# HG changeset patch
# User Ian Campbell <ian.campbell@xxxxxxxxxxxxx>
# Node ID d51e5a7317bb6f9f02b60a9bbb8519817ce55d68
# Parent 1db125262365b993d486272cc28e084bf57e0d66
[LINUX] Kexec: add kexec files to sparse tree.
Signed-off-by: Ian Campbell <ian.campbell@xxxxxxxxxxxxx>
---
linux-2.6-xen-sparse/arch/i386/kernel/crash.c | 183 ++
linux-2.6-xen-sparse/arch/i386/kernel/machine_kexec.c | 89 +
linux-2.6-xen-sparse/arch/x86_64/kernel/crash.c | 186 ++
linux-2.6-xen-sparse/arch/x86_64/kernel/machine_kexec.c | 173 ++
linux-2.6-xen-sparse/include/asm-i386/kexec.h | 103 +
linux-2.6-xen-sparse/include/asm-x86_64/kexec.h | 96 +
linux-2.6-xen-sparse/include/linux/kexec.h | 139 ++
linux-2.6-xen-sparse/kernel/kexec.c | 1081 ++++++++++++++++
8 files changed, 2050 insertions(+)
diff -r 1db125262365 -r d51e5a7317bb
linux-2.6-xen-sparse/arch/i386/kernel/crash.c
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/linux-2.6-xen-sparse/arch/i386/kernel/crash.c Fri Dec 08 11:47:09
2006 +0000
@@ -0,0 +1,183 @@
+/*
+ * Architecture specific (i386) functions for kexec based crash dumps.
+ *
+ * Created by: Hariprasad Nellitheertha (hari@xxxxxxxxxx)
+ *
+ * Copyright (C) IBM Corporation, 2004. All rights reserved.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/smp.h>
+#include <linux/reboot.h>
+#include <linux/kexec.h>
+#include <linux/delay.h>
+#include <linux/elf.h>
+#include <linux/elfcore.h>
+
+#include <asm/processor.h>
+#include <asm/hardirq.h>
+#include <asm/nmi.h>
+#include <asm/hw_irq.h>
+#include <asm/apic.h>
+#include <mach_ipi.h>
+
+
+/* This keeps a track of which one is crashing cpu. */
+static int crashing_cpu;
+
+static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data,
+ size_t data_len)
+{
+ struct elf_note note;
+
+ note.n_namesz = strlen(name) + 1;
+ note.n_descsz = data_len;
+ note.n_type = type;
+ memcpy(buf, ¬e, sizeof(note));
+ buf += (sizeof(note) +3)/4;
+ memcpy(buf, name, note.n_namesz);
+ buf += (note.n_namesz + 3)/4;
+ memcpy(buf, data, note.n_descsz);
+ buf += (note.n_descsz + 3)/4;
+
+ return buf;
+}
+
+static void final_note(u32 *buf)
+{
+ struct elf_note note;
+
+ note.n_namesz = 0;
+ note.n_descsz = 0;
+ note.n_type = 0;
+ memcpy(buf, ¬e, sizeof(note));
+}
+
+static void crash_save_this_cpu(struct pt_regs *regs, int cpu)
+{
+ struct elf_prstatus prstatus;
+ u32 *buf;
+
+ if ((cpu < 0) || (cpu >= NR_CPUS))
+ return;
+
+ /* Using ELF notes here is opportunistic.
+ * I need a well defined structure format
+ * for the data I pass, and I need tags
+ * on the data to indicate what information I have
+ * squirrelled away. ELF notes happen to provide
+ * all of that that no need to invent something new.
+ */
+ buf = (u32*)per_cpu_ptr(crash_notes, cpu);
+ if (!buf)
+ return;
+ memset(&prstatus, 0, sizeof(prstatus));
+ prstatus.pr_pid = current->pid;
+ elf_core_copy_regs(&prstatus.pr_reg, regs);
+ buf = append_elf_note(buf, "CORE", NT_PRSTATUS, &prstatus,
+ sizeof(prstatus));
+ final_note(buf);
+}
+
+static void crash_save_self(struct pt_regs *regs)
+{
+ int cpu;
+
+ cpu = smp_processor_id();
+ crash_save_this_cpu(regs, cpu);
+}
+
+#ifdef CONFIG_SMP
+static atomic_t waiting_for_crash_ipi;
+
+static int crash_nmi_callback(struct pt_regs *regs, int cpu)
+{
+ struct pt_regs fixed_regs;
+
+ /* Don't do anything if this handler is invoked on crashing cpu.
+ * Otherwise, system will completely hang. Crashing cpu can get
+ * an NMI if system was initially booted with nmi_watchdog parameter.
+ */
+ if (cpu == crashing_cpu)
+ return 1;
+ local_irq_disable();
+
+ if (!user_mode(regs)) {
+ crash_fixup_ss_esp(&fixed_regs, regs);
+ regs = &fixed_regs;
+ }
+ crash_save_this_cpu(regs, cpu);
+ disable_local_APIC();
+ atomic_dec(&waiting_for_crash_ipi);
+ /* Assume hlt works */
+ halt();
+ for(;;);
+
+ return 1;
+}
+
+/*
+ * By using the NMI code instead of a vector we just sneak thru the
+ * word generator coming out with just what we want. AND it does
+ * not matter if clustered_apic_mode is set or not.
+ */
+static void smp_send_nmi_allbutself(void)
+{
+ send_IPI_allbutself(APIC_DM_NMI);
+}
+
+static void nmi_shootdown_cpus(void)
+{
+ unsigned long msecs;
+
+ atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+ /* Would it be better to replace the trap vector here? */
+ set_nmi_callback(crash_nmi_callback);
+ /* Ensure the new callback function is set before sending
+ * out the NMI
+ */
+ wmb();
+
+ smp_send_nmi_allbutself();
+
+ msecs = 1000; /* Wait at most a second for the other cpus to stop */
+ while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
+ mdelay(1);
+ msecs--;
+ }
+
+ /* Leave the nmi callback set */
+ disable_local_APIC();
+}
+#else
+static void nmi_shootdown_cpus(void)
+{
+ /* There are no cpus to shootdown */
+}
+#endif
+
+void machine_crash_shutdown(struct pt_regs *regs)
+{
+ /* 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.
+ */
+ /* The kernel is broken so disable interrupts */
+ local_irq_disable();
+
+ /* Make a note of crashing cpu. Will be used in NMI callback.*/
+ crashing_cpu = smp_processor_id();
+ nmi_shootdown_cpus();
+ lapic_shutdown();
+#if defined(CONFIG_X86_IO_APIC)
+ disable_IO_APIC();
+#endif
+ crash_save_self(regs);
+}
diff -r 1db125262365 -r d51e5a7317bb
linux-2.6-xen-sparse/arch/i386/kernel/machine_kexec.c
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/linux-2.6-xen-sparse/arch/i386/kernel/machine_kexec.c Fri Dec 08
11:47:09 2006 +0000
@@ -0,0 +1,89 @@
+/*
+ * machine_kexec.c - handle transition of Linux booting another kernel
+ * Copyright (C) 2002-2005 Eric Biederman <ebiederm@xxxxxxxxxxxx>
+ *
+ * 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 <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
+#include <asm/io.h>
+#include <asm/apic.h>
+#include <asm/cpufeature.h>
+#include <asm/desc.h>
+#include <asm/system.h>
+
+#define PAGE_ALIGNED __attribute__ ((__aligned__(PAGE_SIZE)))
+static u32 kexec_pgd[1024] PAGE_ALIGNED;
+#ifdef CONFIG_X86_PAE
+static u32 kexec_pmd0[1024] PAGE_ALIGNED;
+static u32 kexec_pmd1[1024] PAGE_ALIGNED;
+#endif
+static u32 kexec_pte0[1024] PAGE_ALIGNED;
+static u32 kexec_pte1[1024] PAGE_ALIGNED;
+
+/*
+ * A architecture hook called to validate the
+ * proposed image and prepare the control pages
+ * as needed. The pages for KEXEC_CONTROL_CODE_SIZE
+ * have been allocated, but the segments have yet
+ * been copied into the kernel.
+ *
+ * Do what every setup is needed on image and the
+ * reboot code buffer to allow us to avoid allocations
+ * later.
+ *
+ * Currently nothing.
+ */
+int machine_kexec_prepare(struct kimage *image)
+{
+ return 0;
+}
+
+/*
+ * Undo anything leftover by machine_kexec_prepare
+ * when an image is freed.
+ */
+void machine_kexec_cleanup(struct kimage *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)
+{
+ unsigned long page_list[PAGES_NR];
+ void *control_page;
+
+ /* Interrupts aren't acceptable while we reboot */
+ local_irq_disable();
+
+ control_page = page_address(image->control_code_page);
+ memcpy(control_page, relocate_kernel, PAGE_SIZE);
+
+ page_list[PA_CONTROL_PAGE] = __pa(control_page);
+ page_list[VA_CONTROL_PAGE] = (unsigned long)relocate_kernel;
+ page_list[PA_PGD] = __pa(kexec_pgd);
+ page_list[VA_PGD] = (unsigned long)kexec_pgd;
+#ifdef CONFIG_X86_PAE
+ page_list[PA_PMD_0] = __pa(kexec_pmd0);
+ page_list[VA_PMD_0] = (unsigned long)kexec_pmd0;
+ page_list[PA_PMD_1] = __pa(kexec_pmd1);
+ page_list[VA_PMD_1] = (unsigned long)kexec_pmd1;
+#endif
+ page_list[PA_PTE_0] = __pa(kexec_pte0);
+ page_list[VA_PTE_0] = (unsigned long)kexec_pte0;
+ page_list[PA_PTE_1] = __pa(kexec_pte1);
+ page_list[VA_PTE_1] = (unsigned long)kexec_pte1;
+
+ relocate_kernel((unsigned long)image->head, (unsigned long)page_list,
+ image->start, cpu_has_pae);
+}
diff -r 1db125262365 -r d51e5a7317bb
linux-2.6-xen-sparse/arch/x86_64/kernel/crash.c
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/crash.c Fri Dec 08 11:47:09
2006 +0000
@@ -0,0 +1,186 @@
+/*
+ * Architecture specific (x86_64) functions for kexec based crash dumps.
+ *
+ * Created by: Hariprasad Nellitheertha (hari@xxxxxxxxxx)
+ *
+ * Copyright (C) IBM Corporation, 2004. All rights reserved.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/smp.h>
+#include <linux/irq.h>
+#include <linux/reboot.h>
+#include <linux/kexec.h>
+#include <linux/delay.h>
+#include <linux/elf.h>
+#include <linux/elfcore.h>
+
+#include <asm/processor.h>
+#include <asm/hardirq.h>
+#include <asm/nmi.h>
+#include <asm/hw_irq.h>
+#include <asm/mach_apic.h>
+
+/* This keeps a track of which one is crashing cpu. */
+static int crashing_cpu;
+
+static u32 *append_elf_note(u32 *buf, char *name, unsigned type,
+ void *data, size_t data_len)
+{
+ struct elf_note note;
+
+ note.n_namesz = strlen(name) + 1;
+ note.n_descsz = data_len;
+ note.n_type = type;
+ memcpy(buf, ¬e, sizeof(note));
+ buf += (sizeof(note) +3)/4;
+ memcpy(buf, name, note.n_namesz);
+ buf += (note.n_namesz + 3)/4;
+ memcpy(buf, data, note.n_descsz);
+ buf += (note.n_descsz + 3)/4;
+
+ return buf;
+}
+
+static void final_note(u32 *buf)
+{
+ struct elf_note note;
+
+ note.n_namesz = 0;
+ note.n_descsz = 0;
+ note.n_type = 0;
+ memcpy(buf, ¬e, sizeof(note));
+}
+
+static void crash_save_this_cpu(struct pt_regs *regs, int cpu)
+{
+ struct elf_prstatus prstatus;
+ u32 *buf;
+
+ if ((cpu < 0) || (cpu >= NR_CPUS))
+ return;
+
+ /* Using ELF notes here is opportunistic.
+ * I need a well defined structure format
+ * for the data I pass, and I need tags
+ * on the data to indicate what information I have
+ * squirrelled away. ELF notes happen to provide
+ * all of that that no need to invent something new.
+ */
+
+ buf = (u32*)per_cpu_ptr(crash_notes, cpu);
+
+ if (!buf)
+ return;
+
+ memset(&prstatus, 0, sizeof(prstatus));
+ prstatus.pr_pid = current->pid;
+ elf_core_copy_regs(&prstatus.pr_reg, regs);
+ buf = append_elf_note(buf, "CORE", NT_PRSTATUS, &prstatus,
+ sizeof(prstatus));
+ final_note(buf);
+}
+
+static void crash_save_self(struct pt_regs *regs)
+{
+ int cpu;
+
+ cpu = smp_processor_id();
+ crash_save_this_cpu(regs, cpu);
+}
+
+#ifdef CONFIG_SMP
+static atomic_t waiting_for_crash_ipi;
+
+static int crash_nmi_callback(struct pt_regs *regs, int cpu)
+{
+ /*
+ * Don't do anything if this handler is invoked on crashing cpu.
+ * Otherwise, system will completely hang. Crashing cpu can get
+ * an NMI if system was initially booted with nmi_watchdog parameter.
+ */
+ if (cpu == crashing_cpu)
+ return 1;
+ local_irq_disable();
+
+ crash_save_this_cpu(regs, cpu);
+ disable_local_APIC();
+ atomic_dec(&waiting_for_crash_ipi);
+ /* Assume hlt works */
+ for(;;)
+ asm("hlt");
+
+ return 1;
+}
+
+static void smp_send_nmi_allbutself(void)
+{
+ send_IPI_allbutself(APIC_DM_NMI);
+}
+
+/*
+ * This code is a best effort heuristic to get the
+ * other cpus to stop executing. So races with
+ * cpu hotplug shouldn't matter.
+ */
+
+static void nmi_shootdown_cpus(void)
+{
+ unsigned long msecs;
+
+ atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+ set_nmi_callback(crash_nmi_callback);
+
+ /*
+ * Ensure the new callback function is set before sending
+ * out the NMI
+ */
+ wmb();
+
+ smp_send_nmi_allbutself();
+
+ msecs = 1000; /* Wait at most a second for the other cpus to stop */
+ while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
+ mdelay(1);
+ msecs--;
+ }
+ /* Leave the nmi callback set */
+ disable_local_APIC();
+}
+#else
+static void nmi_shootdown_cpus(void)
+{
+ /* There are no cpus to shootdown */
+}
+#endif
+
+void machine_crash_shutdown(struct pt_regs *regs)
+{
+ /*
+ * 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.
+ */
+ /* The kernel is broken so disable interrupts */
+ local_irq_disable();
+
+ /* Make a note of crashing cpu. Will be used in NMI callback.*/
+ crashing_cpu = smp_processor_id();
+ nmi_shootdown_cpus();
+
+ if(cpu_has_apic)
+ disable_local_APIC();
+
+#if defined(CONFIG_X86_IO_APIC)
+ disable_IO_APIC();
+#endif
+
+ crash_save_self(regs);
+}
diff -r 1db125262365 -r d51e5a7317bb
linux-2.6-xen-sparse/arch/x86_64/kernel/machine_kexec.c
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/linux-2.6-xen-sparse/arch/x86_64/kernel/machine_kexec.c Fri Dec 08
11:47:09 2006 +0000
@@ -0,0 +1,173 @@
+/*
+ * machine_kexec.c - handle transition of Linux booting another kernel
+ * Copyright (C) 2002-2005 Eric Biederman <ebiederm@xxxxxxxxxxxx>
+ *
+ * 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/string.h>
+#include <linux/reboot.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
+#include <asm/io.h>
+
+#define PAGE_ALIGNED __attribute__ ((__aligned__(PAGE_SIZE)))
+static u64 kexec_pgd[512] PAGE_ALIGNED;
+static u64 kexec_pud0[512] PAGE_ALIGNED;
+static u64 kexec_pmd0[512] PAGE_ALIGNED;
+static u64 kexec_pte0[512] PAGE_ALIGNED;
+static u64 kexec_pud1[512] PAGE_ALIGNED;
+static u64 kexec_pmd1[512] PAGE_ALIGNED;
+static u64 kexec_pte1[512] PAGE_ALIGNED;
+
+static void init_level2_page(pmd_t *level2p, unsigned long addr)
+{
+ unsigned long end_addr;
+
+ addr &= PAGE_MASK;
+ end_addr = addr + PUD_SIZE;
+ while (addr < end_addr) {
+ set_pmd(level2p++, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC));
+ addr += PMD_SIZE;
+ }
+}
+
+static int init_level3_page(struct kimage *image, pud_t *level3p,
+ unsigned long addr, unsigned long last_addr)
+{
+ unsigned long end_addr;
+ int result;
+
+ result = 0;
+ addr &= PAGE_MASK;
+ end_addr = addr + PGDIR_SIZE;
+ while ((addr < last_addr) && (addr < end_addr)) {
+ struct page *page;
+ pmd_t *level2p;
+
+ page = kimage_alloc_control_pages(image, 0);
+ if (!page) {
+ result = -ENOMEM;
+ goto out;
+ }
+ level2p = (pmd_t *)page_address(page);
+ init_level2_page(level2p, addr);
+ set_pud(level3p++, __pud(__pa(level2p) | _KERNPG_TABLE));
+ addr += PUD_SIZE;
+ }
+ /* clear the unused entries */
+ while (addr < end_addr) {
+ pud_clear(level3p++);
+ addr += PUD_SIZE;
+ }
+out:
+ return result;
+}
+
+
+static int init_level4_page(struct kimage *image, pgd_t *level4p,
+ unsigned long addr, unsigned long last_addr)
+{
+ unsigned long end_addr;
+ int result;
+
+ result = 0;
+ addr &= PAGE_MASK;
+ end_addr = addr + (PTRS_PER_PGD * PGDIR_SIZE);
+ while ((addr < last_addr) && (addr < end_addr)) {
+ struct page *page;
+ pud_t *level3p;
+
+ page = kimage_alloc_control_pages(image, 0);
+ if (!page) {
+ result = -ENOMEM;
+ goto out;
+ }
+ level3p = (pud_t *)page_address(page);
+ result = init_level3_page(image, level3p, addr, last_addr);
+ if (result) {
+ goto out;
+ }
+ set_pgd(level4p++, __pgd(__pa(level3p) | _KERNPG_TABLE));
+ addr += PGDIR_SIZE;
+ }
+ /* clear the unused entries */
+ while (addr < end_addr) {
+ pgd_clear(level4p++);
+ addr += PGDIR_SIZE;
+ }
+out:
+ return result;
+}
+
+
+static int init_pgtable(struct kimage *image, unsigned long start_pgtable)
+{
+ pgd_t *level4p;
+ level4p = (pgd_t *)__va(start_pgtable);
+ return init_level4_page(image, level4p, 0, end_pfn << PAGE_SHIFT);
+}
+
+int machine_kexec_prepare(struct kimage *image)
+{
+ unsigned long start_pgtable;
+ int result;
+
+ /* Calculate the offsets */
+ start_pgtable = page_to_pfn(image->control_code_page) << PAGE_SHIFT;
+
+ /* Setup the identity mapped 64bit page table */
+ result = init_pgtable(image, start_pgtable);
+ if (result)
+ return result;
+
+ return 0;
+}
+
+void machine_kexec_cleanup(struct kimage *image)
+{
+ return;
+}
+
+/*
+ * 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)
+{
+ unsigned long page_list[PAGES_NR];
+ void *control_page;
+
+ /* Interrupts aren't acceptable while we reboot */
+ local_irq_disable();
+
+ control_page = page_address(image->control_code_page) + PAGE_SIZE;
+ memcpy(control_page, relocate_kernel, PAGE_SIZE);
+
+ page_list[PA_CONTROL_PAGE] = __pa(control_page);
+ page_list[VA_CONTROL_PAGE] = (unsigned long)relocate_kernel;
+ page_list[PA_PGD] = __pa(kexec_pgd);
+ page_list[VA_PGD] = (unsigned long)kexec_pgd;
+ page_list[PA_PUD_0] = __pa(kexec_pud0);
+ page_list[VA_PUD_0] = (unsigned long)kexec_pud0;
+ page_list[PA_PMD_0] = __pa(kexec_pmd0);
+ page_list[VA_PMD_0] = (unsigned long)kexec_pmd0;
+ page_list[PA_PTE_0] = __pa(kexec_pte0);
+ page_list[VA_PTE_0] = (unsigned long)kexec_pte0;
+ page_list[PA_PUD_1] = __pa(kexec_pud1);
+ page_list[VA_PUD_1] = (unsigned long)kexec_pud1;
+ page_list[PA_PMD_1] = __pa(kexec_pmd1);
+ page_list[VA_PMD_1] = (unsigned long)kexec_pmd1;
+ page_list[PA_PTE_1] = __pa(kexec_pte1);
+ page_list[VA_PTE_1] = (unsigned long)kexec_pte1;
+
+ page_list[PA_TABLE_PAGE] =
+ (unsigned long)__pa(page_address(image->control_code_page));
+
+ relocate_kernel((unsigned long)image->head, (unsigned long)page_list,
+ image->start);
+}
diff -r 1db125262365 -r d51e5a7317bb
linux-2.6-xen-sparse/include/asm-i386/kexec.h
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/linux-2.6-xen-sparse/include/asm-i386/kexec.h Fri Dec 08 11:47:09
2006 +0000
@@ -0,0 +1,103 @@
+#ifndef _I386_KEXEC_H
+#define _I386_KEXEC_H
+
+#define PA_CONTROL_PAGE 0
+#define VA_CONTROL_PAGE 1
+#define PA_PGD 2
+#define VA_PGD 3
+#define PA_PTE_0 4
+#define VA_PTE_0 5
+#define PA_PTE_1 6
+#define VA_PTE_1 7
+#ifdef CONFIG_X86_PAE
+#define PA_PMD_0 8
+#define VA_PMD_0 9
+#define PA_PMD_1 10
+#define VA_PMD_1 11
+#define PAGES_NR 12
+#else
+#define PAGES_NR 8
+#endif
+
+#ifndef __ASSEMBLY__
+
+#include <asm/fixmap.h>
+#include <asm/ptrace.h>
+#include <asm/string.h>
+
+/*
+ * 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_386
+
+#define MAX_NOTE_BYTES 1024
+
+/* CPU does not save ss and esp on stack if execution is already
+ * running in kernel mode at the time of NMI occurrence. This code
+ * fixes it.
+ */
+static inline void crash_fixup_ss_esp(struct pt_regs *newregs,
+ struct pt_regs *oldregs)
+{
+ memcpy(newregs, oldregs, sizeof(*newregs));
+ newregs->esp = (unsigned long)&(oldregs->esp);
+ __asm__ __volatile__(
+ "xorl %%eax, %%eax\n\t"
+ "movw %%ss, %%ax\n\t"
+ :"=a"(newregs->xss));
+}
+
+/*
+ * This function is responsible for capturing register states if coming
+ * via panic otherwise just fix up the ss and esp if coming via kernel
+ * mode exception.
+ */
+static inline void crash_setup_regs(struct pt_regs *newregs,
+ struct pt_regs *oldregs)
+{
+ if (oldregs)
+ crash_fixup_ss_esp(newregs, oldregs);
+ else {
+ __asm__ __volatile__("movl %%ebx,%0" : "=m"(newregs->ebx));
+ __asm__ __volatile__("movl %%ecx,%0" : "=m"(newregs->ecx));
+ __asm__ __volatile__("movl %%edx,%0" : "=m"(newregs->edx));
+ __asm__ __volatile__("movl %%esi,%0" : "=m"(newregs->esi));
+ __asm__ __volatile__("movl %%edi,%0" : "=m"(newregs->edi));
+ __asm__ __volatile__("movl %%ebp,%0" : "=m"(newregs->ebp));
+ __asm__ __volatile__("movl %%eax,%0" : "=m"(newregs->eax));
+ __asm__ __volatile__("movl %%esp,%0" : "=m"(newregs->esp));
+ __asm__ __volatile__("movw %%ss, %%ax;" :"=a"(newregs->xss));
+ __asm__ __volatile__("movw %%cs, %%ax;" :"=a"(newregs->xcs));
+ __asm__ __volatile__("movw %%ds, %%ax;" :"=a"(newregs->xds));
+ __asm__ __volatile__("movw %%es, %%ax;" :"=a"(newregs->xes));
+ __asm__ __volatile__("pushfl; popl %0" :"=m"(newregs->eflags));
+
+ newregs->eip = (unsigned long)current_text_addr();
+ }
+}
+asmlinkage NORET_TYPE void
+relocate_kernel(unsigned long indirection_page,
+ unsigned long control_page,
+ unsigned long start_address,
+ unsigned int has_pae) ATTRIB_NORET;
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _I386_KEXEC_H */
diff -r 1db125262365 -r d51e5a7317bb
linux-2.6-xen-sparse/include/asm-x86_64/kexec.h
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/linux-2.6-xen-sparse/include/asm-x86_64/kexec.h Fri Dec 08 11:47:09
2006 +0000
@@ -0,0 +1,96 @@
+#ifndef _X86_64_KEXEC_H
+#define _X86_64_KEXEC_H
+
+#define PA_CONTROL_PAGE 0
+#define VA_CONTROL_PAGE 1
+#define PA_PGD 2
+#define VA_PGD 3
+#define PA_PUD_0 4
+#define VA_PUD_0 5
+#define PA_PMD_0 6
+#define VA_PMD_0 7
+#define PA_PTE_0 8
+#define VA_PTE_0 9
+#define PA_PUD_1 10
+#define VA_PUD_1 11
+#define PA_PMD_1 12
+#define VA_PMD_1 13
+#define PA_PTE_1 14
+#define VA_PTE_1 15
+#define PA_TABLE_PAGE 16
+#define PAGES_NR 17
+
+#ifndef __ASSEMBLY__
+
+#include <linux/string.h>
+
+#include <asm/page.h>
+#include <asm/ptrace.h>
+
+/*
+ * 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.
+ *
+ * So far x86_64 is limited to 40 physical address bits.
+ */
+
+/* Maximum physical address we can use pages from */
+#define KEXEC_SOURCE_MEMORY_LIMIT (0xFFFFFFFFFFUL)
+/* Maximum address we can reach in physical address mode */
+#define KEXEC_DESTINATION_MEMORY_LIMIT (0xFFFFFFFFFFUL)
+/* Maximum address we can use for the control pages */
+#define KEXEC_CONTROL_MEMORY_LIMIT (0xFFFFFFFFFFUL)
+
+/* Allocate one page for the pdp and the second for the code */
+#define KEXEC_CONTROL_CODE_SIZE (4096UL + 4096UL)
+
+/* The native architecture */
+#define KEXEC_ARCH KEXEC_ARCH_X86_64
+
+#define MAX_NOTE_BYTES 1024
+
+/*
+ * Saving the registers of the cpu on which panic occured in
+ * crash_kexec to save a valid sp. The registers of other cpus
+ * will be saved in machine_crash_shutdown while shooting down them.
+ */
+
+static inline void crash_setup_regs(struct pt_regs *newregs,
+ struct pt_regs *oldregs)
+{
+ if (oldregs)
+ memcpy(newregs, oldregs, sizeof(*newregs));
+ else {
+ __asm__ __volatile__("movq %%rbx,%0" : "=m"(newregs->rbx));
+ __asm__ __volatile__("movq %%rcx,%0" : "=m"(newregs->rcx));
+ __asm__ __volatile__("movq %%rdx,%0" : "=m"(newregs->rdx));
+ __asm__ __volatile__("movq %%rsi,%0" : "=m"(newregs->rsi));
+ __asm__ __volatile__("movq %%rdi,%0" : "=m"(newregs->rdi));
+ __asm__ __volatile__("movq %%rbp,%0" : "=m"(newregs->rbp));
+ __asm__ __volatile__("movq %%rax,%0" : "=m"(newregs->rax));
+ __asm__ __volatile__("movq %%rsp,%0" : "=m"(newregs->rsp));
+ __asm__ __volatile__("movq %%r8,%0" : "=m"(newregs->r8));
+ __asm__ __volatile__("movq %%r9,%0" : "=m"(newregs->r9));
+ __asm__ __volatile__("movq %%r10,%0" : "=m"(newregs->r10));
+ __asm__ __volatile__("movq %%r11,%0" : "=m"(newregs->r11));
+ __asm__ __volatile__("movq %%r12,%0" : "=m"(newregs->r12));
+ __asm__ __volatile__("movq %%r13,%0" : "=m"(newregs->r13));
+ __asm__ __volatile__("movq %%r14,%0" : "=m"(newregs->r14));
+ __asm__ __volatile__("movq %%r15,%0" : "=m"(newregs->r15));
+ __asm__ __volatile__("movl %%ss, %%eax;" :"=a"(newregs->ss));
+ __asm__ __volatile__("movl %%cs, %%eax;" :"=a"(newregs->cs));
+ __asm__ __volatile__("pushfq; popq %0" :"=m"(newregs->eflags));
+
+ newregs->rip = (unsigned long)current_text_addr();
+ }
+}
+
+NORET_TYPE void
+relocate_kernel(unsigned long indirection_page,
+ unsigned long page_list,
+ unsigned long start_address) ATTRIB_NORET;
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _X86_64_KEXEC_H */
diff -r 1db125262365 -r d51e5a7317bb linux-2.6-xen-sparse/include/linux/kexec.h
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/linux-2.6-xen-sparse/include/linux/kexec.h Fri Dec 08 11:47:09
2006 +0000
@@ -0,0 +1,139 @@
+#ifndef LINUX_KEXEC_H
+#define LINUX_KEXEC_H
+
+#ifdef CONFIG_KEXEC
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/linkage.h>
+#include <linux/compat.h>
+#include <linux/ioport.h>
+#include <asm/kexec.h>
+
+/* Verify architecture specific macros are defined */
+
+#ifndef KEXEC_SOURCE_MEMORY_LIMIT
+#error KEXEC_SOURCE_MEMORY_LIMIT not defined
+#endif
+
+#ifndef KEXEC_DESTINATION_MEMORY_LIMIT
+#error KEXEC_DESTINATION_MEMORY_LIMIT not defined
+#endif
+
+#ifndef KEXEC_CONTROL_MEMORY_LIMIT
+#error KEXEC_CONTROL_MEMORY_LIMIT not defined
+#endif
+
+#ifndef KEXEC_CONTROL_CODE_SIZE
+#error KEXEC_CONTROL_CODE_SIZE not defined
+#endif
+
+#ifndef KEXEC_ARCH
+#error KEXEC_ARCH not defined
+#endif
+
+/*
+ * This structure is used to hold the arguments that are used when loading
+ * kernel binaries.
+ */
+
+typedef unsigned long kimage_entry_t;
+#define IND_DESTINATION 0x1
+#define IND_INDIRECTION 0x2
+#define IND_DONE 0x4
+#define IND_SOURCE 0x8
+
+#define KEXEC_SEGMENT_MAX 16
+struct kexec_segment {
+ void __user *buf;
+ size_t bufsz;
+ unsigned long mem; /* User space sees this as a (void *) ... */
+ size_t memsz;
+};
+
+#ifdef CONFIG_COMPAT
+struct compat_kexec_segment {
+ compat_uptr_t buf;
+ compat_size_t bufsz;
+ compat_ulong_t mem; /* User space sees this as a (void *) ... */
+ compat_size_t memsz;
+};
+#endif
+
+struct kimage {
+ kimage_entry_t head;
+ kimage_entry_t *entry;
+ kimage_entry_t *last_entry;
+
+ unsigned long destination;
+
+ unsigned long start;
+ struct page *control_code_page;
+
+ unsigned long nr_segments;
+ struct kexec_segment segment[KEXEC_SEGMENT_MAX];
+
+ struct list_head control_pages;
+ struct list_head dest_pages;
+ struct list_head unuseable_pages;
+
+ /* Address of next control page to allocate for crash kernels. */
+ unsigned long control_page;
+
+ /* Flags to indicate special processing */
+ unsigned int type : 1;
+#define KEXEC_TYPE_DEFAULT 0
+#define KEXEC_TYPE_CRASH 1
+};
+
+
+
+/* kexec interface functions */
+extern NORET_TYPE void machine_kexec(struct kimage *image) ATTRIB_NORET;
+extern int machine_kexec_prepare(struct kimage *image);
+extern void machine_kexec_cleanup(struct kimage *image);
+extern asmlinkage long sys_kexec_load(unsigned long entry,
+ unsigned long nr_segments,
+ struct kexec_segment __user *segments,
+ unsigned long flags);
+#ifdef CONFIG_COMPAT
+extern asmlinkage long compat_sys_kexec_load(unsigned long entry,
+ unsigned long nr_segments,
+ struct compat_kexec_segment __user *segments,
+ unsigned long flags);
+#endif
+extern struct page *kimage_alloc_control_pages(struct kimage *image,
+ unsigned int order);
+extern void crash_kexec(struct pt_regs *);
+int kexec_should_crash(struct task_struct *);
+extern struct kimage *kexec_image;
+
+#define KEXEC_ON_CRASH 0x00000001
+#define KEXEC_ARCH_MASK 0xffff0000
+
+/* These values match the ELF architecture values.
+ * Unless there is a good reason that should continue to be the case.
+ */
+#define KEXEC_ARCH_DEFAULT ( 0 << 16)
+#define KEXEC_ARCH_386 ( 3 << 16)
+#define KEXEC_ARCH_X86_64 (62 << 16)
+#define KEXEC_ARCH_PPC (20 << 16)
+#define KEXEC_ARCH_PPC64 (21 << 16)
+#define KEXEC_ARCH_IA_64 (50 << 16)
+#define KEXEC_ARCH_S390 (22 << 16)
+#define KEXEC_ARCH_SH (42 << 16)
+
+#define KEXEC_FLAGS (KEXEC_ON_CRASH) /* List of defined/legal kexec flags
*/
+
+/* Location of a reserved region to hold the crash kernel.
+ */
+extern struct resource crashk_res;
+typedef u32 note_buf_t[MAX_NOTE_BYTES/4];
+extern note_buf_t *crash_notes;
+
+#else /* !CONFIG_KEXEC */
+struct pt_regs;
+struct task_struct;
+static inline void crash_kexec(struct pt_regs *regs) { }
+static inline int kexec_should_crash(struct task_struct *p) { return 0; }
+#endif /* CONFIG_KEXEC */
+#endif /* LINUX_KEXEC_H */
diff -r 1db125262365 -r d51e5a7317bb linux-2.6-xen-sparse/kernel/kexec.c
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/linux-2.6-xen-sparse/kernel/kexec.c Fri Dec 08 11:47:09 2006 +0000
@@ -0,0 +1,1081 @@
+/*
+ * kexec.c - kexec system call
+ * Copyright (C) 2002-2004 Eric Biederman <ebiederm@xxxxxxxxxxxx>
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2. See the file COPYING for more details.
+ */
+
+#include <linux/capability.h>
+#include <linux/mm.h>
+#include <linux/file.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/kexec.h>
+#include <linux/spinlock.h>
+#include <linux/list.h>
+#include <linux/highmem.h>
+#include <linux/syscalls.h>
+#include <linux/reboot.h>
+#include <linux/syscalls.h>
+#include <linux/ioport.h>
+#include <linux/hardirq.h>
+
+#include <asm/page.h>
+#include <asm/uaccess.h>
+#include <asm/io.h>
+#include <asm/system.h>
+#include <asm/semaphore.h>
+
+/* Per cpu memory for storing cpu states in case of system crash. */
+note_buf_t* crash_notes;
+
+/* Location of the reserved area for the crash kernel */
+struct resource crashk_res = {
+ .name = "Crash kernel",
+ .start = 0,
+ .end = 0,
+ .flags = IORESOURCE_BUSY | IORESOURCE_MEM
+};
+
+int kexec_should_crash(struct task_struct *p)
+{
+ if (in_interrupt() || !p->pid || p->pid == 1 || panic_on_oops)
+ return 1;
+ return 0;
+}
+
+/*
+ * When kexec transitions to the new kernel there is a one-to-one
+ * mapping between physical and virtual addresses. On processors
+ * where you can disable the MMU this is trivial, and easy. For
+ * others it is still a simple predictable page table to setup.
+ *
+ * In that environment kexec copies the new kernel to its final
+ * resting place. This means I can only support memory whose
+ * physical address can fit in an unsigned long. In particular
+ * addresses where (pfn << PAGE_SHIFT) > ULONG_MAX cannot be handled.
+ * If the assembly stub has more restrictive requirements
+ * KEXEC_SOURCE_MEMORY_LIMIT and KEXEC_DEST_MEMORY_LIMIT can be
+ * defined more restrictively in <asm/kexec.h>.
+ *
+ * The code for the transition from the current kernel to the
+ * the new kernel is placed in the control_code_buffer, whose size
+ * is given by KEXEC_CONTROL_CODE_SIZE. In the best case only a single
+ * page of memory is necessary, but some architectures require more.
+ * Because this memory must be identity mapped in the transition from
+ * virtual to physical addresses it must live in the range
+ * 0 - TASK_SIZE, as only the user space mappings are arbitrarily
+ * modifiable.
+ *
+ * The assembly stub in the control code buffer is passed a linked list
+ * of descriptor pages detailing the source pages of the new kernel,
+ * and the destination addresses of those source pages. As this data
+ * structure is not used in the context of the current OS, it must
+ * be self-contained.
+ *
+ * The code has been made to work with highmem pages and will use a
+ * destination page in its final resting place (if it happens
+ * to allocate it). The end product of this is that most of the
+ * physical address space, and most of RAM can be used.
+ *
+ * Future directions include:
+ * - allocating a page table with the control code buffer identity
+ * mapped, to simplify machine_kexec and make kexec_on_panic more
+ * reliable.
+ */
+
+/*
+ * KIMAGE_NO_DEST is an impossible destination address..., for
+ * allocating pages whose destination address we do not care about.
+ */
+#define KIMAGE_NO_DEST (-1UL)
+
+static int kimage_is_destination_range(struct kimage *image,
+ unsigned long start, unsigned long end);
+static struct page *kimage_alloc_page(struct kimage *image,
+ gfp_t gfp_mask,
+ unsigned long dest);
+
+static int do_kimage_alloc(struct kimage **rimage, unsigned long entry,
+ unsigned long nr_segments,
+ struct kexec_segment __user *segments)
+{
+ size_t segment_bytes;
+ struct kimage *image;
+ unsigned long i;
+ int result;
+
+ /* Allocate a controlling structure */
+ result = -ENOMEM;
+ image = kmalloc(sizeof(*image), GFP_KERNEL);
+ if (!image)
+ goto out;
+
+ memset(image, 0, sizeof(*image));
+ image->head = 0;
+ image->entry = &image->head;
+ image->last_entry = &image->head;
+ image->control_page = ~0; /* By default this does not apply */
+ image->start = entry;
+ image->type = KEXEC_TYPE_DEFAULT;
+
+ /* Initialize the list of control pages */
+ INIT_LIST_HEAD(&image->control_pages);
+
+ /* Initialize the list of destination pages */
+ INIT_LIST_HEAD(&image->dest_pages);
+
+ /* Initialize the list of unuseable pages */
+ INIT_LIST_HEAD(&image->unuseable_pages);
+
+ /* Read in the segments */
+ image->nr_segments = nr_segments;
+ segment_bytes = nr_segments * sizeof(*segments);
+ result = copy_from_user(image->segment, segments, segment_bytes);
+ if (result)
+ goto out;
+
+ /*
+ * Verify we have good destination addresses. The caller is
+ * responsible for making certain we don't attempt to load
+ * the new image into invalid or reserved areas of RAM. This
+ * just verifies it is an address we can use.
+ *
+ * Since the kernel does everything in page size chunks ensure
+ * the destination addreses are page aligned. Too many
+ * special cases crop of when we don't do this. The most
+ * insidious is getting overlapping destination addresses
+ * simply because addresses are changed to page size
+ * granularity.
+ */
+ result = -EADDRNOTAVAIL;
+ for (i = 0; i < nr_segments; i++) {
+ unsigned long mstart, mend;
+
+ mstart = image->segment[i].mem;
+ mend = mstart + image->segment[i].memsz;
+ if ((mstart & ~PAGE_MASK) || (mend & ~PAGE_MASK))
+ goto out;
+ if (mend >= KEXEC_DESTINATION_MEMORY_LIMIT)
+ goto out;
+ }
+
+ /* Verify our destination addresses do not overlap.
+ * If we alloed overlapping destination addresses
+ * through very weird things can happen with no
+ * easy explanation as one segment stops on another.
+ */
+ result = -EINVAL;
+ for (i = 0; i < nr_segments; i++) {
+ unsigned long mstart, mend;
+ unsigned long j;
+
+ mstart = image->segment[i].mem;
+ mend = mstart + image->segment[i].memsz;
+ for (j = 0; j < i; j++) {
+ unsigned long pstart, pend;
+ pstart = image->segment[j].mem;
+ pend = pstart + image->segment[j].memsz;
+ /* Do the segments overlap ? */
+ if ((mend > pstart) && (mstart < pend))
+ goto out;
+ }
+ }
+
+ /* Ensure our buffer sizes are strictly less than
+ * our memory sizes. This should always be the case,
+ * and it is easier to check up front than to be surprised
+ * later on.
+ */
+ result = -EINVAL;
+ for (i = 0; i < nr_segments; i++) {
+ if (image->segment[i].bufsz > image->segment[i].memsz)
+ goto out;
+ }
+
+ result = 0;
+out:
+ if (result == 0)
+ *rimage = image;
+ else
+ kfree(image);
+
+ return result;
+
+}
+
+static int kimage_normal_alloc(struct kimage **rimage, unsigned long entry,
+ unsigned long nr_segments,
+ struct kexec_segment __user *segments)
+{
+ int result;
+ struct kimage *image;
+
+ /* Allocate and initialize a controlling structure */
+ image = NULL;
+ result = do_kimage_alloc(&image, entry, nr_segments, segments);
+ if (result)
+ goto out;
+
+ *rimage = image;
+
+ /*
+ * Find a location for the control code buffer, and add it
+ * the vector of segments so that it's pages will also be
+ * counted as destination pages.
+ */
+ result = -ENOMEM;
+ image->control_code_page = kimage_alloc_control_pages(image,
+ get_order(KEXEC_CONTROL_CODE_SIZE));
+ if (!image->control_code_page) {
+ printk(KERN_ERR "Could not allocate control_code_buffer\n");
+ goto out;
+ }
+
+ result = 0;
+ out:
+ if (result == 0)
+ *rimage = image;
+ else
+ kfree(image);
+
+ return result;
+}
+
+static int kimage_crash_alloc(struct kimage **rimage, unsigned long entry,
+ unsigned long nr_segments,
+ struct kexec_segment __user *segments)
+{
+ int result;
+ struct kimage *image;
+ unsigned long i;
+
+ image = NULL;
+ /* Verify we have a valid entry point */
+ if ((entry < crashk_res.start) || (entry > crashk_res.end)) {
+ result = -EADDRNOTAVAIL;
+ goto out;
+ }
+
+ /* Allocate and initialize a controlling structure */
+ result = do_kimage_alloc(&image, entry, nr_segments, segments);
+ if (result)
+ goto out;
+
+ /* Enable the special crash kernel control page
+ * allocation policy.
+ */
+ image->control_page = crashk_res.start;
+ image->type = KEXEC_TYPE_CRASH;
+
+ /*
+ * Verify we have good destination addresses. Normally
+ * the caller is responsible for making certain we don't
+ * attempt to load the new image into invalid or reserved
+ * areas of RAM. But crash kernels are preloaded into a
+ * reserved area of ram. We must ensure the addresses
+ * are in the reserved area otherwise preloading the
+ * kernel could corrupt things.
+ */
+ result = -EADDRNOTAVAIL;
+ for (i = 0; i < nr_segments; i++) {
+ unsigned long mstart, mend;
+
+ mstart = image->segment[i].mem;
+ mend = mstart + image->segment[i].memsz - 1;
+ /* Ensure we are within the crash kernel limits */
+ if ((mstart < crashk_res.start) || (mend > crashk_res.end))
+ goto out;
+ }
+
+ /*
+ * Find a location for the control code buffer, and add
+ * the vector of segments so that it's pages will also be
+ * counted as destination pages.
+ */
+ result = -ENOMEM;
+ image->control_code_page = kimage_alloc_control_pages(image,
+ get_order(KEXEC_CONTROL_CODE_SIZE));
+ if (!image->control_code_page) {
+ printk(KERN_ERR "Could not allocate control_code_buffer\n");
+ goto out;
+ }
+
+ result = 0;
+out:
+ if (result == 0)
+ *rimage = image;
+ else
+ kfree(image);
+
+ return result;
+}
+
+static int kimage_is_destination_range(struct kimage *image,
+ unsigned long start,
+ unsigned long end)
+{
+ unsigned long i;
+
+ for (i = 0; i < image->nr_segments; i++) {
+ unsigned long mstart, mend;
+
+ mstart = image->segment[i].mem;
+ mend = mstart + image->segment[i].memsz;
+ if ((end > mstart) && (start < mend))
+ return 1;
+ }
+
+ return 0;
+}
+
+static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order)
+{
+ struct page *pages;
+
+ pages = alloc_pages(gfp_mask, order);
+ if (pages) {
+ unsigned int count, i;
+ pages->mapping = NULL;
+ set_page_private(pages, order);
+ count = 1 << order;
+ for (i = 0; i < count; i++)
+ SetPageReserved(pages + i);
+ }
+
+ return pages;
+}
+
+static void kimage_free_pages(struct page *page)
+{
+ unsigned int order, count, i;
+
+ order = page_private(page);
+ count = 1 << order;
+ for (i = 0; i < count; i++)
+ ClearPageReserved(page + i);
+ __free_pages(page, order);
+}
+
+static void kimage_free_page_list(struct list_head *list)
+{
+ struct list_head *pos, *next;
+
+ list_for_each_safe(pos, next, list) {
+ struct page *page;
+
+ page = list_entry(pos, struct page, lru);
+ list_del(&page->lru);
+ kimage_free_pages(page);
+ }
+}
+
+static struct page *kimage_alloc_normal_control_pages(struct kimage *image,
+ unsigned int order)
+{
+ /* Control pages are special, they are the intermediaries
+ * that are needed while we copy the rest of the pages
+ * to their final resting place. As such they must
+ * not conflict with either the destination addresses
+ * or memory the kernel is already using.
+ *
+ * The only case where we really need more than one of
+ * these are for architectures where we cannot disable
+ * the MMU and must instead generate an identity mapped
+ * page table for all of the memory.
+ *
+ * At worst this runs in O(N) of the image size.
+ */
+ struct list_head extra_pages;
+ struct page *pages;
+ unsigned int count;
+
+ count = 1 << order;
+ INIT_LIST_HEAD(&extra_pages);
+
+ /* Loop while I can allocate a page and the page allocated
+ * is a destination page.
+ */
+ do {
+ unsigned long pfn, epfn, addr, eaddr;
+
+ pages = kimage_alloc_pages(GFP_KERNEL, order);
+ if (!pages)
+ break;
+ pfn = page_to_pfn(pages);
+ epfn = pfn + count;
+ addr = pfn << PAGE_SHIFT;
+ eaddr = epfn << PAGE_SHIFT;
+ if ((epfn >= (KEXEC_CONTROL_MEMORY_LIMIT >> PAGE_SHIFT)) ||
+ kimage_is_destination_range(image, addr, eaddr)) {
+ list_add(&pages->lru, &extra_pages);
+ pages = NULL;
+ }
+ } while (!pages);
+
+ if (pages) {
+ /* Remember the allocated page... */
+ list_add(&pages->lru, &image->control_pages);
+
+ /* Because the page is already in it's destination
+ * location we will never allocate another page at
+ * that address. Therefore kimage_alloc_pages
+ * will not return it (again) and we don't need
+ * to give it an entry in image->segment[].
+ */
+ }
+ /* Deal with the destination pages I have inadvertently allocated.
+ *
+ * Ideally I would convert multi-page allocations into single
+ * page allocations, and add everyting to image->dest_pages.
+ *
+ * For now it is simpler to just free the pages.
+ */
+ kimage_free_page_list(&extra_pages);
+
+ return pages;
+}
+
+static struct page *kimage_alloc_crash_control_pages(struct kimage *image,
+ unsigned int order)
+{
+ /* Control pages are special, they are the intermediaries
+ * that are needed while we copy the rest of the pages
+ * to their final resting place. As such they must
+ * not conflict with either the destination addresses
+ * or memory the kernel is already using.
+ *
+ * Control pages are also the only pags we must allocate
+ * when loading a crash kernel. All of the other pages
+ * are specified by the segments and we just memcpy
+ * into them directly.
+ *
+ * The only case where we really need more than one of
+ * these are for architectures where we cannot disable
+ * the MMU and must instead generate an identity mapped
+ * page table for all of the memory.
+ *
+ * Given the low demand this implements a very simple
+ * allocator that finds the first hole of the appropriate
+ * size in the reserved memory region, and allocates all
+ * of the memory up to and including the hole.
+ */
+ unsigned long hole_start, hole_end, size;
+ struct page *pages;
+
+ pages = NULL;
+ size = (1 << order) << PAGE_SHIFT;
+ hole_start = (image->control_page + (size - 1)) & ~(size - 1);
+ hole_end = hole_start + size - 1;
+ while (hole_end <= crashk_res.end) {
+ unsigned long i;
+
+ if (hole_end > KEXEC_CONTROL_MEMORY_LIMIT)
+ break;
+ if (hole_end > crashk_res.end)
+ break;
+ /* See if I overlap any of the segments */
+ for (i = 0; i < image->nr_segments; i++) {
+ unsigned long mstart, mend;
+
+ mstart = image->segment[i].mem;
+ mend = mstart + image->segment[i].memsz - 1;
+ if ((hole_end >= mstart) && (hole_start <= mend)) {
+ /* Advance the hole to the end of the segment */
+ hole_start = (mend + (size - 1)) & ~(size - 1);
+ hole_end = hole_start + size - 1;
+ break;
+ }
+ }
+ /* If I don't overlap any segments I have found my hole! */
+ if (i == image->nr_segments) {
+ pages = pfn_to_page(hole_start >> PAGE_SHIFT);
+ break;
+ }
+ }
+ if (pages)
+ image->control_page = hole_end;
+
+ return pages;
+}
+
+
+struct page *kimage_alloc_control_pages(struct kimage *image,
+ unsigned int order)
+{
+ struct page *pages = NULL;
+
+ switch (image->type) {
+ case KEXEC_TYPE_DEFAULT:
+ pages = kimage_alloc_normal_control_pages(image, order);
+ break;
+ case KEXEC_TYPE_CRASH:
+ pages = kimage_alloc_crash_control_pages(image, order);
+ break;
+ }
+
+ return pages;
+}
+
+static int kimage_add_entry(struct kimage *image, kimage_entry_t entry)
+{
+ if (*image->entry != 0)
+ image->entry++;
+
+ if (image->entry == image->last_entry) {
+ kimage_entry_t *ind_page;
+ struct page *page;
+
+ page = kimage_alloc_page(image, GFP_KERNEL, KIMAGE_NO_DEST);
+ if (!page)
+ return -ENOMEM;
+
+ ind_page = page_address(page);
+ *image->entry = virt_to_phys(ind_page) | IND_INDIRECTION;
+ image->entry = ind_page;
+ image->last_entry = ind_page +
+ ((PAGE_SIZE/sizeof(kimage_entry_t)) - 1);
+ }
+ *image->entry = entry;
+ image->entry++;
+ *image->entry = 0;
+
+ return 0;
+}
+
+static int kimage_set_destination(struct kimage *image,
+ unsigned long destination)
+{
+ int result;
+
+ destination &= PAGE_MASK;
+ result = kimage_add_entry(image, destination | IND_DESTINATION);
+ if (result == 0)
+ image->destination = destination;
+
+ return result;
+}
+
+
+static int kimage_add_page(struct kimage *image, unsigned long page)
+{
+ int result;
+
+ page &= PAGE_MASK;
+ result = kimage_add_entry(image, page | IND_SOURCE);
+ if (result == 0)
+ image->destination += PAGE_SIZE;
+
+ return result;
+}
+
+
+static void kimage_free_extra_pages(struct kimage *image)
+{
+ /* Walk through and free any extra destination pages I may have */
+ kimage_free_page_list(&image->dest_pages);
+
+ /* Walk through and free any unuseable pages I have cached */
+ kimage_free_page_list(&image->unuseable_pages);
+
+}
+static int kimage_terminate(struct kimage *image)
+{
+ if (*image->entry != 0)
+ image->entry++;
+
+ *image->entry = IND_DONE;
+
+ return 0;
+}
+
+#define for_each_kimage_entry(image, ptr, entry) \
+ for (ptr = &image->head; (entry = *ptr) && !(entry & IND_DONE); \
+ ptr = (entry & IND_INDIRECTION)? \
+ phys_to_virt((entry & PAGE_MASK)): ptr +1)
+
+static void kimage_free_entry(kimage_entry_t entry)
+{
+ struct page *page;
+
+ page = pfn_to_page(entry >> PAGE_SHIFT);
+ kimage_free_pages(page);
+}
+
+static void kimage_free(struct kimage *image)
+{
+ kimage_entry_t *ptr, entry;
+ kimage_entry_t ind = 0;
+
+ if (!image)
+ return;
+
+ kimage_free_extra_pages(image);
+ for_each_kimage_entry(image, ptr, entry) {
+ if (entry & IND_INDIRECTION) {
+ /* Free the previous indirection page */
+ if (ind & IND_INDIRECTION)
+ kimage_free_entry(ind);
+ /* Save this indirection page until we are
+ * done with it.
+ */
+ ind = entry;
+ }
+ else if (entry & IND_SOURCE)
+ kimage_free_entry(entry);
+ }
+ /* Free the final indirection page */
+ if (ind & IND_INDIRECTION)
+ kimage_free_entry(ind);
+
+ /* Handle any machine specific cleanup */
+ machine_kexec_cleanup(image);
+
+ /* Free the kexec control pages... */
+ kimage_free_page_list(&image->control_pages);
+ kfree(image);
+}
+
+static kimage_entry_t *kimage_dst_used(struct kimage *image,
+ unsigned long page)
+{
+ kimage_entry_t *ptr, entry;
+ unsigned long destination = 0;
+
+ for_each_kimage_entry(image, ptr, entry) {
+ if (entry & IND_DESTINATION)
+ destination = entry & PAGE_MASK;
+ else if (entry & IND_SOURCE) {
+ if (page == destination)
+ return ptr;
+ destination += PAGE_SIZE;
+ }
+ }
+
+ return NULL;
+}
+
+static struct page *kimage_alloc_page(struct kimage *image,
+ gfp_t gfp_mask,
+ unsigned long destination)
+{
+ /*
+ * Here we implement safeguards to ensure that a source page
+ * is not copied to its destination page before the data on
+ * the destination page is no longer useful.
+ *
+ * To do this we maintain the invariant that a source page is
+ * either its own destination page, or it is not a
+ * destination page at all.
+ *
+ * That is slightly stronger than required, but the proof
+ * that no problems will not occur is trivial, and the
+ * implementation is simply to verify.
+ *
+ * When allocating all pages normally this algorithm will run
+ * in O(N) time, but in the worst case it will run in O(N^2)
+ * time. If the runtime is a problem the data structures can
+ * be fixed.
+ */
+ struct page *page;
+ unsigned long addr;
+
+ /*
+ * Walk through the list of destination pages, and see if I
+ * have a match.
+ */
+ list_for_each_entry(page, &image->dest_pages, lru) {
+ addr = page_to_pfn(page) << PAGE_SHIFT;
+ if (addr == destination) {
+ list_del(&page->lru);
+ return page;
+ }
+ }
+ page = NULL;
+ while (1) {
+ kimage_entry_t *old;
+
+ /* Allocate a page, if we run out of memory give up */
+ page = kimage_alloc_pages(gfp_mask, 0);
+ if (!page)
+ return NULL;
+ /* If the page cannot be used file it away */
+ if (page_to_pfn(page) >
+ (KEXEC_SOURCE_MEMORY_LIMIT >> PAGE_SHIFT)) {
+ list_add(&page->lru, &image->unuseable_pages);
+ continue;
+ }
+ addr = page_to_pfn(page) << PAGE_SHIFT;
+
+ /* If it is the destination page we want use it */
+ if (addr == destination)
+ break;
+
+ /* If the page is not a destination page use it */
+ if (!kimage_is_destination_range(image, addr,
+ addr + PAGE_SIZE))
+ break;
+
+ /*
+ * I know that the page is someones destination page.
+ * See if there is already a source page for this
+ * destination page. And if so swap the source pages.
+ */
+ old = kimage_dst_used(image, addr);
+ if (old) {
+ /* If so move it */
+ unsigned long old_addr;
+ struct page *old_page;
+
+ old_addr = *old & PAGE_MASK;
+ old_page = pfn_to_page(old_addr >> PAGE_SHIFT);
+ copy_highpage(page, old_page);
+ *old = addr | (*old & ~PAGE_MASK);
+
+ /* The old page I have found cannot be a
+ * destination page, so return it.
+ */
+ addr = old_addr;
+ page = old_page;
+ break;
+ }
+ else {
+ /* Place the page on the destination list I
+ * will use it later.
+ */
+ list_add(&page->lru, &image->dest_pages);
+ }
+ }
+
+ return page;
+}
+
+static int kimage_load_normal_segment(struct kimage *image,
+ struct kexec_segment *segment)
+{
+ unsigned long maddr;
+ unsigned long ubytes, mbytes;
+ int result;
+ unsigned char __user *buf;
+
+ result = 0;
+ buf = segment->buf;
+ ubytes = segment->bufsz;
+ mbytes = segment->memsz;
+ maddr = segment->mem;
+
+ result = kimage_set_destination(image, maddr);
+ if (result < 0)
+ goto out;
+
+ while (mbytes) {
+ struct page *page;
+ char *ptr;
+ size_t uchunk, mchunk;
+
+ page = kimage_alloc_page(image, GFP_HIGHUSER, maddr);
+ if (page == 0) {
+ result = -ENOMEM;
+ goto out;
+ }
+ result = kimage_add_page(image, page_to_pfn(page)
+ << PAGE_SHIFT);
+ if (result < 0)
+ goto out;
+
+ ptr = kmap(page);
+ /* Start with a clear page */
+ memset(ptr, 0, PAGE_SIZE);
+ ptr += maddr & ~PAGE_MASK;
+ mchunk = PAGE_SIZE - (maddr & ~PAGE_MASK);
+ if (mchunk > mbytes)
+ mchunk = mbytes;
+
+ uchunk = mchunk;
+ if (uchunk > ubytes)
+ uchunk = ubytes;
+
+ result = copy_from_user(ptr, buf, uchunk);
+ kunmap(page);
+ if (result) {
+ result = (result < 0) ? result : -EIO;
+ goto out;
+ }
+ ubytes -= uchunk;
+ maddr += mchunk;
+ buf += mchunk;
+ mbytes -= mchunk;
+ }
+out:
+ return result;
+}
+
+static int kimage_load_crash_segment(struct kimage *image,
+ struct kexec_segment *segment)
+{
+ /* For crash dumps kernels we simply copy the data from
+ * user space to it's destination.
+ * We do things a page at a time for the sake of kmap.
+ */
+ unsigned long maddr;
+ unsigned long ubytes, mbytes;
+ int result;
+ unsigned char __user *buf;
+
+ result = 0;
+ buf = segment->buf;
+ ubytes = segment->bufsz;
+ mbytes = segment->memsz;
+ maddr = segment->mem;
+ while (mbytes) {
+ struct page *page;
+ char *ptr;
+ size_t uchunk, mchunk;
+
+ page = pfn_to_page(maddr >> PAGE_SHIFT);
+ if (page == 0) {
+ result = -ENOMEM;
+ goto out;
+ }
+ ptr = kmap(page);
+ ptr += maddr & ~PAGE_MASK;
+ mchunk = PAGE_SIZE - (maddr & ~PAGE_MASK);
+ if (mchunk > mbytes)
+ mchunk = mbytes;
+
+ uchunk = mchunk;
+ if (uchunk > ubytes) {
+ uchunk = ubytes;
+ /* Zero the trailing part of the page */
+ memset(ptr + uchunk, 0, mchunk - uchunk);
+ }
+ result = copy_from_user(ptr, buf, uchunk);
+ kunmap(page);
+ if (result) {
+ result = (result < 0) ? result : -EIO;
+ goto out;
+ }
+ ubytes -= uchunk;
+ maddr += mchunk;
+ buf += mchunk;
+ mbytes -= mchunk;
+ }
+out:
+ return result;
+}
+
+static int kimage_load_segment(struct kimage *image,
+ struct kexec_segment *segment)
+{
+ int result = -ENOMEM;
+
+ switch (image->type) {
+ case KEXEC_TYPE_DEFAULT:
+ result = kimage_load_normal_segment(image, segment);
+ break;
+ case KEXEC_TYPE_CRASH:
+ result = kimage_load_crash_segment(image, segment);
+ break;
+ }
+
+ return result;
+}
+
+/*
+ * Exec Kernel system call: for obvious reasons only root may call it.
+ *
+ * This call breaks up into three pieces.
+ * - A generic part which loads the new kernel from the current
+ * address space, and very carefully places the data in the
+ * allocated pages.
+ *
+ * - A generic part that interacts with the kernel and tells all of
+ * the devices to shut down. Preventing on-going dmas, and placing
+ * the devices in a consistent state so a later kernel can
+ * reinitialize them.
+ *
+ * - A machine specific part that includes the syscall number
+ * and the copies the image to it's final destination. And
+ * jumps into the image at entry.
+ *
+ * kexec does not sync, or unmount filesystems so if you need
+ * that to happen you need to do that yourself.
+ */
+struct kimage *kexec_image = NULL;
+static struct kimage *kexec_crash_image = NULL;
+/*
+ * A home grown binary mutex.
+ * Nothing can wait so this mutex is safe to use
+ * in interrupt context :)
+ */
+static int kexec_lock = 0;
+
+asmlinkage long sys_kexec_load(unsigned long entry, unsigned long nr_segments,
+ struct kexec_segment __user *segments,
+ unsigned long flags)
+{
+ struct kimage **dest_image, *image;
+ int locked;
+ int result;
+
+ /* We only trust the superuser with rebooting the system. */
+ if (!capable(CAP_SYS_BOOT))
+ return -EPERM;
+
+ /*
+ * Verify we have a legal set of flags
+ * This leaves us room for future extensions.
+ */
+ if ((flags & KEXEC_FLAGS) != (flags & ~KEXEC_ARCH_MASK))
+ return -EINVAL;
+
+ /* Verify we are on the appropriate architecture */
+ if (((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH) &&
+ ((flags & KEXEC_ARCH_MASK) != KEXEC_ARCH_DEFAULT))
+ return -EINVAL;
+
+ /* Put an artificial cap on the number
+ * of segments passed to kexec_load.
+ */
+ if (nr_segments > KEXEC_SEGMENT_MAX)
+ return -EINVAL;
+
+ image = NULL;
+ result = 0;
+
+ /* Because we write directly to the reserved memory
+ * region when loading crash kernels we need a mutex here to
+ * prevent multiple crash kernels from attempting to load
+ * simultaneously, and to prevent a crash kernel from loading
+ * over the top of a in use crash kernel.
+ *
+ * KISS: always take the mutex.
+ */
+ locked = xchg(&kexec_lock, 1);
+ if (locked)
+ return -EBUSY;
+
+ dest_image = &kexec_image;
+ if (flags & KEXEC_ON_CRASH)
+ dest_image = &kexec_crash_image;
+ if (nr_segments > 0) {
+ unsigned long i;
+
+ /* Loading another kernel to reboot into */
+ if ((flags & KEXEC_ON_CRASH) == 0)
+ result = kimage_normal_alloc(&image, entry,
+ nr_segments, segments);
+ /* Loading another kernel to switch to if this one crashes */
+ else if (flags & KEXEC_ON_CRASH) {
+ /* Free any current crash dump kernel before
+ * we corrupt it.
+ */
+ kimage_free(xchg(&kexec_crash_image, NULL));
+ result = kimage_crash_alloc(&image, entry,
+ nr_segments, segments);
+ }
+ if (result)
+ goto out;
+
+ result = machine_kexec_prepare(image);
+ if (result)
+ goto out;
+
+ for (i = 0; i < nr_segments; i++) {
+ result = kimage_load_segment(image, &image->segment[i]);
+ if (result)
+ goto out;
+ }
+ result = kimage_terminate(image);
+ if (result)
+ goto out;
+ }
+ /* Install the new kernel, and Uninstall the old */
+ image = xchg(dest_image, image);
+
+out:
+ xchg(&kexec_lock, 0); /* Release the mutex */
+ kimage_free(image);
+
+ return result;
+}
+
+#ifdef CONFIG_COMPAT
+asmlinkage long compat_sys_kexec_load(unsigned long entry,
+ unsigned long nr_segments,
+ struct compat_kexec_segment __user *segments,
+ unsigned long flags)
+{
+ struct compat_kexec_segment in;
+ struct kexec_segment out, __user *ksegments;
+ unsigned long i, result;
+
+ /* Don't allow clients that don't understand the native
+ * architecture to do anything.
+ */
+ if ((flags & KEXEC_ARCH_MASK) == KEXEC_ARCH_DEFAULT)
+ return -EINVAL;
+
+ if (nr_segments > KEXEC_SEGMENT_MAX)
+ return -EINVAL;
+
+ ksegments = compat_alloc_user_space(nr_segments * sizeof(out));
+ for (i=0; i < nr_segments; i++) {
+ result = copy_from_user(&in, &segments[i], sizeof(in));
+ if (result)
+ return -EFAULT;
+
+ out.buf = compat_ptr(in.buf);
+ out.bufsz = in.bufsz;
+ out.mem = in.mem;
+ out.memsz = in.memsz;
+
+ result = copy_to_user(&ksegments[i], &out, sizeof(out));
+ if (result)
+ return -EFAULT;
+ }
+
+ return sys_kexec_load(entry, nr_segments, ksegments, flags);
+}
+#endif
+
+void crash_kexec(struct pt_regs *regs)
+{
+ struct kimage *image;
+ int locked;
+
+
+ /* Take the kexec_lock here to prevent sys_kexec_load
+ * running on one cpu from replacing the crash kernel
+ * we are using after a panic on a different cpu.
+ *
+ * If the crash kernel was not located in a fixed area
+ * of memory the xchg(&kexec_crash_image) would be
+ * sufficient. But since I reuse the memory...
+ */
+ locked = xchg(&kexec_lock, 1);
+ if (!locked) {
+ image = xchg(&kexec_crash_image, NULL);
+ if (image) {
+ struct pt_regs fixed_regs;
+ crash_setup_regs(&fixed_regs, regs);
+ machine_crash_shutdown(&fixed_regs);
+ machine_kexec(image);
+ }
+ xchg(&kexec_lock, 0);
+ }
+}
+
+static int __init crash_notes_memory_init(void)
+{
+ /* Allocate memory for saving cpu registers. */
+ crash_notes = alloc_percpu(note_buf_t);
+ if (!crash_notes) {
+ printk("Kexec: Memory allocation for saving cpu register"
+ " states failed\n");
+ return -ENOMEM;
+ }
+ return 0;
+}
+module_init(crash_notes_memory_init)
_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-changelog
|
Home