linux/arch/x86/kernel/crash.c

486 lines
11 KiB
C
Raw Normal View History

/*
* Architecture specific (i386/x86_64) functions for kexec based crash dumps.
*
* Created by: Hariprasad Nellitheertha (hari@in.ibm.com)
*
* Copyright (C) IBM Corporation, 2004. All rights reserved.
* Copyright (C) Red Hat Inc., 2014. All rights reserved.
* Authors:
* Vivek Goyal <vgoyal@redhat.com>
*
*/
#define pr_fmt(fmt) "kexec: " fmt
#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 <linux/export.h>
#include <linux/slab.h>
x86/mm: Decouple <linux/vmalloc.h> from <asm/io.h> Nothing in <asm/io.h> uses anything from <linux/vmalloc.h>, so remove it from there and fix up the resulting build problems triggered on x86 {64|32}-bit {def|allmod|allno}configs. The breakages were triggering in places where x86 builds relied on vmalloc() facilities but did not include <linux/vmalloc.h> explicitly and relied on the implicit inclusion via <asm/io.h>. Also add: - <linux/init.h> to <linux/io.h> - <asm/pgtable_types> to <asm/io.h> ... which were two other implicit header file dependencies. Suggested-by: David Miller <davem@davemloft.net> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> [ Tidied up the changelog. ] Acked-by: David Miller <davem@davemloft.net> Acked-by: Takashi Iwai <tiwai@suse.de> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Acked-by: Vinod Koul <vinod.koul@intel.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Anton Vorontsov <anton@enomsg.org> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Colin Cross <ccross@android.com> Cc: David Vrabel <david.vrabel@citrix.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Haiyang Zhang <haiyangz@microsoft.com> Cc: James E.J. Bottomley <JBottomley@odin.com> Cc: Jaroslav Kysela <perex@perex.cz> Cc: K. Y. Srinivasan <kys@microsoft.com> Cc: Kees Cook <keescook@chromium.org> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Kristen Carlson Accardi <kristen@linux.intel.com> Cc: Len Brown <lenb@kernel.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rafael J. Wysocki <rjw@rjwysocki.net> Cc: Suma Ramars <sramars@cisco.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-06-02 17:01:38 +08:00
#include <linux/vmalloc.h>
#include <asm/processor.h>
#include <asm/hardirq.h>
#include <asm/nmi.h>
#include <asm/hw_irq.h>
#include <asm/apic.h>
#include <asm/e820/types.h>
#include <asm/io_apic.h>
#include <asm/hpet.h>
#include <linux/kdebug.h>
#include <asm/cpu.h>
#include <asm/reboot.h>
#include <asm/virtext.h>
#include <asm/intel_pt.h>
x86/headers: Fix -Wmissing-prototypes warning When building the kernel with W=1 we get a lot of -Wmissing-prototypes warnings, which are trivial in nature and easy to fix - and which may mask some real future bugs if the prototypes get out of sync with the function definition. This patch fixes most of -Wmissing-prototypes warnings which are in the root directory of arch/x86/kernel, not including the subdirectories. These are the warnings fixed in this patch: arch/x86/kernel/signal.c:865:17: warning: no previous prototype for ‘sys32_x32_rt_sigreturn’ [-Wmissing-prototypes] arch/x86/kernel/signal_compat.c:164:6: warning: no previous prototype for ‘sigaction_compat_abi’ [-Wmissing-prototypes] arch/x86/kernel/traps.c:625:46: warning: no previous prototype for ‘sync_regs’ [-Wmissing-prototypes] arch/x86/kernel/traps.c:640:24: warning: no previous prototype for ‘fixup_bad_iret’ [-Wmissing-prototypes] arch/x86/kernel/traps.c:929:13: warning: no previous prototype for ‘trap_init’ [-Wmissing-prototypes] arch/x86/kernel/irq.c:270:28: warning: no previous prototype for ‘smp_x86_platform_ipi’ [-Wmissing-prototypes] arch/x86/kernel/irq.c:301:16: warning: no previous prototype for ‘smp_kvm_posted_intr_ipi’ [-Wmissing-prototypes] arch/x86/kernel/irq.c:314:16: warning: no previous prototype for ‘smp_kvm_posted_intr_wakeup_ipi’ [-Wmissing-prototypes] arch/x86/kernel/irq.c:328:16: warning: no previous prototype for ‘smp_kvm_posted_intr_nested_ipi’ [-Wmissing-prototypes] arch/x86/kernel/irq_work.c:16:28: warning: no previous prototype for ‘smp_irq_work_interrupt’ [-Wmissing-prototypes] arch/x86/kernel/irqinit.c:79:13: warning: no previous prototype for ‘init_IRQ’ [-Wmissing-prototypes] arch/x86/kernel/quirks.c:672:13: warning: no previous prototype for ‘early_platform_quirks’ [-Wmissing-prototypes] arch/x86/kernel/tsc.c:1499:15: warning: no previous prototype for ‘calibrate_delay_is_known’ [-Wmissing-prototypes] arch/x86/kernel/process.c:653:13: warning: no previous prototype for ‘arch_post_acpi_subsys_init’ [-Wmissing-prototypes] arch/x86/kernel/process.c:717:15: warning: no previous prototype for ‘arch_randomize_brk’ [-Wmissing-prototypes] arch/x86/kernel/process.c:784:6: warning: no previous prototype for ‘do_arch_prctl_common’ [-Wmissing-prototypes] arch/x86/kernel/reboot.c:869:6: warning: no previous prototype for ‘nmi_panic_self_stop’ [-Wmissing-prototypes] arch/x86/kernel/smp.c:176:27: warning: no previous prototype for ‘smp_reboot_interrupt’ [-Wmissing-prototypes] arch/x86/kernel/smp.c:260:28: warning: no previous prototype for ‘smp_reschedule_interrupt’ [-Wmissing-prototypes] arch/x86/kernel/smp.c:281:28: warning: no previous prototype for ‘smp_call_function_interrupt’ [-Wmissing-prototypes] arch/x86/kernel/smp.c:291:28: warning: no previous prototype for ‘smp_call_function_single_interrupt’ [-Wmissing-prototypes] arch/x86/kernel/ftrace.c:840:6: warning: no previous prototype for ‘arch_ftrace_update_trampoline’ [-Wmissing-prototypes] arch/x86/kernel/ftrace.c:934:7: warning: no previous prototype for ‘arch_ftrace_trampoline_func’ [-Wmissing-prototypes] arch/x86/kernel/ftrace.c:946:6: warning: no previous prototype for ‘arch_ftrace_trampoline_free’ [-Wmissing-prototypes] arch/x86/kernel/crash.c:114:6: warning: no previous prototype for ‘crash_smp_send_stop’ [-Wmissing-prototypes] arch/x86/kernel/crash.c:351:5: warning: no previous prototype for ‘crash_setup_memmap_entries’ [-Wmissing-prototypes] arch/x86/kernel/crash.c:424:5: warning: no previous prototype for ‘crash_load_segments’ [-Wmissing-prototypes] arch/x86/kernel/machine_kexec_64.c:372:7: warning: no previous prototype for ‘arch_kexec_kernel_image_load’ [-Wmissing-prototypes] arch/x86/kernel/paravirt-spinlocks.c:12:16: warning: no previous prototype for ‘__native_queued_spin_unlock’ [-Wmissing-prototypes] arch/x86/kernel/paravirt-spinlocks.c:18:6: warning: no previous prototype for ‘pv_is_native_spin_unlock’ [-Wmissing-prototypes] arch/x86/kernel/paravirt-spinlocks.c:24:16: warning: no previous prototype for ‘__native_vcpu_is_preempted’ [-Wmissing-prototypes] arch/x86/kernel/paravirt-spinlocks.c:30:6: warning: no previous prototype for ‘pv_is_native_vcpu_is_preempted’ [-Wmissing-prototypes] arch/x86/kernel/kvm.c:258:1: warning: no previous prototype for ‘do_async_page_fault’ [-Wmissing-prototypes] arch/x86/kernel/jailhouse.c:200:6: warning: no previous prototype for ‘jailhouse_paravirt’ [-Wmissing-prototypes] arch/x86/kernel/check.c:91:13: warning: no previous prototype for ‘setup_bios_corruption_check’ [-Wmissing-prototypes] arch/x86/kernel/check.c:139:6: warning: no previous prototype for ‘check_for_bios_corruption’ [-Wmissing-prototypes] arch/x86/kernel/devicetree.c:32:13: warning: no previous prototype for ‘early_init_dt_scan_chosen_arch’ [-Wmissing-prototypes] arch/x86/kernel/devicetree.c:42:13: warning: no previous prototype for ‘add_dtb’ [-Wmissing-prototypes] arch/x86/kernel/devicetree.c:108:6: warning: no previous prototype for ‘x86_of_pci_init’ [-Wmissing-prototypes] arch/x86/kernel/devicetree.c:314:13: warning: no previous prototype for ‘x86_dtb_init’ [-Wmissing-prototypes] arch/x86/kernel/tracepoint.c:16:5: warning: no previous prototype for ‘trace_pagefault_reg’ [-Wmissing-prototypes] arch/x86/kernel/tracepoint.c:22:6: warning: no previous prototype for ‘trace_pagefault_unreg’ [-Wmissing-prototypes] arch/x86/kernel/head64.c:113:22: warning: no previous prototype for ‘__startup_64’ [-Wmissing-prototypes] arch/x86/kernel/head64.c:262:15: warning: no previous prototype for ‘__startup_secondary_64’ [-Wmissing-prototypes] arch/x86/kernel/head64.c:350:12: warning: no previous prototype for ‘early_make_pgtable’ [-Wmissing-prototypes] [ mingo: rewrote the changelog, fixed build errors. ] Signed-off-by: Yi Wang <wang.yi59@zte.com.cn> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: akataria@vmware.com Cc: akpm@linux-foundation.org Cc: andy.shevchenko@gmail.com Cc: anton@enomsg.org Cc: ard.biesheuvel@linaro.org Cc: bhe@redhat.com Cc: bhelgaas@google.com Cc: bp@alien8.de Cc: ccross@android.com Cc: devicetree@vger.kernel.org Cc: douly.fnst@cn.fujitsu.com Cc: dwmw@amazon.co.uk Cc: dyoung@redhat.com Cc: ebiederm@xmission.com Cc: frank.rowand@sony.com Cc: frowand.list@gmail.com Cc: ivan.gorinov@intel.com Cc: jailhouse-dev@googlegroups.com Cc: jan.kiszka@siemens.com Cc: jgross@suse.com Cc: jroedel@suse.de Cc: keescook@chromium.org Cc: kexec@lists.infradead.org Cc: konrad.wilk@oracle.com Cc: kvm@vger.kernel.org Cc: linux-efi@vger.kernel.org Cc: linux-pci@vger.kernel.org Cc: luto@kernel.org Cc: m.mizuma@jp.fujitsu.com Cc: namit@vmware.com Cc: oleg@redhat.com Cc: pasha.tatashin@oracle.com Cc: pbonzini@redhat.com Cc: prarit@redhat.com Cc: pravin.shedge4linux@gmail.com Cc: rajvi.jingar@intel.com Cc: rkrcmar@redhat.com Cc: robh+dt@kernel.org Cc: robh@kernel.org Cc: rostedt@goodmis.org Cc: takahiro.akashi@linaro.org Cc: thomas.lendacky@amd.com Cc: tony.luck@intel.com Cc: up2wing@gmail.com Cc: virtualization@lists.linux-foundation.org Cc: zhe.he@windriver.com Cc: zhong.weidong@zte.com.cn Link: http://lkml.kernel.org/r/1542852249-19820-1-git-send-email-wang.yi59@zte.com.cn Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-11-22 10:04:09 +08:00
#include <asm/crash.h>
/* Used while preparing memory map entries for second kernel */
struct crash_memmap_data {
struct boot_params *params;
/* Type of memory */
unsigned int type;
};
/*
* This is used to VMCLEAR all VMCSs loaded on the
* processor. And when loading kvm_intel module, the
* callback function pointer will be assigned.
*
* protected by rcu.
*/
crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss = NULL;
EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss);
unsigned long crash_zero_bytes;
static inline void cpu_crash_vmclear_loaded_vmcss(void)
{
crash_vmclear_fn *do_vmclear_operation = NULL;
rcu_read_lock();
do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss);
if (do_vmclear_operation)
do_vmclear_operation();
rcu_read_unlock();
}
#if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
{
#ifdef CONFIG_X86_32
struct pt_regs fixed_regs;
if (!user_mode(regs)) {
crash_fixup_ss_esp(&fixed_regs, regs);
regs = &fixed_regs;
}
#endif
crash_save_cpu(regs, cpu);
/*
* VMCLEAR VMCSs loaded on all cpus if needed.
*/
cpu_crash_vmclear_loaded_vmcss();
/* Disable VMX or SVM if needed.
*
* We need to disable virtualization on all CPUs.
* Having VMX or SVM enabled on any CPU may break rebooting
* after the kdump kernel has finished its task.
*/
cpu_emergency_vmxoff();
cpu_emergency_svm_disable();
/*
* Disable Intel PT to stop its logging
*/
cpu_emergency_stop_pt();
disable_local_APIC();
}
x86/panic: replace smp_send_stop() with kdump friendly version in panic path Daniel Walker reported problems which happens when crash_kexec_post_notifiers kernel option is enabled (https://lkml.org/lkml/2015/6/24/44). In that case, smp_send_stop() is called before entering kdump routines which assume other CPUs are still online. As the result, for x86, kdump routines fail to save other CPUs' registers and disable virtualization extensions. To fix this problem, call a new kdump friendly function, crash_smp_send_stop(), instead of the smp_send_stop() when crash_kexec_post_notifiers is enabled. crash_smp_send_stop() is a weak function, and it just call smp_send_stop(). Architecture codes should override it so that kdump can work appropriately. This patch only provides x86-specific version. For Xen's PV kernel, just keep the current behavior. NOTES: - Right solution would be to place crash_smp_send_stop() before __crash_kexec() invocation in all cases and remove smp_send_stop(), but we can't do that until all architectures implement own crash_smp_send_stop() - crash_smp_send_stop()-like work is still needed by machine_crash_shutdown() because crash_kexec() can be called without entering panic() Fixes: f06e5153f4ae (kernel/panic.c: add "crash_kexec_post_notifiers" option) Link: http://lkml.kernel.org/r/20160810080948.11028.15344.stgit@sysi4-13.yrl.intra.hitachi.co.jp Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Reported-by: Daniel Walker <dwalker@fifo99.com> Cc: Dave Young <dyoung@redhat.com> Cc: Baoquan He <bhe@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Daniel Walker <dwalker@fifo99.com> Cc: Xunlei Pang <xpang@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Borislav Petkov <bp@suse.de> Cc: David Vrabel <david.vrabel@citrix.com> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Daney <david.daney@cavium.com> Cc: Aaro Koskinen <aaro.koskinen@iki.fi> Cc: "Steven J. Hill" <steven.hill@cavium.com> Cc: Corey Minyard <cminyard@mvista.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-12 04:54:23 +08:00
void kdump_nmi_shootdown_cpus(void)
{
nmi_shootdown_cpus(kdump_nmi_callback);
disable_local_APIC();
}
x86/panic: replace smp_send_stop() with kdump friendly version in panic path Daniel Walker reported problems which happens when crash_kexec_post_notifiers kernel option is enabled (https://lkml.org/lkml/2015/6/24/44). In that case, smp_send_stop() is called before entering kdump routines which assume other CPUs are still online. As the result, for x86, kdump routines fail to save other CPUs' registers and disable virtualization extensions. To fix this problem, call a new kdump friendly function, crash_smp_send_stop(), instead of the smp_send_stop() when crash_kexec_post_notifiers is enabled. crash_smp_send_stop() is a weak function, and it just call smp_send_stop(). Architecture codes should override it so that kdump can work appropriately. This patch only provides x86-specific version. For Xen's PV kernel, just keep the current behavior. NOTES: - Right solution would be to place crash_smp_send_stop() before __crash_kexec() invocation in all cases and remove smp_send_stop(), but we can't do that until all architectures implement own crash_smp_send_stop() - crash_smp_send_stop()-like work is still needed by machine_crash_shutdown() because crash_kexec() can be called without entering panic() Fixes: f06e5153f4ae (kernel/panic.c: add "crash_kexec_post_notifiers" option) Link: http://lkml.kernel.org/r/20160810080948.11028.15344.stgit@sysi4-13.yrl.intra.hitachi.co.jp Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Reported-by: Daniel Walker <dwalker@fifo99.com> Cc: Dave Young <dyoung@redhat.com> Cc: Baoquan He <bhe@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Daniel Walker <dwalker@fifo99.com> Cc: Xunlei Pang <xpang@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Borislav Petkov <bp@suse.de> Cc: David Vrabel <david.vrabel@citrix.com> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Daney <david.daney@cavium.com> Cc: Aaro Koskinen <aaro.koskinen@iki.fi> Cc: "Steven J. Hill" <steven.hill@cavium.com> Cc: Corey Minyard <cminyard@mvista.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-12 04:54:23 +08:00
/* Override the weak function in kernel/panic.c */
void crash_smp_send_stop(void)
{
static int cpus_stopped;
if (cpus_stopped)
return;
if (smp_ops.crash_stop_other_cpus)
smp_ops.crash_stop_other_cpus();
else
smp_send_stop();
cpus_stopped = 1;
}
#else
x86/panic: replace smp_send_stop() with kdump friendly version in panic path Daniel Walker reported problems which happens when crash_kexec_post_notifiers kernel option is enabled (https://lkml.org/lkml/2015/6/24/44). In that case, smp_send_stop() is called before entering kdump routines which assume other CPUs are still online. As the result, for x86, kdump routines fail to save other CPUs' registers and disable virtualization extensions. To fix this problem, call a new kdump friendly function, crash_smp_send_stop(), instead of the smp_send_stop() when crash_kexec_post_notifiers is enabled. crash_smp_send_stop() is a weak function, and it just call smp_send_stop(). Architecture codes should override it so that kdump can work appropriately. This patch only provides x86-specific version. For Xen's PV kernel, just keep the current behavior. NOTES: - Right solution would be to place crash_smp_send_stop() before __crash_kexec() invocation in all cases and remove smp_send_stop(), but we can't do that until all architectures implement own crash_smp_send_stop() - crash_smp_send_stop()-like work is still needed by machine_crash_shutdown() because crash_kexec() can be called without entering panic() Fixes: f06e5153f4ae (kernel/panic.c: add "crash_kexec_post_notifiers" option) Link: http://lkml.kernel.org/r/20160810080948.11028.15344.stgit@sysi4-13.yrl.intra.hitachi.co.jp Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Reported-by: Daniel Walker <dwalker@fifo99.com> Cc: Dave Young <dyoung@redhat.com> Cc: Baoquan He <bhe@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Daniel Walker <dwalker@fifo99.com> Cc: Xunlei Pang <xpang@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Borislav Petkov <bp@suse.de> Cc: David Vrabel <david.vrabel@citrix.com> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Daney <david.daney@cavium.com> Cc: Aaro Koskinen <aaro.koskinen@iki.fi> Cc: "Steven J. Hill" <steven.hill@cavium.com> Cc: Corey Minyard <cminyard@mvista.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-12 04:54:23 +08:00
void crash_smp_send_stop(void)
{
/* There are no cpus to shootdown */
}
#endif
void native_machine_crash_shutdown(struct pt_regs *regs)
{
/* This function is only called after the system
* has panicked 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();
x86/panic: replace smp_send_stop() with kdump friendly version in panic path Daniel Walker reported problems which happens when crash_kexec_post_notifiers kernel option is enabled (https://lkml.org/lkml/2015/6/24/44). In that case, smp_send_stop() is called before entering kdump routines which assume other CPUs are still online. As the result, for x86, kdump routines fail to save other CPUs' registers and disable virtualization extensions. To fix this problem, call a new kdump friendly function, crash_smp_send_stop(), instead of the smp_send_stop() when crash_kexec_post_notifiers is enabled. crash_smp_send_stop() is a weak function, and it just call smp_send_stop(). Architecture codes should override it so that kdump can work appropriately. This patch only provides x86-specific version. For Xen's PV kernel, just keep the current behavior. NOTES: - Right solution would be to place crash_smp_send_stop() before __crash_kexec() invocation in all cases and remove smp_send_stop(), but we can't do that until all architectures implement own crash_smp_send_stop() - crash_smp_send_stop()-like work is still needed by machine_crash_shutdown() because crash_kexec() can be called without entering panic() Fixes: f06e5153f4ae (kernel/panic.c: add "crash_kexec_post_notifiers" option) Link: http://lkml.kernel.org/r/20160810080948.11028.15344.stgit@sysi4-13.yrl.intra.hitachi.co.jp Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Reported-by: Daniel Walker <dwalker@fifo99.com> Cc: Dave Young <dyoung@redhat.com> Cc: Baoquan He <bhe@redhat.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Daniel Walker <dwalker@fifo99.com> Cc: Xunlei Pang <xpang@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Borislav Petkov <bp@suse.de> Cc: David Vrabel <david.vrabel@citrix.com> Cc: Toshi Kani <toshi.kani@hpe.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: David Daney <david.daney@cavium.com> Cc: Aaro Koskinen <aaro.koskinen@iki.fi> Cc: "Steven J. Hill" <steven.hill@cavium.com> Cc: Corey Minyard <cminyard@mvista.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-10-12 04:54:23 +08:00
crash_smp_send_stop();
/*
* VMCLEAR VMCSs loaded on this cpu if needed.
*/
cpu_crash_vmclear_loaded_vmcss();
/* Booting kdump kernel with VMX or SVM enabled won't work,
* because (among other limitations) we can't disable paging
* with the virt flags.
*/
cpu_emergency_vmxoff();
cpu_emergency_svm_disable();
/*
* Disable Intel PT to stop its logging
*/
cpu_emergency_stop_pt();
x86/ioapic/kcrash: Prevent crash_kexec() from deadlocking on ioapic_lock Prevent crash_kexec() from deadlocking on ioapic_lock. When crash_kexec() is executed on a CPU, the CPU will take ioapic_lock in disable_IO_APIC(). So if the cpu gets an NMI while locking ioapic_lock, a deadlock will happen. In this patch, ioapic_lock is zapped/initialized before disable_IO_APIC(). You can reproduce this deadlock the following way: 1. Add mdelay(1000) after raw_spin_lock_irqsave() in native_ioapic_set_affinity()@arch/x86/kernel/apic/io_apic.c Although the deadlock can occur without this modification, it will increase the potential of the deadlock problem. 2. Build and install the kernel 3. Set up the OS which will run panic() and kexec when NMI is injected # echo "kernel.unknown_nmi_panic=1" >> /etc/sysctl.conf # vim /etc/default/grub add "nmi_watchdog=0 crashkernel=256M" in GRUB_CMDLINE_LINUX line # grub2-mkconfig 4. Reboot the OS 5. Run following command for each vcpu on the guest # while true; do echo <CPU num> > /proc/irq/<IO-APIC-edge or IO-APIC-fasteoi>/smp_affinitity; done; By running this command, cpus will get ioapic_lock for setting affinity. 6. Inject NMI (push a dump button or execute 'virsh inject-nmi <domain>' if you use VM). After injecting NMI, panic() is called in an nmi-handler context. Then, kexec will normally run in panic(), but the operation will be stopped by deadlock on ioapic_lock in crash_kexec()->machine_crash_shutdown()-> native_machine_crash_shutdown()->disable_IO_APIC()->clear_IO_APIC()-> clear_IO_APIC_pin()->ioapic_read_entry(). Signed-off-by: Yoshihiro YUNOMAE <yoshihiro.yunomae.ez@hitachi.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Joerg Roedel <joro@8bytes.org> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com> Cc: Sebastian Andrzej Siewior <sebastian@breakpoint.cc> Cc: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: yrl.pp-manager.tt@hitachi.com Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Seiji Aguchi <seiji.aguchi@hds.com> Link: http://lkml.kernel.org/r/20130820070107.28245.83806.stgit@yunodevel Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-08-20 15:01:07 +08:00
#ifdef CONFIG_X86_IO_APIC
/* Prevent crash_kexec() from deadlocking on ioapic_lock. */
ioapic_zap_locks();
x86/apic: Fix restoring boot IRQ mode in reboot and kexec/kdump This is a regression fix. Before, to fix erratum AVR31, the following commit: 522e66464467 ("x86/apic: Disable I/O APIC before shutdown of the local APIC") ... moved the lapic_shutdown() call to after disable_IO_APIC() in the reboot and kexec/kdump code paths. This introduced the following regression: disable_IO_APIC() not only clears the IO-APIC, but it also restores boot IRQ mode by setting the LAPIC/APIC/IMCR, calling lapic_shutdown() after disable_IO_APIC() will disable LAPIC and ruin the possible virtual wire mode setting which the code has been trying to do all along. The consequence is that a KVM guest kernel always prints the warning below during kexec/kdump as the kernel boots up: [ 0.001000] WARNING: CPU: 0 PID: 0 at arch/x86/kernel/apic/apic.c:1467 setup_local_APIC+0x228/0x330 [ ........] [ 0.001000] Call Trace: [ 0.001000] apic_bsp_setup+0x56/0x74 [ 0.001000] x86_late_time_init+0x11/0x16 [ 0.001000] start_kernel+0x3c9/0x486 [ 0.001000] secondary_startup_64+0xa5/0xb0 [ ........] [ 0.001000] masked ExtINT on CPU#0 To fix this, just call clear_IO_APIC() to stop the IO-APIC where disable_IO_APIC() was called, and call restore_boot_irq_mode() to restore boot IRQ mode before a reboot or a kexec/kdump jump. Signed-off-by: Baoquan He <bhe@redhat.com> Reviewed-by: Eric W. Biederman <ebiederm@xmission.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: douly.fnst@cn.fujitsu.com Cc: joro@8bytes.org Cc: prarit@redhat.com Cc: stable@vger.kernel.org Cc: uobergfe@redhat.com Fixes: commit 522e66464467 ("x86/apic: Disable I/O APIC before shutdown of the local APIC") Link: http://lkml.kernel.org/r/20180214054656.3780-4-bhe@redhat.com [ Rewrote the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-02-14 13:46:53 +08:00
clear_IO_APIC();
#endif
lapic_shutdown();
x86/apic: Fix restoring boot IRQ mode in reboot and kexec/kdump This is a regression fix. Before, to fix erratum AVR31, the following commit: 522e66464467 ("x86/apic: Disable I/O APIC before shutdown of the local APIC") ... moved the lapic_shutdown() call to after disable_IO_APIC() in the reboot and kexec/kdump code paths. This introduced the following regression: disable_IO_APIC() not only clears the IO-APIC, but it also restores boot IRQ mode by setting the LAPIC/APIC/IMCR, calling lapic_shutdown() after disable_IO_APIC() will disable LAPIC and ruin the possible virtual wire mode setting which the code has been trying to do all along. The consequence is that a KVM guest kernel always prints the warning below during kexec/kdump as the kernel boots up: [ 0.001000] WARNING: CPU: 0 PID: 0 at arch/x86/kernel/apic/apic.c:1467 setup_local_APIC+0x228/0x330 [ ........] [ 0.001000] Call Trace: [ 0.001000] apic_bsp_setup+0x56/0x74 [ 0.001000] x86_late_time_init+0x11/0x16 [ 0.001000] start_kernel+0x3c9/0x486 [ 0.001000] secondary_startup_64+0xa5/0xb0 [ ........] [ 0.001000] masked ExtINT on CPU#0 To fix this, just call clear_IO_APIC() to stop the IO-APIC where disable_IO_APIC() was called, and call restore_boot_irq_mode() to restore boot IRQ mode before a reboot or a kexec/kdump jump. Signed-off-by: Baoquan He <bhe@redhat.com> Reviewed-by: Eric W. Biederman <ebiederm@xmission.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: douly.fnst@cn.fujitsu.com Cc: joro@8bytes.org Cc: prarit@redhat.com Cc: stable@vger.kernel.org Cc: uobergfe@redhat.com Fixes: commit 522e66464467 ("x86/apic: Disable I/O APIC before shutdown of the local APIC") Link: http://lkml.kernel.org/r/20180214054656.3780-4-bhe@redhat.com [ Rewrote the changelog. ] Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-02-14 13:46:53 +08:00
restore_boot_irq_mode();
#ifdef CONFIG_HPET_TIMER
hpet_disable();
#endif
crash_save_cpu(regs, safe_smp_processor_id());
}
kexec: create a new config option CONFIG_KEXEC_FILE for new syscall Currently new system call kexec_file_load() and all the associated code compiles if CONFIG_KEXEC=y. But new syscall also compiles purgatory code which currently uses gcc option -mcmodel=large. This option seems to be available only gcc 4.4 onwards. Hiding new functionality behind a new config option will not break existing users of old gcc. Those who wish to enable new functionality will require new gcc. Having said that, I am trying to figure out how can I move away from using -mcmodel=large but that can take a while. I think there are other advantages of introducing this new config option. As this option will be enabled only on x86_64, other arches don't have to compile generic kexec code which will never be used. This new code selects CRYPTO=y and CRYPTO_SHA256=y. And all other arches had to do this for CONFIG_KEXEC. Now with introduction of new config option, we can remove crypto dependency from other arches. Now CONFIG_KEXEC_FILE is available only on x86_64. So whereever I had CONFIG_X86_64 defined, I got rid of that. For CONFIG_KEXEC_FILE, instead of doing select CRYPTO=y, I changed it to "depends on CRYPTO=y". This should be safer as "select" is not recursive. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: H. Peter Anvin <hpa@zytor.com> Tested-by: Shaun Ruffell <sruffell@digium.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-30 06:18:46 +08:00
#ifdef CONFIG_KEXEC_FILE
static int get_nr_ram_ranges_callback(struct resource *res, void *arg)
{
x86/kexec: Fix kexec crash in syscall kexec_file_load() The original bug is a page fault crash that sometimes happens on big machines when preparing ELF headers: BUG: unable to handle kernel paging request at ffffc90613fc9000 IP: [<ffffffff8103d645>] prepare_elf64_ram_headers_callback+0x165/0x260 The bug is caused by us under-counting the number of memory ranges and subsequently not allocating enough ELF header space for them. The bug is typically masked on smaller systems, because the ELF header allocation is rounded up to the next page. This patch modifies the code in fill_up_crash_elf_data() by using walk_system_ram_res() instead of walk_system_ram_range() to correctly count the max number of crash memory ranges. That's because the walk_system_ram_range() filters out small memory regions that reside in the same page, but walk_system_ram_res() does not. Here's how I found the bug: After tracing prepare_elf64_headers() and prepare_elf64_ram_headers_callback(), the code uses walk_system_ram_res() to fill-in crash memory regions information to the program header, so it counts those small memory regions that reside in a page area. But, when the kernel was using walk_system_ram_range() in fill_up_crash_elf_data() to count the number of crash memory regions, it filters out small regions. I printed those small memory regions, for example: kexec: Get nr_ram ranges. vaddr=0xffff880077592258 paddr=0x77592258, sz=0xdc0 Based on the code in walk_system_ram_range(), this memory region will be filtered out: pfn = (0x77592258 + 0x1000 - 1) >> 12 = 0x77593 end_pfn = (0x77592258 + 0xfc0 -1 + 1) >> 12 = 0x77593 end_pfn - pfn = 0x77593 - 0x77593 = 0 <=== if (end_pfn > pfn) is FALSE So, the max_nr_ranges that's counted by the kernel doesn't include small memory regions - causing us to under-allocate the required space. That causes the page fault crash that happens in a later code path when preparing ELF headers. This bug is not easy to reproduce on small machines that have few CPUs, because the allocated page aligned ELF buffer has more free space to cover those small memory regions' PT_LOAD headers. Signed-off-by: Lee, Chun-Yi <jlee@suse.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Baoquan He <bhe@redhat.com> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Takashi Iwai <tiwai@suse.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: kexec@lists.infradead.org Cc: linux-kernel@vger.kernel.org Cc: <stable@vger.kernel.org> Link: http://lkml.kernel.org/r/1443531537-29436-1-git-send-email-jlee@suse.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-09-29 20:58:57 +08:00
unsigned int *nr_ranges = arg;
(*nr_ranges)++;
return 0;
}
/* Gather all the required information to prepare elf headers for ram regions */
static struct crash_mem *fill_up_crash_elf_data(void)
{
unsigned int nr_ranges = 0;
struct crash_mem *cmem;
x86/kexec: Fix kexec crash in syscall kexec_file_load() The original bug is a page fault crash that sometimes happens on big machines when preparing ELF headers: BUG: unable to handle kernel paging request at ffffc90613fc9000 IP: [<ffffffff8103d645>] prepare_elf64_ram_headers_callback+0x165/0x260 The bug is caused by us under-counting the number of memory ranges and subsequently not allocating enough ELF header space for them. The bug is typically masked on smaller systems, because the ELF header allocation is rounded up to the next page. This patch modifies the code in fill_up_crash_elf_data() by using walk_system_ram_res() instead of walk_system_ram_range() to correctly count the max number of crash memory ranges. That's because the walk_system_ram_range() filters out small memory regions that reside in the same page, but walk_system_ram_res() does not. Here's how I found the bug: After tracing prepare_elf64_headers() and prepare_elf64_ram_headers_callback(), the code uses walk_system_ram_res() to fill-in crash memory regions information to the program header, so it counts those small memory regions that reside in a page area. But, when the kernel was using walk_system_ram_range() in fill_up_crash_elf_data() to count the number of crash memory regions, it filters out small regions. I printed those small memory regions, for example: kexec: Get nr_ram ranges. vaddr=0xffff880077592258 paddr=0x77592258, sz=0xdc0 Based on the code in walk_system_ram_range(), this memory region will be filtered out: pfn = (0x77592258 + 0x1000 - 1) >> 12 = 0x77593 end_pfn = (0x77592258 + 0xfc0 -1 + 1) >> 12 = 0x77593 end_pfn - pfn = 0x77593 - 0x77593 = 0 <=== if (end_pfn > pfn) is FALSE So, the max_nr_ranges that's counted by the kernel doesn't include small memory regions - causing us to under-allocate the required space. That causes the page fault crash that happens in a later code path when preparing ELF headers. This bug is not easy to reproduce on small machines that have few CPUs, because the allocated page aligned ELF buffer has more free space to cover those small memory regions' PT_LOAD headers. Signed-off-by: Lee, Chun-Yi <jlee@suse.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Baoquan He <bhe@redhat.com> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Takashi Iwai <tiwai@suse.de> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Viresh Kumar <viresh.kumar@linaro.org> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: kexec@lists.infradead.org Cc: linux-kernel@vger.kernel.org Cc: <stable@vger.kernel.org> Link: http://lkml.kernel.org/r/1443531537-29436-1-git-send-email-jlee@suse.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-09-29 20:58:57 +08:00
walk_system_ram_res(0, -1, &nr_ranges,
get_nr_ram_ranges_callback);
if (!nr_ranges)
return NULL;
/*
* Exclusion of crash region and/or crashk_low_res may cause
* another range split. So add extra two slots here.
*/
nr_ranges += 2;
cmem = vzalloc(sizeof(struct crash_mem) +
sizeof(struct crash_mem_range) * nr_ranges);
if (!cmem)
return NULL;
cmem->max_nr_ranges = nr_ranges;
cmem->nr_ranges = 0;
return cmem;
}
/*
* Look for any unwanted ranges between mstart, mend and remove them. This
* might lead to split and split ranges are put in cmem->ranges[] array
*/
static int elf_header_exclude_ranges(struct crash_mem *cmem)
{
int ret = 0;
/* Exclude crashkernel region */
ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end);
if (ret)
return ret;
if (crashk_low_res.end) {
ret = crash_exclude_mem_range(cmem, crashk_low_res.start,
crashk_low_res.end);
if (ret)
return ret;
}
return ret;
}
static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg)
{
struct crash_mem *cmem = arg;
cmem->ranges[cmem->nr_ranges].start = res->start;
cmem->ranges[cmem->nr_ranges].end = res->end;
cmem->nr_ranges++;
return 0;
}
/* Prepare elf headers. Return addr and size */
static int prepare_elf_headers(struct kimage *image, void **addr,
unsigned long *sz)
{
struct crash_mem *cmem;
Elf64_Ehdr *ehdr;
Elf64_Phdr *phdr;
int ret, i;
cmem = fill_up_crash_elf_data();
if (!cmem)
return -ENOMEM;
ret = walk_system_ram_res(0, -1, cmem,
prepare_elf64_ram_headers_callback);
if (ret)
goto out;
/* Exclude unwanted mem ranges */
ret = elf_header_exclude_ranges(cmem);
if (ret)
goto out;
/* By default prepare 64bit headers */
ret = crash_prepare_elf64_headers(cmem,
IS_ENABLED(CONFIG_X86_64), addr, sz);
if (ret)
goto out;
/*
* If a range matches backup region, adjust offset to backup
* segment.
*/
ehdr = (Elf64_Ehdr *)*addr;
phdr = (Elf64_Phdr *)(ehdr + 1);
for (i = 0; i < ehdr->e_phnum; phdr++, i++)
if (phdr->p_type == PT_LOAD &&
phdr->p_paddr == image->arch.backup_src_start &&
phdr->p_memsz == image->arch.backup_src_sz) {
phdr->p_offset = image->arch.backup_load_addr;
break;
}
out:
vfree(cmem);
return ret;
}
x86/boot/e820: Rename the basic e820 data types to 'struct e820_entry' and 'struct e820_array' The 'e820entry' and 'e820map' names have various annoyances: - the missing underscore departs from the usual kernel style and makes the code look weird, - in the past I kept confusing the 'map' with the 'entry', because a 'map' is ambiguous in that regard, - it's not really clear from the 'e820map' that this is a regular C array. Rename them to 'struct e820_entry' and 'struct e820_array' accordingly. ( Leave the legacy UAPI header alone but do the rename in the bootparam.h and e820/types.h file - outside tools relying on these defines should either adjust their code, or should use the legacy header, or should create their private copies for the definitions. ) No change in functionality. Cc: Alex Thorlton <athorlton@sgi.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Huang, Ying <ying.huang@intel.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Juergen Gross <jgross@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Jackson <pj@sgi.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rafael J. Wysocki <rjw@sisk.pl> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wei Yang <richard.weiyang@gmail.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-01-27 19:54:38 +08:00
static int add_e820_entry(struct boot_params *params, struct e820_entry *entry)
{
unsigned int nr_e820_entries;
nr_e820_entries = params->e820_entries;
if (nr_e820_entries >= E820_MAX_ENTRIES_ZEROPAGE)
return 1;
memcpy(&params->e820_table[nr_e820_entries], entry,
x86/boot/e820: Rename the basic e820 data types to 'struct e820_entry' and 'struct e820_array' The 'e820entry' and 'e820map' names have various annoyances: - the missing underscore departs from the usual kernel style and makes the code look weird, - in the past I kept confusing the 'map' with the 'entry', because a 'map' is ambiguous in that regard, - it's not really clear from the 'e820map' that this is a regular C array. Rename them to 'struct e820_entry' and 'struct e820_array' accordingly. ( Leave the legacy UAPI header alone but do the rename in the bootparam.h and e820/types.h file - outside tools relying on these defines should either adjust their code, or should use the legacy header, or should create their private copies for the definitions. ) No change in functionality. Cc: Alex Thorlton <athorlton@sgi.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Huang, Ying <ying.huang@intel.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Juergen Gross <jgross@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Jackson <pj@sgi.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rafael J. Wysocki <rjw@sisk.pl> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wei Yang <richard.weiyang@gmail.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-01-27 19:54:38 +08:00
sizeof(struct e820_entry));
params->e820_entries++;
return 0;
}
static int memmap_entry_callback(struct resource *res, void *arg)
{
struct crash_memmap_data *cmd = arg;
struct boot_params *params = cmd->params;
x86/boot/e820: Rename the basic e820 data types to 'struct e820_entry' and 'struct e820_array' The 'e820entry' and 'e820map' names have various annoyances: - the missing underscore departs from the usual kernel style and makes the code look weird, - in the past I kept confusing the 'map' with the 'entry', because a 'map' is ambiguous in that regard, - it's not really clear from the 'e820map' that this is a regular C array. Rename them to 'struct e820_entry' and 'struct e820_array' accordingly. ( Leave the legacy UAPI header alone but do the rename in the bootparam.h and e820/types.h file - outside tools relying on these defines should either adjust their code, or should use the legacy header, or should create their private copies for the definitions. ) No change in functionality. Cc: Alex Thorlton <athorlton@sgi.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Huang, Ying <ying.huang@intel.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Juergen Gross <jgross@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Jackson <pj@sgi.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rafael J. Wysocki <rjw@sisk.pl> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wei Yang <richard.weiyang@gmail.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-01-27 19:54:38 +08:00
struct e820_entry ei;
ei.addr = res->start;
ei.size = resource_size(res);
ei.type = cmd->type;
add_e820_entry(params, &ei);
return 0;
}
static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem,
unsigned long long mstart,
unsigned long long mend)
{
unsigned long start, end;
int ret = 0;
cmem->ranges[0].start = mstart;
cmem->ranges[0].end = mend;
cmem->nr_ranges = 1;
/* Exclude Backup region */
start = image->arch.backup_load_addr;
end = start + image->arch.backup_src_sz - 1;
ret = crash_exclude_mem_range(cmem, start, end);
if (ret)
return ret;
/* Exclude elf header region */
start = image->arch.elf_load_addr;
end = start + image->arch.elf_headers_sz - 1;
return crash_exclude_mem_range(cmem, start, end);
}
/* Prepare memory map for crash dump kernel */
int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params)
{
int i, ret = 0;
unsigned long flags;
x86/boot/e820: Rename the basic e820 data types to 'struct e820_entry' and 'struct e820_array' The 'e820entry' and 'e820map' names have various annoyances: - the missing underscore departs from the usual kernel style and makes the code look weird, - in the past I kept confusing the 'map' with the 'entry', because a 'map' is ambiguous in that regard, - it's not really clear from the 'e820map' that this is a regular C array. Rename them to 'struct e820_entry' and 'struct e820_array' accordingly. ( Leave the legacy UAPI header alone but do the rename in the bootparam.h and e820/types.h file - outside tools relying on these defines should either adjust their code, or should use the legacy header, or should create their private copies for the definitions. ) No change in functionality. Cc: Alex Thorlton <athorlton@sgi.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Huang, Ying <ying.huang@intel.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Juergen Gross <jgross@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul Jackson <pj@sgi.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rafael J. Wysocki <rjw@sisk.pl> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wei Yang <richard.weiyang@gmail.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-01-27 19:54:38 +08:00
struct e820_entry ei;
struct crash_memmap_data cmd;
struct crash_mem *cmem;
cmem = vzalloc(sizeof(struct crash_mem));
if (!cmem)
return -ENOMEM;
memset(&cmd, 0, sizeof(struct crash_memmap_data));
cmd.params = params;
/* Add first 640K segment */
ei.addr = image->arch.backup_src_start;
ei.size = image->arch.backup_src_sz;
ei.type = E820_TYPE_RAM;
add_e820_entry(params, &ei);
/* Add ACPI tables */
cmd.type = E820_TYPE_ACPI;
flags = IORESOURCE_MEM | IORESOURCE_BUSY;
x86, kexec, nvdimm: Use walk_iomem_res_desc() for iomem search Change the callers of walk_iomem_res() scanning for the following resources by name to use walk_iomem_res_desc() instead. "ACPI Tables" "ACPI Non-volatile Storage" "Persistent Memory (legacy)" "Crash kernel" Note, the caller of walk_iomem_res() with "GART" will be removed in a later patch. Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Dave Young <dyoung@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Chun-Yi <joeyli.kernel@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Don Zickus <dzickus@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Lee, Chun-Yi <joeyli.kernel@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Minfei Huang <mnfhuang@gmail.com> Cc: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Takao Indoh <indou.takao@jp.fujitsu.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: kexec@lists.infradead.org Cc: linux-arch@vger.kernel.org Cc: linux-mm <linux-mm@kvack.org> Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/1453841853-11383-15-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-01-27 04:57:30 +08:00
walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1, &cmd,
memmap_entry_callback);
/* Add ACPI Non-volatile Storage */
cmd.type = E820_TYPE_NVS;
x86, kexec, nvdimm: Use walk_iomem_res_desc() for iomem search Change the callers of walk_iomem_res() scanning for the following resources by name to use walk_iomem_res_desc() instead. "ACPI Tables" "ACPI Non-volatile Storage" "Persistent Memory (legacy)" "Crash kernel" Note, the caller of walk_iomem_res() with "GART" will be removed in a later patch. Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Signed-off-by: Borislav Petkov <bp@suse.de> Reviewed-by: Dave Young <dyoung@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Chun-Yi <joeyli.kernel@gmail.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Don Zickus <dzickus@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Lee, Chun-Yi <joeyli.kernel@gmail.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luis R. Rodriguez <mcgrof@suse.com> Cc: Minfei Huang <mnfhuang@gmail.com> Cc: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Takao Indoh <indou.takao@jp.fujitsu.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: kexec@lists.infradead.org Cc: linux-arch@vger.kernel.org Cc: linux-mm <linux-mm@kvack.org> Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/1453841853-11383-15-git-send-email-bp@alien8.de Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-01-27 04:57:30 +08:00
walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1, &cmd,
memmap_entry_callback);
/* Add crashk_low_res region */
if (crashk_low_res.end) {
ei.addr = crashk_low_res.start;
ei.size = crashk_low_res.end - crashk_low_res.start + 1;
ei.type = E820_TYPE_RAM;
add_e820_entry(params, &ei);
}
/* Exclude some ranges from crashk_res and add rest to memmap */
ret = memmap_exclude_ranges(image, cmem, crashk_res.start,
crashk_res.end);
if (ret)
goto out;
for (i = 0; i < cmem->nr_ranges; i++) {
ei.size = cmem->ranges[i].end - cmem->ranges[i].start + 1;
/* If entry is less than a page, skip it */
if (ei.size < PAGE_SIZE)
continue;
ei.addr = cmem->ranges[i].start;
ei.type = E820_TYPE_RAM;
add_e820_entry(params, &ei);
}
out:
vfree(cmem);
return ret;
}
static int determine_backup_region(struct resource *res, void *arg)
{
struct kimage *image = arg;
image->arch.backup_src_start = res->start;
image->arch.backup_src_sz = resource_size(res);
/* Expecting only one range for backup region */
return 1;
}
int crash_load_segments(struct kimage *image)
{
int ret;
struct kexec_buf kbuf = { .image = image, .buf_min = 0,
.buf_max = ULONG_MAX, .top_down = false };
/*
* Determine and load a segment for backup area. First 640K RAM
* region is backup source
*/
ret = walk_system_ram_res(KEXEC_BACKUP_SRC_START, KEXEC_BACKUP_SRC_END,
image, determine_backup_region);
/* Zero or postive return values are ok */
if (ret < 0)
return ret;
/* Add backup segment. */
if (image->arch.backup_src_sz) {
kbuf.buffer = &crash_zero_bytes;
kbuf.bufsz = sizeof(crash_zero_bytes);
kbuf.memsz = image->arch.backup_src_sz;
kbuf.buf_align = PAGE_SIZE;
/*
* Ideally there is no source for backup segment. This is
* copied in purgatory after crash. Just add a zero filled
* segment for now to make sure checksum logic works fine.
*/
ret = kexec_add_buffer(&kbuf);
if (ret)
return ret;
image->arch.backup_load_addr = kbuf.mem;
pr_debug("Loaded backup region at 0x%lx backup_start=0x%lx memsz=0x%lx\n",
image->arch.backup_load_addr,
image->arch.backup_src_start, kbuf.memsz);
}
/* Prepare elf headers and add a segment */
ret = prepare_elf_headers(image, &kbuf.buffer, &kbuf.bufsz);
if (ret)
return ret;
image->arch.elf_headers = kbuf.buffer;
image->arch.elf_headers_sz = kbuf.bufsz;
kbuf.memsz = kbuf.bufsz;
kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
ret = kexec_add_buffer(&kbuf);
if (ret) {
vfree((void *)image->arch.elf_headers);
return ret;
}
image->arch.elf_load_addr = kbuf.mem;
pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
image->arch.elf_load_addr, kbuf.bufsz, kbuf.bufsz);
return ret;
}
kexec: create a new config option CONFIG_KEXEC_FILE for new syscall Currently new system call kexec_file_load() and all the associated code compiles if CONFIG_KEXEC=y. But new syscall also compiles purgatory code which currently uses gcc option -mcmodel=large. This option seems to be available only gcc 4.4 onwards. Hiding new functionality behind a new config option will not break existing users of old gcc. Those who wish to enable new functionality will require new gcc. Having said that, I am trying to figure out how can I move away from using -mcmodel=large but that can take a while. I think there are other advantages of introducing this new config option. As this option will be enabled only on x86_64, other arches don't have to compile generic kexec code which will never be used. This new code selects CRYPTO=y and CRYPTO_SHA256=y. And all other arches had to do this for CONFIG_KEXEC. Now with introduction of new config option, we can remove crypto dependency from other arches. Now CONFIG_KEXEC_FILE is available only on x86_64. So whereever I had CONFIG_X86_64 defined, I got rid of that. For CONFIG_KEXEC_FILE, instead of doing select CRYPTO=y, I changed it to "depends on CRYPTO=y". This should be safer as "select" is not recursive. Signed-off-by: Vivek Goyal <vgoyal@redhat.com> Cc: Eric Biederman <ebiederm@xmission.com> Cc: H. Peter Anvin <hpa@zytor.com> Tested-by: Shaun Ruffell <sruffell@digium.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-08-30 06:18:46 +08:00
#endif /* CONFIG_KEXEC_FILE */