[PATCH] Support for relocatable kdump kernel

[PATCH] Support for relocatable kdump kernel

[Mohan Kumar M]

Support for relocatable kdump kernel

This patch adds relocatable kernel support for kdump. With this one can
use the same regular kernel to capture the kdump. A signature (0xfeed1234)
is passed in r8 from panic code to the next kernel through kexec_sequence
and purgatory code. The signature is used to differentiate between
relocatable kdump kernel and non-kdump kernels.

The purgatory code compares the signature and sets the __kdump_flag in
head_64.S.  During the boot up, kernel code checks __kdump_flag and if it
is set, the kernel will behave as relocatable kdump kernel. This kernel
will boot at the address where it was loaded by kexec-tools ie at the
address reserved through crashkernel boot parameter

CONFIG_CRASH_DUMP depends on CONFIG_RELOCATABLE option to build kdump
kernel as relocatable. So the same kernel can be used as production and
kdump kernel.

This patch incorporates the changes suggested by Paul Mackerrass to avoid
GOT use and to avoid two copies of the code.

Signed-off-by: Mohan Kumar M <mohan@in.ibm.com>
---
 Documentation/kdump/kdump.txt          |   14 ++++++++++---
 arch/powerpc/Kconfig                   |    8 ++-----
 arch/powerpc/include/asm/kdump.h       |   16 +++++++++++++++
 arch/powerpc/kernel/crash_dump.c       |    2 +
 arch/powerpc/kernel/head_64.S          |   34 ++++++++++++++++++++++++++++-----
 arch/powerpc/kernel/iommu.c            |    2 -
 arch/powerpc/kernel/machine_kexec.c    |    2 +
 arch/powerpc/kernel/machine_kexec_64.c |   12 +++++++----
 arch/powerpc/kernel/misc_64.S          |   10 ++++++---
 9 files changed, 79 insertions(+), 21 deletions(-)

diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt
index 0705040..3f4bc84 100644
--- a/Documentation/kdump/kdump.txt
+++ b/Documentation/kdump/kdump.txt
@@ -109,7 +109,8 @@ There are two possible methods of using Kdump.
 2) Or use the system kernel binary itself as dump-capture kernel and there is
    no need to build a separate dump-capture kernel. This is possible
    only with the architecutres which support a relocatable kernel. As
-   of today, i386, x86_64 and ia64 architectures support relocatable kernel.
+   of today, i386, x86_64, ppc64 and ia64 architectures support relocatable
+   kernel.
 
 Building a relocatable kernel is advantageous from the point of view that
 one does not have to build a second kernel for capturing the dump. But
@@ -207,8 +208,15 @@ Dump-capture kernel config options (Arch Dependent, i386 and x86_64)
 Dump-capture kernel config options (Arch Dependent, ppc64)
 ----------------------------------------------------------
 
-*  Make and install the kernel and its modules. DO NOT add this kernel
-   to the boot loader configuration files.
+1) Enable "Build a kdump crash kernel" support under "Kernel" options:
+
+   CONFIG_CRASH_DUMP=y
+
+2)   Enable "Build a relocatable kernel" support
+
+   CONFIG_RELOCATABLE=y
+
+   Make and install the kernel and its modules.
 
 Dump-capture kernel config options (Arch Dependent, ia64)
 ----------------------------------------------------------
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 17c988b..6b3e840 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -321,11 +321,11 @@ config KEXEC
 
 config CRASH_DUMP
 	bool "Build a kdump crash kernel"
-	depends on PPC_MULTIPLATFORM && PPC64
+	depends on PPC_MULTIPLATFORM && PPC64 && RELOCATABLE
 	help
 	  Build a kernel suitable for use as a kdump capture kernel.
-	  The kernel will be linked at a different address than normal, and
-	  so can only be used for Kdump.
+	  The same kernel binary can be used as production kernel and dump capture
+	  kernel
 
 	  Don't change this unless you know what you are doing.
 
@@ -824,11 +824,9 @@ config PAGE_OFFSET
 	default "0xc000000000000000"
 config KERNEL_START
 	hex
-	default "0xc000000002000000" if CRASH_DUMP
 	default "0xc000000000000000"
 config PHYSICAL_START
 	hex
-	default "0x02000000" if CRASH_DUMP
 	default "0x00000000"
 endif
 
diff --git a/arch/powerpc/include/asm/kdump.h b/arch/powerpc/include/asm/kdump.h
index f6c93c7..5308754 100644
--- a/arch/powerpc/include/asm/kdump.h
+++ b/arch/powerpc/include/asm/kdump.h
@@ -9,6 +9,12 @@
  * Reserve to the end of the FWNMI area, see head_64.S */
 #define KDUMP_RESERVE_LIMIT	0x10000 /* 64K */
 
+/*
+ * Used to differentiate between relocatable kdump kernel and other
+ * kernels
+ */
+#define KDUMP_SIGNATURE	0xfeed1234
+
 #ifdef CONFIG_CRASH_DUMP
 
 #define KDUMP_TRAMPOLINE_START	0x0100
@@ -19,11 +25,21 @@
 #endif /* CONFIG_CRASH_DUMP */
 
 #ifndef __ASSEMBLY__
+
+extern unsigned long long __kdump_flag;
+
 #ifdef CONFIG_CRASH_DUMP
+#ifdef CONFIG_RELOCATABLE
+
+static inline void reserve_kdump_trampoline(void) { ; }
+static inline void setup_kdump_trampoline(void) { ; }
+
+#else
 
 extern void reserve_kdump_trampoline(void);
 extern void setup_kdump_trampoline(void);
 
+#endif /* CONFIG_RELOCATABLE */
 #else /* !CONFIG_CRASH_DUMP */
 
 static inline void reserve_kdump_trampoline(void) { ; }
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index a323c9b..eaf9d6d 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -27,6 +27,7 @@
 #define DBG(fmt...)
 #endif
 
+#ifndef CONFIG_RELOCATABLE
 void __init reserve_kdump_trampoline(void)
 {
 	lmb_reserve(0, KDUMP_RESERVE_LIMIT);
@@ -65,6 +66,7 @@ void __init setup_kdump_trampoline(void)
 
 	DBG(" <- setup_kdump_trampoline()\n");
 }
+#endif /* CONFIG_RELOCATABLE */
 
 #ifdef CONFIG_PROC_VMCORE
 static int __init parse_elfcorehdr(char *p)
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index e409338..5b12b10 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -97,6 +97,14 @@ __secondary_hold_spinloop:
 __secondary_hold_acknowledge:
 	.llong	0x0
 
+	/* This flag is set only for kdump kernels so that */
+	/* it will be relocatable. Purgatory code user space kexec-tools */
+	/* sets this flag. Do not move this variable as purgatory code */
+	/* relies on the position of this variables */
+	.globl	__kdump_flag
+__kdump_flag:
+	.llong	0x0
+
 #ifdef CONFIG_PPC_ISERIES
 	/*
 	 * At offset 0x20, there is a pointer to iSeries LPAR data.
@@ -1384,8 +1392,13 @@ _STATIC(__after_prom_start)
 	/* process relocations for the final address of the kernel */
 	lis	r25,PAGE_OFFSET@highest	/* compute virtual base of kernel */
 	sldi	r25,r25,32
+#ifdef CONFIG_CRASH_DUMP
+	ld	r7,__kdump_flag-_stext(r26)
+	cmpldi	cr0,r7,1	/* relocatable kernel ? */
+	bne	1f
 	add	r25,r25,r26
-	mr	r3,r25
+#endif
+1:	mr	r3,r25
 	bl	.relocate
 #endif
 
@@ -1401,9 +1414,21 @@ _STATIC(__after_prom_start)
 	beq	9f			/* have already put us at zero */
 	li	r6,0x100		/* Start offset, the first 0x100 */
 					/* bytes were copied earlier.	 */
-#ifdef CONFIG_RELOCATABLE
+
+#ifdef CONFIG_CRASH_DUMP
+/*
+ * Check if the kernel has to be running as relocatable kernel based on the
+ * variable __kdump_flag, if it is set the kernel is treated as relocatble
+ * kernel, otherwise it will be moved to PHYSICAL_START
+ */
+	ld	r7,__kdump_flag-_stext(r26)
+	cmpldi	cr0,r7,1
+	bne	regular
+
 	li	r5,__end_interrupts - _stext	/* just copy interrupts */
-#else
+	b	5f
+regular:
+#endif
 	lis	r5,(copy_to_here - _stext)@ha
 	addi	r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */
 
@@ -1420,8 +1445,7 @@ p_end:	.llong	_end - _stext
 4:	/* Now copy the rest of the kernel up to _end */
 	addis	r5,r26,(p_end - _stext)@ha
 	ld	r5,(p_end - _stext)@l(r5)	/* get _end */
-#endif
-	bl	.copy_and_flush		/* copy the rest */
+5:	bl	.copy_and_flush		/* copy the rest */
 
 9:	b	.start_here_multiplatform
 
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 550a193..24f7797 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -494,7 +494,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
 	spin_lock_init(&tbl->it_lock);
 
 #ifdef CONFIG_CRASH_DUMP
-	if (ppc_md.tce_get) {
+	if (ppc_md.tce_get && __kdump_flag) {
 		unsigned long index;
 		unsigned long tceval;
 		unsigned long tcecount = 0;
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index aab7688..ac2a21f 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -88,11 +88,13 @@ void __init reserve_crashkernel(void)
 
 	crash_size = crashk_res.end - crashk_res.start + 1;
 
+#ifndef CONFIG_RELOCATABLE
 	if (crashk_res.start != KDUMP_KERNELBASE)
 		printk("Crash kernel location must be 0x%x\n",
 				KDUMP_KERNELBASE);
 
 	crashk_res.start = KDUMP_KERNELBASE;
+#endif
 	crash_size = PAGE_ALIGN(crash_size);
 	crashk_res.end = crashk_res.start + crash_size - 1;
 
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index a168514..6a45a9e 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -255,11 +255,13 @@ static union thread_union kexec_stack
 /* Our assembly helper, in kexec_stub.S */
 extern NORET_TYPE void kexec_sequence(void *newstack, unsigned long start,
 					void *image, void *control,
-					void (*clear_all)(void)) ATTRIB_NORET;
+					void (*clear_all)(void),
+				unsigned long long kdump_flag) ATTRIB_NORET;
 
 /* too late to fail here */
 void default_machine_kexec(struct kimage *image)
 {
+	unsigned long long kdump_flag = 0;
 	/* prepare control code if any */
 
 	/*
@@ -270,8 +272,10 @@ void default_machine_kexec(struct kimage *image)
         * using debugger IPI.
         */
 
-       if (crashing_cpu == -1)
-               kexec_prepare_cpus();
+	if (crashing_cpu == -1)
+		kexec_prepare_cpus();
+	else
+		kdump_flag = KDUMP_SIGNATURE;
 
 	/* switch to a staticly allocated stack.  Based on irq stack code.
 	 * XXX: the task struct will likely be invalid once we do the copy!
@@ -284,7 +288,7 @@ void default_machine_kexec(struct kimage *image)
 	 */
 	kexec_sequence(&kexec_stack, image->start, image,
 			page_address(image->control_code_page),
-			ppc_md.hpte_clear_all);
+			ppc_md.hpte_clear_all, kdump_flag);
 	/* NOTREACHED */
 }
 
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 4dd70cf..c93e5f7 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -609,10 +609,13 @@ real_mode:	/* assume normal blr return */
 
 
 /*
- * kexec_sequence(newstack, start, image, control, clear_all())
+ * kexec_sequence(newstack, start, image, control, clear_all(), kdump_flag)
  *
  * does the grungy work with stack switching and real mode switches
  * also does simple calls to other code
+ *
+ * kdump_flag says whether the next kernel should be running at the reserved
+ * load address as needed for relocatable kdump kernel
  */
 
 _GLOBAL(kexec_sequence)
@@ -645,7 +648,7 @@ _GLOBAL(kexec_sequence)
 	mr	r29,r5			/* image (virt) */
 	mr	r28,r6			/* control, unused */
 	mr	r27,r7			/* clear_all() fn desc */
-	mr	r26,r8			/* spare */
+	mr	r26,r8			/* kdump flag */
 	lhz	r25,PACAHWCPUID(r13)	/* get our phys cpu from paca */
 
 	/* disable interrupts, we are overwriting kernel data next */
@@ -707,5 +710,6 @@ _GLOBAL(kexec_sequence)
 	mr	r4,r30	# start, aka phys mem offset
 	mtlr	4
 	li	r5,0
-	blr	/* image->start(physid, image->start, 0); */
+	mr	r6,r26			/* kdump_flag */
+	blr	/* image->start(physid, image->start, 0, kdump_flag); */
 #endif /* CONFIG_KEXEC */

Re: [PATCH] Support for relocatable kdump kernel

[Paul Mackerras]

Mohan Kumar M writes:

> Support for relocatable kdump kernel

> @@ -1401,9 +1414,21 @@ _STATIC(__after_prom_start)
>  	beq	9f			/* have already put us at zero */
>  	li	r6,0x100		/* Start offset, the first 0x100 */
>  					/* bytes were copied earlier.	 */
> -#ifdef CONFIG_RELOCATABLE
> +
> +#ifdef CONFIG_CRASH_DUMP

What tree is this patch against?  No tree that I can find has a line
saying "#ifdef CONFIG_RELOCATABLE" at that point.  Or is there a
prerequisite patch that I haven't seen yet?

Paul.

Re: [PATCH] Support for relocatable kdump kernel

[Mohan Kumar M]

Paul Mackerras wrote:
> Mohan Kumar M writes:
> 
>> Support for relocatable kdump kernel
> 
>> @@ -1401,9 +1414,21 @@ _STATIC(__after_prom_start)
>>  	beq	9f			/* have already put us at zero */
>>  	li	r6,0x100		/* Start offset, the first 0x100 */
>>  					/* bytes were copied earlier.	 */
>> -#ifdef CONFIG_RELOCATABLE
>> +
>> +#ifdef CONFIG_CRASH_DUMP
> 
> What tree is this patch against?  No tree that I can find has a line
> saying "#ifdef CONFIG_RELOCATABLE" at that point.  Or is there a
> prerequisite patch that I haven't seen yet?

Hi Paul,

My patch is based on your PATCH 5 of relocatable kernel patchset (which 
demonstrates kernel can be relocatable).

Do I need to resend the patch by generating the diff with your patch5 also?

Regards,
Mohan.

Re: [PATCH] Support for relocatable kdump kernel

[Milton Miller]

On Wed Oct 22 at 14:38:10 EST in 2008, Michael Ellerman wrote:
> This adds relocatable kernel support for kdump. With this one can
> use the same regular kernel to capture the kdump. A signature 
> (0xfeed1234)
> is passed in r6 from panic code to the next kernel through 
> kexec_sequence
> and purgatory code. The signature is used to differentiate between
> kdump kernel and non-kdump kernels.

I object to this signature being passed from the kernel.  The
purgatory code should be modified to set this based on a memory
variable in its space, and that varable should be set by the
userspace code code that prepares purgatory.  (The standard
kexec-tools has library code to do this and we already use it
to tell purgatory the location of the device tree and kernel).

> The purgatory code compares the signature and sets the __kdump_flag in
> head_64.S.  During the boot up, kernel code checks __kdump_flag and if 
> it
> is set, the kernel will behave as relocatable kdump kernel. This kernel
> will boot at the address where it was loaded by kexec-tools ie. at the
> address reserved through crashkernel boot parameter.

I was hoping for a more generic test, but I haven't had the time to
write code for this so I'll accept this part for now.


> CONFIG_CRASH_DUMP depends on CONFIG_RELOCATABLE option to build kdump
> kernel as relocatable. So the same kernel can be used as production and
> kdump kernel.
>
>

>
> diff --git a/arch/powerpc/include/asm/kdump.h 
> b/arch/powerpc/include/asm/kdump.h
> index f6c93c7..a503da9 100644
> --- a/arch/powerpc/include/asm/kdump.h
> +++ b/arch/powerpc/include/asm/kdump.h
> @@ -9,6 +9,12 @@
>   * Reserve to the end of the FWNMI area, see head_64.S */
>  #define KDUMP_RESERVE_LIMIT    0x10000 /* 64K */
>
> +/*
> + * Used to differentiate between relocatable kdump kernel and other
> + * kernels
> + */
> +#define KDUMP_SIGNATURE        0xfeed1234
> +

This can go

>  #ifdef CONFIG_CRASH_DUMP
>
>  #define KDUMP_TRAMPOLINE_START 0x0100
> @@ -19,17 +25,18 @@
>  #endif /* CONFIG_CRASH_DUMP */
>
>  #ifndef __ASSEMBLY__
> -#ifdef CONFIG_CRASH_DUMP
>
> +extern unsigned long __kdump_flag;
> +

This will not be needed.  It will only be referenced by the
assembly code in head.S.

> +#if defined(CONFIG_CRASH_DUMP) && !defined(CONFIG_RELOCATABLE)
>  extern void reserve_kdump_trampoline(void);
>  extern void setup_kdump_trampoline(void);
> -
> -#else /* !CONFIG_CRASH_DUMP */
> -
> +#else
> +/* !CRASH_DUMP || RELOCATABLE */
>  static inline void reserve_kdump_trampoline(void) { ; }
>  static inline void setup_kdump_trampoline(void) { ; }
> +#endif
>
> -#endif /* CONFIG_CRASH_DUMP */
>  #endif /* __ASSEMBLY__ */
>
>  #endif /* __PPC64_KDUMP_H */
> diff --git a/arch/powerpc/kernel/crash_dump.c 
> b/arch/powerpc/kernel/crash_dump.c
> index 97e0563..19671ac 100644
> --- a/arch/powerpc/kernel/crash_dump.c
> +++ b/arch/powerpc/kernel/crash_dump.c
> @@ -30,6 +30,7 @@
>  /* Stores the physical address of elf header of crash image. */
>  unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
>
> +#ifndef CONFIG_RELOCATABLE

is this done somewhere else for the relocatable case?
a comment pointing to where would be helpful.

>  void __init reserve_kdump_trampoline(void)
>  {
>         lmb_reserve(0, KDUMP_RESERVE_LIMIT);
> @@ -68,6 +69,7 @@ void __init setup_kdump_trampoline(void)
>
>         DBG(" <- setup_kdump_trampoline()\n");
>  }
> +#endif /* CONFIG_RELOCATABLE */
>
>  /*
>   * Note: elfcorehdr_addr is not just limited to vmcore. It is also 
> used by
> diff --git a/arch/powerpc/kernel/head_64.S 
> b/arch/powerpc/kernel/head_64.S
> index 84856be..69489bd 100644
> --- a/arch/powerpc/kernel/head_64.S
> +++ b/arch/powerpc/kernel/head_64.S
> @@ -97,6 +97,12 @@ __secondary_hold_spinloop:
>  __secondary_hold_acknowledge:
>         .llong  0x0
>
> +       /* This flag is set by purgatory if we should be a kdump 
> kernel. */
> +       /* Do not move this variable as purgatory knows about it. */
> +       .globl  __kdump_flag
> +__kdump_flag:
> +       .llong  0x0
> +
>  #ifdef CONFIG_PPC_ISERIES
>         /*
>          * At offset 0x20, there is a pointer to iSeries LPAR data.
> @@ -1384,7 +1390,13 @@ _STATIC(__after_prom_start)
>         /* process relocations for the final address of the kernel */
>         lis     r25,PAGE_OFFSET at highest      /* compute virtual 
> base of kernel */
>         sldi    r25,r25,32
> -       mr      r3,r25
> +#ifdef CONFIG_CRASH_DUMP
> +       ld      r7,__kdump_flag-_stext(r26)
> +       cmpldi  cr0,r7,1        /* kdump kernel ? - stay where we are 
> */
> +       bne     1f
> +       add     r25,r25,r26
> +#endif
> +1:     mr      r3,r25
>         bl      .relocate
>  #endif
>
> @@ -1398,11 +1410,26 @@ _STATIC(__after_prom_start)
>         li      r3,0                    /* target addr */
>         mr.     r4,r26                  /* In some cases the loader 
> may  */
>         beq     9f                      /* have already put us at zero 
> */
> -       lis     r5,(copy_to_here - _stext)@ha
> -       addi    r5,r5,(copy_to_here - _stext)@l /* # bytes of memory 
> to copy */
>         li      r6,0x100                /* Start offset, the first 
> 0x100 */
>                                         /* bytes were copied earlier.  
>   */
>
> +#ifdef CONFIG_CRASH_DUMP
> +/*
> + * Check if the kernel has to be running as relocatable kernel based 
> on the
> + * variable __kdump_flag, if it is set the kernel is treated as 
> relocatable
> + * kernel, otherwise it will be moved to PHYSICAL_START
> + */
> +       ld      r7,__kdump_flag-_stext(r26)
> +       cmpldi  cr0,r7,1
> +       bne     3f
> +
> +       li      r5,__end_interrupts - _stext    /* just copy 
> interrupts */
> +       b       5f
> +3:
> +#endif
> +       lis     r5,(copy_to_here - _stext)@ha
> +       addi    r5,r5,(copy_to_here - _stext)@l /* # bytes of memory 
> to copy */
> +
>         bl      .copy_and_flush         /* copy the first n bytes      
>   */
>                                         /* this includes the code 
> being  */
>                                         /* executed here.              
>   */
> @@ -1411,15 +1438,15 @@ _STATIC(__after_prom_start)
>         mtctr   r8
>         bctr
>
> +p_end: .llong  _end - _stext
> +
>  4:     /* Now copy the rest of the kernel up to _end */
>         addis   r5,r26,(p_end - _stext)@ha
>         ld      r5,(p_end - _stext)@l(r5)       /* get _end */
> -       bl      .copy_and_flush         /* copy the rest */
> +5:     bl      .copy_and_flush         /* copy the rest */
>
>  9:     b       .start_here_multiplatform
>
> -p_end: .llong  _end - _stext
> -
>  /*
>   * Copy routine used to copy the kernel to start at physical address 0
>   * and flush and invalidate the caches as needed.
> diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
> index ea1ba89..3857d7e 100644
> --- a/arch/powerpc/kernel/iommu.c
> +++ b/arch/powerpc/kernel/iommu.c
> @@ -458,6 +458,42 @@ void iommu_unmap_sg(struct iommu_table *tbl, 
> struct scatterlist *sglist,
>         spin_unlock_irqrestore(&(tbl->it_lock), flags);
>  }
>
> +static void iommu_table_clear(struct iommu_table *tbl)
> +{
> +       if (!__kdump_flag) {

This test should be using the new is_kdump_kernel in
include/linux/crash_dump.h.   (That tests the presence
of the elfcore= command line, but it (1) is common
with other architectures, and (2) allows the kernel
to be running offset for other uses.

> +               /* Clear the table in case firmware left allocations 
> in it */
> +               ppc_md.tce_free(tbl, tbl->it_offset, tbl->it_size);
> +               return;
> +       }
>
> +
> +#ifdef CONFIG_CRASH_DUMP
> +       if (ppc_md.tce_get) {
> +               unsigned long index, tceval, tcecount = 0;
> +
>

> --- a/arch/powerpc/kernel/machine_kexec.c
> +++ b/arch/powerpc/kernel/machine_kexec.c
> @@ -88,11 +88,13 @@ void __init reserve_crashkernel(void)
>
>         crash_size = crashk_res.end - crashk_res.start + 1;
>
> +#ifndef CONFIG_RELOCATABLE
>         if (crashk_res.start != KDUMP_KERNELBASE)
>                 printk("Crash kernel location must be 0x%x\n",
>                                 KDUMP_KERNELBASE);
>
>         crashk_res.start = KDUMP_KERNELBASE;
> +#endif

actually, we should never test on ppc64, as we don't care
if the base kernel is compiled CONFIG_RELOCATABLE but only
that the dump kernel must be.

>         crash_size = PAGE_ALIGN(crash_size);
>         crashk_res.end = crashk_res.start + crash_size - 1;
>
> diff --git a/arch/powerpc/kernel/machine_kexec_64.c 
> b/arch/powerpc/kernel/machine_kexec_64.c
> index 4bd8b4f..e6efec7 100644
> --- a/arch/powerpc/kernel/machine_kexec_64.c
> +++ b/arch/powerpc/kernel/machine_kexec_64.c
> @@ -255,11 +255,14 @@ static union thread_union kexec_stack
>  /* Our assembly helper, in kexec_stub.S */
>  extern NORET_TYPE void kexec_sequence(void *newstack, unsigned long 
> start,
>                                         void *image, void *control,
> -                                       void (*clear_all)(void)) 
> ATTRIB_NORET;
> +                                       void (*clear_all)(void),
> +                                       unsigned long kdump_flag) 
> ATTRIB_NORET;
>
>  /* too late to fail here */
>  void default_machine_kexec(struct kimage *image)
>  {
> +       unsigned long kdump_flag = 0;
> +
>         /* prepare control code if any */
>
>         /*
> @@ -270,8 +273,10 @@ void default_machine_kexec(struct kimage *image)
>          * using debugger IPI.
>          */
>
> -       if (crashing_cpu == -1)
> -               kexec_prepare_cpus();
> +       if (crashing_cpu == -1)
> +               kexec_prepare_cpus();
> +       else
> +               kdump_flag = KDUMP_SIGNATURE;
>
>         /* switch to a staticly allocated stack.  Based on irq stack 
> code.
>          * XXX: the task struct will likely be invalid once we do the 
> copy!
> @@ -284,7 +289,7 @@ void default_machine_kexec(struct kimage *image)
>          */
>         kexec_sequence(&kexec_stack, image->start, image,
>                         page_address(image->control_code_page),
> -                       ppc_md.hpte_clear_all);
> +                       ppc_md.hpte_clear_all, kdump_flag);
>         /* NOTREACHED */
>  }
>
>
> diff --git a/arch/powerpc/kernel/misc_64.S 
> b/arch/powerpc/kernel/misc_64.S
> index 3053fe5..a243fd0 100644
> --- a/arch/powerpc/kernel/misc_64.S
> +++ b/arch/powerpc/kernel/misc_64.S
> @@ -611,10 +611,12 @@ real_mode:        /* assume normal blr return */
>
>
>  /*
> - * kexec_sequence(newstack, start, image, control, clear_all())
> + * kexec_sequence(newstack, start, image, control, clear_all(), 
> kdump_flag)
>   *
>   * does the grungy work with stack switching and real mode switches
>   * also does simple calls to other code
> + *
> + * kdump_flag says whether the next kernel should be a kdump kernel.
>   */
>
>  _GLOBAL(kexec_sequence)
> @@ -647,7 +649,7 @@ _GLOBAL(kexec_sequence)
>         mr      r29,r5                  /* image (virt) */
>         mr      r28,r6                  /* control, unused */
>         mr      r27,r7                  /* clear_all() fn desc */
> -       mr      r26,r8                  /* spare */
> +       mr      r26,r8                  /* kdump flag */
>         lhz     r25,PACAHWCPUID(r13)    /* get our phys cpu from paca 
> */
>
>         /* disable interrupts, we are overwriting kernel data next */
> @@ -709,5 +711,6 @@ _GLOBAL(kexec_sequence)
>         mr      r4,r30  # start, aka phys mem offset
>         mtlr    4
>         li      r5,0
> -       blr     /* image->start(physid, image->start, 0); */
> +       mr      r6,r26                  /* kdump_flag */
> +       blr     /* image->start(physid, image->start, 0, kdump_flag); 
> */
>  #endif /* CONFIG_KEXEC */

please remove these changes and signature.
as explained above, this should be handled by the user space loading
the kexec kernel.   We never use the same kexec target for kdump and
a normal reboot.


> diff --git a/arch/powerpc/platforms/cell/ras.c 
> b/arch/powerpc/platforms/cell/ras.c
> index 2a14b05..665af1c 100644
> --- a/arch/powerpc/platforms/cell/ras.c
> +++ b/arch/powerpc/platforms/cell/ras.c
> @@ -21,6 +21,7 @@
>  #include <asm/machdep.h>
>  #include <asm/rtas.h>
>  #include <asm/cell-regs.h>
> +#include <asm/kdump.h>
>
>  #include "ras.h"
>
> @@ -111,9 +112,8 @@ static int __init cbe_ptcal_enable_on_node(int 
> nid, int order)
>         int ret = -ENOMEM;
>         unsigned long addr;
>
> -#ifdef CONFIG_CRASH_DUMP
> -       rtas_call(ptcal_stop_tok, 1, 1, NULL, nid);
> -#endif
> +       if (__kdump_flag)
> +               rtas_call(ptcal_stop_tok, 1, 1, NULL, nid);
>

This should use is_kdump_kernel() from include/linux/crash_dump.h

>         area = kmalloc(sizeof(*area), GFP_KERNEL);
>         if (!area)
> diff --git a/arch/powerpc/platforms/pseries/iommu.c 
> b/arch/powerpc/platforms/pseries/iommu.c
> index a8c4466..d56491d 100644
> --- a/arch/powerpc/platforms/pseries/iommu.c
> +++ b/arch/powerpc/platforms/pseries/iommu.c
> @@ -44,6 +44,7 @@
>  #include <asm/tce.h>
>  #include <asm/ppc-pci.h>
>  #include <asm/udbg.h>
> +#include <asm/kdump.h>
>
>  #include "plpar_wrappers.h"
>
> @@ -291,9 +292,8 @@ static void iommu_table_setparms(struct 
> pci_controller *phb,
>
>         tbl->it_base = (unsigned long)__va(*basep);
>
> -#ifndef CONFIG_CRASH_DUMP
> -       memset((void *)tbl->it_base, 0, *sizep);
> -#endif
> +       if (!__kdump_flag)
> +               memset((void *)tbl->it_base, 0, *sizep);
>

as should this.

>
>         tbl->it_busno = phb->bus->number;
>


thanks,
milton

[PATCH] Support for relocatable kdump kernel

[Michael Ellerman]

From: Mohan Kumar M <mohan@in.ibm.com>

This adds relocatable kernel support for kdump. With this one can
use the same regular kernel to capture the kdump. A signature (0xfeed1234)
is passed in r6 from panic code to the next kernel through kexec_sequence
and purgatory code. The signature is used to differentiate between
kdump kernel and non-kdump kernels.

The purgatory code compares the signature and sets the __kdump_flag in
head_64.S.  During the boot up, kernel code checks __kdump_flag and if it
is set, the kernel will behave as relocatable kdump kernel. This kernel
will boot at the address where it was loaded by kexec-tools ie. at the
address reserved through crashkernel boot parameter.

CONFIG_CRASH_DUMP depends on CONFIG_RELOCATABLE option to build kdump
kernel as relocatable. So the same kernel can be used as production and
kdump kernel.

This patch incorporates the changes suggested by Paul Mackerras to avoid
GOT use and to avoid two copies of the code.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Mohan Kumar M <mohan@in.ibm.com>
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
---
 Documentation/kdump/kdump.txt          |   14 +++++-
 arch/powerpc/Kconfig                   |   10 +---
 arch/powerpc/include/asm/kdump.h       |   17 ++++++--
 arch/powerpc/kernel/crash_dump.c       |    2 +
 arch/powerpc/kernel/head_64.S          |   39 +++++++++++++++---
 arch/powerpc/kernel/iommu.c            |   69 +++++++++++++++++---------------
 arch/powerpc/kernel/machine_kexec.c    |    2 +
 arch/powerpc/kernel/machine_kexec_64.c |   13 ++++--
 arch/powerpc/kernel/misc_64.S          |    9 +++-
 arch/powerpc/platforms/cell/ras.c      |    6 +-
 arch/powerpc/platforms/pseries/iommu.c |    6 +-
 11 files changed, 121 insertions(+), 66 deletions(-)

diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt
index 0705040..3f4bc84 100644
--- a/Documentation/kdump/kdump.txt
+++ b/Documentation/kdump/kdump.txt
@@ -109,7 +109,8 @@ There are two possible methods of using Kdump.
 2) Or use the system kernel binary itself as dump-capture kernel and there is
    no need to build a separate dump-capture kernel. This is possible
    only with the architecutres which support a relocatable kernel. As
-   of today, i386, x86_64 and ia64 architectures support relocatable kernel.
+   of today, i386, x86_64, ppc64 and ia64 architectures support relocatable
+   kernel.
 
 Building a relocatable kernel is advantageous from the point of view that
 one does not have to build a second kernel for capturing the dump. But
@@ -207,8 +208,15 @@ Dump-capture kernel config options (Arch Dependent, i386 and x86_64)
 Dump-capture kernel config options (Arch Dependent, ppc64)
 ----------------------------------------------------------
 
-*  Make and install the kernel and its modules. DO NOT add this kernel
-   to the boot loader configuration files.
+1) Enable "Build a kdump crash kernel" support under "Kernel" options:
+
+   CONFIG_CRASH_DUMP=y
+
+2)   Enable "Build a relocatable kernel" support
+
+   CONFIG_RELOCATABLE=y
+
+   Make and install the kernel and its modules.
 
 Dump-capture kernel config options (Arch Dependent, ia64)
 ----------------------------------------------------------
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 369d93e..5b15278 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -323,13 +323,11 @@ config KEXEC
 
 config CRASH_DUMP
 	bool "Build a kdump crash kernel"
-	depends on PPC_MULTIPLATFORM && PPC64
+	depends on PPC_MULTIPLATFORM && PPC64 && RELOCATABLE
 	help
 	  Build a kernel suitable for use as a kdump capture kernel.
-	  The kernel will be linked at a different address than normal, and
-	  so can only be used for Kdump.
-
-	  Don't change this unless you know what you are doing.
+	  The same kernel binary can be used as production kernel and dump
+	  capture kernel.
 
 config PHYP_DUMP
 	bool "Hypervisor-assisted dump (EXPERIMENTAL)"
@@ -829,11 +827,9 @@ config PAGE_OFFSET
 	default "0xc000000000000000"
 config KERNEL_START
 	hex
-	default "0xc000000002000000" if CRASH_DUMP
 	default "0xc000000000000000"
 config PHYSICAL_START
 	hex
-	default "0x02000000" if CRASH_DUMP
 	default "0x00000000"
 endif
 
diff --git a/arch/powerpc/include/asm/kdump.h b/arch/powerpc/include/asm/kdump.h
index f6c93c7..a503da9 100644
--- a/arch/powerpc/include/asm/kdump.h
+++ b/arch/powerpc/include/asm/kdump.h
@@ -9,6 +9,12 @@
  * Reserve to the end of the FWNMI area, see head_64.S */
 #define KDUMP_RESERVE_LIMIT	0x10000 /* 64K */
 
+/*
+ * Used to differentiate between relocatable kdump kernel and other
+ * kernels
+ */
+#define KDUMP_SIGNATURE	0xfeed1234
+
 #ifdef CONFIG_CRASH_DUMP
 
 #define KDUMP_TRAMPOLINE_START	0x0100
@@ -19,17 +25,18 @@
 #endif /* CONFIG_CRASH_DUMP */
 
 #ifndef __ASSEMBLY__
-#ifdef CONFIG_CRASH_DUMP
 
+extern unsigned long __kdump_flag;
+
+#if defined(CONFIG_CRASH_DUMP) && !defined(CONFIG_RELOCATABLE)
 extern void reserve_kdump_trampoline(void);
 extern void setup_kdump_trampoline(void);
-
-#else /* !CONFIG_CRASH_DUMP */
-
+#else
+/* !CRASH_DUMP || RELOCATABLE */
 static inline void reserve_kdump_trampoline(void) { ; }
 static inline void setup_kdump_trampoline(void) { ; }
+#endif
 
-#endif /* CONFIG_CRASH_DUMP */
 #endif /* __ASSEMBLY__ */
 
 #endif /* __PPC64_KDUMP_H */
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 97e0563..19671ac 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -30,6 +30,7 @@
 /* Stores the physical address of elf header of crash image. */
 unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
 
+#ifndef CONFIG_RELOCATABLE
 void __init reserve_kdump_trampoline(void)
 {
 	lmb_reserve(0, KDUMP_RESERVE_LIMIT);
@@ -68,6 +69,7 @@ void __init setup_kdump_trampoline(void)
 
 	DBG(" <- setup_kdump_trampoline()\n");
 }
+#endif /* CONFIG_RELOCATABLE */
 
 /*
  * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 84856be..69489bd 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -97,6 +97,12 @@ __secondary_hold_spinloop:
 __secondary_hold_acknowledge:
 	.llong	0x0
 
+	/* This flag is set by purgatory if we should be a kdump kernel. */
+	/* Do not move this variable as purgatory knows about it. */
+	.globl	__kdump_flag
+__kdump_flag:
+	.llong	0x0
+
 #ifdef CONFIG_PPC_ISERIES
 	/*
 	 * At offset 0x20, there is a pointer to iSeries LPAR data.
@@ -1384,7 +1390,13 @@ _STATIC(__after_prom_start)
 	/* process relocations for the final address of the kernel */
 	lis	r25,PAGE_OFFSET@highest	/* compute virtual base of kernel */
 	sldi	r25,r25,32
-	mr	r3,r25
+#ifdef CONFIG_CRASH_DUMP
+	ld	r7,__kdump_flag-_stext(r26)
+	cmpldi	cr0,r7,1	/* kdump kernel ? - stay where we are */
+	bne	1f
+	add	r25,r25,r26
+#endif
+1:	mr	r3,r25
 	bl	.relocate
 #endif
 
@@ -1398,11 +1410,26 @@ _STATIC(__after_prom_start)
 	li	r3,0			/* target addr */
 	mr.	r4,r26			/* In some cases the loader may  */
 	beq	9f			/* have already put us at zero */
-	lis	r5,(copy_to_here - _stext)@ha
-	addi	r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */
 	li	r6,0x100		/* Start offset, the first 0x100 */
 					/* bytes were copied earlier.	 */
 
+#ifdef CONFIG_CRASH_DUMP
+/*
+ * Check if the kernel has to be running as relocatable kernel based on the
+ * variable __kdump_flag, if it is set the kernel is treated as relocatable
+ * kernel, otherwise it will be moved to PHYSICAL_START
+ */
+	ld	r7,__kdump_flag-_stext(r26)
+	cmpldi	cr0,r7,1
+	bne	3f
+
+	li	r5,__end_interrupts - _stext	/* just copy interrupts */
+	b	5f
+3:
+#endif
+	lis	r5,(copy_to_here - _stext)@ha
+	addi	r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */
+
 	bl	.copy_and_flush		/* copy the first n bytes	 */
 					/* this includes the code being	 */
 					/* executed here.		 */
@@ -1411,15 +1438,15 @@ _STATIC(__after_prom_start)
 	mtctr	r8
 	bctr
 
+p_end:	.llong	_end - _stext
+
 4:	/* Now copy the rest of the kernel up to _end */
 	addis	r5,r26,(p_end - _stext)@ha
 	ld	r5,(p_end - _stext)@l(r5)	/* get _end */
-	bl	.copy_and_flush		/* copy the rest */
+5:	bl	.copy_and_flush		/* copy the rest */
 
 9:	b	.start_here_multiplatform
 
-p_end:	.llong	_end - _stext
-
 /*
  * Copy routine used to copy the kernel to start at physical address 0
  * and flush and invalidate the caches as needed.
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index ea1ba89..3857d7e 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -458,6 +458,42 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 	spin_unlock_irqrestore(&(tbl->it_lock), flags);
 }
 
+static void iommu_table_clear(struct iommu_table *tbl)
+{
+	if (!__kdump_flag) {
+		/* Clear the table in case firmware left allocations in it */
+		ppc_md.tce_free(tbl, tbl->it_offset, tbl->it_size);
+		return;
+	}
+
+#ifdef CONFIG_CRASH_DUMP
+	if (ppc_md.tce_get) {
+		unsigned long index, tceval, tcecount = 0;
+
+		/* Reserve the existing mappings left by the first kernel. */
+		for (index = 0; index < tbl->it_size; index++) {
+			tceval = ppc_md.tce_get(tbl, index + tbl->it_offset);
+			/*
+			 * Freed TCE entry contains 0x7fffffffffffffff on JS20
+			 */
+			if (tceval && (tceval != 0x7fffffffffffffffUL)) {
+				__set_bit(index, tbl->it_map);
+				tcecount++;
+			}
+		}
+
+		if ((tbl->it_size - tcecount) < KDUMP_MIN_TCE_ENTRIES) {
+			printk(KERN_WARNING "TCE table is full; freeing ");
+			printk(KERN_WARNING "%d entries for the kdump boot\n",
+				KDUMP_MIN_TCE_ENTRIES);
+			for (index = tbl->it_size - KDUMP_MIN_TCE_ENTRIES;
+				index < tbl->it_size; index++)
+				__clear_bit(index, tbl->it_map);
+		}
+	}
+#endif
+}
+
 /*
  * Build a iommu_table structure.  This contains a bit map which
  * is used to manage allocation of the tce space.
@@ -484,38 +520,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
 	tbl->it_largehint = tbl->it_halfpoint;
 	spin_lock_init(&tbl->it_lock);
 
-#ifdef CONFIG_CRASH_DUMP
-	if (ppc_md.tce_get) {
-		unsigned long index;
-		unsigned long tceval;
-		unsigned long tcecount = 0;
-
-		/*
-		 * Reserve the existing mappings left by the first kernel.
-		 */
-		for (index = 0; index < tbl->it_size; index++) {
-			tceval = ppc_md.tce_get(tbl, index + tbl->it_offset);
-			/*
-			 * Freed TCE entry contains 0x7fffffffffffffff on JS20
-			 */
-			if (tceval && (tceval != 0x7fffffffffffffffUL)) {
-				__set_bit(index, tbl->it_map);
-				tcecount++;
-			}
-		}
-		if ((tbl->it_size - tcecount) < KDUMP_MIN_TCE_ENTRIES) {
-			printk(KERN_WARNING "TCE table is full; ");
-			printk(KERN_WARNING "freeing %d entries for the kdump boot\n",
-				KDUMP_MIN_TCE_ENTRIES);
-			for (index = tbl->it_size - KDUMP_MIN_TCE_ENTRIES;
-				index < tbl->it_size; index++)
-				__clear_bit(index, tbl->it_map);
-		}
-	}
-#else
-	/* Clear the hardware table in case firmware left allocations in it */
-	ppc_md.tce_free(tbl, tbl->it_offset, tbl->it_size);
-#endif
+	iommu_table_clear(tbl);
 
 	if (!welcomed) {
 		printk(KERN_INFO "IOMMU table initialized, virtual merging %s\n",
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index aab7688..ac2a21f 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -88,11 +88,13 @@ void __init reserve_crashkernel(void)
 
 	crash_size = crashk_res.end - crashk_res.start + 1;
 
+#ifndef CONFIG_RELOCATABLE
 	if (crashk_res.start != KDUMP_KERNELBASE)
 		printk("Crash kernel location must be 0x%x\n",
 				KDUMP_KERNELBASE);
 
 	crashk_res.start = KDUMP_KERNELBASE;
+#endif
 	crash_size = PAGE_ALIGN(crash_size);
 	crashk_res.end = crashk_res.start + crash_size - 1;
 
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index 4bd8b4f..e6efec7 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -255,11 +255,14 @@ static union thread_union kexec_stack
 /* Our assembly helper, in kexec_stub.S */
 extern NORET_TYPE void kexec_sequence(void *newstack, unsigned long start,
 					void *image, void *control,
-					void (*clear_all)(void)) ATTRIB_NORET;
+					void (*clear_all)(void),
+					unsigned long kdump_flag) ATTRIB_NORET;
 
 /* too late to fail here */
 void default_machine_kexec(struct kimage *image)
 {
+	unsigned long kdump_flag = 0;
+
 	/* prepare control code if any */
 
 	/*
@@ -270,8 +273,10 @@ void default_machine_kexec(struct kimage *image)
         * using debugger IPI.
         */
 
-       if (crashing_cpu == -1)
-               kexec_prepare_cpus();
+	if (crashing_cpu == -1)
+		kexec_prepare_cpus();
+	else
+		kdump_flag = KDUMP_SIGNATURE;
 
 	/* switch to a staticly allocated stack.  Based on irq stack code.
 	 * XXX: the task struct will likely be invalid once we do the copy!
@@ -284,7 +289,7 @@ void default_machine_kexec(struct kimage *image)
 	 */
 	kexec_sequence(&kexec_stack, image->start, image,
 			page_address(image->control_code_page),
-			ppc_md.hpte_clear_all);
+			ppc_md.hpte_clear_all, kdump_flag);
 	/* NOTREACHED */
 }
 
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 3053fe5..a243fd0 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -611,10 +611,12 @@ real_mode:	/* assume normal blr return */
 
 
 /*
- * kexec_sequence(newstack, start, image, control, clear_all())
+ * kexec_sequence(newstack, start, image, control, clear_all(), kdump_flag)
  *
  * does the grungy work with stack switching and real mode switches
  * also does simple calls to other code
+ *
+ * kdump_flag says whether the next kernel should be a kdump kernel.
  */
 
 _GLOBAL(kexec_sequence)
@@ -647,7 +649,7 @@ _GLOBAL(kexec_sequence)
 	mr	r29,r5			/* image (virt) */
 	mr	r28,r6			/* control, unused */
 	mr	r27,r7			/* clear_all() fn desc */
-	mr	r26,r8			/* spare */
+	mr	r26,r8			/* kdump flag */
 	lhz	r25,PACAHWCPUID(r13)	/* get our phys cpu from paca */
 
 	/* disable interrupts, we are overwriting kernel data next */
@@ -709,5 +711,6 @@ _GLOBAL(kexec_sequence)
 	mr	r4,r30	# start, aka phys mem offset
 	mtlr	4
 	li	r5,0
-	blr	/* image->start(physid, image->start, 0); */
+	mr	r6,r26			/* kdump_flag */
+	blr	/* image->start(physid, image->start, 0, kdump_flag); */
 #endif /* CONFIG_KEXEC */
diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
index 2a14b05..665af1c 100644
--- a/arch/powerpc/platforms/cell/ras.c
+++ b/arch/powerpc/platforms/cell/ras.c
@@ -21,6 +21,7 @@
 #include <asm/machdep.h>
 #include <asm/rtas.h>
 #include <asm/cell-regs.h>
+#include <asm/kdump.h>
 
 #include "ras.h"
 
@@ -111,9 +112,8 @@ static int __init cbe_ptcal_enable_on_node(int nid, int order)
 	int ret = -ENOMEM;
 	unsigned long addr;
 
-#ifdef CONFIG_CRASH_DUMP
-	rtas_call(ptcal_stop_tok, 1, 1, NULL, nid);
-#endif
+	if (__kdump_flag)
+		rtas_call(ptcal_stop_tok, 1, 1, NULL, nid);
 
 	area = kmalloc(sizeof(*area), GFP_KERNEL);
 	if (!area)
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index a8c4466..d56491d 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -44,6 +44,7 @@
 #include <asm/tce.h>
 #include <asm/ppc-pci.h>
 #include <asm/udbg.h>
+#include <asm/kdump.h>
 
 #include "plpar_wrappers.h"
 
@@ -291,9 +292,8 @@ static void iommu_table_setparms(struct pci_controller *phb,
 
 	tbl->it_base = (unsigned long)__va(*basep);
 
-#ifndef CONFIG_CRASH_DUMP
-	memset((void *)tbl->it_base, 0, *sizep);
-#endif
+	if (!__kdump_flag)
+		memset((void *)tbl->it_base, 0, *sizep);
 
 	tbl->it_busno = phb->bus->number;
 
-- 
1.5.5

Re: [PATCH] Support for relocatable kdump kernel

[Mohan Kumar M]

Michael Ellerman wrote:

> Does it? I see CONFIG_CRASH_DUMP depending on PPC64, so there is no
> 32-bit kdump possible. Or is someone working on it out-of-tree?
> 

IIUC Anton Vorontsov is working on the 32-bit kdump kernel support.

>> Do you expect a function to do the checking in iommu.c?
> 
> You'd use the function in iommu.c, but it should be defined in some
> header.
> 
Yeah, I will do that.

> OK. Does old purgatory ensure that the register is 0? Otherwise I think
> it's possible that a new kernel could get confused by cruft left in that
> register by an old purgatory - causing the 2nd kernel to think it's a
> kdump kernel when it shouldn't be.

__kdump_flag is by default is 0 and old purgatory code even won't know 
that it need to modify __kdump_flag. So unless __kdump_flag is 1, the 
kernel will behave as a normal one.

Regards,
Mohan.

Re: [PATCH] Support for relocatable kdump kernel

[Michael Ellerman]

[-- Attachment #1: Type: text/plain, Size: 4568 bytes --]

On Mon, 2008-10-20 at 15:04 +0530, Mohan Kumar M wrote:
> Michael Ellerman wrote:
> >>>  #ifdef CONFIG_CRASH_DUMP
> >>> +#ifdef CONFIG_RELOCATABLE
> >>> +
> >>> +static inline void reserve_kdump_trampoline(void) { ; }
> >>> +static inline void setup_kdump_trampoline(void) { ; }
> >>> +
> >>> +#else
> >>>  
> >>>  extern void reserve_kdump_trampoline(void);
> >>>  extern void setup_kdump_trampoline(void);
> >>>  
> >>> +#endif /* CONFIG_RELOCATABLE */
> > 
> > You've disabled the else case with your Kconfig changes, so you should
> > just rip all that code out.
> 
> I made Kconfig changes only to the 64 bit powerpc path and still the 32 
> bit powerpc code uses the legacy kdump code. So we need to retain some 
> of legacy kdump code.

Does it? I see CONFIG_CRASH_DUMP depending on PPC64, so there is no
32-bit kdump possible. Or is someone working on it out-of-tree?

> >>> diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
> >>> index e409338..5b12b10 100644
> >>> --- a/arch/powerpc/kernel/head_64.S
> >>> +++ b/arch/powerpc/kernel/head_64.S
> >>> @@ -97,6 +97,14 @@ __secondary_hold_spinloop:
> >>>  __secondary_hold_acknowledge:
> >>>  	.llong	0x0
> >>>  
> >>> +	/* This flag is set only for kdump kernels so that */
> >>> +	/* it will be relocatable. Purgatory code user space kexec-tools */
> >>> +	/* sets this flag. Do not move this variable as purgatory code */
> >>> +	/* relies on the position of this variables */
> >>> +	.globl	__kdump_flag
> >>> +__kdump_flag:
> >>> +	.llong	0x0
> > 
> > I guess the __ matches the other flags here, it's not the prettiest
> > though. For client code (like in iommu.c) it'd be nice to have static
> > inline, perhaps is_kdump_kernel() that hides this.
> > 
> Do you expect a function to do the checking in iommu.c?

You'd use the function in iommu.c, but it should be defined in some
header.

> >>>  #ifdef CONFIG_PPC_ISERIES
> >>>  	/*
> >>>  	 * At offset 0x20, there is a pointer to iSeries LPAR data.
> >>> @@ -1384,8 +1392,13 @@ _STATIC(__after_prom_start)
> >>>  	/* process relocations for the final address of the kernel */
> >>>  	lis	r25,PAGE_OFFSET@highest	/* compute virtual base of kernel */
> >>>  	sldi	r25,r25,32
> >>> +#ifdef CONFIG_CRASH_DUMP
> >>> +	ld	r7,__kdump_flag-_stext(r26)
> >>> +	cmpldi	cr0,r7,1	/* relocatable kernel ? */
> > 
> > You don't use the signature here?
> 
> kexec-tools check the signature and based on the signature it sets 
> __kdump_flag to 1 (or 0). So kernel code just checks whether its set or not.

OK. Does old purgatory ensure that the register is 0? Otherwise I think
it's possible that a new kernel could get confused by cruft left in that
register by an old purgatory - causing the 2nd kernel to think it's a
kdump kernel when it shouldn't be.

> >>> @@ -1401,9 +1414,21 @@ _STATIC(__after_prom_start)
> >>>  	beq	9f			/* have already put us at zero */
> >>>  	li	r6,0x100		/* Start offset, the first 0x100 */
> >>>  					/* bytes were copied earlier.	 */
> >>> -#ifdef CONFIG_RELOCATABLE
> >>> +
> >>> +#ifdef CONFIG_CRASH_DUMP
> >>> +/*
> >>> + * Check if the kernel has to be running as relocatable kernel based on the
> >>> + * variable __kdump_flag, if it is set the kernel is treated as relocatble
> >>> + * kernel, otherwise it will be moved to PHYSICAL_START
> >>> + */
> >>> +	ld	r7,__kdump_flag-_stext(r26)
> >>> +	cmpldi	cr0,r7,1
> >>> +	bne	regular
> >>> +
> >>>  	li	r5,__end_interrupts - _stext	/* just copy interrupts */
> >>> -#else
> >>> +	b	5f
> >>> +regular:
> >>> +#endif
> >>>  	lis	r5,(copy_to_here - _stext)@ha
> >>>  	addi	r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */
> > 
> > I'm jet lagged to hell, so I'm not sure I can trust my parsing of this.
> > But I think this definitely breaks CONFIG_RELOCATABLE without
> > CRASH_DUMP, and I'm not sure it's right otherwise.
> >
> Hmmm, I compiled and tried the kernel with 3 config option combinations: 
> 1. CONFIG_RELOCATABLE and CONFIG_CRASH_DUMP 2. CONFIG_RELOCATABLE 3. 
> Without CONFIG_RELOCATABLE (without CONFIG_CRASH_DUMP)
> 
> All of the above 3 combinations worked. This patch relies on Pauls' 
> patch5 in the relocatable kernel patcheset.

OK if you've tested.

cheers

-- 
Michael Ellerman
OzLabs, IBM Australia Development Lab

wwweb: http://michael.ellerman.id.au
phone: +61 2 6212 1183 (tie line 70 21183)

We do not inherit the earth from our ancestors,
we borrow it from our children. - S.M.A.R.T Person

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 189 bytes --]

Re: [PATCH] Support for relocatable kdump kernel

[Mohan Kumar M]

Michael Ellerman wrote:
>>> -------- Forwarded Message --------
>>> The purgatory code compares the signature and sets the __kdump_flag in
>>> head_64.S.  During the boot up, kernel code checks __kdump_flag and if it
>>> is set, the kernel will behave as relocatable kdump kernel. This kernel
>>> will boot at the address where it was loaded by kexec-tools ie at the
>>> address reserved through crashkernel boot parameter
>>>
>>> CONFIG_CRASH_DUMP depends on CONFIG_RELOCATABLE option to build kdump
>>> kernel as relocatable. So the same kernel can be used as production and
>>> kdump kernel.
> 
> Those two statements aren't really related. A CONFIG_RELOCATABLE kernel
> can be used as both a kdump and a normal kernel, and we need to make
> sure that a CONFIG_CRASH_DUMP kernel can be used as both - ie. that
> there's no code that uses CONFIG_CRASH_DUMP to do anything we /don't/
> want in a normal kernel.
> 
Hi Mike,

Thank you very much for the detailed review.

For 64 bit powerpc, we are going to support only relocatable kdump 
kernel (as per Paulus' suggestions). To enable CRASH_DUMP one needs 
CONFIG_RELOCATABLE to be enabled first.

>>>  #ifdef CONFIG_CRASH_DUMP
>>> +#ifdef CONFIG_RELOCATABLE
>>> +
>>> +static inline void reserve_kdump_trampoline(void) { ; }
>>> +static inline void setup_kdump_trampoline(void) { ; }
>>> +
>>> +#else
>>>  
>>>  extern void reserve_kdump_trampoline(void);
>>>  extern void setup_kdump_trampoline(void);
>>>  
>>> +#endif /* CONFIG_RELOCATABLE */
> 
> You've disabled the else case with your Kconfig changes, so you should
> just rip all that code out.

I made Kconfig changes only to the 64 bit powerpc path and still the 32 
bit powerpc code uses the legacy kdump code. So we need to retain some 
of legacy kdump code.

> 
>>>  static inline void reserve_kdump_trampoline(void) { ; }
>>> diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
>>> index a323c9b..eaf9d6d 100644
>>> --- a/arch/powerpc/kernel/crash_dump.c
>>> +++ b/arch/powerpc/kernel/crash_dump.c
>>> @@ -27,6 +27,7 @@
>>>  #define DBG(fmt...)
>>>  #endif
>>>  
>>> +#ifndef CONFIG_RELOCATABLE
>>>  void __init reserve_kdump_trampoline(void)
>>>  {
>>>  	lmb_reserve(0, KDUMP_RESERVE_LIMIT);
>>> @@ -65,6 +66,7 @@ void __init setup_kdump_trampoline(void)
>>>  
>>>  	DBG(" <- setup_kdump_trampoline()\n");
>>>  }
>>> +#endif /* CONFIG_RELOCATABLE */
>>>  
>>>  #ifdef CONFIG_PROC_VMCORE
>>>  static int __init parse_elfcorehdr(char *p)
>>> diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
>>> index e409338..5b12b10 100644
>>> --- a/arch/powerpc/kernel/head_64.S
>>> +++ b/arch/powerpc/kernel/head_64.S
>>> @@ -97,6 +97,14 @@ __secondary_hold_spinloop:
>>>  __secondary_hold_acknowledge:
>>>  	.llong	0x0
>>>  
>>> +	/* This flag is set only for kdump kernels so that */
>>> +	/* it will be relocatable. Purgatory code user space kexec-tools */
>>> +	/* sets this flag. Do not move this variable as purgatory code */
>>> +	/* relies on the position of this variables */
>>> +	.globl	__kdump_flag
>>> +__kdump_flag:
>>> +	.llong	0x0
> 
> I guess the __ matches the other flags here, it's not the prettiest
> though. For client code (like in iommu.c) it'd be nice to have static
> inline, perhaps is_kdump_kernel() that hides this.
> 
Do you expect a function to do the checking in iommu.c?

>>>  #ifdef CONFIG_PPC_ISERIES
>>>  	/*
>>>  	 * At offset 0x20, there is a pointer to iSeries LPAR data.
>>> @@ -1384,8 +1392,13 @@ _STATIC(__after_prom_start)
>>>  	/* process relocations for the final address of the kernel */
>>>  	lis	r25,PAGE_OFFSET@highest	/* compute virtual base of kernel */
>>>  	sldi	r25,r25,32
>>> +#ifdef CONFIG_CRASH_DUMP
>>> +	ld	r7,__kdump_flag-_stext(r26)
>>> +	cmpldi	cr0,r7,1	/* relocatable kernel ? */
> 
> You don't use the signature here?

kexec-tools check the signature and based on the signature it sets 
__kdump_flag to 1 (or 0). So kernel code just checks whether its set or not.

> 
>>> +	bne	1f
>>>  	add	r25,r25,r26
>>> -	mr	r3,r25
>>> +#endif
>>> +1:	mr	r3,r25
>>>  	bl	.relocate
>>>  #endif
>>>  
>>> @@ -1401,9 +1414,21 @@ _STATIC(__after_prom_start)
>>>  	beq	9f			/* have already put us at zero */
>>>  	li	r6,0x100		/* Start offset, the first 0x100 */
>>>  					/* bytes were copied earlier.	 */
>>> -#ifdef CONFIG_RELOCATABLE
>>> +
>>> +#ifdef CONFIG_CRASH_DUMP
>>> +/*
>>> + * Check if the kernel has to be running as relocatable kernel based on the
>>> + * variable __kdump_flag, if it is set the kernel is treated as relocatble
>>> + * kernel, otherwise it will be moved to PHYSICAL_START
>>> + */
>>> +	ld	r7,__kdump_flag-_stext(r26)
>>> +	cmpldi	cr0,r7,1
>>> +	bne	regular
>>> +
>>>  	li	r5,__end_interrupts - _stext	/* just copy interrupts */
>>> -#else
>>> +	b	5f
>>> +regular:
>>> +#endif
>>>  	lis	r5,(copy_to_here - _stext)@ha
>>>  	addi	r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */
> 
> I'm jet lagged to hell, so I'm not sure I can trust my parsing of this.
> But I think this definitely breaks CONFIG_RELOCATABLE without
> CRASH_DUMP, and I'm not sure it's right otherwise.
>
Hmmm, I compiled and tried the kernel with 3 config option combinations: 
1. CONFIG_RELOCATABLE and CONFIG_CRASH_DUMP 2. CONFIG_RELOCATABLE 3. 
Without CONFIG_RELOCATABLE (without CONFIG_CRASH_DUMP)

All of the above 3 combinations worked. This patch relies on Pauls' 
patch5 in the relocatable kernel patcheset.

Regards,
Mohan.

Re: [PATCH] Support for relocatable kdump kernel

[Michael Ellerman]

[-- Attachment #1: Type: text/plain, Size: 13832 bytes --]

> > -------- Forwarded Message --------
> > From: Mohan Kumar M <mohan@in.ibm.com>
> > To: paulus@samba.org
> > Cc: linuxppc-dev@ozlabs.org, kexec@lists.infradead.org
> > Subject: [PATCH] Support for relocatable kdump kernel
> > Date: Mon, 13 Oct 2008 05:04:20 +0530
> > 
> > Support for relocatable kdump kernel
> > 
> > This patch adds relocatable kernel support for kdump. With this one can
> > use the same regular kernel to capture the kdump. A signature (0xfeed1234)
> > is passed in r8 from panic code to the next kernel through kexec_sequence
> > and purgatory code. The signature is used to differentiate between
> > relocatable kdump kernel and non-kdump kernels.

You should put a big fat warning here in the changelog. By changing the
calling sequence (adding to it), we now require that for a new kernel to
work as a kdump kernel it has to be loaded with new kexec tools.

> > The purgatory code compares the signature and sets the __kdump_flag in
> > head_64.S.  During the boot up, kernel code checks __kdump_flag and if it
> > is set, the kernel will behave as relocatable kdump kernel. This kernel
> > will boot at the address where it was loaded by kexec-tools ie at the
> > address reserved through crashkernel boot parameter
> > 
> > CONFIG_CRASH_DUMP depends on CONFIG_RELOCATABLE option to build kdump
> > kernel as relocatable. So the same kernel can be used as production and
> > kdump kernel.

Those two statements aren't really related. A CONFIG_RELOCATABLE kernel
can be used as both a kdump and a normal kernel, and we need to make
sure that a CONFIG_CRASH_DUMP kernel can be used as both - ie. that
there's no code that uses CONFIG_CRASH_DUMP to do anything we /don't/
want in a normal kernel.

> > This patch incorporates the changes suggested by Paul Mackerrass to avoid
> > GOT use and to avoid two copies of the code.
> > 
> > Signed-off-by: Mohan Kumar M <mohan@in.ibm.com>

> > diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt
> > index 0705040..3f4bc84 100644
> > --- a/Documentation/kdump/kdump.txt
> > +++ b/Documentation/kdump/kdump.txt
> > @@ -109,7 +109,8 @@ There are two possible methods of using Kdump.
> >  2) Or use the system kernel binary itself as dump-capture kernel and there is
> >     no need to build a separate dump-capture kernel. This is possible
> >     only with the architecutres which support a relocatable kernel. As
> > -   of today, i386, x86_64 and ia64 architectures support relocatable kernel.
> > +   of today, i386, x86_64, ppc64 and ia64 architectures support relocatable
> > +   kernel.

This is a little bit unclear as the kernel now doesn't have a ppc64
architecture. You might want to say "64-bit powerpc (ppc64)", because
that matches the kernel arch and also kexec-tools (which still has
ppc32/64 IIRC)

> >  
> >  Building a relocatable kernel is advantageous from the point of view that
> >  one does not have to build a second kernel for capturing the dump. But
> > @@ -207,8 +208,15 @@ Dump-capture kernel config options (Arch Dependent, i386 and x86_64)
> >  Dump-capture kernel config options (Arch Dependent, ppc64)
> >  ----------------------------------------------------------
> >  
> > -*  Make and install the kernel and its modules. DO NOT add this kernel
> > -   to the boot loader configuration files.
> > +1) Enable "Build a kdump crash kernel" support under "Kernel" options:
> > +
> > +   CONFIG_CRASH_DUMP=y
> > +
> > +2)   Enable "Build a relocatable kernel" support
> > +
> > +   CONFIG_RELOCATABLE=y
> > +
> > +   Make and install the kernel and its modules.
> >  
> >  Dump-capture kernel config options (Arch Dependent, ia64)
> >  ----------------------------------------------------------
> > diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
> > index 17c988b..6b3e840 100644
> > --- a/arch/powerpc/Kconfig
> > +++ b/arch/powerpc/Kconfig
> > @@ -321,11 +321,11 @@ config KEXEC
> >  
> >  config CRASH_DUMP
> >  	bool "Build a kdump crash kernel"
> > -	depends on PPC_MULTIPLATFORM && PPC64
> > +	depends on PPC_MULTIPLATFORM && PPC64 && RELOCATABLE
> >  	help
> >  	  Build a kernel suitable for use as a kdump capture kernel.
> > -	  The kernel will be linked at a different address than normal, and
> > -	  so can only be used for Kdump.
> > +	  The same kernel binary can be used as production kernel and dump capture
> > +	  kernel
> >  
> >  	  Don't change this unless you know what you are doing.
> >  
> > @@ -824,11 +824,9 @@ config PAGE_OFFSET
> >  	default "0xc000000000000000"
> >  config KERNEL_START
> >  	hex
> > -	default "0xc000000002000000" if CRASH_DUMP
> >  	default "0xc000000000000000"
> >  config PHYSICAL_START
> >  	hex
> > -	default "0x02000000" if CRASH_DUMP
> >  	default "0x00000000"
> >  endif
> >  
> > diff --git a/arch/powerpc/include/asm/kdump.h b/arch/powerpc/include/asm/kdump.h
> > index f6c93c7..5308754 100644
> > --- a/arch/powerpc/include/asm/kdump.h
> > +++ b/arch/powerpc/include/asm/kdump.h
> > @@ -9,6 +9,12 @@
> >   * Reserve to the end of the FWNMI area, see head_64.S */
> >  #define KDUMP_RESERVE_LIMIT	0x10000 /* 64K */
> >  
> > +/*
> > + * Used to differentiate between relocatable kdump kernel and other
> > + * kernels
> > + */
> > +#define KDUMP_SIGNATURE	0xfeed1234
> > +
> >  #ifdef CONFIG_CRASH_DUMP
> >  
> >  #define KDUMP_TRAMPOLINE_START	0x0100
> > @@ -19,11 +25,21 @@
> >  #endif /* CONFIG_CRASH_DUMP */
> >  
> >  #ifndef __ASSEMBLY__
> > +
> > +extern unsigned long long __kdump_flag;

Why long long ?

> >  #ifdef CONFIG_CRASH_DUMP
> > +#ifdef CONFIG_RELOCATABLE
> > +
> > +static inline void reserve_kdump_trampoline(void) { ; }
> > +static inline void setup_kdump_trampoline(void) { ; }
> > +
> > +#else
> >  
> >  extern void reserve_kdump_trampoline(void);
> >  extern void setup_kdump_trampoline(void);
> >  
> > +#endif /* CONFIG_RELOCATABLE */

You've disabled the else case with your Kconfig changes, so you should
just rip all that code out.

> >  static inline void reserve_kdump_trampoline(void) { ; }
> > diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
> > index a323c9b..eaf9d6d 100644
> > --- a/arch/powerpc/kernel/crash_dump.c
> > +++ b/arch/powerpc/kernel/crash_dump.c
> > @@ -27,6 +27,7 @@
> >  #define DBG(fmt...)
> >  #endif
> >  
> > +#ifndef CONFIG_RELOCATABLE
> >  void __init reserve_kdump_trampoline(void)
> >  {
> >  	lmb_reserve(0, KDUMP_RESERVE_LIMIT);
> > @@ -65,6 +66,7 @@ void __init setup_kdump_trampoline(void)
> >  
> >  	DBG(" <- setup_kdump_trampoline()\n");
> >  }
> > +#endif /* CONFIG_RELOCATABLE */
> >  
> >  #ifdef CONFIG_PROC_VMCORE
> >  static int __init parse_elfcorehdr(char *p)
> > diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
> > index e409338..5b12b10 100644
> > --- a/arch/powerpc/kernel/head_64.S
> > +++ b/arch/powerpc/kernel/head_64.S
> > @@ -97,6 +97,14 @@ __secondary_hold_spinloop:
> >  __secondary_hold_acknowledge:
> >  	.llong	0x0
> >  
> > +	/* This flag is set only for kdump kernels so that */
> > +	/* it will be relocatable. Purgatory code user space kexec-tools */
> > +	/* sets this flag. Do not move this variable as purgatory code */
> > +	/* relies on the position of this variables */
> > +	.globl	__kdump_flag
> > +__kdump_flag:
> > +	.llong	0x0

I guess the __ matches the other flags here, it's not the prettiest
though. For client code (like in iommu.c) it'd be nice to have static
inline, perhaps is_kdump_kernel() that hides this.

> >  #ifdef CONFIG_PPC_ISERIES
> >  	/*
> >  	 * At offset 0x20, there is a pointer to iSeries LPAR data.
> > @@ -1384,8 +1392,13 @@ _STATIC(__after_prom_start)
> >  	/* process relocations for the final address of the kernel */
> >  	lis	r25,PAGE_OFFSET@highest	/* compute virtual base of kernel */
> >  	sldi	r25,r25,32
> > +#ifdef CONFIG_CRASH_DUMP
> > +	ld	r7,__kdump_flag-_stext(r26)
> > +	cmpldi	cr0,r7,1	/* relocatable kernel ? */

You don't use the signature here?

> > +	bne	1f
> >  	add	r25,r25,r26
> > -	mr	r3,r25
> > +#endif
> > +1:	mr	r3,r25
> >  	bl	.relocate
> >  #endif
> >  
> > @@ -1401,9 +1414,21 @@ _STATIC(__after_prom_start)
> >  	beq	9f			/* have already put us at zero */
> >  	li	r6,0x100		/* Start offset, the first 0x100 */
> >  					/* bytes were copied earlier.	 */
> > -#ifdef CONFIG_RELOCATABLE
> > +
> > +#ifdef CONFIG_CRASH_DUMP
> > +/*
> > + * Check if the kernel has to be running as relocatable kernel based on the
> > + * variable __kdump_flag, if it is set the kernel is treated as relocatble
> > + * kernel, otherwise it will be moved to PHYSICAL_START
> > + */
> > +	ld	r7,__kdump_flag-_stext(r26)
> > +	cmpldi	cr0,r7,1
> > +	bne	regular
> > +
> >  	li	r5,__end_interrupts - _stext	/* just copy interrupts */
> > -#else
> > +	b	5f
> > +regular:
> > +#endif
> >  	lis	r5,(copy_to_here - _stext)@ha
> >  	addi	r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */

I'm jet lagged to hell, so I'm not sure I can trust my parsing of this.
But I think this definitely breaks CONFIG_RELOCATABLE without
CRASH_DUMP, and I'm not sure it's right otherwise.

> > @@ -1420,8 +1445,7 @@ p_end:	.llong	_end - _stext
> >  4:	/* Now copy the rest of the kernel up to _end */
> >  	addis	r5,r26,(p_end - _stext)@ha
> >  	ld	r5,(p_end - _stext)@l(r5)	/* get _end */
> > -#endif
> > -	bl	.copy_and_flush		/* copy the rest */
> > +5:	bl	.copy_and_flush		/* copy the rest */
> >  
> >  9:	b	.start_here_multiplatform
> >  
> > diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
> > index 550a193..24f7797 100644
> > --- a/arch/powerpc/kernel/iommu.c
> > +++ b/arch/powerpc/kernel/iommu.c
> > @@ -494,7 +494,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
> >  	spin_lock_init(&tbl->it_lock);
> >  
> >  #ifdef CONFIG_CRASH_DUMP
> > -	if (ppc_md.tce_get) {
> > +	if (ppc_md.tce_get && __kdump_flag) {
> >  		unsigned long index;
> >  		unsigned long tceval;
> >  		unsigned long tcecount = 0;


I see more code that needs this sort of treatment in pseries/iommu.c and
cell/ras.c

> > diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
> > index aab7688..ac2a21f 100644
> > --- a/arch/powerpc/kernel/machine_kexec.c
> > +++ b/arch/powerpc/kernel/machine_kexec.c
> > @@ -88,11 +88,13 @@ void __init reserve_crashkernel(void)
> >  
> >  	crash_size = crashk_res.end - crashk_res.start + 1;
> >  
> > +#ifndef CONFIG_RELOCATABLE
> >  	if (crashk_res.start != KDUMP_KERNELBASE)
> >  		printk("Crash kernel location must be 0x%x\n",
> >  				KDUMP_KERNELBASE);

We still need code here for the RELOCATABLE case that checks a) the
kernel is being allocated inside the RMO, and b) that it's 64k aligned.

> >  
> >  	crashk_res.start = KDUMP_KERNELBASE;
> > +#endif
> >  	crash_size = PAGE_ALIGN(crash_size);
> >  	crashk_res.end = crashk_res.start + crash_size - 1;
> >  
> > diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
> > index a168514..6a45a9e 100644
> > --- a/arch/powerpc/kernel/machine_kexec_64.c
> > +++ b/arch/powerpc/kernel/machine_kexec_64.c
> > @@ -255,11 +255,13 @@ static union thread_union kexec_stack
> >  /* Our assembly helper, in kexec_stub.S */
> >  extern NORET_TYPE void kexec_sequence(void *newstack, unsigned long start,
> >  					void *image, void *control,
> > -					void (*clear_all)(void)) ATTRIB_NORET;
> > +					void (*clear_all)(void),
> > +				unsigned long long kdump_flag) ATTRIB_NORET;
> >  
> >  /* too late to fail here */
> >  void default_machine_kexec(struct kimage *image)
> >  {
> > +	unsigned long long kdump_flag = 0;
> >  	/* prepare control code if any */
> >  
> >  	/*
> > @@ -270,8 +272,10 @@ void default_machine_kexec(struct kimage *image)
> >          * using debugger IPI.
> >          */
> >  
> > -       if (crashing_cpu == -1)
> > -               kexec_prepare_cpus();
> > +	if (crashing_cpu == -1)
> > +		kexec_prepare_cpus();
> > +	else
> > +		kdump_flag = KDUMP_SIGNATURE;
> >  
> >  	/* switch to a staticly allocated stack.  Based on irq stack code.
> >  	 * XXX: the task struct will likely be invalid once we do the copy!
> > @@ -284,7 +288,7 @@ void default_machine_kexec(struct kimage *image)
> >  	 */
> >  	kexec_sequence(&kexec_stack, image->start, image,
> >  			page_address(image->control_code_page),
> > -			ppc_md.hpte_clear_all);
> > +			ppc_md.hpte_clear_all, kdump_flag);
> >  	/* NOTREACHED */
> >  }
> >  
> > diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
> > index 4dd70cf..c93e5f7 100644
> > --- a/arch/powerpc/kernel/misc_64.S
> > +++ b/arch/powerpc/kernel/misc_64.S
> > @@ -609,10 +609,13 @@ real_mode:	/* assume normal blr return */
> >  
> > 
> >  /*
> > - * kexec_sequence(newstack, start, image, control, clear_all())
> > + * kexec_sequence(newstack, start, image, control, clear_all(), kdump_flag)
> >   *
> >   * does the grungy work with stack switching and real mode switches
> >   * also does simple calls to other code
> > + *
> > + * kdump_flag says whether the next kernel should be running at the reserved
> > + * load address as needed for relocatable kdump kernel
> >   */

Doesn't it just say "we crashed in the first kernel" - what the 2nd
kernel does is up to it.

cheers

-- 
Michael Ellerman
OzLabs, IBM Australia Development Lab

wwweb: http://michael.ellerman.id.au
phone: +61 2 6212 1183 (tie line 70 21183)

We do not inherit the earth from our ancestors,
we borrow it from our children. - S.M.A.R.T Person

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 189 bytes --]

Re: [PATCH] Support for relocatable kdump kernel

[Mohan Kumar M]

Hi Paul,

Thank you for the review. I will implement the changes you suggested and 
send the patches.

Regards,
Mohan.

> Mohan Kumar M writes:
> 
>> Support for relocatable kdump kernel
> 
> [snip]
> 
>> @@ -1384,7 +1392,15 @@ _STATIC(__after_prom_start)
>>  	/* process relocations for the final address of the kernel */
>>  	lis	r25,PAGE_OFFSET@highest	/* compute virtual base of kernel */
>>  	sldi	r25,r25,32
>> -	mr	r3,r25
>> +#ifdef CONFIG_CRASH_DUMP
>> +	ld	r7,__kdump_flag@got(r2)
>> +	add	r7,r7,r26
>> +	ld	r7,0(r7)
> 
> I think it is dangerous to use an address from the GOT at this point
> when we haven't called relocate() yet.  In fact those 3 instructions
> can be replaced by one:
> 
> 	ld	r7,__kdump_flag-_stext(r26)
> 
> since we have our base address (i.e. the address of _stext) in r26 at
> this point.
> 
>> +#ifdef CONFIG_RELOCATABLE
>> +#ifdef CONFIG_CRASH_DUMP
>> +/*
>> + * Check if the kernel has to be running as relocatable kernel based on the
>> + * variable __kdump_flag, if it is set the kernel is treated as relocatble
>> + * kernel, otherwise it will be moved to PHYSICAL_START
>> + */
>> +	ld	r7,__kdump_flag@got(r2)
>> +	ld	r7,0(r7)
> 
> Here again I would rather you did
> 
> 	ld	r7,__kdump_flag-_stext(r26)
> 
> since the kernel is relocated for its final location by this point,
> but it is not running at the final location yet.
> 
>> +	cmpldi	cr0,r7,1
>> +	bne	regular
>> +
>> +	li	r5,__end_interrupts - _stext	/* just copy interrupts */
>> +	b	5f
>> +regular:
>> +#endif
>> +	lis	r5,(copy_to_here - _stext)@ha
>> +	addi	r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */
>>  
>>  	bl	.copy_and_flush		/* copy the first n bytes	 */
>>  					/* this includes the code being	 */
>> @@ -1411,15 +1443,33 @@ _STATIC(__after_prom_start)
>>  	mtctr	r8
>>  	bctr
>>  
>> +p_end:	.llong	_end - _stext
>> +
>>  4:	/* Now copy the rest of the kernel up to _end */
>>  	addis	r5,r26,(p_end - _stext)@ha
>>  	ld	r5,(p_end - _stext)@l(r5)	/* get _end */
>> -	bl	.copy_and_flush		/* copy the rest */
>> +#else
>> +	lis	r5,(copy_to_here - _stext)@ha
>> +	addi	r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */
>>  
>> -9:	b	.start_here_multiplatform
>> +	bl	.copy_and_flush		/* copy the first n bytes	 */
>> +					/* this includes the code being	 */
>> +					/* executed here.		 */
>> +	addis	r8,r3,(4f - _stext)@ha	/* Jump to the copy of this code */
>> +	addi	r8,r8,(4f - _stext)@l	/* that we just made */
>> +	mtctr	r8
>> +	bctr
>>  
>>  p_end:	.llong	_end - _stext
>>  
>> +4:	/* Now copy the rest of the kernel up to _end */
>> +	addis	r5,r26,(p_end - _stext)@ha
>> +	ld	r5,(p_end - _stext)@l(r5)	/* get _end */
>> +#endif
>> +5:	bl	.copy_and_flush		/* copy the rest */
>> +
>> +9:	b	.start_here_multiplatform
> 
> You have ended up with two separate copies of the code here depending
> on whether or not we have CONFIG_RELOCATABLE set.  I don't think the
> code paths should be different to such an extent.  Please try to make
> the ifdef as small as possible (ideally, nonexistent).
> 
> Paul.
> 
> _______________________________________________
> kexec mailing list
> kexec@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/kexec

Re: [PATCH] Support for relocatable kdump kernel

[Paul Mackerras]

Mohan Kumar M writes:

> Support for relocatable kdump kernel

[snip]

> @@ -1384,7 +1392,15 @@ _STATIC(__after_prom_start)
>  	/* process relocations for the final address of the kernel */
>  	lis	r25,PAGE_OFFSET@highest	/* compute virtual base of kernel */
>  	sldi	r25,r25,32
> -	mr	r3,r25
> +#ifdef CONFIG_CRASH_DUMP
> +	ld	r7,__kdump_flag@got(r2)
> +	add	r7,r7,r26
> +	ld	r7,0(r7)

I think it is dangerous to use an address from the GOT at this point
when we haven't called relocate() yet.  In fact those 3 instructions
can be replaced by one:

	ld	r7,__kdump_flag-_stext(r26)

since we have our base address (i.e. the address of _stext) in r26 at
this point.

> +#ifdef CONFIG_RELOCATABLE
> +#ifdef CONFIG_CRASH_DUMP
> +/*
> + * Check if the kernel has to be running as relocatable kernel based on the
> + * variable __kdump_flag, if it is set the kernel is treated as relocatble
> + * kernel, otherwise it will be moved to PHYSICAL_START
> + */
> +	ld	r7,__kdump_flag@got(r2)
> +	ld	r7,0(r7)

Here again I would rather you did

	ld	r7,__kdump_flag-_stext(r26)

since the kernel is relocated for its final location by this point,
but it is not running at the final location yet.

> +	cmpldi	cr0,r7,1
> +	bne	regular
> +
> +	li	r5,__end_interrupts - _stext	/* just copy interrupts */
> +	b	5f
> +regular:
> +#endif
> +	lis	r5,(copy_to_here - _stext)@ha
> +	addi	r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */
>  
>  	bl	.copy_and_flush		/* copy the first n bytes	 */
>  					/* this includes the code being	 */
> @@ -1411,15 +1443,33 @@ _STATIC(__after_prom_start)
>  	mtctr	r8
>  	bctr
>  
> +p_end:	.llong	_end - _stext
> +
>  4:	/* Now copy the rest of the kernel up to _end */
>  	addis	r5,r26,(p_end - _stext)@ha
>  	ld	r5,(p_end - _stext)@l(r5)	/* get _end */
> -	bl	.copy_and_flush		/* copy the rest */
> +#else
> +	lis	r5,(copy_to_here - _stext)@ha
> +	addi	r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */
>  
> -9:	b	.start_here_multiplatform
> +	bl	.copy_and_flush		/* copy the first n bytes	 */
> +					/* this includes the code being	 */
> +					/* executed here.		 */
> +	addis	r8,r3,(4f - _stext)@ha	/* Jump to the copy of this code */
> +	addi	r8,r8,(4f - _stext)@l	/* that we just made */
> +	mtctr	r8
> +	bctr
>  
>  p_end:	.llong	_end - _stext
>  
> +4:	/* Now copy the rest of the kernel up to _end */
> +	addis	r5,r26,(p_end - _stext)@ha
> +	ld	r5,(p_end - _stext)@l(r5)	/* get _end */
> +#endif
> +5:	bl	.copy_and_flush		/* copy the rest */
> +
> +9:	b	.start_here_multiplatform

You have ended up with two separate copies of the code here depending
on whether or not we have CONFIG_RELOCATABLE set.  I don't think the
code paths should be different to such an extent.  Please try to make
the ifdef as small as possible (ideally, nonexistent).

Paul.

[PATCH] Support for relocatable kdump kernel

[Mohan Kumar M]

Support for relocatable kdump kernel

This patch adds relocatable kernel support for kdump. With this one can
use the same regular kernel to capture the kdump. A signature (0xfeed1234)
is passed in r8 from panic code to the next kernel through kexec_sequence
and purgatory code. The signature is used to differentiate between
relocatable kdump kernel and non-kdump kernels.

The purgatory code compares the signature and sets the __kdump_flag in
head_64.S.  During the boot up, kernel code checks __kdump_flag and if it
is set, the kernel will behave as relocatable kdump kernel. This kernel
will boot at the address where it was loaded by kexec-tools ie at the
address reserved through crashkernel boot parameter.

Enabling both CONFIG_RELOCATABLE and CONFIG_CRASH_DUMP options makes the
kdump kernel as relocatable. So the same kernel can be used as
production and kdump kernel.

Signed-off-by: Mohan Kumar M <mohan@in.ibm.com>
---
 Documentation/kdump/kdump.txt          |   14 ++++++--
 arch/powerpc/Kconfig                   |    4 +-
 arch/powerpc/include/asm/kdump.h       |   16 ++++++++
 arch/powerpc/kernel/crash_dump.c       |    2 +
 arch/powerpc/kernel/head_64.S          |   60 +++++++++++++++++++++++++++++---
 arch/powerpc/kernel/iommu.c            |    2 +-
 arch/powerpc/kernel/machine_kexec.c    |    2 +
 arch/powerpc/kernel/machine_kexec_64.c |   12 ++++--
 arch/powerpc/kernel/misc_64.S          |   10 ++++--
 9 files changed, 104 insertions(+), 18 deletions(-)

diff --git a/Documentation/kdump/kdump.txt b/Documentation/kdump/kdump.txt
index 0705040..3f4bc84 100644
--- a/Documentation/kdump/kdump.txt
+++ b/Documentation/kdump/kdump.txt
@@ -109,7 +109,8 @@ There are two possible methods of using Kdump.
 2) Or use the system kernel binary itself as dump-capture kernel and there is
    no need to build a separate dump-capture kernel. This is possible
    only with the architecutres which support a relocatable kernel. As
-   of today, i386, x86_64 and ia64 architectures support relocatable kernel.
+   of today, i386, x86_64, ppc64 and ia64 architectures support relocatable
+   kernel.
 
 Building a relocatable kernel is advantageous from the point of view that
 one does not have to build a second kernel for capturing the dump. But
@@ -207,8 +208,15 @@ Dump-capture kernel config options (Arch Dependent, i386 and x86_64)
 Dump-capture kernel config options (Arch Dependent, ppc64)
 ----------------------------------------------------------
 
-*  Make and install the kernel and its modules. DO NOT add this kernel
-   to the boot loader configuration files.
+1) Enable "Build a kdump crash kernel" support under "Kernel" options:
+
+   CONFIG_CRASH_DUMP=y
+
+2)   Enable "Build a relocatable kernel" support
+
+   CONFIG_RELOCATABLE=y
+
+   Make and install the kernel and its modules.
 
 Dump-capture kernel config options (Arch Dependent, ia64)
 ----------------------------------------------------------
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 17c988b..f04a96a 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -824,11 +824,11 @@ config PAGE_OFFSET
 	default "0xc000000000000000"
 config KERNEL_START
 	hex
-	default "0xc000000002000000" if CRASH_DUMP
+	default "0xc000000002000000" if CRASH_DUMP && !RELOCATABLE
 	default "0xc000000000000000"
 config PHYSICAL_START
 	hex
-	default "0x02000000" if CRASH_DUMP
+	default "0x02000000" if CRASH_DUMP && !RELOCATABLE
 	default "0x00000000"
 endif
 
diff --git a/arch/powerpc/include/asm/kdump.h b/arch/powerpc/include/asm/kdump.h
index f6c93c7..5308754 100644
--- a/arch/powerpc/include/asm/kdump.h
+++ b/arch/powerpc/include/asm/kdump.h
@@ -9,6 +9,12 @@
  * Reserve to the end of the FWNMI area, see head_64.S */
 #define KDUMP_RESERVE_LIMIT	0x10000 /* 64K */
 
+/*
+ * Used to differentiate between relocatable kdump kernel and other
+ * kernels
+ */
+#define KDUMP_SIGNATURE	0xfeed1234
+
 #ifdef CONFIG_CRASH_DUMP
 
 #define KDUMP_TRAMPOLINE_START	0x0100
@@ -19,11 +25,21 @@
 #endif /* CONFIG_CRASH_DUMP */
 
 #ifndef __ASSEMBLY__
+
+extern unsigned long long __kdump_flag;
+
 #ifdef CONFIG_CRASH_DUMP
+#ifdef CONFIG_RELOCATABLE
+
+static inline void reserve_kdump_trampoline(void) { ; }
+static inline void setup_kdump_trampoline(void) { ; }
+
+#else
 
 extern void reserve_kdump_trampoline(void);
 extern void setup_kdump_trampoline(void);
 
+#endif /* CONFIG_RELOCATABLE */
 #else /* !CONFIG_CRASH_DUMP */
 
 static inline void reserve_kdump_trampoline(void) { ; }
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index a323c9b..eaf9d6d 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -27,6 +27,7 @@
 #define DBG(fmt...)
 #endif
 
+#ifndef CONFIG_RELOCATABLE
 void __init reserve_kdump_trampoline(void)
 {
 	lmb_reserve(0, KDUMP_RESERVE_LIMIT);
@@ -65,6 +66,7 @@ void __init setup_kdump_trampoline(void)
 
 	DBG(" <- setup_kdump_trampoline()\n");
 }
+#endif /* CONFIG_RELOCATABLE */
 
 #ifdef CONFIG_PROC_VMCORE
 static int __init parse_elfcorehdr(char *p)
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 8934500..29c2c34 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -97,6 +97,14 @@ __secondary_hold_spinloop:
 __secondary_hold_acknowledge:
 	.llong	0x0
 
+	/* This flag is set only for kdump kernels so that */
+	/* it will be relocatable. Purgatory code user space kexec-tools */
+	/* sets this flag. Do not move this variable as purgatory code */
+	/* relies on the position of this variables */
+	.globl	__kdump_flag
+__kdump_flag:
+	.llong	0x0
+
 #ifdef CONFIG_PPC_ISERIES
 	/*
 	 * At offset 0x20, there is a pointer to iSeries LPAR data.
@@ -1384,7 +1392,15 @@ _STATIC(__after_prom_start)
 	/* process relocations for the final address of the kernel */
 	lis	r25,PAGE_OFFSET@highest	/* compute virtual base of kernel */
 	sldi	r25,r25,32
-	mr	r3,r25
+#ifdef CONFIG_CRASH_DUMP
+	ld	r7,__kdump_flag@got(r2)
+	add	r7,r7,r26
+	ld	r7,0(r7)
+	cmpldi	cr0,r7,1	/* relocatable kernel ? */
+	bne	1f
+	add	r25,r25,r26
+#endif
+1:	mr	r3,r25
 	bl	.relocate
 #endif
 
@@ -1398,10 +1414,26 @@ _STATIC(__after_prom_start)
 	LOAD_REG_IMMEDIATE(r3, PHYSICAL_START) /* target addr */
 	mr.	r4,r26			/* In some cases the loader may  */
 	beq	9f			/* have already put us at zero */
-	lis	r5,(copy_to_here - _stext)@ha
-	addi	r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */
 	li	r6,0x100		/* Start offset, the first 0x100 */
 					/* bytes were copied earlier.	 */
+#ifdef CONFIG_RELOCATABLE
+#ifdef CONFIG_CRASH_DUMP
+/*
+ * Check if the kernel has to be running as relocatable kernel based on the
+ * variable __kdump_flag, if it is set the kernel is treated as relocatble
+ * kernel, otherwise it will be moved to PHYSICAL_START
+ */
+	ld	r7,__kdump_flag@got(r2)
+	ld	r7,0(r7)
+	cmpldi	cr0,r7,1
+	bne	regular
+
+	li	r5,__end_interrupts - _stext	/* just copy interrupts */
+	b	5f
+regular:
+#endif
+	lis	r5,(copy_to_here - _stext)@ha
+	addi	r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */
 
 	bl	.copy_and_flush		/* copy the first n bytes	 */
 					/* this includes the code being	 */
@@ -1411,15 +1443,33 @@ _STATIC(__after_prom_start)
 	mtctr	r8
 	bctr
 
+p_end:	.llong	_end - _stext
+
 4:	/* Now copy the rest of the kernel up to _end */
 	addis	r5,r26,(p_end - _stext)@ha
 	ld	r5,(p_end - _stext)@l(r5)	/* get _end */
-	bl	.copy_and_flush		/* copy the rest */
+#else
+	lis	r5,(copy_to_here - _stext)@ha
+	addi	r5,r5,(copy_to_here - _stext)@l /* # bytes of memory to copy */
 
-9:	b	.start_here_multiplatform
+	bl	.copy_and_flush		/* copy the first n bytes	 */
+					/* this includes the code being	 */
+					/* executed here.		 */
+	addis	r8,r3,(4f - _stext)@ha	/* Jump to the copy of this code */
+	addi	r8,r8,(4f - _stext)@l	/* that we just made */
+	mtctr	r8
+	bctr
 
 p_end:	.llong	_end - _stext
 
+4:	/* Now copy the rest of the kernel up to _end */
+	addis	r5,r26,(p_end - _stext)@ha
+	ld	r5,(p_end - _stext)@l(r5)	/* get _end */
+#endif
+5:	bl	.copy_and_flush		/* copy the rest */
+
+9:	b	.start_here_multiplatform
+
 /*
  * Copy routine used to copy the kernel to start at physical address 0
  * and flush and invalidate the caches as needed.
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index 550a193..24f7797 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -494,7 +494,7 @@ struct iommu_table *iommu_init_table(struct iommu_table *tbl, int nid)
 	spin_lock_init(&tbl->it_lock);
 
 #ifdef CONFIG_CRASH_DUMP
-	if (ppc_md.tce_get) {
+	if (ppc_md.tce_get && __kdump_flag) {
 		unsigned long index;
 		unsigned long tceval;
 		unsigned long tcecount = 0;
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
index aab7688..ac2a21f 100644
--- a/arch/powerpc/kernel/machine_kexec.c
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -88,11 +88,13 @@ void __init reserve_crashkernel(void)
 
 	crash_size = crashk_res.end - crashk_res.start + 1;
 
+#ifndef CONFIG_RELOCATABLE
 	if (crashk_res.start != KDUMP_KERNELBASE)
 		printk("Crash kernel location must be 0x%x\n",
 				KDUMP_KERNELBASE);
 
 	crashk_res.start = KDUMP_KERNELBASE;
+#endif
 	crash_size = PAGE_ALIGN(crash_size);
 	crashk_res.end = crashk_res.start + crash_size - 1;
 
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index a168514..6a45a9e 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -255,11 +255,13 @@ static union thread_union kexec_stack
 /* Our assembly helper, in kexec_stub.S */
 extern NORET_TYPE void kexec_sequence(void *newstack, unsigned long start,
 					void *image, void *control,
-					void (*clear_all)(void)) ATTRIB_NORET;
+					void (*clear_all)(void),
+				unsigned long long kdump_flag) ATTRIB_NORET;
 
 /* too late to fail here */
 void default_machine_kexec(struct kimage *image)
 {
+	unsigned long long kdump_flag = 0;
 	/* prepare control code if any */
 
 	/*
@@ -270,8 +272,10 @@ void default_machine_kexec(struct kimage *image)
         * using debugger IPI.
         */
 
-       if (crashing_cpu == -1)
-               kexec_prepare_cpus();
+	if (crashing_cpu == -1)
+		kexec_prepare_cpus();
+	else
+		kdump_flag = KDUMP_SIGNATURE;
 
 	/* switch to a staticly allocated stack.  Based on irq stack code.
 	 * XXX: the task struct will likely be invalid once we do the copy!
@@ -284,7 +288,7 @@ void default_machine_kexec(struct kimage *image)
 	 */
 	kexec_sequence(&kexec_stack, image->start, image,
 			page_address(image->control_code_page),
-			ppc_md.hpte_clear_all);
+			ppc_md.hpte_clear_all, kdump_flag);
 	/* NOTREACHED */
 }
 
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 4dd70cf..c93e5f7 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -609,10 +609,13 @@ real_mode:	/* assume normal blr return */
 
 
 /*
- * kexec_sequence(newstack, start, image, control, clear_all())
+ * kexec_sequence(newstack, start, image, control, clear_all(), kdump_flag)
  *
  * does the grungy work with stack switching and real mode switches
  * also does simple calls to other code
+ *
+ * kdump_flag says whether the next kernel should be running at the reserved
+ * load address as needed for relocatable kdump kernel
  */
 
 _GLOBAL(kexec_sequence)
@@ -645,7 +648,7 @@ _GLOBAL(kexec_sequence)
 	mr	r29,r5			/* image (virt) */
 	mr	r28,r6			/* control, unused */
 	mr	r27,r7			/* clear_all() fn desc */
-	mr	r26,r8			/* spare */
+	mr	r26,r8			/* kdump flag */
 	lhz	r25,PACAHWCPUID(r13)	/* get our phys cpu from paca */
 
 	/* disable interrupts, we are overwriting kernel data next */
@@ -707,5 +710,6 @@ _GLOBAL(kexec_sequence)
 	mr	r4,r30	# start, aka phys mem offset
 	mtlr	4
 	li	r5,0
-	blr	/* image->start(physid, image->start, 0); */
+	mr	r6,r26			/* kdump_flag */
+	blr	/* image->start(physid, image->start, 0, kdump_flag); */
 #endif /* CONFIG_KEXEC */
-- 
1.5.5.1