7 files changed, 336 insertions, 1 deletions

diff --git a/arch/ppc/Kconfig b/arch/ppc/Kconfig
index 979590a9baf9..a7835cd3f51f 100644
--- a/arch/ppc/Kconfig
+++ b/arch/ppc/Kconfig
@@ -217,6 +217,26 @@ config MATH_EMULATION
           here.  Saying Y here will not hurt performance (on any machine) but
           will increase the size of the kernel.
 
+config KEXEC
+        bool "kexec system call (EXPERIMENTAL)"
+        depends on EXPERIMENTAL
+        help
+          kexec is a system call that implements the ability to shutdown your
+          current kernel, and to start another kernel.  It is like a reboot
+          but it is indepedent of the system firmware.   And like a reboot
+          you can start any kernel with it, not just Linux.
+
+          The name comes from the similiarity to the exec system call.
+
+          It is an ongoing process to be certain the hardware in a machine
+          is properly shutdown, so do not be surprised if this code does not
+          initially work for you.  It may help to enable device hotplugging
+          support.  As of this writing the exact hardware interface is
+          strongly in flux, so no good recommendation can be made.
+
+          In the GameCube implementation, kexec allows you to load and
+          run DOL files, including kernel and homebrew DOLs.
+
 source "drivers/cpufreq/Kconfig"
 
 config CPU_FREQ_PMAC
diff --git a/arch/ppc/kernel/Makefile b/arch/ppc/kernel/Makefile
index 8276c0b551d2..b1457a8a9c0f 100644
--- a/arch/ppc/kernel/Makefile
+++ b/arch/ppc/kernel/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_ALTIVEC)		+= vecemu.o vector.o
 ifndef CONFIG_E200
 obj-$(CONFIG_FSL_BOOKE)         += perfmon_fsl_booke.o
 endif
+obj-$(CONFIG_KEXEC)             += machine_kexec.o relocate_kernel.o
 
 ifndef CONFIG_MATH_EMULATION
 obj-$(CONFIG_8xx)               += softemu8xx.o
diff --git a/arch/ppc/kernel/machine_kexec.c b/arch/ppc/kernel/machine_kexec.c
new file mode 100644
index 000000000000..435ad9ea0a83
--- /dev/null
+++ b/arch/ppc/kernel/machine_kexec.c
@@ -0,0 +1,122 @@
+/*
+ * machine_kexec.c - handle transition of Linux booting another kernel
+ * Copyright (C) 2002-2003 Eric Biederman  <ebiederm@xmission.com>
+ *
+ * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ */
+
+#include <linux/mm.h>
+#include <linux/kexec.h>
+#include <linux/delay.h>
+#include <linux/reboot.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/mmu_context.h>
+#include <asm/io.h>
+#include <asm/hw_irq.h>
+#include <asm/cacheflush.h>
+#include <asm/machdep.h>
+
+typedef NORET_TYPE void (*relocate_new_kernel_t)(
+        unsigned long indirection_page, unsigned long reboot_code_buffer,
+        unsigned long start_address) ATTRIB_NORET;
+
+const extern unsigned char relocate_new_kernel[];
+const extern unsigned int relocate_new_kernel_size;
+
+void machine_shutdown(void)
+{
+        if (ppc_md.machine_shutdown) {
+                ppc_md.machine_shutdown();
+        }
+}
+
+void machine_crash_shutdown(void)
+{
+        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(;;);
+}
+
+
+/*
+ * 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 machine_kexec_simple(struct kimage *image)
+{
+        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);
+}
+
diff --git a/arch/ppc/kernel/misc.S b/arch/ppc/kernel/misc.S
index a3132f8e799c..b6a63a49a232 100644
--- a/arch/ppc/kernel/misc.S
+++ b/arch/ppc/kernel/misc.S
@@ -1444,7 +1444,7 @@ _GLOBAL(sys_call_table)
         .long sys_mq_timedreceive       /* 265 */
         .long sys_mq_notify
         .long sys_mq_getsetattr
-        .long sys_ni_syscall            /* 268 reserved for sys_kexec_load */
+        .long sys_kexec_load
         .long sys_add_key
         .long sys_request_key           /* 270 */
         .long sys_keyctl
diff --git a/arch/ppc/kernel/relocate_kernel.S b/arch/ppc/kernel/relocate_kernel.S
new file mode 100644
index 000000000000..7ff69c4af920
--- /dev/null
+++ b/arch/ppc/kernel/relocate_kernel.S
@@ -0,0 +1,123 @@
+/*
+ * relocate_kernel.S - put the kernel image in place to boot
+ * Copyright (C) 2002-2003 Eric Biederman  <ebiederm@xmission.com>
+ *
+ * GameCube/ppc32 port Copyright (C) 2004 Albert Herranz
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ */
+
+#include <asm/reg.h>
+#include <asm/ppc_asm.h>
+#include <asm/processor.h>
+
+#include <asm/kexec.h>
+
+#define PAGE_SIZE      4096 /* must be same value as in <asm/page.h> */
+
+        /*
+         * 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   SRR1, r8
+        addi    r8, r4, 1f - relocate_new_kernel
+        mtspr   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
+
diff --git a/include/asm-ppc/kexec.h b/include/asm-ppc/kexec.h
new file mode 100644
index 000000000000..73191310d8db
--- /dev/null
+++ b/include/asm-ppc/kexec.h
@@ -0,0 +1,38 @@
+#ifndef _PPC_KEXEC_H
+#define _PPC_KEXEC_H
+
+#ifdef CONFIG_KEXEC
+
+/*
+ * KEXEC_SOURCE_MEMORY_LIMIT maximum page get_free_page can return.
+ * I.e. Maximum page that is mapped directly into kernel memory,
+ * and kmap is not required.
+ *
+ * Someone correct me if FIXADDR_START - PAGEOFFSET is not the correct
+ * calculation for the amount of memory directly mappable into the
+ * kernel memory space.
+ */
+
+/* Maximum physical address we can use pages from */
+#define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
+/* Maximum address we can reach in physical address mode */
+#define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL)
+/* Maximum address we can use for the control code buffer */
+#define KEXEC_CONTROL_MEMORY_LIMIT TASK_SIZE
+
+#define KEXEC_CONTROL_CODE_SIZE 4096
+
+/* The native architecture */
+#define KEXEC_ARCH KEXEC_ARCH_PPC
+
+#ifndef __ASSEMBLY__
+
+struct kimage;
+
+extern void machine_kexec_simple(struct kimage *image);
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* CONFIG_KEXEC */
+
+#endif /* _PPC_KEXEC_H */
diff --git a/include/asm-ppc/machdep.h b/include/asm-ppc/machdep.h
index b78d40870c95..1d4ab70a56f3 100644
--- a/include/asm-ppc/machdep.h
+++ b/include/asm-ppc/machdep.h
@@ -4,6 +4,7 @@
 
 #include <linux/config.h>
 #include <linux/init.h>
+#include <linux/kexec.h>
 
 #include <asm/setup.h>
 #include <asm/page.h>
@@ -114,6 +115,36 @@ struct machdep_calls {
         /* functions for dealing with other cpus */
         struct smp_ops_t *smp_ops;
 #endif /* CONFIG_SMP */
+
+#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);
+
+        /* 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?
+         */
+        void (*machine_crash_shutdown)(void);
+
+        /* Called to do what every setup is needed on image and the
+         * reboot code buffer. Returns 0 on success.
+         * Provide your own (maybe dummy) implementation if your platform
+         * claims to support kexec.
+         */
+        int (*machine_kexec_prepare)(struct kimage *image);
+
+        /* Called to handle any machine specific cleanup on image */
+        void (*machine_kexec_cleanup)(struct kimage *image);
+
+        /* Called to perform the _real_ kexec.
+         * Do NOT allocate memory or fail here. We are past the point of
+         * no return.
+         */
+        void (*machine_kexec)(struct kimage *image);
+#endif /* CONFIG_KEXEC */
 };
 
 extern struct machdep_calls ppc_md;