kexec on ia64

diff -urN linux-2.6.8/arch/ia64/kernel/efi.c linux-2.6.8-ia64/arch/ia64/kernel/efi.c
@@ -17,6 +17,9 @@
  *
  * Goutham Rao: <[email protected]>
  *	Skip non-WB memory and ignore empty memory ranges.
+ *
+ * Nov 12, 2004: Added initial support for kexec 
+ * 				- Khalid Aziz <[email protected]>
  */
 #include <linux/config.h>
 #include <linux/module.h>

@@ -37,6 +40,10 @@
 extern efi_status_t efi_call_phys (void *, ...);
 
 struct efi efi;
+#ifdef CONFIG_KEXEC
+unsigned long kexec_reboot = 0;
+unsigned long saved_efi_memmap_size;
+#endif
 EXPORT_SYMBOL(efi);
 static efi_runtime_services_t *runtime;
 static unsigned long mem_limit = ~0UL, max_addr = ~0UL;

@@ -464,6 +471,9 @@
 		 * Cannot write to CRx with PSR.ic=1
 		 */
 		psr = ia64_clear_ic();
+#if CONFIG_KEXEC
+		ia64_ptr(0x01, vaddr & mask, IA64_GRANULE_SHIFT);
+#endif
 		ia64_itr(0x1, IA64_TR_PALCODE, vaddr & mask,
 			 pte_val(pfn_pte(md->phys_addr >> PAGE_SHIFT, PAGE_KERNEL)),
 			 IA64_GRANULE_SHIFT);

@@ -503,6 +513,14 @@
 			if (end != cp)
 				break;
 			cp = end;
+#ifdef CONFIG_KEXEC
+		} else if (memcmp(cp, "kexec_reboot", 12) == 0) {
+			cp += 12;
+			kexec_reboot = 1;
+			if (end != cp)
+				break;
+			cp = end;
+#endif
 		} else {
 			while (*cp != ' ' && *cp)
 				++cp;

@@ -595,6 +613,9 @@
 	}
 #endif
 
+#ifdef CONFIG_KEXEC
+	saved_efi_memmap_size = ia64_boot_param->efi_memmap_size;
+#endif
 	efi_map_pal_code();
 	efi_enter_virtual_mode();
 }

@@ -647,10 +668,17 @@
 		}
 	}
 
-	status = efi_call_phys(__va(runtime->set_virtual_address_map),
+#ifdef CONFIG_KEXEC
+	if (kexec_reboot == 0)
+		status = efi_call_phys(__va(runtime->set_virtual_address_map),
 			       ia64_boot_param->efi_memmap_size,
 			       efi_desc_size, ia64_boot_param->efi_memdesc_version,
 			       ia64_boot_param->efi_memmap);
+	else {
+		printk(KERN_INFO "kexec'd kernel: Not virtualizing EFI\n");
+		status = EFI_SUCCESS;
+	}
+#endif
 	if (status != EFI_SUCCESS) {
 		printk(KERN_WARNING "warning: unable to switch EFI into virtual mode "
 		       "(status=%lu)\n", status);

179 lines not on this page · raw message

diff -urN linux-2.6.8/arch/ia64/mm/contig.c linux-2.6.8-ia64/arch/ia64/mm/contig.c
@@ -29,6 +29,11 @@
 static unsigned long num_dma_physpages;
 #endif
 
+#ifdef CONFIG_KEXEC
+void *saved_efi_memmap;
+extern unsigned long saved_efi_memmap_size;
+#endif
+
 /**
  * show_mem - display a memory statistics summary
  *

@@ -164,6 +169,11 @@
 	/* Free all available memory, then mark bootmem-map as being in use. */
 	efi_memmap_walk(filter_rsvd_memory, free_bootmem);
 	reserve_bootmem(bootmap_start, bootmap_size);
+#ifdef CONFIG_KEXEC
+	/* Save EFI memory map for use later when kexec'ing a kernel */
+	saved_efi_memmap = alloc_bootmem(saved_efi_memmap_size);
+	memcpy(saved_efi_memmap, __va(ia64_boot_param->efi_memmap), saved_efi_memmap_size);
+#endif
 
 	find_initrd();
 }

diff -urN linux-2.6.8/arch/ia64/mm/discontig.c linux-2.6.8-ia64/arch/ia64/mm/discontig.c
@@ -40,6 +40,11 @@
 
 static struct early_node_data mem_data[NR_NODES] __initdata;
 
+#ifdef CONFIG_KEXEC
+void *saved_efi_memmap;
+extern unsigned long saved_efi_memmap_size;
+#endif
+
 /**
  * reassign_cpu_only_nodes - called from find_memory to move CPU-only nodes to a memory node
  *

@@ -459,6 +464,12 @@
 	reserve_pernode_space();
 	initialize_pernode_data();
 
+#ifdef CONFIG_KEXEC
+	/* Save EFI memory map for use later when kexec'ing a kernel */
+	saved_efi_memmap = alloc_bootmem(saved_efi_memmap_size);
+	memcpy(saved_efi_memmap, __va(ia64_boot_param->efi_memmap), saved_efi_memmap_size);
+#endif
+
 	max_pfn = max_low_pfn;
 
 	find_initrd();

diff -urN linux-2.6.8/include/asm-ia64/kexec.h linux-2.6.8-ia64/include/asm-ia64/kexec.h
@@ -0,0 +1,14 @@
+#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)
+
+#endif /* _ASM_IA64_KEXEC_H */

diff -urN linux-2.6.8/include/asm-ia64/mmu_context.h linux-2.6.8-ia64/include/asm-ia64/mmu_context.h
@@ -203,5 +203,7 @@
 
 #define switch_mm(prev_mm,next_mm,next_task)	activate_mm(prev_mm, next_mm)
 
+extern void use_mm(struct mm_struct *mm);
+
 # endif /* ! __ASSEMBLY__ */
 #endif /* _ASM_IA64_MMU_CONTEXT_H */

diff -urN linux-2.6.8/kernel/sys.c linux-2.6.8-ia64/kernel/sys.c
@@ -516,7 +516,7 @@
 			return -EINVAL;
 		}
 		notifier_call_chain(&reboot_notifier_list, SYS_RESTART, NULL);
-		system_state = SYSTEM_BOOTING;
+		system_state = SYSTEM_RESTART;
 		device_shutdown();
 		printk(KERN_EMERG "Starting new kernel\n");
 		machine_shutdown();

306 lines not on this page · raw message

47 lines not on this page · raw message

diff -urN kexec-tools-1.98/kexec/kexec-ia64.h kexec-tools-1.98-ia64/kexec/kexec-ia64.h
@@ -0,0 +1,9 @@
+#ifndef KEXEC_IA64_H
+#define KEXEC_IA64_H
+
+int elf64_ia64_probe(FILE *file);
+int elf64_ia64_load(FILE *file, int argc, char **argv,
+	void **ret_entry, struct kexec_segment **ret_segments, int *ret_nr_segments);
+void elf64_ia64_usage(void);
+
+#endif /* KEXEC_IA64_H */

diff -urN kexec-tools-1.98/kexec/kexec.c kexec-tools-1.98-ia64/kexec/kexec.c
@@ -35,6 +35,16 @@
 {
 	int i;
 
+#ifdef __ia64__
+	/*
+	 * /proc/iomem on ia64 does not show where all memory is. If
+	 * that is fixed up, we can make use of that to validate
+	 * the memory range kernel will be loade din. Until then.....
+	 * -- Khalid Aziz
+	 */
+	return 0;
+#endif
+
 	for (i = 0; i < memory_ranges; i++) {
 		unsigned long mstart, mend;
 		unsigned long sstart, send;

@@ -923,3 +923,90 @@ efi_memmap_init(unsigned long *s, unsign
 	*s = (u64)kern_memmap;
 	*e = (u64)++k;
 }
+
+void
+efi_initialize_iomem_resources(struct resource *code_resource,
+			       struct resource *data_resource)
+{
+	struct resource *res;
+	void *efi_map_start, *efi_map_end, *p;
+	efi_memory_desc_t *md;
+	u64 efi_desc_size;
+	char *name;
+	unsigned long flags;
+
+	efi_map_start = __va(ia64_boot_param->efi_memmap);
+	efi_map_end   = efi_map_start + ia64_boot_param->efi_memmap_size;
+	efi_desc_size = ia64_boot_param->efi_memdesc_size;
+
+	res = NULL;
+
+	for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) {
+		md = p;
+
+		if (md->num_pages == 0) /* should not happen */
+			continue;
+
+		flags = IORESOURCE_MEM;
+		switch (md->type) {
+
+			case EFI_MEMORY_MAPPED_IO:
+			case EFI_MEMORY_MAPPED_IO_PORT_SPACE:
+				continue;
+
+			case EFI_LOADER_CODE:
+			case EFI_LOADER_DATA:
+			case EFI_BOOT_SERVICES_DATA:
+			case EFI_BOOT_SERVICES_CODE:
+			case EFI_CONVENTIONAL_MEMORY:
+				if (md->attribute & EFI_MEMORY_WP) {
+					name = "System ROM";
+					flags |= IORESOURCE_READONLY;
+				} else {
+					name = "System RAM";
+				}
+				break;
+
+			case EFI_ACPI_MEMORY_NVS:
+				name = "ACPI Non-volatile Storage";
+				flags |= IORESOURCE_BUSY;
+				break;
+
+			case EFI_UNUSABLE_MEMORY:
+				name = "reserved";
+				flags |= IORESOURCE_BUSY | IORESOURCE_DISABLED;
+				break;
+
+			case EFI_RESERVED_TYPE:
+			case EFI_RUNTIME_SERVICES_CODE:
+			case EFI_RUNTIME_SERVICES_DATA:
+			case EFI_ACPI_RECLAIM_MEMORY:
+			default:
+				name = "reserved";
+				flags |= IORESOURCE_BUSY;
+				break;
+		}
+
+		if ((res = kcalloc(1, sizeof(struct resource), GFP_KERNEL)) == NULL) {
+			printk(KERN_ERR "failed to alocate resource for iomem\n");
+			return;
+		}
+
+		res->name = name;
+		res->start = md->phys_addr;
+		res->end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1;
+		res->flags = flags;
+
+		if (insert_resource(&iomem_resource, res) < 0)
+			kfree(res);
+		else {
+			/*
+			 * We don't know which region contains
+			 * kernel data so we try it repeatedly and
+			 * let the resource manager test it.
+			 */
+			insert_resource(res, code_resource);
+			insert_resource(res, data_resource);
+		}
+	}
+}

@@ -78,6 +78,19 @@ struct screen_info screen_info;
 unsigned long vga_console_iobase;
 unsigned long vga_console_membase;
 
+static struct resource data_resource = {
+	.name	= "Kernel data",
+	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+};
+
+static struct resource code_resource = {
+	.name	= "Kernel code",
+	.flags	= IORESOURCE_BUSY | IORESOURCE_MEM
+};
+extern void efi_initialize_iomem_resources(struct resource *,
+		struct resource *);
+extern char _text[], _edata[], _etext[];
+
 unsigned long ia64_max_cacheline_size;
 unsigned long ia64_iobase;	/* virtual address for I/O accesses */
 EXPORT_SYMBOL(ia64_iobase);

@@ -171,6 +184,22 @@ sort_regions (struct rsvd_region *rsvd_r
 	}
 }
 
+/*
+ * Request address space for all standard resources
+ */
+static int __init register_memory(void)
+{
+	code_resource.start = ia64_tpa(_text);
+	code_resource.end   = ia64_tpa(_etext) - 1;
+	data_resource.start = ia64_tpa(_etext);
+	data_resource.end   = ia64_tpa(_edata) - 1;
+	efi_initialize_iomem_resources(&code_resource, &data_resource);
+
+	return 0;
+}
+
+__initcall(register_memory);
+
 /**
  * reserve_memory - setup reserved memory areas
  *

450 lines not on this page · raw message

@@ -211,6 +211,9 @@ reserve_memory (void)
 	}
 #endif
 
+	efi_memmap_init(&rsvd_region[n].start, &rsvd_region[n].end);
+	n++;
+
 	/* end of memory marker */
 	rsvd_region[n].start = ~0UL;
 	rsvd_region[n].end   = ~0UL;

@@ -205,23 +205,18 @@ EXPORT_SYMBOL(uncached_free_page);
 static int __init
 uncached_build_memmap(unsigned long start, unsigned long end, void *arg)
 {
-	long length;
-	unsigned long vstart, vend;
+	long length = end - start;
 	int node;
 
-	length = end - start;
-	vstart = start + __IA64_UNCACHED_OFFSET;
-	vend = end + __IA64_UNCACHED_OFFSET;
-
 	dprintk(KERN_ERR "uncached_build_memmap(%lx %lx)\n", start, end);
 
-	memset((char *)vstart, 0, length);
+	memset((char *)start, 0, length);
 
-	node = paddr_to_nid(start);
+	node = paddr_to_nid(start - __IA64_UNCACHED_OFFSET);
 
-	for (; vstart < vend ; vstart += PAGE_SIZE) {
-		dprintk(KERN_INFO "sticking %lx into the pool!\n", vstart);
-		gen_pool_free(uncached_pool[node], vstart, PAGE_SIZE);
+	for (; start < end ; start += PAGE_SIZE) {
+		dprintk(KERN_INFO "sticking %lx into the pool!\n", start);
+		gen_pool_free(uncached_pool[node], start, PAGE_SIZE);
 	}
 
 	return 0;

@@ -16,10 +16,11 @@
  * 	- initrd (optional)
  * 	- command line string
  * 	- kernel code & data
+ * 	- Kernel memory map built from EFI memory map
  *
  * More could be added if necessary
  */
-#define IA64_MAX_RSVD_REGIONS 5
+#define IA64_MAX_RSVD_REGIONS 6
 
 struct rsvd_region {
 	unsigned long start;	/* virtual address of beginning of element */

@@ -33,6 +34,7 @@ extern void find_memory (void);
 extern void reserve_memory (void);
 extern void find_initrd (void);
 extern int filter_rsvd_memory (unsigned long start, unsigned long end, void *arg);
+extern void efi_memmap_init(unsigned long *, unsigned long *);
 
 /*
  * For rounding an address to the next IA64_GRANULE_SIZE or order

diff -urNp linux-2.6.14-rc4/arch/ia64/hp/common/sba_iommu.c linux-2.6.14-rc4-kexec-ia64/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)
 {

44 lines not on this page · raw message

diff -urNp linux-2.6.14-rc4/arch/ia64/kernel/efi.c linux-2.6.14-rc4-kexec-ia64/arch/ia64/kernel/efi.c
@@ -38,6 +38,9 @@
 extern efi_status_t efi_call_phys (void *, ...);
 
 struct efi efi;
+#ifdef CONFIG_KEXEC
+unsigned long kexec_reboot = 0;
+#endif
 EXPORT_SYMBOL(efi);
 static efi_runtime_services_t *runtime;
 static unsigned long mem_limit = ~0UL, max_addr = ~0UL;

@@ -526,6 +529,9 @@ efi_map_pal_code (void)
 	 * Cannot write to CRx with PSR.ic=1
 	 */
 	psr = ia64_clear_ic();
+#ifdef CONFIG_KEXEC
+	ia64_ptr(0x01, GRANULEROUNDDOWN((unsigned long) pal_vaddr), IA64_GRANULE_SHIFT);
+#endif
 	ia64_itr(0x1, IA64_TR_PALCODE, GRANULEROUNDDOWN((unsigned long) pal_vaddr),
 		 pte_val(pfn_pte(__pa(pal_vaddr) >> PAGE_SHIFT, PAGE_KERNEL)),
 		 IA64_GRANULE_SHIFT);

@@ -549,15 +555,22 @@ efi_init (void)
 		if (memcmp(cp, "mem=", 4) == 0) {
 			cp += 4;
 			mem_limit = memparse(cp, &end);
-			if (end != cp)
-				break;
 			cp = end;
+			while (*cp == ' ')
+				++cp;
 		} else if (memcmp(cp, "max_addr=", 9) == 0) {
 			cp += 9;
 			max_addr = GRANULEROUNDDOWN(memparse(cp, &end));
-			if (end != cp)
-				break;
 			cp = end;
+			while (*cp == ' ')
+				++cp;
+#ifdef CONFIG_KEXEC
+		} else if (memcmp(cp, "kexec_reboot", 12) == 0) {
+			cp += 13;
+			kexec_reboot = 1;
+			while (*cp == ' ')
+				++cp;
+#endif
 		} else {
 			while (*cp != ' ' && *cp)
 				++cp;

@@ -702,10 +715,17 @@ efi_enter_virtual_mode (void)
 		}
 	}
 
+#ifdef CONFIG_KEXEC
+	if (kexec_reboot == 0)
+#endif
 	status = efi_call_phys(__va(runtime->set_virtual_address_map),
 			       ia64_boot_param->efi_memmap_size,
 			       efi_desc_size, ia64_boot_param->efi_memdesc_version,
 			       ia64_boot_param->efi_memmap);
+#ifdef CONFIG_KEXEC
+	else
+		status = EFI_SUCCESS;
+#endif
 	if (status != EFI_SUCCESS) {
 		printk(KERN_WARNING "warning: unable to switch EFI into virtual mode "
 		       "(status=%lu)\n", status);

224 lines not on this page · raw message

diff -urNp linux-2.6.14-rc4/arch/ia64/kernel/smp.c linux-2.6.14-rc4-kexec-ia64/arch/ia64/kernel/smp.c
@@ -30,6 +30,9 @@
 #include <linux/delay.h>
 #include <linux/efi.h>
 #include <linux/bitops.h>
+#ifdef CONFIG_KEXEC
+#include <linux/kexec.h>
+#endif
 
 #include <asm/atomic.h>
 #include <asm/current.h>

@@ -84,6 +87,43 @@ unlock_ipi_calllock(void)
 	spin_unlock_irq(&call_lock);
 }
 
+#ifdef CONFIG_KEXEC
+extern void kexec_fake_sal_rendez(void *start, unsigned long wake_up,
+		unsigned long pal_base);
+
+#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);
+
+/*
+ * 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)
 {

diff -urNp linux-2.6.14-rc4/include/asm-ia64/kexec.h linux-2.6.14-rc4-kexec-ia64/include/asm-ia64/kexec.h
@@ -0,0 +1,22 @@
+#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
+typedef u32 note_buf_t[MAX_NOTE_BYTES/4];
+
+extern note_buf_t crash_notes[];
+
+#endif /* _ASM_IA64_KEXEC_H */

diff -urNp linux-2.6.14-rc4/kernel/irq/handle.c linux-2.6.14-rc4-kexec-ia64/kernel/irq/handle.c
@@ -100,6 +100,26 @@ fastcall int handle_IRQ_event(unsigned i
 }
 
 /*
+ * Terminate any outstanding interrupts
+ */
+void terminate_irqs(void)
+{
+	struct irqaction * action;
+	irq_desc_t *idesc;
+	unsigned long flags;
+	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);
+	}
+}
+
+/*
  * do_IRQ handles all normal device IRQ's (the special
  * SMP cross-CPU interrupts have their own specific
  * handlers).