[IA64] IA64 Kexec/kdump (a7956113) · Commits · 戴 / test

arch/ia64/Kconfig

+23 −0

Original line number	Diff line number	Diff line
		@@ -434,6 +434,29 @@ config IA64_ESI

		source "drivers/sn/Kconfig"

		config KEXEC
		bool "kexec system call (EXPERIMENTAL)"
		depends on EXPERIMENTAL && !IA64_HP_SIM && (!SMP \|\| HOTPLUG_CPU)
		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 && IA64_MCA_RECOVERY && !IA64_HP_SIM && (!SMP \|\| HOTPLUG_CPU)
		help
		Generate crash dump after being started by kexec.

		source "drivers/firmware/Kconfig"

		source "fs/Kconfig.binfmt"

arch/ia64/kernel/Makefile

+1 −0

Original line number	Diff line number	Diff line
		@@ -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
		obj-$(CONFIG_AUDIT) += audit.o
		obj-$(CONFIG_PCI_MSI) += msi_ia64.o

arch/ia64/kernel/crash.c

0 → 100644

+245 −0

Original line number	Diff line number	Diff line
		/*
		* arch/ia64/kernel/crash.c
		*
		* Architecture specific (ia64) functions for kexec based crash dumps.
		*
		* Created by: Khalid Aziz <khalid.aziz@hp.com>
		* Copyright (C) 2005 Hewlett-Packard Development Company, L.P.
		* Copyright (C) 2005 Intel Corp Zou Nan hai <nanhai.zou@intel.com>
		*
		*/
		#include <linux/smp.h>
		#include <linux/delay.h>
		#include <linux/crash_dump.h>
		#include <linux/bootmem.h>
		#include <linux/kexec.h>
		#include <linux/elfcore.h>
		#include <linux/sysctl.h>
		#include <linux/init.h>

		#include <asm/kdebug.h>
		#include <asm/mca.h>
		#include <asm/uaccess.h>

		int kdump_status[NR_CPUS];
		atomic_t kdump_cpu_freezed;
		atomic_t kdump_in_progress;
		int kdump_on_init = 1;
		ssize_t
		copy_oldmem_page(unsigned long pfn, char *buf,
		size_t csize, unsigned long offset, int userbuf)
		{
		void *vaddr;

		if (!csize)
		return 0;
		vaddr = __va(pfn<<PAGE_SHIFT);
		if (userbuf) {
		if (copy_to_user(buf, (vaddr + offset), csize)) {
		return -EFAULT;
		}
		} else
		memcpy(buf, (vaddr + offset), csize);
		return csize;
		}

		static inline Elf64_Word
		append_elf_note(Elf64_Word buf, char name, unsigned type, void data,
		size_t data_len)
		{
		struct elf_note note = (struct elf_note )buf;
		note->n_namesz = strlen(name) + 1;
		note->n_descsz = data_len;
		note->n_type = type;
		buf += (sizeof(*note) + 3)/4;
		memcpy(buf, name, note->n_namesz);
		buf += (note->n_namesz + 3)/4;
		memcpy(buf, data, data_len);
		buf += (data_len + 3)/4;
		return buf;
		}

		static void
		final_note(void *buf)
		{
		memset(buf, 0, sizeof(struct elf_note));
		}

		extern void ia64_dump_cpu_regs(void *);

		static DEFINE_PER_CPU(struct elf_prstatus, elf_prstatus);

		void
		crash_save_this_cpu()
		{
		void *buf;
		unsigned long cfm, sof, sol;

		int cpu = smp_processor_id();
		struct elf_prstatus *prstatus = &per_cpu(elf_prstatus, cpu);

		elf_greg_t dst = (elf_greg_t )&(prstatus->pr_reg);
		memset(prstatus, 0, sizeof(*prstatus));
		prstatus->pr_pid = current->pid;

		ia64_dump_cpu_regs(dst);
		cfm = dst[43];
		sol = (cfm >> 7) & 0x7f;
		sof = cfm & 0x7f;
		dst[46] = (unsigned long)ia64_rse_skip_regs((unsigned long *)dst[46],
		sof - sol);

		buf = (u64 *) per_cpu_ptr(crash_notes, cpu);
		if (!buf)
		return;
		buf = append_elf_note(buf, "CORE", NT_PRSTATUS, prstatus,
		sizeof(*prstatus));
		final_note(buf);
		}

		static int
		kdump_wait_cpu_freeze(void)
		{
		int cpu_num = num_online_cpus() - 1;
		int timeout = 1000;
		while(timeout-- > 0) {
		if (atomic_read(&kdump_cpu_freezed) == cpu_num)
		return 0;
		udelay(1000);
		}
		return 1;
		}

		void
		machine_crash_shutdown(struct pt_regs *pt)
		{
		/* This function is only called after the system
		* has paniced or is otherwise in a critical state.
		* The minimum amount of code to allow a kexec'd kernel
		* to run successfully needs to happen here.
		*
		* In practice this means shooting down the other cpus in
		* an SMP system.
		*/
		kexec_disable_iosapic();
		#ifdef CONFIG_SMP
		kdump_smp_send_stop();
		if (kdump_wait_cpu_freeze() && kdump_on_init) {
		//not all cpu response to IPI, send INIT to freeze them
		kdump_smp_send_init();
		}
		#endif
		}

		static void
		machine_kdump_on_init(void)
		{
		local_irq_disable();
		kexec_disable_iosapic();
		machine_kexec(ia64_kimage);
		}

		void
		kdump_cpu_freeze(struct unw_frame_info info, void arg)
		{
		int cpuid;
		local_irq_disable();
		cpuid = smp_processor_id();
		crash_save_this_cpu();
		current->thread.ksp = (__u64)info->sw - 16;
		atomic_inc(&kdump_cpu_freezed);
		kdump_status[cpuid] = 1;
		mb();
		if (cpuid == 0) {
		for (;;)
		cpu_relax();
		} else
		ia64_jump_to_sal(&sal_boot_rendez_state[cpuid]);
		}

		static int
		kdump_init_notifier(struct notifier_block self, unsigned long val, void data)
		{
		struct ia64_mca_notify_die *nd;
		struct die_args *args = data;

		if (!kdump_on_init)
		return NOTIFY_DONE;

		if (val != DIE_INIT_MONARCH_ENTER &&
		val != DIE_INIT_SLAVE_ENTER &&
		val != DIE_MCA_RENDZVOUS_LEAVE &&
		val != DIE_MCA_MONARCH_LEAVE)
		return NOTIFY_DONE;

		nd = (struct ia64_mca_notify_die *)args->err;
		/* Reason code 1 means machine check rendezous*/
		if ((val == DIE_INIT_MONARCH_ENTER \|\| DIE_INIT_SLAVE_ENTER) &&
		nd->sos->rv_rc == 1)
		return NOTIFY_DONE;

		switch (val) {
		case DIE_INIT_MONARCH_ENTER:
		machine_kdump_on_init();
		break;
		case DIE_INIT_SLAVE_ENTER:
		unw_init_running(kdump_cpu_freeze, NULL);
		break;
		case DIE_MCA_RENDZVOUS_LEAVE:
		if (atomic_read(&kdump_in_progress))
		unw_init_running(kdump_cpu_freeze, NULL);
		break;
		case DIE_MCA_MONARCH_LEAVE:
		/* die_register->signr indicate if MCA is recoverable */
		if (!args->signr)
		machine_kdump_on_init();
		break;
		}
		return NOTIFY_DONE;
		}

		#ifdef CONFIG_SYSCTL
		static ctl_table kdump_on_init_table[] = {
		{
		.ctl_name = CTL_UNNUMBERED,
		.procname = "kdump_on_init",
		.data = &kdump_on_init,
		.maxlen = sizeof(int),
		.mode = 0644,
		.proc_handler = &proc_dointvec,
		},
		{ .ctl_name = 0 }
		};

		static ctl_table sys_table[] = {
		{
		.ctl_name = CTL_KERN,
		.procname = "kernel",
		.mode = 0555,
		.child = kdump_on_init_table,
		},
		{ .ctl_name = 0 }
		};
		#endif

		static int
		machine_crash_setup(void)
		{
		char *from = strstr(saved_command_line, "elfcorehdr=");
		static struct notifier_block kdump_init_notifier_nb = {
		.notifier_call = kdump_init_notifier,
		};
		int ret;
		if (from)
		elfcorehdr_addr = memparse(from+11, &from);
		saved_max_pfn = (unsigned long)-1;
		if((ret = register_die_notifier(&kdump_init_notifier_nb)) != 0)
		return ret;
		#ifdef CONFIG_SYSCTL
		register_sysctl_table(sys_table, 0);
		#endif
		return 0;
		}

		__initcall(machine_crash_setup);

arch/ia64/kernel/efi.c

+62 −3

Original line number	Diff line number	Diff line
		@@ -26,6 +26,7 @@
		#include <linux/types.h>
		#include <linux/time.h>
		#include <linux/efi.h>
		#include <linux/kexec.h>

		#include <asm/io.h>
		#include <asm/kregs.h>
		@@ -41,7 +42,7 @@ 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)

		@@ -421,6 +422,8 @@ 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;
		@@ -428,6 +431,8 @@ 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);

		@@ -894,7 +899,8 @@ 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;
		@@ -1004,7 +1010,8 @@ efi_memmap_init(unsigned long s, unsigned long e)
		} 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;
		@@ -1116,6 +1123,58 @@ efi_initialize_iomem_resources(struct resource *code_resource,
		*/
		insert_resource(res, code_resource);
		insert_resource(res, data_resource);
		#ifdef CONFIG_KEXEC
		insert_resource(res, &efi_memmap_res);
		insert_resource(res, &boot_param_res);
		if (crashk_res.end > crashk_res.start)
		insert_resource(res, &crashk_res);
		#endif
		}
		}
		}

		#ifdef CONFIG_KEXEC
		/* find a block of memory aligned to 64M exclude reserved regions
		rsvd_regions are sorted
		*/
		unsigned long
		kdump_find_rsvd_region (unsigned long size,
		struct rsvd_region *r, int n)
		{
		int i;
		u64 start, end;
		u64 alignment = 1UL << _PAGE_SIZE_64M;
		void efi_map_start, efi_map_end, *p;
		efi_memory_desc_t *md;
		u64 efi_desc_size;

		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;

		for (p = efi_map_start; p < efi_map_end; p += efi_desc_size) {
		md = p;
		if (!efi_wb(md))
		continue;
		start = ALIGN(md->phys_addr, alignment);
		end = efi_md_end(md);
		for (i = 0; i < n; i++) {
		if (__pa(r[i].start) >= start && __pa(r[i].end) < end) {
		if (__pa(r[i].start) > start + size)
		return start;
		start = ALIGN(__pa(r[i].end), alignment);
		if (i < n-1 && __pa(r[i+1].start) < start + size)
		continue;
		else
		break;
		}
		}
		if (end > start + size)
		return start;
		}

		printk(KERN_WARNING "Cannot reserve 0x%lx byte of memory for crashdump\n",
		size);
		return ~0UL;
		}
		#endif

arch/ia64/kernel/entry.S

+1 −1

Original line number	Diff line number	Diff line
		@@ -1575,7 +1575,7 @@ 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

Admin message