[S390] kdump backend code

This patch provides the architecture specific part of the s390 kdump
support.

Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

18 files changed, 1078 insertions, 12 deletions

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 6b99fc3f9b6..a9fbd43395f 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -569,6 +569,16 @@ config KEXEC
 	  current kernel, and to start another kernel.  It is like a reboot
 	  but is independent of hardware/microcode support.
 
+config CRASH_DUMP
+	bool "kernel crash dumps"
+	depends on 64BIT
+	help
+	  Generate crash dump after being started by kexec.
+	  Crash dump kernels are loaded in the main kernel with kexec-tools
+	  into a specially reserved region and then later executed after
+	  a crash by kdump/kexec.
+	  For more details see Documentation/kdump/kdump.txt
+
 config ZFCPDUMP
 	def_bool n
 	prompt "zfcpdump support"
diff --git a/arch/s390/include/asm/ipl.h b/arch/s390/include/asm/ipl.h
index 97cc4403fab..6940abfbe1d 100644
--- a/arch/s390/include/asm/ipl.h
+++ b/arch/s390/include/asm/ipl.h
@@ -168,5 +168,6 @@ enum diag308_rc {
 
 extern int diag308(unsigned long subcode, void *addr);
 extern void diag308_reset(void);
+extern void store_status(void);
 
 #endif /* _ASM_S390_IPL_H */
diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h
index bb729b84a21..fb1c96fa348 100644
--- a/arch/s390/include/asm/kexec.h
+++ b/arch/s390/include/asm/kexec.h
@@ -30,6 +30,9 @@
 /* Not more than 2GB */
 #define KEXEC_CONTROL_MEMORY_LIMIT (1UL<<31)
 
+/* Maximum address we can use for the crash control pages */
+#define KEXEC_CRASH_CONTROL_MEMORY_LIMIT (-1UL)
+
 /* Allocate one page for the pdp and the second for the code */
 #define KEXEC_CONTROL_PAGE_SIZE 4096
 
diff --git a/arch/s390/include/asm/reset.h b/arch/s390/include/asm/reset.h
index f584f4a5258..3d6ad4ad2a3 100644
--- a/arch/s390/include/asm/reset.h
+++ b/arch/s390/include/asm/reset.h
@@ -17,5 +17,5 @@ struct reset_call {
 
 extern void register_reset_call(struct reset_call *reset);
 extern void unregister_reset_call(struct reset_call *reset);
-extern void s390_reset_system(void);
+extern void s390_reset_system(void (*func)(void *), void *data);
 #endif /* _ASM_S390_RESET_H */
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index d5e2ef10537..5a099714df0 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -26,15 +26,21 @@
 #define IPL_DEVICE        (*(unsigned long *)  (0x10404))
 #define INITRD_START      (*(unsigned long *)  (0x1040C))
 #define INITRD_SIZE       (*(unsigned long *)  (0x10414))
+#define OLDMEM_BASE	  (*(unsigned long *)  (0x1041C))
+#define OLDMEM_SIZE	  (*(unsigned long *)  (0x10424))
 #else /* __s390x__ */
 #define IPL_DEVICE        (*(unsigned long *)  (0x10400))
 #define INITRD_START      (*(unsigned long *)  (0x10408))
 #define INITRD_SIZE       (*(unsigned long *)  (0x10410))
+#define OLDMEM_BASE	  (*(unsigned long *)  (0x10418))
+#define OLDMEM_SIZE	  (*(unsigned long *)  (0x10420))
 #endif /* __s390x__ */
 #define COMMAND_LINE      ((char *)            (0x10480))
 
 #define CHUNK_READ_WRITE 0
 #define CHUNK_READ_ONLY  1
+#define CHUNK_OLDMEM	 4
+#define CHUNK_CRASHK	 5
 
 struct mem_chunk {
 	unsigned long addr;
@@ -48,6 +54,8 @@ extern int memory_end_set;
 extern unsigned long memory_end;
 
 void detect_memory_layout(struct mem_chunk chunk[]);
+void create_mem_hole(struct mem_chunk memory_chunk[], unsigned long addr,
+		     unsigned long size, int type);
 
 #define PRIMARY_SPACE_MODE	0
 #define ACCESS_REGISTER_MODE	1
@@ -106,6 +114,7 @@ extern unsigned int user_mode;
 #endif /* __s390x__ */
 
 #define ZFCPDUMP_HSA_SIZE	(32UL<<20)
+#define ZFCPDUMP_HSA_SIZE_MAX	(64UL<<20)
 
 /*
  * Console mode. Override with conmode=
@@ -134,10 +143,14 @@ extern char kernel_nss_name[];
 #define IPL_DEVICE        0x10404
 #define INITRD_START      0x1040C
 #define INITRD_SIZE       0x10414
+#define OLDMEM_BASE	  0x1041C
+#define OLDMEM_SIZE	  0x10424
 #else /* __s390x__ */
 #define IPL_DEVICE        0x10400
 #define INITRD_START      0x10408
 #define INITRD_SIZE       0x10410
+#define OLDMEM_BASE	  0x10418
+#define OLDMEM_SIZE	  0x10420
 #endif /* __s390x__ */
 #define COMMAND_LINE      0x10480
 
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index df3732249ba..dd4f0764091 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -48,6 +48,7 @@ obj-$(CONFIG_FUNCTION_TRACER)	+= $(if $(CONFIG_64BIT),mcount64.o,mcount.o)
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)  += ftrace.o
+obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 
 # Kexec part
 S390_KEXEC_OBJS := machine_kexec.o crash.o
diff --git a/arch/s390/kernel/base.S b/arch/s390/kernel/base.S
index 255435663bf..f8828d38fa6 100644
--- a/arch/s390/kernel/base.S
+++ b/arch/s390/kernel/base.S
@@ -86,6 +86,8 @@ s390_base_pgm_handler_fn:
 ENTRY(diag308_reset)
 	larl	%r4,.Lctlregs		# Save control registers
 	stctg	%c0,%c15,0(%r4)
+	larl	%r4,.Lfpctl		# Floating point control register
+	stfpc	0(%r4)
 	larl	%r4,.Lrestart_psw	# Setup restart PSW at absolute 0
 	lghi	%r3,0
 	lg	%r4,0(%r4)		# Save PSW
@@ -99,6 +101,8 @@ ENTRY(diag308_reset)
 	sam64				# Switch to 64 bit addressing mode
 	larl	%r4,.Lctlregs		# Restore control registers
 	lctlg	%c0,%c15,0(%r4)
+	larl	%r4,.Lfpctl		# Restore floating point ctl register
+	lfpc	0(%r4)
 	br	%r14
 .align 16
 .Lrestart_psw:
@@ -110,6 +114,8 @@ ENTRY(diag308_reset)
 	.rept	16
 	.quad	0
 	.endr
+.Lfpctl:
+	.long	0
 	.previous
 
 #else /* CONFIG_64BIT */
diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
new file mode 100644
index 00000000000..2a9a3f40557
--- /dev/null
+++ b/arch/s390/kernel/crash_dump.c
@@ -0,0 +1,427 @@
+/*
+ * S390 kdump implementation
+ *
+ * Copyright IBM Corp. 2011
+ * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com>
+ */
+
+#include <linux/crash_dump.h>
+#include <asm/lowcore.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/gfp.h>
+#include <linux/slab.h>
+#include <linux/crash_dump.h>
+#include <linux/bootmem.h>
+#include <linux/elf.h>
+#include <asm/ipl.h>
+
+#define PTR_ADD(x, y) (((char *) (x)) + ((unsigned long) (y)))
+#define PTR_SUB(x, y) (((char *) (x)) - ((unsigned long) (y)))
+#define PTR_DIFF(x, y) ((unsigned long)(((char *) (x)) - ((unsigned long) (y))))
+
+/*
+ * Copy one page from "oldmem"
+ *
+ * For the kdump reserved memory this functions performs a swap operation:
+ *  - [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE] is mapped to [0 - OLDMEM_SIZE].
+ *  - [0 - OLDMEM_SIZE] is mapped to [OLDMEM_BASE - OLDMEM_BASE + OLDMEM_SIZE]
+ */
+ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
+			 size_t csize, unsigned long offset, int userbuf)
+{
+	unsigned long src;
+	int rc;
+
+	if (!csize)
+		return 0;
+
+	src = (pfn << PAGE_SHIFT) + offset;
+	if (src < OLDMEM_SIZE)
+		src += OLDMEM_BASE;
+	else if (src > OLDMEM_BASE &&
+		 src < OLDMEM_BASE + OLDMEM_SIZE)
+		src -= OLDMEM_BASE;
+	if (userbuf)
+		rc = copy_to_user_real((void __user *) buf, (void *) src,
+				       csize);
+	else
+		rc = memcpy_real(buf, (void *) src, csize);
+	return rc < 0 ? rc : csize;
+}
+
+/*
+ * Copy memory from old kernel
+ */
+static int copy_from_oldmem(void *dest, void *src, size_t count)
+{
+	unsigned long copied = 0;
+	int rc;
+
+	if ((unsigned long) src < OLDMEM_SIZE) {
+		copied = min(count, OLDMEM_SIZE - (unsigned long) src);
+		rc = memcpy_real(dest, src + OLDMEM_BASE, copied);
+		if (rc)
+			return rc;
+	}
+	return memcpy_real(dest + copied, src + copied, count - copied);
+}
+
+/*
+ * Alloc memory and panic in case of ENOMEM
+ */
+static void *kzalloc_panic(int len)
+{
+	void *rc;
+
+	rc = kzalloc(len, GFP_KERNEL);
+	if (!rc)
+		panic("s390 kdump kzalloc (%d) failed", len);
+	return rc;
+}
+
+/*
+ * Get memory layout and create hole for oldmem
+ */
+static struct mem_chunk *get_memory_layout(void)
+{
+	struct mem_chunk *chunk_array;
+
+	chunk_array = kzalloc_panic(MEMORY_CHUNKS * sizeof(struct mem_chunk));
+	detect_memory_layout(chunk_array);
+	create_mem_hole(chunk_array, OLDMEM_BASE, OLDMEM_SIZE, CHUNK_CRASHK);
+	return chunk_array;
+}
+
+/*
+ * Initialize ELF note
+ */
+static void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len,
+		     const char *name)
+{
+	Elf64_Nhdr *note;
+	u64 len;
+
+	note = (Elf64_Nhdr *)buf;
+	note->n_namesz = strlen(name) + 1;
+	note->n_descsz = d_len;
+	note->n_type = type;
+	len = sizeof(Elf64_Nhdr);
+
+	memcpy(buf + len, name, note->n_namesz);
+	len = roundup(len + note->n_namesz, 4);
+
+	memcpy(buf + len, desc, note->n_descsz);
+	len = roundup(len + note->n_descsz, 4);
+
+	return PTR_ADD(buf, len);
+}
+
+/*
+ * Initialize prstatus note
+ */
+static void *nt_prstatus(void *ptr, struct save_area *sa)
+{
+	struct elf_prstatus nt_prstatus;
+	static int cpu_nr = 1;
+
+	memset(&nt_prstatus, 0, sizeof(nt_prstatus));
+	memcpy(&nt_prstatus.pr_reg.gprs, sa->gp_regs, sizeof(sa->gp_regs));
+	memcpy(&nt_prstatus.pr_reg.psw, sa->psw, sizeof(sa->psw));
+	memcpy(&nt_prstatus.pr_reg.acrs, sa->acc_regs, sizeof(sa->acc_regs));
+	nt_prstatus.pr_pid = cpu_nr;
+	cpu_nr++;
+
+	return nt_init(ptr, NT_PRSTATUS, &nt_prstatus, sizeof(nt_prstatus),
+			 "CORE");
+}
+
+/*
+ * Initialize fpregset (floating point) note
+ */
+static void *nt_fpregset(void *ptr, struct save_area *sa)
+{
+	elf_fpregset_t nt_fpregset;
+
+	memset(&nt_fpregset, 0, sizeof(nt_fpregset));
+	memcpy(&nt_fpregset.fpc, &sa->fp_ctrl_reg, sizeof(sa->fp_ctrl_reg));
+	memcpy(&nt_fpregset.fprs, &sa->fp_regs, sizeof(sa->fp_regs));
+
+	return nt_init(ptr, NT_PRFPREG, &nt_fpregset, sizeof(nt_fpregset),
+		       "CORE");
+}
+
+/*
+ * Initialize timer note
+ */
+static void *nt_s390_timer(void *ptr, struct save_area *sa)
+{
+	return nt_init(ptr, NT_S390_TIMER, &sa->timer, sizeof(sa->timer),
+			 KEXEC_CORE_NOTE_NAME);
+}
+
+/*
+ * Initialize TOD clock comparator note
+ */
+static void *nt_s390_tod_cmp(void *ptr, struct save_area *sa)
+{
+	return nt_init(ptr, NT_S390_TODCMP, &sa->clk_cmp,
+		       sizeof(sa->clk_cmp), KEXEC_CORE_NOTE_NAME);
+}
+
+/*
+ * Initialize TOD programmable register note
+ */
+static void *nt_s390_tod_preg(void *ptr, struct save_area *sa)
+{
+	return nt_init(ptr, NT_S390_TODPREG, &sa->tod_reg,
+		       sizeof(sa->tod_reg), KEXEC_CORE_NOTE_NAME);
+}
+
+/*
+ * Initialize control register note
+ */
+static void *nt_s390_ctrs(void *ptr, struct save_area *sa)
+{
+	return nt_init(ptr, NT_S390_CTRS, &sa->ctrl_regs,
+		       sizeof(sa->ctrl_regs), KEXEC_CORE_NOTE_NAME);
+}
+
+/*
+ * Initialize prefix register note
+ */
+static void *nt_s390_prefix(void *ptr, struct save_area *sa)
+{
+	return nt_init(ptr, NT_S390_PREFIX, &sa->pref_reg,
+			 sizeof(sa->pref_reg), KEXEC_CORE_NOTE_NAME);
+}
+
+/*
+ * Fill ELF notes for one CPU with save area registers
+ */
+void *fill_cpu_elf_notes(void *ptr, struct save_area *sa)
+{
+	ptr = nt_prstatus(ptr, sa);
+	ptr = nt_fpregset(ptr, sa);
+	ptr = nt_s390_timer(ptr, sa);
+	ptr = nt_s390_tod_cmp(ptr, sa);
+	ptr = nt_s390_tod_preg(ptr, sa);
+	ptr = nt_s390_ctrs(ptr, sa);
+	ptr = nt_s390_prefix(ptr, sa);
+	return ptr;
+}
+
+/*
+ * Initialize prpsinfo note (new kernel)
+ */
+static void *nt_prpsinfo(void *ptr)
+{
+	struct elf_prpsinfo prpsinfo;
+
+	memset(&prpsinfo, 0, sizeof(prpsinfo));
+	prpsinfo.pr_sname = 'R';
+	strcpy(prpsinfo.pr_fname, "vmlinux");
+	return nt_init(ptr, NT_PRPSINFO, &prpsinfo, sizeof(prpsinfo),
+		       KEXEC_CORE_NOTE_NAME);
+}
+
+/*
+ * Initialize vmcoreinfo note (new kernel)
+ */
+static void *nt_vmcoreinfo(void *ptr)
+{
+	char nt_name[11], *vmcoreinfo;
+	Elf64_Nhdr note;
+	void *addr;
+
+	if (copy_from_oldmem(&addr, &S390_lowcore.vmcore_info, sizeof(addr)))
+		return ptr;
+	memset(nt_name, 0, sizeof(nt_name));
+	if (copy_from_oldmem(&note, addr, sizeof(note)))
+		return ptr;
+	if (copy_from_oldmem(nt_name, addr + sizeof(note), sizeof(nt_name) - 1))
+		return ptr;
+	if (strcmp(nt_name, "VMCOREINFO") != 0)
+		return ptr;
+	vmcoreinfo = kzalloc_panic(note.n_descsz + 1);
+	if (copy_from_oldmem(vmcoreinfo, addr + 24, note.n_descsz))
+		return ptr;
+	vmcoreinfo[note.n_descsz + 1] = 0;
+	return nt_init(ptr, 0, vmcoreinfo, note.n_descsz, "VMCOREINFO");
+}
+
+/*
+ * Initialize ELF header (new kernel)
+ */
+static void *ehdr_init(Elf64_Ehdr *ehdr, int mem_chunk_cnt)
+{
+	memset(ehdr, 0, sizeof(*ehdr));
+	memcpy(ehdr->e_ident, ELFMAG, SELFMAG);
+	ehdr->e_ident[EI_CLASS] = ELFCLASS64;
+	ehdr->e_ident[EI_DATA] = ELFDATA2MSB;
+	ehdr->e_ident[EI_VERSION] = EV_CURRENT;
+	memset(ehdr->e_ident + EI_PAD, 0, EI_NIDENT - EI_PAD);
+	ehdr->e_type = ET_CORE;
+	ehdr->e_machine = EM_S390;
+	ehdr->e_version = EV_CURRENT;
+	ehdr->e_phoff = sizeof(Elf64_Ehdr);
+	ehdr->e_ehsize = sizeof(Elf64_Ehdr);
+	ehdr->e_phentsize = sizeof(Elf64_Phdr);
+	ehdr->e_phnum = mem_chunk_cnt + 1;
+	return ehdr + 1;
+}
+
+/*
+ * Return CPU count for ELF header (new kernel)
+ */
+static int get_cpu_cnt(void)
+{
+	int i, cpus = 0;
+
+	for (i = 0; zfcpdump_save_areas[i]; i++) {
+		if (zfcpdump_save_areas[i]->pref_reg == 0)
+			continue;
+		cpus++;
+	}
+	return cpus;
+}
+
+/*
+ * Return memory chunk count for ELF header (new kernel)
+ */
+static int get_mem_chunk_cnt(void)
+{
+	struct mem_chunk *chunk_array, *mem_chunk;
+	int i, cnt = 0;
+
+	chunk_array = get_memory_layout();
+	for (i = 0; i < MEMORY_CHUNKS; i++) {
+		mem_chunk = &chunk_array[i];
+		if (chunk_array[i].type != CHUNK_READ_WRITE &&
+		    chunk_array[i].type != CHUNK_READ_ONLY)
+			continue;
+		if (mem_chunk->size == 0)
+			continue;
+		cnt++;
+	}
+	kfree(chunk_array);
+	return cnt;
+}
+
+/*
+ * Relocate pointer in order to allow vmcore code access the data
+ */
+static inline unsigned long relocate(unsigned long addr)
+{
+	return OLDMEM_BASE + addr;
+}
+
+/*
+ * Initialize ELF loads (new kernel)
+ */
+static int loads_init(Elf64_Phdr *phdr, u64 loads_offset)
+{
+	struct mem_chunk *chunk_array, *mem_chunk;
+	int i;
+
+	chunk_array = get_memory_layout();
+	for (i = 0; i < MEMORY_CHUNKS; i++) {
+		mem_chunk = &chunk_array[i];
+		if (mem_chunk->size == 0)
+			break;
+		if (chunk_array[i].type != CHUNK_READ_WRITE &&
+		    chunk_array[i].type != CHUNK_READ_ONLY)
+			continue;
+		else
+			phdr->p_filesz = mem_chunk->size;
+		phdr->p_type = PT_LOAD;
+		phdr->p_offset = mem_chunk->addr;
+		phdr->p_vaddr = mem_chunk->addr;
+		phdr->p_paddr = mem_chunk->addr;
+		phdr->p_memsz = mem_chunk->size;
+		phdr->p_flags = PF_R | PF_W | PF_X;
+		phdr->p_align = PAGE_SIZE;
+		phdr++;
+	}
+	kfree(chunk_array);
+	return i;
+}
+
+/*
+ * Initialize notes (new kernel)
+ */
+static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset)
+{
+	struct save_area *sa;
+	void *ptr_start = ptr;
+	int i;
+
+	ptr = nt_prpsinfo(ptr);
+
+	for (i = 0; zfcpdump_save_areas[i]; i++) {
+		sa = zfcpdump_save_areas[i];
+		if (sa->pref_reg == 0)
+			continue;
+		ptr = fill_cpu_elf_notes(ptr, sa);
+	}
+	ptr = nt_vmcoreinfo(ptr);
+	memset(phdr, 0, sizeof(*phdr));
+	phdr->p_type = PT_NOTE;
+	phdr->p_offset = relocate(notes_offset);
+	phdr->p_filesz = (unsigned long) PTR_SUB(ptr, ptr_start);
+	phdr->p_memsz = phdr->p_filesz;
+	return ptr;
+}
+
+/*
+ * Create ELF core header (new kernel)
+ */
+static void s390_elf_corehdr_create(char **elfcorebuf, size_t *elfcorebuf_sz)
+{
+	Elf64_Phdr *phdr_notes, *phdr_loads;
+	int mem_chunk_cnt;
+	void *ptr, *hdr;
+	u32 alloc_size;
+	u64 hdr_off;
+
+	mem_chunk_cnt = get_mem_chunk_cnt();
+
+	alloc_size = 0x1000 + get_cpu_cnt() * 0x300 +
+		mem_chunk_cnt * sizeof(Elf64_Phdr);
+	hdr = kzalloc_panic(alloc_size);
+	/* Init elf header */
+	ptr = ehdr_init(hdr, mem_chunk_cnt);
+	/* Init program headers */
+	phdr_notes = ptr;
+	ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr));
+	phdr_loads = ptr;
+	ptr = PTR_ADD(ptr, sizeof(Elf64_Phdr) * mem_chunk_cnt);
+	/* Init notes */
+	hdr_off = PTR_DIFF(ptr, hdr);
+	ptr = notes_init(phdr_notes, ptr, ((unsigned long) hdr) + hdr_off);
+	/* Init loads */
+	hdr_off = PTR_DIFF(ptr, hdr);
+	loads_init(phdr_loads, ((unsigned long) hdr) + hdr_off);
+	*elfcorebuf_sz = hdr_off;
+	*elfcorebuf = (void *) relocate((unsigned long) hdr);
+	BUG_ON(*elfcorebuf_sz > alloc_size);
+}
+
+/*
+ * Create kdump ELF core header in new kernel, if it has not been passed via
+ * the "elfcorehdr" kernel parameter
+ */
+static int setup_kdump_elfcorehdr(void)
+{
+	size_t elfcorebuf_sz;
+	char *elfcorebuf;
+
+	if (!OLDMEM_BASE || is_kdump_kernel())
+		return -EINVAL;
+	s390_elf_corehdr_create(&elfcorebuf, &elfcorebuf_sz);
+	elfcorehdr_addr = (unsigned long long) elfcorebuf;
+	elfcorehdr_size = elfcorebuf_sz;
+	return 0;
+}
+
+subsys_initcall(setup_kdump_elfcorehdr);
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
index 2d781bab37b..900068d2bf9 100644
--- a/arch/s390/kernel/head.S
+++ b/arch/s390/kernel/head.S
@@ -449,10 +449,28 @@ ENTRY(start)
 #
 	.org	0x10000
 ENTRY(startup)
+	j	.Lep_startup_normal
+	.org	0x10008
+#
+# This is a list of s390 kernel entry points. At address 0x1000f the number of
+# valid entry points is stored.
+#
+# IMPORTANT: Do not change this table, it is s390 kernel ABI!
+#
+	.ascii	"S390EP"
+	.byte	0x00,0x01
+#
+# kdump startup-code at 0x10010, running in 64 bit absolute addressing mode
+#
+	.org	0x10010
+ENTRY(startup_kdump)
+	j	.Lep_startup_kdump
+.Lep_startup_normal:
 	basr	%r13,0			# get base
 .LPG0:
 	xc	0x200(256),0x200	# partially clear lowcore
 	xc	0x300(256),0x300
+	xc	0xe00(256),0xe00
 	stck	__LC_LAST_UPDATE_CLOCK
 	spt	5f-.LPG0(%r13)
 	mvc	__LC_LAST_UPDATE_TIMER(8),5f-.LPG0(%r13)
@@ -534,6 +552,8 @@ ENTRY(startup)
 	.align	8
 5:	.long	0x7fffffff,0xffffffff
 
+#include "head_kdump.S"
+
 #
 # params at 10400 (setup.h)
 #
@@ -541,6 +561,8 @@ ENTRY(startup)
 	.long	0,0			# IPL_DEVICE
 	.long	0,0			# INITRD_START
 	.long	0,0			# INITRD_SIZE
+	.long	0,0			# OLDMEM_BASE
+	.long	0,0			# OLDMEM_SIZE
 
 	.org	COMMAND_LINE
 	.byte	"root=/dev/ram0 ro"
diff --git a/arch/s390/kernel/head_kdump.S b/arch/s390/kernel/head_kdump.S
new file mode 100644
index 00000000000..e1ac3893e97
--- /dev/null
+++ b/arch/s390/kernel/head_kdump.S
@@ -0,0 +1,119 @@
+/*
+ * S390 kdump lowlevel functions (new kernel)
+ *
+ * Copyright IBM Corp. 2011
+ * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com>
+ */
+
+#define DATAMOVER_ADDR	0x4000
+#define COPY_PAGE_ADDR	0x6000
+
+#ifdef CONFIG_CRASH_DUMP
+
+#
+# kdump entry (new kernel - not yet relocated)
+#
+# Note: This code has to be position independent
+#
+
+.align 2
+.Lep_startup_kdump:
+	lhi	%r1,2				# mode 2 = esame (dump)
+	sigp	%r1,%r0,0x12			# Switch to esame mode
+	sam64					# Switch to 64 bit addressing
+	basr	%r13,0
+.Lbase:
+	larl	%r2,.Lbase_addr			# Check, if we have been
+	lg	%r2,0(%r2)			# already relocated:
+	clgr	%r2,%r13			#
+	jne	.Lrelocate			# No : Start data mover
+	lghi	%r2,0				# Yes: Start kdump kernel
+	brasl	%r14,startup_kdump_relocated
+
+.Lrelocate:
+	larl	%r4,startup
+	lg	%r2,0x418(%r4)			# Get kdump base
+	lg	%r3,0x420(%r4)			# Get kdump size
+
+	larl	%r10,.Lcopy_start		# Source of data mover
+	lghi	%r8,DATAMOVER_ADDR		# Target of data mover
+	mvc	0(256,%r8),0(%r10)		# Copy data mover code
+
+	agr	%r8,%r2				# Copy data mover to
+	mvc	0(256,%r8),0(%r10)		# reserved mem
+
+	lghi	%r14,DATAMOVER_ADDR		# Jump to copied data mover
+	basr	%r14,%r14
+.Lbase_addr:
+	.quad	.Lbase
+
+#
+# kdump data mover code (runs at address DATAMOVER_ADDR)
+#
+# r2: kdump base address
+# r3: kdump size
+#
+.Lcopy_start:
+	basr	%r13,0				# Base
+0:
+	lgr	%r11,%r2			# Save kdump base address
+	lgr	%r12,%r2
+	agr	%r12,%r3			# Compute kdump end address
+
+	lghi	%r5,0
+	lghi	%r10,COPY_PAGE_ADDR		# Load copy page address
+1:
+	mvc	0(256,%r10),0(%r5)		# Copy old kernel to tmp
+	mvc	0(256,%r5),0(%r11)		# Copy new kernel to old
+	mvc	0(256,%r11),0(%r10)		# Copy tmp to new
+	aghi	%r11,256
+	aghi	%r5,256
+	clgr	%r11,%r12
+	jl	1b
+
+	lg	%r14,.Lstartup_kdump-0b(%r13)
+	basr	%r14,%r14			# Start relocated kernel
+.Lstartup_kdump:
+	.long	0x00000000,0x00000000 + startup_kdump_relocated
+.Lcopy_end:
+
+#
+# Startup of kdump (relocated new kernel)
+#
+.align 2
+startup_kdump_relocated:
+	basr	%r13,0
+0:
+	mvc	0(8,%r0),.Lrestart_psw-0b(%r13)	# Setup restart PSW
+	mvc	464(16,%r0),.Lpgm_psw-0b(%r13)	# Setup pgm check PSW
+	lhi	%r1,1				# Start new kernel
+	diag	%r1,%r1,0x308			# with diag 308
+
+.Lno_diag308:					# No diag 308
+	sam31					# Switch to 31 bit addr mode
+	sr	%r1,%r1				# Erase register r1
+	sr	%r2,%r2				# Erase register r2
+	sigp	%r1,%r2,0x12			# Switch to 31 bit arch mode
+	lpsw	0				# Start new kernel...
+.align	8
+.Lrestart_psw:
+	.long	0x00080000,0x80000000 + startup
+.Lpgm_psw:
+	.quad	0x0000000180000000,0x0000000000000000 + .Lno_diag308
+#else
+.align 2
+.Lep_startup_kdump:
+#ifdef CONFIG_64BIT
+	larl	%r13,startup_kdump_crash
+	lpswe	0(%r13)
+.align 8
+startup_kdump_crash:
+	.quad	0x0002000080000000,0x0000000000000000 + startup_kdump_crash
+#else
+	basr	%r13,0
+0:	lpsw	startup_kdump_crash-0b(%r13)
+.align 8
+startup_kdump_crash:
+	.long	0x000a0000,0x00000000 + startup_kdump_crash
+#endif /* CONFIG_64BIT */
+#endif /* CONFIG_CRASH_DUMP */
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index 90769b4bc7f..ca0520c5254 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -16,6 +16,7 @@
 #include <linux/ctype.h>
 #include <linux/fs.h>
 #include <linux/gfp.h>
+#include <linux/crash_dump.h>
 #include <asm/ipl.h>
 #include <asm/smp.h>
 #include <asm/setup.h>
@@ -1740,6 +1741,9 @@ void do_restart(void)
 {
 	smp_restart_with_online_cpu();
 	smp_send_stop();
+#ifdef CONFIG_CRASH_DUMP
+	crash_kexec(NULL);
+#endif
 	on_restart_trigger.action->fn(&on_restart_trigger);
 	stop_run(&on_restart_trigger);
 }
@@ -2010,7 +2014,7 @@ static void do_reset_calls(void)
 
 u32 dump_prefix_page;
 
-void s390_reset_system(void)
+void s390_reset_system(void (*func)(void *), void *data)
 {
 	struct _lowcore *lc;
 
@@ -2038,6 +2042,10 @@ void s390_reset_system(void)
 	S390_lowcore.program_new_psw.addr =
 		PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler;
 
+	/* Store status at absolute zero */
+	store_status();
+
 	do_reset_calls();
+	if (func)
+		func(data);
 }
-
diff --git a/arch/s390/kernel/machine_kexec.c b/arch/s390/kernel/machine_kexec.c
index b09b9c62573..0ceac06a029 100644
--- a/arch/s390/kernel/machine_kexec.c
+++ b/arch/s390/kernel/machine_kexec.c
@@ -1,10 +1,11 @@
 /*
  * arch/s390/kernel/machine_kexec.c
  *
- * Copyright IBM Corp. 2005,2006
+ * Copyright IBM Corp. 2005,2011
  *
  * Author(s): Rolf Adelsberger,
  *	      Heiko Carstens <heiko.carstens@de.ibm.com>
+ *	      Michael Holzheu <holzheu@linux.vnet.ibm.com>
  */
 
 #include <linux/device.h>
@@ -21,12 +22,131 @@
 #include <asm/smp.h>
 #include <asm/reset.h>
 #include <asm/ipl.h>
+#include <asm/diag.h>
+#include <asm/asm-offsets.h>
 
 typedef void (*relocate_kernel_t)(kimage_entry_t *, unsigned long);
 
 extern const unsigned char relocate_kernel[];
 extern const unsigned long long relocate_kernel_len;
 
+#ifdef CONFIG_CRASH_DUMP
+
+void *fill_cpu_elf_notes(void *ptr, struct save_area *sa);
+
+/*
+ * Create ELF notes for one CPU
+ */
+static void add_elf_notes(int cpu)
+{
+	struct save_area *sa = (void *) 4608 + store_prefix();
+	void *ptr;
+
+	memcpy((void *) (4608UL + sa->pref_reg), sa, sizeof(*sa));
+	ptr = (u64 *) per_cpu_ptr(crash_notes, cpu);
+	ptr = fill_cpu_elf_notes(ptr, sa);
+	memset(ptr, 0, sizeof(struct elf_note));
+}
+
+/*
+ * Store status of next available physical CPU
+ */
+static int store_status_next(int start_cpu, int this_cpu)
+{
+	struct save_area *sa = (void *) 4608 + store_prefix();
+	int cpu, rc;
+
+	for (cpu = start_cpu; cpu < 65536; cpu++) {
+		if (cpu == this_cpu)
+			continue;
+		do {
+			rc = raw_sigp(cpu, sigp_stop_and_store_status);
+		} while (rc == sigp_busy);
+		if (rc != sigp_order_code_accepted)
+			continue;
+		if (sa->pref_reg)
+			return cpu;
+	}
+	return -1;
+}
+
+/*
+ * Initialize CPU ELF notes
+ */
+void setup_regs(void)
+{
+	unsigned long sa = S390_lowcore.prefixreg_save_area + SAVE_AREA_BASE;
+	int cpu, this_cpu, phys_cpu = 0, first = 1;
+
+	this_cpu = stap();
+
+	if (!S390_lowcore.prefixreg_save_area)
+		first = 0;
+	for_each_online_cpu(cpu) {
+		if (first) {
+			add_elf_notes(cpu);
+			first = 0;
+			continue;
+		}
+		phys_cpu = store_status_next(phys_cpu, this_cpu);
+		if (phys_cpu == -1)
+			break;
+		add_elf_notes(cpu);
+		phys_cpu++;
+	}
+	/* Copy dump CPU store status info to absolute zero */
+	memcpy((void *) SAVE_AREA_BASE, (void *) sa, sizeof(struct save_area));
+}
+
+#endif
+
+/*
+ * Start kdump: We expect here that a store status has been done on our CPU
+ */
+static void __do_machine_kdump(void *image)
+{
+#ifdef CONFIG_CRASH_DUMP
+	int (*start_kdump)(int) = (void *)((struct kimage *) image)->start;
+
+	__load_psw_mask(PSW_BASE_BITS | PSW_DEFAULT_KEY);
+	setup_regs();
+	start_kdump(1);
+#endif
+}
+
+/*
+ * Check if kdump checksums are valid: We call purgatory with parameter "0"
+ */
+static int kdump_csum_valid(struct kimage *image)
+{
+#ifdef CONFIG_CRASH_DUMP
+	int (*start_kdump)(int) = (void *)image->start;
+	int rc;
+
+	__arch_local_irq_stnsm(0xfb); /* disable DAT */
+	rc = start_kdump(0);
+	__arch_local_irq_stosm(0x04); /* enable DAT */
+	return rc ? 0 : -EINVAL;
+#else
+	return -EINVAL;
+#endif
+}
+
+/*
+ * Give back memory to hypervisor before new kdump is loaded
+ */
+static int machine_kexec_prepare_kdump(void)
+{
+#ifdef CONFIG_CRASH_DUMP
+	if (MACHINE_IS_VM)
+		diag10_range(PFN_DOWN(crashk_res.start),
+			     PFN_DOWN(crashk_res.end - crashk_res.start + 1));
+	return 0;
+#else
+	return -EINVAL;
+#endif
+}
+
 int machine_kexec_prepare(struct kimage *image)
 {
 	void *reboot_code_buffer;
@@ -35,6 +155,9 @@ int machine_kexec_prepare(struct kimage *image)
 	if (ipl_flags & IPL_NSS_VALID)
 		return -ENOSYS;
 
+	if (image->type == KEXEC_TYPE_CRASH)
+		return machine_kexec_prepare_kdump();
+
 	/* We don't support anything but the default image type for now. */
 	if (image->type != KEXEC_TYPE_DEFAULT)
 		return -EINVAL;
@@ -51,27 +174,53 @@ void machine_kexec_cleanup(struct kimage *image)
 {
 }
 
+void arch_crash_save_vmcoreinfo(void)
+{
+	VMCOREINFO_SYMBOL(lowcore_ptr);
+	VMCOREINFO_LENGTH(lowcore_ptr, NR_CPUS);
+}
+
 void machine_shutdown(void)
 {
 }
 
-static void __machine_kexec(void *data)
+/*
+ * Do normal kexec
+ */
+static void __do_machine_kexec(void *data)
 {
 	relocate_kernel_t data_mover;
 	struct kimage *image = data;
 
-	pfault_fini();
-	s390_reset_system();
-
 	data_mover = (relocate_kernel_t) page_to_phys(image->control_code_page);
 
 	/* Call the moving routine */
 	(*data_mover)(&image->head, image->start);
-	for (;;);
 }
 
+/*
+ * Reset system and call either kdump or normal kexec
+ */
+static void __machine_kexec(void *data)
+{
+	struct kimage *image = data;
+
+	pfault_fini();
+	if (image->type == KEXEC_TYPE_CRASH)
+		s390_reset_system(__do_machine_kdump, data);
+	else
+		s390_reset_system(__do_machine_kexec, data);
+	disabled_wait((unsigned long) __builtin_return_address(0));
+}
+
+/*
+ * Do either kdump or normal kexec. In case of kdump we first ask
+ * purgatory, if kdump checksums are valid.
+ */