Skip to contentSkip to conversation

Ia64 kdump patch

PATCH Zou Nan hai 1 participant 1 message Jun 7, 2006

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

The ia64 kdump patch is in 2 parts.

the kexec-kdump-ia64-2.6.16.patch should apply on top of the previous kexec patch by Khalid in Tony's test tree.

the kexec-tools-kdump-ia64.patch should apply to kexec-tools-1.101 with kexec-tools-1.101-kdump.patch

To test it.
Build first SMP kernel with KEXEC and KDUMP enabled.

Boot it with kernel parameter "crashkernel=XXX@YYY" means reserver XXX from YYY for crashdumping. Build an UP kernel with KEXEC KDUMP VMCORE enabled. load this kernel as a crashdumping kernel kexec -p vmlinux.gz --initrd=initrd --append="...."

trigger a crash,
maybe "echo c > /proc/sysrq-trigger"
after the crash kernel boots,
cp /proc/vmcore core

gdb first_kernel_vmlinux core

please test and review.

arch/ia64/hp/common/sba_iommu.c +22 -0
diff -Nraup linux-2.6.16/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
@@ -1624,6 +1624,28 @@ ioc_iova_init(struct ioc *ioc)
 	READ_REG(ioc->ioc_hpa + IOC_IBASE);
 }
 
+#ifdef CONFIG_KEXEC
+void
+ioc_iova_disable(void)
+{
+	struct ioc *ioc;
+
+	ioc = ioc_list;
+
+	while (ioc != NULL) {
+		/* Disable IOVA translation */
+		WRITE_REG(ioc->ibase & 0xfffffffffffffffe, ioc->ioc_hpa + IOC_IBASE);
+		READ_REG(ioc->ioc_hpa + IOC_IBASE);
+
+		/* Clear I/O TLB of any possible entries */
+		WRITE_REG(ioc->ibase | (get_iovp_order(ioc->iov_size) + iovp_shift), ioc->ioc_hpa + IOC_PCOM);
+		READ_REG(ioc->ioc_hpa + IOC_PCOM);
+
+		ioc = ioc->next;
+	}
+}
+#endif
+
 static void __init
 ioc_resource_init(struct ioc *ioc)
 {
arch/ia64/Kconfig +23 -0
diff -Nraup linux-2.6.16/arch/ia64/Kconfig b/arch/ia64/Kconfig
@@ -376,6 +376,29 @@ config IA64_PALINFO
 config SGI_SN
 	def_bool y if (IA64_SGI_SN2 || IA64_GENERIC)
 
+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.
+
+config CRASH_DUMP
+	  bool "kernel crash dumps (EXPERIMENTAL)"
+	  depends on EXPERIMENTAL
+	  help
+	    Generate crash dump after being started by kexec.
+
 source "drivers/firmware/Kconfig"
 
 source "fs/Kconfig.binfmt"
arch/ia64/kernel/crash.c +152 -0

152 lines not on this page · raw message

arch/ia64/kernel/efi.c +14 -3
diff -Nraup linux-2.6.16/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
@@ -25,6 +25,7 @@
 #include <linux/types.h>
 #include <linux/time.h>
 #include <linux/efi.h>
+#include <linux/kexec.h>
 
 #include <asm/io.h>
 #include <asm/kregs.h>
@@ -40,7 +41,7 @@ extern efi_status_t efi_call_phys (void 
 struct efi efi;
 EXPORT_SYMBOL(efi);
 static efi_runtime_services_t *runtime;
-static unsigned long mem_limit = ~0UL, max_addr = ~0UL;
+static unsigned long mem_limit = ~0UL, max_addr = ~0UL, min_addr = 0UL;
 
 #define efi_call_virt(f, args...)	(*(f))(args)
 
@@ -420,6 +421,8 @@ efi_init (void)
 			mem_limit = memparse(cp + 4, &cp);
 		} else if (memcmp(cp, "max_addr=", 9) == 0) {
 			max_addr = GRANULEROUNDDOWN(memparse(cp + 9, &cp));
+		} else if (memcmp(cp, "min_addr=", 9) == 0) {
+			min_addr = GRANULEROUNDDOWN(memparse(cp + 9, &cp));
 		} else {
 			while (*cp != ' ' && *cp)
 				++cp;
@@ -427,6 +430,8 @@ efi_init (void)
 				++cp;
 		}
 	}
+	if (min_addr != 0UL)
+		printk(KERN_INFO "Ignoring memory below %luMB\n", min_addr >> 20);
 	if (max_addr != ~0UL)
 		printk(KERN_INFO "Ignoring memory above %luMB\n", max_addr >> 20);
 
@@ -839,7 +844,8 @@ find_memmap_space (void)
 		as = max(contig_low, md->phys_addr);
 		ae = min(contig_high, efi_md_end(md));
 
-		/* keep within max_addr= command line arg */
+		/* keep within max_addr= and min_addr= command line arg */
+		as = max(as, min_addr);
 		ae = min(ae, max_addr);
 		if (ae <= as)
 			continue;
@@ -949,7 +955,8 @@ efi_memmap_init(unsigned long *s, unsign
 		} else
 			ae = efi_md_end(md);
 
-		/* keep within max_addr= command line arg */
+		/* keep within max_addr= and min_addr= command line arg */
+		as = max(as, min_addr);
 		ae = min(ae, max_addr);
 		if (ae <= as)
 			continue;
@@ -1061,6 +1068,10 @@ efi_initialize_iomem_resources(struct re
 			 */
 			insert_resource(res, code_resource);
 			insert_resource(res, data_resource);
+#ifdef CONFIG_KEXEC
+			if (crashk_res.end > crashk_res.start)
+				insert_resource(res, &crashk_res);
+#endif
 		}
 	}
 }
arch/ia64/kernel/entry.S +1 -1
diff -Nraup linux-2.6.16/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
@@ -1590,7 +1590,7 @@ sys_call_table:
 	data8 sys_mq_timedreceive		// 1265
 	data8 sys_mq_notify
 	data8 sys_mq_getsetattr
-	data8 sys_ni_syscall			// reserved for kexec_load
+	data8 sys_kexec_load
 	data8 sys_ni_syscall			// reserved for vserver
 	data8 sys_waitid			// 1270
 	data8 sys_add_key
arch/ia64/kernel/machine_kexec.c +115 -0

115 lines not on this page · raw message

arch/ia64/kernel/Makefile +1 -0
diff -Nraup linux-2.6.16/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_IA64_CYCLONE)	+= cyclone.o
 obj-$(CONFIG_CPU_FREQ)		+= cpufreq/
 obj-$(CONFIG_IA64_MCA_RECOVERY)	+= mca_recovery.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o jprobes.o
+obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o crash.o
 obj-$(CONFIG_IA64_UNCACHED_ALLOCATOR)	+= uncached.o
 mca_recovery-y			+= mca_drv.o mca_drv_asm.o
 
arch/ia64/kernel/relocate_kernel.S +353 -0

353 lines not on this page · raw message

arch/ia64/kernel/setup.c +38 -0
diff -Nraup linux-2.6.16/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
@@ -44,6 +44,8 @@
 #include <linux/platform.h>
 #include <linux/pm.h>
 #include <linux/cpufreq.h>
+#include <linux/kexec.h>
+#include <linux/crash_dump.h>
 
 #include <asm/ia32.h>
 #include <asm/machvec.h>
@@ -251,6 +253,32 @@ reserve_memory (void)
 	}
 #endif
 
+#ifdef CONFIG_KEXEC
+	/* crashkernel=size@addr specifies the location to reserve for
+	 * a crash kernel.  By reserving this memory we guarantee
+	 * that linux never set's it up as a DMA target.
+	 * Useful for holding code to do something appropriate
+	 * after a kernel panic.
+	 */
+	{
+		char *from = strstr(saved_command_line, "crashkernel=");
+		if (from) {
+			unsigned long size, base;
+			size = memparse(from + 12, &from);
+			if (*from == '@') {
+				base = memparse(from + 1, &from);
+				rsvd_region[n].start =
+					(unsigned long)__va(base);
+				rsvd_region[n].end =
+					(unsigned long)__va(base + size);
+				crashk_res.start = base;
+				crashk_res.end = base + size - 1;
+				n++;
+			}
+		}
+	}
+#endif
+
 	efi_memmap_init(&rsvd_region[n].start, &rsvd_region[n].end);
 	n++;
 
@@ -496,6 +524,16 @@ setup_arch (char **cmdline_p)
 	if (!strstr(saved_command_line, "nomca"))
 		ia64_mca_init();
 
+#ifdef CONFIG_CRASH_DUMP
+	{
+		char *from = strstr(saved_command_line, "elfcorehdr=");
+
+		if (from)
+			elfcorehdr_addr = memparse(from+11, &from);
+		saved_max_pfn = (unsigned long) -1;
+	}
+#endif
+
 	platform_setup(cmdline_p);
 	paging_init();
 }
arch/ia64/kernel/smp.c +29 -0
diff -Nraup linux-2.6.16/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c
@@ -30,6 +30,7 @@
 #include <linux/delay.h>
 #include <linux/efi.h>
 #include <linux/bitops.h>
+#include <linux/kexec.h>
 
 #include <asm/atomic.h>
 #include <asm/current.h>
@@ -84,6 +85,34 @@ unlock_ipi_calllock(void)
 	spin_unlock_irq(&call_lock);
 }
 
+#ifdef CONFIG_KEXEC
+/*
+ * Stop the CPU and put it in fake SAL rendezvous. This allows CPU to wake
+ * up with IPI from boot processor
+ */
+void
+kexec_stop_this_cpu (void *func)
+{
+	unsigned long pta, impl_va_bits, pal_base;
+
+	/*
+	 * Remove this CPU by putting it into fake SAL rendezvous
+	 */
+	cpu_clear(smp_processor_id(), cpu_online_map);
+	max_xtp();
+	ia64_eoi();
+
+	/* Disable VHPT */
+	impl_va_bits = ffz(~(local_cpu_data->unimpl_va_mask | (7UL << 61)));
+	pta = POW2(61) - POW2(vmlpt_bits);
+	ia64_set_pta(pta | (0 << 8) | (vmlpt_bits << 2) | 0);
+
+	local_irq_disable();
+	pal_base = __get_cpu_var(ia64_mca_pal_base);
+	kexec_fake_sal_rendez(func, ap_wakeup_vector, pal_base);
+}
+#endif
+
 static void
 stop_this_cpu (void)
 {
include/asm-ia64/kexec.h +34 -0
diff -Nraup linux-2.6.16/include/asm-ia64/kexec.h b/include/asm-ia64/kexec.h
@@ -0,0 +1,34 @@
+#ifndef _ASM_IA64_KEXEC_H
+#define _ASM_IA64_KEXEC_H
+
+
+/* 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 (8192 + 8192 + 4096)
+
+/* The native architecture */
+#define KEXEC_ARCH KEXEC_ARCH_IA_64
+
+#define MAX_NOTE_BYTES 1024
+
+#define pte_bits	3
+#define vmlpt_bits	(impl_va_bits - PAGE_SHIFT + pte_bits)
+#define POW2(n)		(1ULL << (n))
+
+DECLARE_PER_CPU(u64, ia64_mca_pal_base);
+const extern unsigned int relocate_new_kernel_size;
+volatile extern long kexec_rendez;
+extern void relocate_new_kernel(unsigned long, unsigned long, 
+		struct ia64_boot_param *, unsigned long);
+extern void kexec_fake_sal_rendez(void *start, unsigned long wake_up,
+		unsigned long pal_base);
+static inline void
+crash_setup_regs(struct pt_regs *newregs, struct pt_regs *oldregs)
+{
+}
+#endif /* _ASM_IA64_KEXEC_H */
include/asm-ia64/machvec_hpzx1.h +2 -0
diff -Nraup linux-2.6.16/include/asm-ia64/machvec_hpzx1.h b/include/asm-ia64/machvec_hpzx1.h
@@ -34,4 +34,6 @@ extern ia64_mv_dma_mapping_error	sba_dma
 #define platform_dma_supported			sba_dma_supported
 #define platform_dma_mapping_error		sba_dma_mapping_error
 
+extern void ioc_iova_disable(void);
+
 #endif /* _ASM_IA64_MACHVEC_HPZX1_h */
include/asm-ia64/meminit.h +2 -1
diff -Nraup linux-2.6.16/include/asm-ia64/meminit.h b/include/asm-ia64/meminit.h
@@ -16,11 +16,12 @@
  * 	- initrd (optional)
  * 	- command line string
  * 	- kernel code & data
+ * 	- crash dumping code reserved region
  * 	- Kernel memory map built from EFI memory map
  *
  * More could be added if necessary
  */
-#define IA64_MAX_RSVD_REGIONS 6
+#define IA64_MAX_RSVD_REGIONS 7
 
 struct rsvd_region {
 	unsigned long start;	/* virtual address of beginning of element */
include/asm-ia64/smp.h +3 -0
diff -Nraup linux-2.6.16/include/asm-ia64/smp.h b/include/asm-ia64/smp.h
@@ -129,6 +129,9 @@ extern void smp_send_reschedule (int cpu
 extern void lock_ipi_calllock(void);
 extern void unlock_ipi_calllock(void);
 extern void identify_siblings (struct cpuinfo_ia64 *);
+#ifdef CONFIG_KEXEC
+extern void kexec_stop_this_cpu(void *);
+#endif
 
 #else
 
include/linux/irq.h +1 -0
diff -Nraup linux-2.6.16/include/linux/irq.h b/include/linux/irq.h
@@ -94,6 +94,7 @@ irq_descp (int irq)
 #include <asm/hw_irq.h> /* the arch dependent stuff */
 
 extern int setup_irq(unsigned int irq, struct irqaction * new);
+extern void terminate_irqs(void);
 
 #ifdef CONFIG_GENERIC_HARDIRQS
 extern cpumask_t irq_affinity[NR_IRQS];
kernel/irq/manage.c +19 -0
diff -Nraup linux-2.6.16/kernel/irq/manage.c b/kernel/irq/manage.c
@@ -377,3 +377,22 @@ int request_irq(unsigned int irq,
 
 EXPORT_SYMBOL(request_irq);
 
+/*
+ * Terminate any outstanding interrupts
+ */
+void terminate_irqs(void)
+{
+	struct irqaction * action;
+	irq_desc_t *idesc;
+	int i;
+
+	for (i=0; i < NR_IRQS; i++) {
+		idesc = irq_descp(i);
+		action = idesc->action;
+		if (!action)
+			continue;
+		if (idesc->handler->end)
+			idesc->handler->end(i);
+	}
+}
+
kexec/arch/ia64/crashdump-ia64.c +351 -0

351 lines not on this page · raw message

kexec/arch/ia64/crashdump-ia64.h +13 -0
diff -Nraup a/kexec/arch/ia64/crashdump-ia64.h b/kexec/arch/ia64/crashdump-ia64.h
@@ -0,0 +1,13 @@
+#ifndef CRASHDUMP_IA64_H
+#define CRASHDUMP_IA64_H
+
+#define PAGE_OFFSET             0xe000000000000000UL
+#define __pa(x)			((unsigned long)(x)-PAGE_OFFSET)
+extern int load_crashdump_segments(struct kexec_info *info, 
+		struct mem_ehdr *ehdr, unsigned long max_addr, 
+		unsigned long min_base, char **cmdline);
+
+#define CRASH_MAX_MEMMAP_NR     (KEXEC_MAX_SEGMENTS + 1)
+#define CRASH_MAX_MEMORY_RANGES (MAX_MEMORY_RANGES + 2)
+
+#endif
kexec/arch/ia64/kexec-elf-ia64.c +125 -23

208 lines not on this page · raw message

kexec/arch/ia64/kexec-elf-rel-ia64.c +123 -5

158 lines not on this page · raw message

kexec/arch/ia64/kexec-ia64.c +74 -53

169 lines not on this page · raw message

kexec/arch/ia64/kexec-ia64.h +3 -1
diff -Nraup a/kexec/arch/ia64/kexec-ia64.h b/kexec/arch/ia64/kexec-ia64.h
@@ -5,5 +5,7 @@ int elf_ia64_probe(const char *buf, off_
 int elf_ia64_load(int argc, char **argv, const char *buf, off_t len,
 	struct kexec_info *info);
 void elf_ia64_usage(void);
-
+#define MAX_MEMORY_RANGES 1024
+#define EFI_PAGE_SIZE	  (1UL<<12)
+#define ELF_PAGE_SIZE	  (1UL<<16)
 #endif /* KEXEC_IA64_H */
kexec/arch/ia64/Makefile +2 -0
diff -Nraup a/kexec/arch/ia64/Makefile b/kexec/arch/ia64/Makefile
@@ -4,3 +4,5 @@
 KEXEC_C_SRCS+= kexec/arch/ia64/kexec-ia64.c 
 KEXEC_C_SRCS+= kexec/arch/ia64/kexec-elf-ia64.c 
 KEXEC_C_SRCS+= kexec/arch/ia64/kexec-elf-rel-ia64.c
+KEXEC_C_SRCS+= kexec/arch/ia64/crashdump-ia64.c
+
kexec/kexec.c +4 -1
diff -Nraup a/kexec/kexec.c b/kexec/kexec.c
@@ -96,6 +96,9 @@ int valid_memory_range(unsigned long sst
 			continue;
 		mstart = memory_range[i].start;
 		mend = memory_range[i].end;
+		if (i < memory_ranges - 1 && mend == memory_range[i+1].start)
+			mend = memory_range[i+1].end;
+
 		/* Check to see if we are fully contained */
 		if ((mstart <= sstart) && (mend >= send)) {
 			return 1;
@@ -187,7 +190,7 @@ unsigned long locate_hole(struct kexec_i
 	}
 
 	/* Compute the free memory ranges */
-	max_mem_ranges = memory_ranges + (info->nr_segments -1);
+	max_mem_ranges = memory_ranges + (info->nr_segments);
 	mem_range = malloc(max_mem_ranges *sizeof(struct memory_range));
 	mem_ranges = 0;
 		
kexec/kexec-syscall.h +1 -1
diff -Nraup a/kexec/kexec-syscall.h b/kexec/kexec-syscall.h
@@ -68,6 +68,6 @@ static inline long kexec_reboot(void)
 #define KEXEC_ARCH_PPC64   (21 << 16)
 #define KEXEC_ARCH_IA_64   (50 << 16)
 
-#define KEXEC_MAX_SEGMENTS 8
+#define KEXEC_MAX_SEGMENTS 16
 
 #endif /* KEXEC_SYSCALL_H */
purgatory/arch/ia64/console-ia64.c +43 -1

48 lines not on this page · raw message

purgatory/arch/ia64/entry.S +67 -0

67 lines not on this page · raw message

purgatory/arch/ia64/io.h +94 -0

94 lines not on this page · raw message

purgatory/arch/ia64/Makefile +3 -3
diff -Nraup a/purgatory/arch/ia64/Makefile b/purgatory/arch/ia64/Makefile
@@ -1,9 +1,9 @@
 #
 # Purgatory ia64
 #
-
-PURGATORY_S_SRCS+=
+PCFLAGS		+= -ffixed-r28
+PURGATORY_S_SRCS+= purgatory/arch/ia64/entry.S
 PURGATORY_C_SRCS+= purgatory/arch/ia64/purgatory-ia64.c
 PURGATORY_C_SRCS+= purgatory/arch/ia64/console-ia64.c
-PURGATORY_C_SRCS+=
+PURGATORY_C_SRCS+= purgatory/arch/ia64/vga.c
 
purgatory/arch/ia64/purgatory-ia64.c +264 -2

273 lines not on this page · raw message

purgatory/arch/ia64/purgatory-ia64.h +1 -2
diff -Nraup a/purgatory/arch/ia64/purgatory-ia64.h b/purgatory/arch/ia64/purgatory-ia64.h
@@ -1,6 +1,5 @@
 #ifndef PURGATORY_IA64_H
 #define PURGATORY_IA64_H
 
-/* nothing yet */
-
+void reset_vga(void);
 #endif /* PURGATORY_IA64_H */
purgatory/arch/ia64/vga.c +143 -0

143 lines not on this page · raw message