[PATCH] powerpc: Merge kexec

This patch merges, to some extent, the PPC32 and PPC64 kexec implementations.

We adopt the PPC32 approach of having ppc_md callbacks for the kexec functions.
The current PPC64 implementation becomes the "default" implementation for PPC64
which platforms can select if they need no special treatment.

I've added these default callbacks to pseries/maple/cell/powermac, this means
iSeries no longer supports kexec - but it never worked anyway.

I've renamed PPC32's machine_kexec_simple to default_machine_kexec, inline with
PPC64. Judging by the comments it might be better named machine_kexec_non_of,
or something, but at the moment it's the only implementation for PPC32 so it's
the "default".

Kexec requires machine_shutdown(), which is in machine_kexec.c on PPC32, but we
already have in setup-common.c on powerpc. All this does is call
ppc_md.nvram_sync, which only powermac implements, so instead make
machine_shutdown a ppc_md member and have it call core99_nvram_sync directly
on powermac.

I've also stuck relocate_kernel.S into misc_32.S for powerpc.

Built for ARCH=ppc, and 32 & 64 bit ARCH=powerpc, with KEXEC=y/n. Booted on
P5 LPAR and successfully kexec'ed.

Should apply on top of 493f25ef4087395891c99fcfe2c72e62e293e89f.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>

14 files changed, 281 insertions, 33 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 9ed551b6c172..e7776a438a84 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -65,8 +65,9 @@ pci64-$(CONFIG_PPC64)		+= pci_64.o pci_dn.o pci_iommu.o \
                                    pci_direct_iommu.o iomap.o
 obj-$(CONFIG_PCI)               += $(pci64-y)
 
-kexec64-$(CONFIG_PPC64)         += machine_kexec_64.o
-obj-$(CONFIG_KEXEC)             += $(kexec64-y)
+kexec-$(CONFIG_PPC64)           := machine_kexec_64.o
+kexec-$(CONFIG_PPC32)           := machine_kexec_32.o
+obj-$(CONFIG_KEXEC)             += machine_kexec.o $(kexec-y)
 
 ifeq ($(CONFIG_PPC_ISERIES),y)
 $(obj)/head_64.o: $(obj)/lparmap.s
diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c
new file mode 100644
index 000000000000..d8225c797199
--- /dev/null
+++ b/arch/powerpc/kernel/machine_kexec.c
@@ -0,0 +1,67 @@
+/*
+ * Code to handle transition of Linux booting another kernel.
+ *
+ * Copyright (C) 2002-2003 Eric Biederman  <ebiederm@xmission.com>
+ * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
+ * Copyright (C) 2005 IBM Corporation.
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ */
+
+#include <linux/kexec.h>
+#include <linux/reboot.h>
+#include <linux/threads.h>
+#include <asm/machdep.h>
+
+/*
+ * Provide a dummy crash_notes definition until crash dump is implemented.
+ * This prevents breakage of crash_notes attribute in kernel/ksysfs.c.
+ */
+note_buf_t crash_notes[NR_CPUS];
+
+void machine_crash_shutdown(struct pt_regs *regs)
+{
+        if (ppc_md.machine_crash_shutdown)
+                ppc_md.machine_crash_shutdown();
+}
+
+/*
+ * Do what every setup is needed on image and the
+ * reboot code buffer to allow us to avoid allocations
+ * later.
+ */
+int machine_kexec_prepare(struct kimage *image)
+{
+        if (ppc_md.machine_kexec_prepare)
+                return ppc_md.machine_kexec_prepare(image);
+        /*
+         * Fail if platform doesn't provide its own machine_kexec_prepare
+         * implementation.
+         */
+        return -ENOSYS;
+}
+
+void machine_kexec_cleanup(struct kimage *image)
+{
+        if (ppc_md.machine_kexec_cleanup)
+                ppc_md.machine_kexec_cleanup(image);
+}
+
+/*
+ * Do not allocate memory (or fail in any way) in machine_kexec().
+ * We are past the point of no return, committed to rebooting now.
+ */
+NORET_TYPE void machine_kexec(struct kimage *image)
+{
+        if (ppc_md.machine_kexec)
+                ppc_md.machine_kexec(image);
+        else {
+                /*
+                 * Fall back to normal restart if platform doesn't provide
+                 * its own kexec function, and user insist to kexec...
+                 */
+                machine_restart(NULL);
+        }
+        for(;;);
+}
diff --git a/arch/powerpc/kernel/machine_kexec_32.c b/arch/powerpc/kernel/machine_kexec_32.c
new file mode 100644
index 000000000000..443606134dff
--- /dev/null
+++ b/arch/powerpc/kernel/machine_kexec_32.c
@@ -0,0 +1,65 @@
+/*
+ * PPC32 code to handle Linux booting another kernel.
+ *
+ * Copyright (C) 2002-2003 Eric Biederman  <ebiederm@xmission.com>
+ * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
+ * Copyright (C) 2005 IBM Corporation.
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ */
+
+#include <linux/kexec.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <asm/cacheflush.h>
+#include <asm/hw_irq.h>
+#include <asm/io.h>
+
+typedef NORET_TYPE void (*relocate_new_kernel_t)(
+                                unsigned long indirection_page,
+                                unsigned long reboot_code_buffer,
+                                unsigned long start_address) ATTRIB_NORET;
+
+/*
+ * This is a generic machine_kexec function suitable at least for
+ * non-OpenFirmware embedded platforms.
+ * It merely copies the image relocation code to the control page and
+ * jumps to it.
+ * A platform specific function may just call this one.
+ */
+void default_machine_kexec(struct kimage *image)
+{
+        const extern unsigned char relocate_new_kernel[];
+        const extern unsigned int relocate_new_kernel_size;
+        unsigned long page_list;
+        unsigned long reboot_code_buffer, reboot_code_buffer_phys;
+        relocate_new_kernel_t rnk;
+
+        /* Interrupts aren't acceptable while we reboot */
+        local_irq_disable();
+
+        page_list = image->head;
+
+        /* we need both effective and real address here */
+        reboot_code_buffer =
+                        (unsigned long)page_address(image->control_code_page);
+        reboot_code_buffer_phys = virt_to_phys((void *)reboot_code_buffer);
+
+        /* copy our kernel relocation code to the control code page */
+        memcpy((void *)reboot_code_buffer, relocate_new_kernel,
+                                                relocate_new_kernel_size);
+
+        flush_icache_range(reboot_code_buffer,
+                                reboot_code_buffer + KEXEC_CONTROL_CODE_SIZE);
+        printk(KERN_INFO "Bye!\n");
+
+        /* now call it */
+        rnk = (relocate_new_kernel_t) reboot_code_buffer;
+        (*rnk)(page_list, reboot_code_buffer_phys, image->start);
+}
+
+int default_machine_kexec_prepare(struct kimage *image)
+{
+        return 0;
+}
diff --git a/arch/powerpc/kernel/machine_kexec_64.c b/arch/powerpc/kernel/machine_kexec_64.c
index 97c51e452be7..ec0f06bfc24a 100644
--- a/arch/powerpc/kernel/machine_kexec_64.c
+++ b/arch/powerpc/kernel/machine_kexec_64.c
@@ -1,5 +1,5 @@
 /*
- * machine_kexec.c - handle transition of Linux booting another kernel
+ * PPC64 code to handle Linux booting another kernel.
  *
  * Copyright (C) 2004-2005, IBM Corp.
  *
@@ -28,21 +28,7 @@
 
 #define HASH_GROUP_SIZE 0x80    /* size of each hash group, asm/mmu.h */
 
-/* Have this around till we move it into crash specific file */
-note_buf_t crash_notes[NR_CPUS];
-
-/* Dummy for now. Not sure if we need to have a crash shutdown in here
- * and if what it will achieve. Letting it be now to compile the code
- * in generic kexec environment
- */
-void machine_crash_shutdown(struct pt_regs *regs)
-{
-        /* do nothing right now */
-        /* smp_relase_cpus() if we want smp on panic kernel */
-        /* cpu_irq_down to isolate us until we are ready */
-}
-
-int machine_kexec_prepare(struct kimage *image)
+int default_machine_kexec_prepare(struct kimage *image)
 {
         int i;
         unsigned long begin, end;       /* limits of segment */
@@ -111,11 +97,6 @@ int machine_kexec_prepare(struct kimage *image)
         return 0;
 }
 
-void machine_kexec_cleanup(struct kimage *image)
-{
-        /* we do nothing in prepare that needs to be undone */
-}
-
 #define IND_FLAGS (IND_DESTINATION | IND_INDIRECTION | IND_DONE | IND_SOURCE)
 
 static void copy_segments(unsigned long ind)
@@ -283,7 +264,7 @@ extern NORET_TYPE void kexec_sequence(void *newstack, unsigned long start,
                                         void (*clear_all)(void)) ATTRIB_NORET;
 
 /* too late to fail here */
-void machine_kexec(struct kimage *image)
+void default_machine_kexec(struct kimage *image)
 {
 
         /* prepare control code if any */
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 624a983a9676..01d0d97a16e1 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -5,6 +5,10 @@
  * Largely rewritten by Cort Dougan (cort@cs.nmt.edu)
  * and Paul Mackerras.
  *
+ * kexec bits:
+ * Copyright (C) 2002-2003 Eric Biederman  <ebiederm@xmission.com>
+ * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
+ *
  * 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
@@ -24,6 +28,8 @@
 #include <asm/ppc_asm.h>
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
+#include <asm/processor.h>
+#include <asm/kexec.h>
 
         .text
 
@@ -1006,3 +1012,110 @@ _GLOBAL(execve)
  */
 _GLOBAL(__main)
         blr
+
+#ifdef CONFIG_KEXEC
+        /*
+         * Must be relocatable PIC code callable as a C function.
+         */
+        .globl relocate_new_kernel
+relocate_new_kernel:
+        /* r3 = page_list   */
+        /* r4 = reboot_code_buffer */
+        /* r5 = start_address      */
+
+        li      r0, 0
+
+        /*
+         * Set Machine Status Register to a known status,
+         * switch the MMU off and jump to 1: in a single step.
+         */
+
+        mr      r8, r0
+        ori     r8, r8, MSR_RI|MSR_ME
+        mtspr   SPRN_SRR1, r8
+        addi    r8, r4, 1f - relocate_new_kernel
+        mtspr   SPRN_SRR0, r8
+        sync
+        rfi
+
+1:
+        /* from this point address translation is turned off */
+        /* and interrupts are disabled */
+
+        /* set a new stack at the bottom of our page... */
+        /* (not really needed now) */
+        addi    r1, r4, KEXEC_CONTROL_CODE_SIZE - 8 /* for LR Save+Back Chain */
+        stw     r0, 0(r1)
+
+        /* Do the copies */
+        li      r6, 0 /* checksum */
+        mr      r0, r3
+        b       1f
+
+0:      /* top, read another word for the indirection page */
+        lwzu    r0, 4(r3)
+
+1:
+        /* is it a destination page? (r8) */
+        rlwinm. r7, r0, 0, 31, 31 /* IND_DESTINATION (1<<0) */
+        beq     2f
+
+        rlwinm  r8, r0, 0, 0, 19 /* clear kexec flags, page align */
+        b       0b
+
+2:      /* is it an indirection page? (r3) */
+        rlwinm. r7, r0, 0, 30, 30 /* IND_INDIRECTION (1<<1) */
+        beq     2f
+
+        rlwinm  r3, r0, 0, 0, 19 /* clear kexec flags, page align */
+        subi    r3, r3, 4
+        b       0b
+
+2:      /* are we done? */
+        rlwinm. r7, r0, 0, 29, 29 /* IND_DONE (1<<2) */
+        beq     2f
+        b       3f
+
+2:      /* is it a source page? (r9) */
+        rlwinm. r7, r0, 0, 28, 28 /* IND_SOURCE (1<<3) */
+        beq     0b
+
+        rlwinm  r9, r0, 0, 0, 19 /* clear kexec flags, page align */
+
+        li      r7, PAGE_SIZE / 4
+        mtctr   r7
+        subi    r9, r9, 4
+        subi    r8, r8, 4
+9:
+        lwzu    r0, 4(r9)  /* do the copy */
+        xor     r6, r6, r0
+        stwu    r0, 4(r8)
+        dcbst   0, r8
+        sync
+        icbi    0, r8
+        bdnz    9b
+
+        addi    r9, r9, 4
+        addi    r8, r8, 4
+        b       0b
+
+3:
+
+        /* To be certain of avoiding problems with self-modifying code
+         * execute a serializing instruction here.
+         */
+        isync
+        sync
+
+        /* jump to the entry point, usually the setup routine */
+        mtlr    r5
+        blrl
+
+1:      b       1b
+
+relocate_new_kernel_end:
+
+        .globl relocate_new_kernel_size
+relocate_new_kernel_size:
+        .long relocate_new_kernel_end - relocate_new_kernel
+#endif
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index bd3eb4292b53..6088a39edc26 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -93,8 +93,8 @@ EXPORT_SYMBOL(ppc_do_canonicalize_irqs);
 /* also used by kexec */
 void machine_shutdown(void)
 {
-        if (ppc_md.nvram_sync)
-                ppc_md.nvram_sync();
+        if (ppc_md.machine_shutdown)
+                ppc_md.machine_shutdown();
 }
 
 void machine_restart(char *cmd)
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
index 9a495634d0c2..d45dc18855a5 100644
--- a/arch/powerpc/platforms/cell/setup.c
+++ b/arch/powerpc/platforms/cell/setup.c
@@ -33,6 +33,7 @@
 #include <asm/mmu.h>
 #include <asm/processor.h>
 #include <asm/io.h>
+#include <asm/kexec.h>
 #include <asm/pgtable.h>
 #include <asm/prom.h>
 #include <asm/rtas.h>
@@ -138,4 +139,8 @@ struct machdep_calls __initdata cell_md = {
         .set_rtc_time           = rtas_set_rtc_time,
         .calibrate_decr         = generic_calibrate_decr,
         .progress               = cell_progress,
+#ifdef CONFIG_KEXEC
+        .machine_kexec          = default_machine_kexec,
+        .machine_kexec_prepare  = default_machine_kexec_prepare,
+#endif
 };
diff --git a/arch/powerpc/platforms/maple/setup.c b/arch/powerpc/platforms/maple/setup.c
index 7ece8983a105..95b2352655fe 100644
--- a/arch/powerpc/platforms/maple/setup.c
+++ b/arch/powerpc/platforms/maple/setup.c
@@ -51,6 +51,7 @@
 #include <asm/pgtable.h>
 #include <asm/bitops.h>
 #include <asm/io.h>
+#include <asm/kexec.h>
 #include <asm/pci-bridge.h>
 #include <asm/iommu.h>
 #include <asm/machdep.h>
@@ -292,4 +293,8 @@ struct machdep_calls __initdata maple_md = {
         .calibrate_decr         = generic_calibrate_decr,
         .progress               = maple_progress,
         .idle_loop              = native_idle,
+#ifdef CONFIG_KEXEC
+        .machine_kexec          = default_machine_kexec,
+        .machine_kexec_prepare  = default_machine_kexec_prepare,
+#endif
 };
diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c
index 4042e2f06ee0..59e0e51cf663 100644
--- a/arch/powerpc/platforms/powermac/nvram.c
+++ b/arch/powerpc/platforms/powermac/nvram.c
@@ -549,6 +549,7 @@ static int __init core99_nvram_setup(struct device_node *dp)
         ppc_md.nvram_write      = core99_nvram_write;
         ppc_md.nvram_size       = core99_nvram_size;
         ppc_md.nvram_sync       = core99_nvram_sync;
+        ppc_md.machine_shutdown = core99_nvram_sync;
         /* 
          * Maybe we could be smarter here though making an exclusive list
          * of known flash chips is a bit nasty as older OF didn't provide us
diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c
index 7acb0546671f..3b7a492d9b68 100644
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -60,6 +60,7 @@
 #include <asm/system.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
+#include <asm/kexec.h>
 #include <asm/pci-bridge.h>
 #include <asm/ohare.h>
 #include <asm/mediabay.h>
@@ -773,7 +774,11 @@ struct machdep_calls __initdata pmac_md = {
         .pci_probe_mode         = pmac_probe_mode,
         .idle_loop              = native_idle,
         .enable_pmcs            = power4_enable_pmcs,
+#ifdef CONFIG_KEXEC
+        .machine_kexec          = default_machine_kexec,
+        .machine_kexec_prepare  = default_machine_kexec_prepare,
 #endif
+#endif /* CONFIG_PPC64 */
 #ifdef CONFIG_PPC32
         .pcibios_enable_device_hook = pmac_pci_enable_device_hook,
         .pcibios_after_init     = pmac_pcibios_after_init,
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 4a465f067ede..8a4238a3757f 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -56,6 +56,7 @@
 #include <asm/dma.h>
 #include <asm/machdep.h>
 #include <asm/irq.h>
+#include <asm/kexec.h>
 #include <asm/time.h>
 #include <asm/nvram.h>
 #include "xics.h"
@@ -638,5 +639,7 @@ struct machdep_calls __initdata pSeries_md = {
         .machine_check_exception = pSeries_machine_check_exception,
 #ifdef CONFIG_KEXEC
         .kexec_cpu_down         = pseries_kexec_cpu_down,
+        .machine_kexec          = default_machine_kexec,
+        .machine_kexec_prepare  = default_machine_kexec_prepare,
 #endif
 };
diff --git a/arch/ppc/kernel/Makefile b/arch/ppc/kernel/Makefile
index 0bb23fce4293..e6c1d615bb86 100644
--- a/arch/ppc/kernel/Makefile
+++ b/arch/ppc/kernel/Makefile
@@ -49,5 +49,4 @@ obj-$(CONFIG_TAU)		+= temp.o
 ifndef CONFIG_E200
 obj-$(CONFIG_FSL_BOOKE)         += perfmon_fsl_booke.o
 endif
-obj-$(CONFIG_KEXEC)             += machine_kexec.o relocate_kernel.o
 endif
diff --git a/include/asm-powerpc/kexec.h b/include/asm-powerpc/kexec.h
index c72ffc709ea8..934b4981651d 100644
--- a/include/asm-powerpc/kexec.h
+++ b/include/asm-powerpc/kexec.h
@@ -41,10 +41,11 @@ extern note_buf_t crash_notes[];
 extern void kexec_smp_wait(void);       /* get and clear naca physid, wait for
                                           master to copy new code to 0 */
 extern void __init kexec_setup(void);
-#else
-struct kimage;
-extern void machine_kexec_simple(struct kimage *image);
 #endif
 
+struct kimage;
+extern void default_machine_kexec(struct kimage *image);
+extern int default_machine_kexec_prepare(struct kimage *image);
+
 #endif /* ! __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_KEXEC_H */
diff --git a/include/asm-powerpc/machdep.h b/include/asm-powerpc/machdep.h
index c011abb8b600..d6a1a2b5507d 100644
--- a/include/asm-powerpc/machdep.h
+++ b/include/asm-powerpc/machdep.h
@@ -27,6 +27,9 @@ struct device_node;
 struct iommu_table;
 struct rtc_time;
 struct file;
+#ifdef CONFIG_KEXEC
+struct kimage;
+#endif
 
 #ifdef CONFIG_SMP
 struct smp_ops_t {
@@ -207,14 +210,14 @@ struct machdep_calls {
 
         /* this is for modules, since _machine can be a define -- Cort */
         int ppc_machine;
+#endif /* CONFIG_PPC32 */
 
-#ifdef CONFIG_KEXEC
         /* Called to shutdown machine specific hardware not already controlled
          * by other drivers.
-         * XXX Should we move this one out of kexec scope?
          */
         void (*machine_shutdown)(void);
 
+#ifdef CONFIG_KEXEC
         /* Called to do the minimal shutdown needed to run a kexec'd kernel
          * to run successfully.
          * XXX Should we move this one out of kexec scope?
@@ -237,7 +240,6 @@ struct machdep_calls {
          */
         void (*machine_kexec)(struct kimage *image);
 #endif /* CONFIG_KEXEC */
-#endif /* CONFIG_PPC32 */
 };
 
 extern void default_idle(void);