > > > 
> > > > top_down is also not used?
> > > 
> > > It's unused in the default implementation, but the powerpc implementation
> > > in patch 8 uses it:
> > Well, arch_kexec_walk_mem use kbuf as "data", you can even drop
> > "image_type" since kbuf has all you want kbuf->image->type, and
> > kbuf->top_down
> > 
> > int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf,
> > 			       int (*func)(u64, u64, void *))
> 
> Sounds good to me, but I had to move struct kexec_buf from
> kernel/kexec_internal.h to include/linux/kexec.h.
> 
> Here's the updated patch. What do you think?
> 
> []'s
> Thiago Jung Bauermann
> IBM Linux Technology Center
> 
> 
>     kexec_file: Generalize kexec_add_buffer.
>     
>     Allow architectures to specify different memory walking functions for
>     kexec_add_buffer. Intel uses iomem to track reserved memory ranges,
>     but PowerPC uses the memblock subsystem.
>     
>     Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
>     Cc: Eric Biederman <ebiederm@xmission.com>
>     Cc: Dave Young <dyoung@redhat.com>
>     Cc: kexec@lists.infradead.org
>     Cc: linux-kernel@vger.kernel.org
> 
> diff --git a/include/linux/kexec.h b/include/linux/kexec.h
> index e8acb2b43dd9..d8df01107ae2 100644
> --- a/include/linux/kexec.h
> +++ b/include/linux/kexec.h
> @@ -201,6 +201,20 @@ struct kimage {
>  #endif
>  };
>  
> +/*
> + * Keeps track of buffer parameters as provided by caller for requesting
> + * memory placement of buffer.
> + */
> +struct kexec_buf {
> +	struct kimage *image;
> +	unsigned long mem;
> +	unsigned long memsz;
> +	unsigned long buf_align;
> +	unsigned long buf_min;
> +	unsigned long buf_max;
> +	bool top_down;		/* allocate from top of memory hole */
> +};
> +

kexec_buf should go within #ifdef for kexec file like struct purgatory_info

Other than that it looks good.

Thanks
Dave

^ permalink raw reply	[flat|nested] 20+ messages in thread

* Re: [PATCH v2 2/9] kexec_file: Generalize kexec_add_buffer.
  2016-06-20  2:26               ` Dave Young
@ 2016-06-20 16:01                 ` Thiago Jung Bauermann
  0 siblings, 0 replies; 20+ messages in thread
From: Thiago Jung Bauermann @ 2016-06-20 16:01 UTC (permalink / raw)
  To: Dave Young; +Cc: kexec, linuxppc-dev, linux-kernel, Eric Biederman

Am Montag, 20 Juni 2016, 10:26:05 schrieb Dave Young:
> kexec_buf should go within #ifdef for kexec file like struct
> purgatory_info
> 
> Other than that it looks good.

Great! Here it is.
-- 
[]'s
Thiago Jung Bauermann
IBM Linux Technology Center


    kexec_file: Generalize kexec_add_buffer.
    
    Allow architectures to specify different memory walking functions for
    kexec_add_buffer. Intel uses iomem to track reserved memory ranges,
    but PowerPC uses the memblock subsystem.
    
    Signed-off-by: Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
    Cc: Eric Biederman <ebiederm@xmission.com>
    Cc: Dave Young <dyoung@redhat.com>
    Cc: kexec@lists.infradead.org
    Cc: linux-kernel@vger.kernel.org

diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index e8acb2b43dd9..3d91bcfc180d 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -146,7 +146,24 @@ struct kexec_file_ops {
 	kexec_verify_sig_t *verify_sig;
 #endif
 };
-#endif
+
+/*
+ * Keeps track of buffer parameters as provided by caller for requesting
+ * memory placement of buffer.
+ */
+struct kexec_buf {
+	struct kimage *image;
+	unsigned long mem;
+	unsigned long memsz;
+	unsigned long buf_align;
+	unsigned long buf_min;
+	unsigned long buf_max;
+	bool top_down;		/* allocate from top of memory hole */
+};
+
+int __weak arch_kexec_walk_mem(struct kexec_buf *kbuf,
+			       int (*func)(u64, u64, void *));
+#endif /* CONFIG_KEXEC_FILE */
 
 struct kimage {
 	kimage_entry_t head;
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index b6eec7527e9f..b1f1f6402518 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -428,6 +428,27 @@ static int locate_mem_hole_callback(u64 start, u64 end, void *arg)
 	return locate_mem_hole_bottom_up(start, end, kbuf);
 }
 
+/**
+ * arch_kexec_walk_mem - call func(data) on free memory regions
+ * @kbuf:	Context info for the search. Also passed to @func.
+ * @func:	Function to call for each memory region.
+ *
+ * Return: The memory walk will stop when func returns a non-zero value
+ * and that value will be returned. If all free regions are visited without
+ * func returning non-zero, then zero will be returned.
+ */
+int __weak 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
+		return walk_system_ram_res(0, ULONG_MAX, kbuf, func);
+}
+
 /*
  * Helper function for placing a buffer in a kexec segment. This assumes
  * that kexec_mutex is held.
@@ -472,14 +493,7 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz,
 	kbuf->top_down = top_down;
 
 	/* Walk the RAM ranges and allocate a suitable range for the buffer */
-	if (image->type == KEXEC_TYPE_CRASH)
-		ret = walk_iomem_res_desc(crashk_res.desc,
-				IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY,
-				crashk_res.start, crashk_res.end, kbuf,
-				locate_mem_hole_callback);
-	else
-		ret = walk_system_ram_res(0, -1, kbuf,
-					  locate_mem_hole_callback);
+	ret = arch_kexec_walk_mem(kbuf, locate_mem_hole_callback);
 	if (ret != 1) {
 		/* A suitable memory range could not be found for buffer */
 		return -EADDRNOTAVAIL;
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index eefd5bf960c2..4cef7e4706b0 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -20,20 +20,6 @@ struct kexec_sha_region {
 	unsigned long len;
 };
 
-/*
- * Keeps track of buffer parameters as provided by caller for requesting
- * memory placement of buffer.
- */
-struct kexec_buf {
-	struct kimage *image;
-	unsigned long mem;
-	unsigned long memsz;
-	unsigned long buf_align;
-	unsigned long buf_min;
-	unsigned long buf_max;
-	bool top_down;		/* allocate from top of memory hole */
-};
-
 void kimage_file_post_load_cleanup(struct kimage *image);
 #else /* CONFIG_KEXEC_FILE */
 static inline void kimage_file_post_load_cleanup(struct kimage *image) { }

^ permalink raw reply	[flat|nested] 20+ messages in thread

end of thread, other threads:[~2016-06-20 17:47 UTC | newest]

Thread overview: 20+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2016-06-14 14:59 [PATCH v2 0/9] kexec_file_load implementation for PowerPC Thiago Jung Bauermann
2016-06-14 14:59 ` [PATCH v2 1/9] kexec_file: Remove unused members from struct kexec_buf Thiago Jung Bauermann
2016-06-14 14:59 ` [PATCH v2 2/9] kexec_file: Generalize kexec_add_buffer Thiago Jung Bauermann
2016-06-15  7:33   ` Dave Young
2016-06-15 16:21     ` Thiago Jung Bauermann
2016-06-16  1:58       ` Dave Young
2016-06-16 20:39         ` Thiago Jung Bauermann
2016-06-17  7:35           ` Dave Young
2016-06-17 20:51             ` Thiago Jung Bauermann
2016-06-20  2:26               ` Dave Young
2016-06-20 16:01                 ` Thiago Jung Bauermann
2016-06-14 14:59 ` [PATCH v2 3/9] kexec_file: Factor out kexec_locate_mem_hole from kexec_add_buffer Thiago Jung Bauermann
2016-06-14 14:59 ` [PATCH v2 4/9] powerpc: Factor out relocation code from module_64.c to elf_util_64.c Thiago Jung Bauermann
2016-06-14 14:59 ` [PATCH v2 5/9] powerpc: Generalize elf64_apply_relocate_add Thiago Jung Bauermann
2016-06-14 14:59 ` [PATCH v2 6/9] powerpc: Add functions to read ELF files of any endianness Thiago Jung Bauermann
2016-06-14 14:59 ` [PATCH v2 7/9] powerpc: Implement kexec_file_load Thiago Jung Bauermann
2016-06-14 14:59 ` [PATCH v2 8/9] powerpc: Add support for loading ELF kernels with kexec_file_load Thiago Jung Bauermann
2016-06-14 14:59 ` [PATCH v2 9/9] powerpc: Add purgatory for kexec_file_load implementation Thiago Jung Bauermann
2016-06-16  5:48 ` [PATCH v2 0/9] kexec_file_load implementation for PowerPC Michael Ellerman
2016-06-16 19:55   ` Thiago Jung Bauermann

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).