linux/kernel/panic.c
Linus Torvalds de848da12f drm next for 6.12-rc1
string:
 - add mem_is_zero()
 
 core:
 - support more device numbers
 - use XArray for minor ids
 - add backlight constants
 - Split dma fence array creation into alloc and arm
 
 fbdev:
 - remove usage of old fbdev hooks
 
 kms:
 - Add might_fault() to drm_modeset_lock priming
 - Add dynamic per-crtc vblank configuration support
 
 dma-buf:
 - docs cleanup
 
 buddy:
 - Add start address support for trim function
 
 printk:
 - pass description to kmsg_dump
 
 scheduler;
 - Remove full_recover from drm_sched_start
 
 ttm:
 - Make LRU walk restartable after dropping locks
 - Allow direct reclaim to allocate local memory
 
 panic:
 - add display QR code (in rust)
 
 displayport:
 - mst: GUID improvements
 
 bridge:
 - Silence error message on -EPROBE_DEFER
 - analogix: Clean aup
 - bridge-connector: Fix double free
 - lt6505: Disable interrupt when powered off
 - tc358767: Make default DP port preemphasis configurable
 - lt9611uxc: require DRM_BRIDGE_ATTACH_NO_CONNECTOR
 - anx7625: simplify OF array handling
 - dw-hdmi: simplify clock handling
 - lontium-lt8912b: fix mode validation
 - nwl-dsi: fix mode vsync/hsync polarity
 
 xe:
 - Enable LunarLake and Battlemage support
 - Introducing Xe2 ccs modifiers for integrated and discrete graphics
 - rename xe perf to xe observation
 - use wb caching on DGFX for system memory
 - add fence timeouts
 - Lunar Lake graphics/media/display workarounds
 - Battlemage workarounds
 - Battlemage GSC support
 - GSC and HuC fw updates for LL/BM
 - use dma_fence_chain_free
 - refactor hw engine lookup and mmio access
 - enable priority mem read for Xe2
 - Add first GuC BMG fw
 - fix dma-resv lock
 - Fix DGFX display suspend/resume
 - Use xe_managed for kernel BOs
 - Use reserved copy engine for user binds on faulting devices
 - Allow mixing dma-fence jobs and long-running faulting jobs
 - fix media TLB invalidation
 - fix rpm in TTM swapout path
 - track resources and VF state by PF
 
 i915:
 - Type-C programming fix for MTL+
 - FBC cleanup
 - Calc vblank delay more accurately
 - On DP MST, Enable LT fallback for UHBR<->non-UHBR rates
 - Fix DP LTTPR detection
 - limit relocations to INT_MAX
 - fix long hangs in buddy allocator on DG2/A380
 
 amdgpu:
 - Per-queue reset support
 - SDMA devcoredump support
 - DCN 4.0.1 updates
 - GFX12/VCN4/JPEG4 updates
 - Convert vbios embedded EDID to drm_edid
 - GFX9.3/9.4 devcoredump support
 - process isolation framework for GFX 9.4.3/4
 - take IOMMU mappings into account for P2P DMA
 
 amdkfd:
 - CRIU fixes
 - HMM fix
 - Enable process isolation support for GFX 9.4.3/4
 - Allow users to target recommended SDMA engines
 - KFD support for targetting queues on recommended SDMA engines
 
 radeon:
 - remove .load and drm_dev_alloc
 - Fix vbios embedded EDID size handling
 - Convert vbios embedded EDID to drm_edid
 - Use GEM references instead of TTM
 - r100 cp init cleanup
 - Fix potential overflows in evergreen CS offset tracking
 
 msm:
 - DPU:
 - implement DP/PHY mapping on SC8180X
 - Enable writeback on SM8150, SC8180X, SM6125, SM6350
 - DP:
 - Enable widebus on all relevant chipsets
 - MSM8998 HDMI support
 - GPU:
 - A642L speedbin support
 - A615/A306/A621 support
 - A7xx devcoredump support
 
 ast:
 - astdp: Support AST2600 with VGA
 - Clean up HPD
 - Fix timeout loop for DP link training
 - reorganize output code by type (VGA, DP, etc)
 - convert to struct drm_edid
 - fix BMC handling for all outputs
 
 exynos:
 - drop stale MAINTAINERS pattern
 - constify struct
 
 loongson:
 - use GEM refcount over TTM
 
 mgag200:
 - Improve BMC handling
 - Support VBLANK intterupts
 - transparently support BMC outputs
 
 nouveau:
 - Refactor and clean up internals
 - Use GEM refcount over TTM's
 
 gm12u320:
 - convert to struct drm_edid
 
 gma500:
 - update i2c terms
 
 lcdif:
 - pixel clock fix
 
 host1x:
 - fix syncpoint IRQ during resume
 - use iommu_paging_domain_alloc()
 
 imx:
 - ipuv3: convert to struct drm_edid
 
 omapdrm:
 - improve error handling
 - use common helper for_each_endpoint_of_node()
 
 panel:
 - add support for BOE TV101WUM-LL2 plus DT bindings
 - novatek-nt35950: improve error handling
 - nv3051d: improve error handling
 - panel-edp: add support for BOE NE140WUM-N6G; revert support for
   SDC ATNA45AF01
 - visionox-vtdr6130: improve error handling; use
   devm_regulator_bulk_get_const()
 - boe-th101mb31ig002: Support for starry-er88577 MIPI-DSI panel plus
   DT; Fix porch parameter
 - edp: Support AOU B116XTN02.3, AUO B116XAN06.1, AOU B116XAT04.1,
   BOE NV140WUM-N41, BOE NV133WUM-N63, BOE NV116WHM-A4D, CMN N116BCA-EA2,
   CMN N116BCP-EA2, CSW MNB601LS1-4
 - himax-hx8394: Support Microchip AC40T08A MIPI Display panel plus DT
 - ilitek-ili9806e: Support Densitron DMT028VGHMCMI-1D TFT plus DT
 - jd9365da: Support Melfas lmfbx101117480 MIPI-DSI panel plus DT; Refactor
   for code sharing
 - panel-edp: fix name for HKC MB116AN01
 - jd9365da: fix "exit sleep" commands
 - jdi-fhd-r63452: simplify error handling with DSI multi-style
   helpers
 - mantix-mlaf057we51: simplify error handling with DSI multi-style
   helpers
 - simple:
   support Innolux G070ACE-LH3 plus DT bindings
   support On Tat Industrial Company KD50G21-40NT-A1 plus DT bindings
 - st7701:
   decouple DSI and DRM code
   add SPI support
   support Anbernic RG28XX plus DT bindings
 
 mediatek:
 - support alpha blending
 - remove cl in struct cmdq_pkt
 - ovl adaptor fix
 - add power domain binding for mediatek DPI controller
 
 renesas:
 - rz-du: add support for RZ/G2UL plus DT bindings
 
 rockchip:
 - Improve DP sink-capability reporting
 - dw_hdmi: Support 4k@60Hz
 - vop: Support RGB display on Rockchip RK3066; Support 4096px width
 
 sti:
 - convert to struct drm_edid
 
 stm:
 - Avoid UAF wih managed plane and CRTC helpers
 - Fix module owner
 - Fix error handling in probe
 - Depend on COMMON_CLK
 - ltdc: Fix transparency after disabling plane; Remove unused interrupt
 
 tegra:
 - gr3d: improve PM domain handling
 - convert to struct drm_edid
 - Call drm_atomic_helper_shutdown()
 
 vc4:
 - fix PM during detect
 - replace DRM_ERROR() with drm_error()
 - v3d: simplify clock retrieval
 
 v3d:
 - Clean up perfmon
 
 virtio:
 - add DRM capset
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEEEKbZHaGwW9KfbeusDHTzWXnEhr4FAmbq43gACgkQDHTzWXnE
 hr4+lg/+O/r41E7ioitcM0DWeWem0dTlvQr41pJ8jujHvw+bXNdg0BMGWtsTyTLA
 eOft2AwofsFjg+O7l8IFXOT37mQLdIdfjb3+w5brI198InL3OWC3QV8ZSwY9VGET
 n8crO9jFoxNmHZnFniBZbtI6egTyl6H+2ey3E0MTnKiPUKZQvsK/4+x532yVLPob
 UUOze5wcjyGZc7LJEIZPohPVneCb9ki7sabDQqh4cxIQ0Eg+nqPpWjYM4XVd+lTS
 8QmssbR49LrJ7z9m90qVE+8TjYUCn+ChDPMs61KZAAnc8k++nK41btjGZ23mDKPb
 YEguahCYthWJ4U8K18iXBPnLPxZv5+harQ8OIWAUYqdIOWSXHozvuJ2Z84eHV13a
 9mQ5vIymXang8G1nEXwX/vml9uhVhBCeWu3qfdse2jfaTWYUb1YzhqUoFvqI0R0K
 8wT03MyNdx965CSqAhpH5Jd559ueZmpd+jsHOfhAS+1gxfD6NgoPXv7lpnMUmGWX
 SnaeC9RLD4cgy7j2Swo7TEqQHrvK5XhZSwX94kU6RPmFE5RRKqWgFVQmwuikDMId
 UpNqDnPT5NL2UX4TNG4V4coyTXvKgVcSB9TA7j8NSLfwdGHhiz73pkYosaZXKyxe
 u6qKMwMONfZiT20nhD7RhH0AFnnKosAcO14dhn0TKFZPY6Ce9O8=
 =7jR+
 -----END PGP SIGNATURE-----

Merge tag 'drm-next-2024-09-19' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "This adds a couple of patches outside the drm core, all should be
  acked appropriately, the string and pstore ones are the main ones that
  come to mind.

  Otherwise it's the usual drivers, xe is getting enabled by default on
  some new hardware, we've changed the device number handling to allow
  more devices, and we added some optional rust code to create QR codes
  in the panic handler, an idea first suggested I think 10 years ago :-)

  string:
   - add mem_is_zero()

  core:
   - support more device numbers
   - use XArray for minor ids
   - add backlight constants
   - Split dma fence array creation into alloc and arm

  fbdev:
   - remove usage of old fbdev hooks

  kms:
   - Add might_fault() to drm_modeset_lock priming
   - Add dynamic per-crtc vblank configuration support

  dma-buf:
   - docs cleanup

  buddy:
   - Add start address support for trim function

  printk:
   - pass description to kmsg_dump

  scheduler:
   - Remove full_recover from drm_sched_start

  ttm:
   - Make LRU walk restartable after dropping locks
   - Allow direct reclaim to allocate local memory

  panic:
   - add display QR code (in rust)

  displayport:
   - mst: GUID improvements

  bridge:
   - Silence error message on -EPROBE_DEFER
   - analogix: Clean aup
   - bridge-connector: Fix double free
   - lt6505: Disable interrupt when powered off
   - tc358767: Make default DP port preemphasis configurable
   - lt9611uxc: require DRM_BRIDGE_ATTACH_NO_CONNECTOR
   - anx7625: simplify OF array handling
   - dw-hdmi: simplify clock handling
   - lontium-lt8912b: fix mode validation
   - nwl-dsi: fix mode vsync/hsync polarity

  xe:
   - Enable LunarLake and Battlemage support
   - Introducing Xe2 ccs modifiers for integrated and discrete graphics
   - rename xe perf to xe observation
   - use wb caching on DGFX for system memory
   - add fence timeouts
   - Lunar Lake graphics/media/display workarounds
   - Battlemage workarounds
   - Battlemage GSC support
   - GSC and HuC fw updates for LL/BM
   - use dma_fence_chain_free
   - refactor hw engine lookup and mmio access
   - enable priority mem read for Xe2
   - Add first GuC BMG fw
   - fix dma-resv lock
   - Fix DGFX display suspend/resume
   - Use xe_managed for kernel BOs
   - Use reserved copy engine for user binds on faulting devices
   - Allow mixing dma-fence jobs and long-running faulting jobs
   - fix media TLB invalidation
   - fix rpm in TTM swapout path
   - track resources and VF state by PF

  i915:
   - Type-C programming fix for MTL+
   - FBC cleanup
   - Calc vblank delay more accurately
   - On DP MST, Enable LT fallback for UHBR<->non-UHBR rates
   - Fix DP LTTPR detection
   - limit relocations to INT_MAX
   - fix long hangs in buddy allocator on DG2/A380

  amdgpu:
   - Per-queue reset support
   - SDMA devcoredump support
   - DCN 4.0.1 updates
   - GFX12/VCN4/JPEG4 updates
   - Convert vbios embedded EDID to drm_edid
   - GFX9.3/9.4 devcoredump support
   - process isolation framework for GFX 9.4.3/4
   - take IOMMU mappings into account for P2P DMA

  amdkfd:
   - CRIU fixes
   - HMM fix
   - Enable process isolation support for GFX 9.4.3/4
   - Allow users to target recommended SDMA engines
   - KFD support for targetting queues on recommended SDMA engines

  radeon:
   - remove .load and drm_dev_alloc
   - Fix vbios embedded EDID size handling
   - Convert vbios embedded EDID to drm_edid
   - Use GEM references instead of TTM
   - r100 cp init cleanup
   - Fix potential overflows in evergreen CS offset tracking

  msm:
   - DPU:
      - implement DP/PHY mapping on SC8180X
      - Enable writeback on SM8150, SC8180X, SM6125, SM6350
   - DP:
      - Enable widebus on all relevant chipsets
      - MSM8998 HDMI support
   - GPU:
      - A642L speedbin support
      - A615/A306/A621 support
      - A7xx devcoredump support

  ast:
   - astdp: Support AST2600 with VGA
   - Clean up HPD
   - Fix timeout loop for DP link training
   - reorganize output code by type (VGA, DP, etc)
   - convert to struct drm_edid
   - fix BMC handling for all outputs

  exynos:
   - drop stale MAINTAINERS pattern
   - constify struct

  loongson:
   - use GEM refcount over TTM

  mgag200:
   - Improve BMC handling
   - Support VBLANK intterupts
   - transparently support BMC outputs

  nouveau:
   - Refactor and clean up internals
   - Use GEM refcount over TTM's

  gm12u320:
   - convert to struct drm_edid

  gma500:
   - update i2c terms

  lcdif:
   - pixel clock fix

  host1x:
   - fix syncpoint IRQ during resume
   - use iommu_paging_domain_alloc()

  imx:
   - ipuv3: convert to struct drm_edid

  omapdrm:
   - improve error handling
   - use common helper for_each_endpoint_of_node()

  panel:
   - add support for BOE TV101WUM-LL2 plus DT bindings
   - novatek-nt35950: improve error handling
   - nv3051d: improve error handling
   - panel-edp:
      - add support for BOE NE140WUM-N6G
      - revert support for SDC ATNA45AF01
   - visionox-vtdr6130:
      - improve error handling
      - use devm_regulator_bulk_get_const()
   - boe-th101mb31ig002:
      - Support for starry-er88577 MIPI-DSI panel plus DT
      - Fix porch parameter
   - edp: Support AOU B116XTN02.3, AUO B116XAN06.1, AOU B116XAT04.1, BOE
     NV140WUM-N41, BOE NV133WUM-N63, BOE NV116WHM-A4D, CMN N116BCA-EA2,
     CMN N116BCP-EA2, CSW MNB601LS1-4
   - himax-hx8394: Support Microchip AC40T08A MIPI Display panel plus DT
   - ilitek-ili9806e: Support Densitron DMT028VGHMCMI-1D TFT plus DT
   - jd9365da:
      - Support Melfas lmfbx101117480 MIPI-DSI panel plus DT
      - Refactor for code sharing
   - panel-edp: fix name for HKC MB116AN01
   - jd9365da: fix "exit sleep" commands
   - jdi-fhd-r63452: simplify error handling with DSI multi-style
     helpers
   - mantix-mlaf057we51: simplify error handling with DSI multi-style
     helpers
   - simple:
      - support Innolux G070ACE-LH3 plus DT bindings
      - support On Tat Industrial Company KD50G21-40NT-A1 plus DT
        bindings
   - st7701:
      - decouple DSI and DRM code
      - add SPI support
      - support Anbernic RG28XX plus DT bindings

  mediatek:
   - support alpha blending
   - remove cl in struct cmdq_pkt
   - ovl adaptor fix
   - add power domain binding for mediatek DPI controller

  renesas:
   - rz-du: add support for RZ/G2UL plus DT bindings

  rockchip:
   - Improve DP sink-capability reporting
   - dw_hdmi: Support 4k@60Hz
   - vop:
      - Support RGB display on Rockchip RK3066
      - Support 4096px width

  sti:
   - convert to struct drm_edid

  stm:
   - Avoid UAF wih managed plane and CRTC helpers
   - Fix module owner
   - Fix error handling in probe
   - Depend on COMMON_CLK
   - ltdc:
      - Fix transparency after disabling plane
      - Remove unused interrupt

  tegra:
   - gr3d: improve PM domain handling
   - convert to struct drm_edid
   - Call drm_atomic_helper_shutdown()

  vc4:
   - fix PM during detect
   - replace DRM_ERROR() with drm_error()
   - v3d: simplify clock retrieval

  v3d:
   - Clean up perfmon

  virtio:
   - add DRM capset"

* tag 'drm-next-2024-09-19' of https://gitlab.freedesktop.org/drm/kernel: (1326 commits)
  drm/xe: Fix missing conversion to xe_display_pm_runtime_resume
  drm/xe/xe2hpg: Add Wa_15016589081
  drm/xe: Don't keep stale pointer to bo->ggtt_node
  drm/xe: fix missing 'xe_vm_put'
  drm/xe: fix build warning with CONFIG_PM=n
  drm/xe: Suppress missing outer rpm protection warning
  drm/xe: prevent potential UAF in pf_provision_vf_ggtt()
  drm/amd/display: Add all planes on CRTC to state for overlay cursor
  drm/i915/bios: fix printk format width
  drm/i915/display: Fix BMG CCS modifiers
  drm/amdgpu: get rid of bogus includes of fdtable.h
  drm/amdkfd: CRIU fixes
  drm/amdgpu: fix a race in kfd_mem_export_dmabuf()
  drm: new helper: drm_gem_prime_handle_to_dmabuf()
  drm/amdgpu/atomfirmware: Silence UBSAN warning
  drm/amdgpu: Fix kdoc entry in 'amdgpu_vm_cpu_prepare'
  drm/amd/amdgpu: apply command submission parser for JPEG v1
  drm/amd/amdgpu: apply command submission parser for JPEG v2+
  drm/amd/pm: fix the pp_dpm_pcie issue on smu v14.0.2/3
  drm/amd/pm: update the features set on smu v14.0.2/3
  ...
2024-09-19 10:18:15 +02:00

886 lines
22 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/kernel/panic.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
/*
* This function is used through-out the kernel (including mm and fs)
* to indicate a major problem.
*/
#include <linux/debug_locks.h>
#include <linux/sched/debug.h>
#include <linux/interrupt.h>
#include <linux/kgdb.h>
#include <linux/kmsg_dump.h>
#include <linux/kallsyms.h>
#include <linux/notifier.h>
#include <linux/vt_kern.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/ftrace.h>
#include <linux/reboot.h>
#include <linux/delay.h>
#include <linux/kexec.h>
#include <linux/panic_notifier.h>
#include <linux/sched.h>
#include <linux/string_helpers.h>
#include <linux/sysrq.h>
#include <linux/init.h>
#include <linux/nmi.h>
#include <linux/console.h>
#include <linux/bug.h>
#include <linux/ratelimit.h>
#include <linux/debugfs.h>
#include <linux/sysfs.h>
#include <linux/context_tracking.h>
#include <linux/seq_buf.h>
#include <trace/events/error_report.h>
#include <asm/sections.h>
#define PANIC_TIMER_STEP 100
#define PANIC_BLINK_SPD 18
#ifdef CONFIG_SMP
/*
* Should we dump all CPUs backtraces in an oops event?
* Defaults to 0, can be changed via sysctl.
*/
static unsigned int __read_mostly sysctl_oops_all_cpu_backtrace;
#else
#define sysctl_oops_all_cpu_backtrace 0
#endif /* CONFIG_SMP */
int panic_on_oops = CONFIG_PANIC_ON_OOPS_VALUE;
static unsigned long tainted_mask =
IS_ENABLED(CONFIG_RANDSTRUCT) ? (1 << TAINT_RANDSTRUCT) : 0;
static int pause_on_oops;
static int pause_on_oops_flag;
static DEFINE_SPINLOCK(pause_on_oops_lock);
bool crash_kexec_post_notifiers;
int panic_on_warn __read_mostly;
unsigned long panic_on_taint;
bool panic_on_taint_nousertaint = false;
static unsigned int warn_limit __read_mostly;
bool panic_triggering_all_cpu_backtrace;
int panic_timeout = CONFIG_PANIC_TIMEOUT;
EXPORT_SYMBOL_GPL(panic_timeout);
#define PANIC_PRINT_TASK_INFO 0x00000001
#define PANIC_PRINT_MEM_INFO 0x00000002
#define PANIC_PRINT_TIMER_INFO 0x00000004
#define PANIC_PRINT_LOCK_INFO 0x00000008
#define PANIC_PRINT_FTRACE_INFO 0x00000010
#define PANIC_PRINT_ALL_PRINTK_MSG 0x00000020
#define PANIC_PRINT_ALL_CPU_BT 0x00000040
#define PANIC_PRINT_BLOCKED_TASKS 0x00000080
unsigned long panic_print;
ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
EXPORT_SYMBOL(panic_notifier_list);
#ifdef CONFIG_SYSCTL
static struct ctl_table kern_panic_table[] = {
#ifdef CONFIG_SMP
{
.procname = "oops_all_cpu_backtrace",
.data = &sysctl_oops_all_cpu_backtrace,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
#endif
{
.procname = "warn_limit",
.data = &warn_limit,
.maxlen = sizeof(warn_limit),
.mode = 0644,
.proc_handler = proc_douintvec,
},
};
static __init int kernel_panic_sysctls_init(void)
{
register_sysctl_init("kernel", kern_panic_table);
return 0;
}
late_initcall(kernel_panic_sysctls_init);
#endif
static atomic_t warn_count = ATOMIC_INIT(0);
#ifdef CONFIG_SYSFS
static ssize_t warn_count_show(struct kobject *kobj, struct kobj_attribute *attr,
char *page)
{
return sysfs_emit(page, "%d\n", atomic_read(&warn_count));
}
static struct kobj_attribute warn_count_attr = __ATTR_RO(warn_count);
static __init int kernel_panic_sysfs_init(void)
{
sysfs_add_file_to_group(kernel_kobj, &warn_count_attr.attr, NULL);
return 0;
}
late_initcall(kernel_panic_sysfs_init);
#endif
static long no_blink(int state)
{
return 0;
}
/* Returns how long it waited in ms */
long (*panic_blink)(int state);
EXPORT_SYMBOL(panic_blink);
/*
* Stop ourself in panic -- architecture code may override this
*/
void __weak __noreturn panic_smp_self_stop(void)
{
while (1)
cpu_relax();
}
/*
* Stop ourselves in NMI context if another CPU has already panicked. Arch code
* may override this to prepare for crash dumping, e.g. save regs info.
*/
void __weak __noreturn nmi_panic_self_stop(struct pt_regs *regs)
{
panic_smp_self_stop();
}
/*
* Stop other CPUs in panic. Architecture dependent code may override this
* with more suitable version. For example, if the architecture supports
* crash dump, it should save registers of each stopped CPU and disable
* per-CPU features such as virtualization extensions.
*/
void __weak crash_smp_send_stop(void)
{
static int cpus_stopped;
/*
* This function can be called twice in panic path, but obviously
* we execute this only once.
*/
if (cpus_stopped)
return;
/*
* Note smp_send_stop is the usual smp shutdown function, which
* unfortunately means it may not be hardened to work in a panic
* situation.
*/
smp_send_stop();
cpus_stopped = 1;
}
atomic_t panic_cpu = ATOMIC_INIT(PANIC_CPU_INVALID);
/*
* A variant of panic() called from NMI context. We return if we've already
* panicked on this CPU. If another CPU already panicked, loop in
* nmi_panic_self_stop() which can provide architecture dependent code such
* as saving register state for crash dump.
*/
void nmi_panic(struct pt_regs *regs, const char *msg)
{
int old_cpu, this_cpu;
old_cpu = PANIC_CPU_INVALID;
this_cpu = raw_smp_processor_id();
/* atomic_try_cmpxchg updates old_cpu on failure */
if (atomic_try_cmpxchg(&panic_cpu, &old_cpu, this_cpu))
panic("%s", msg);
else if (old_cpu != this_cpu)
nmi_panic_self_stop(regs);
}
EXPORT_SYMBOL(nmi_panic);
static void panic_print_sys_info(bool console_flush)
{
if (console_flush) {
if (panic_print & PANIC_PRINT_ALL_PRINTK_MSG)
console_flush_on_panic(CONSOLE_REPLAY_ALL);
return;
}
if (panic_print & PANIC_PRINT_TASK_INFO)
show_state();
if (panic_print & PANIC_PRINT_MEM_INFO)
show_mem();
if (panic_print & PANIC_PRINT_TIMER_INFO)
sysrq_timer_list_show();
if (panic_print & PANIC_PRINT_LOCK_INFO)
debug_show_all_locks();
if (panic_print & PANIC_PRINT_FTRACE_INFO)
ftrace_dump(DUMP_ALL);
if (panic_print & PANIC_PRINT_BLOCKED_TASKS)
show_state_filter(TASK_UNINTERRUPTIBLE);
}
void check_panic_on_warn(const char *origin)
{
unsigned int limit;
if (panic_on_warn)
panic("%s: panic_on_warn set ...\n", origin);
limit = READ_ONCE(warn_limit);
if (atomic_inc_return(&warn_count) >= limit && limit)
panic("%s: system warned too often (kernel.warn_limit is %d)",
origin, limit);
}
/*
* Helper that triggers the NMI backtrace (if set in panic_print)
* and then performs the secondary CPUs shutdown - we cannot have
* the NMI backtrace after the CPUs are off!
*/
static void panic_other_cpus_shutdown(bool crash_kexec)
{
if (panic_print & PANIC_PRINT_ALL_CPU_BT) {
/* Temporary allow non-panic CPUs to write their backtraces. */
panic_triggering_all_cpu_backtrace = true;
trigger_all_cpu_backtrace();
panic_triggering_all_cpu_backtrace = false;
}
/*
* Note that smp_send_stop() is the usual SMP shutdown function,
* which unfortunately may not be hardened to work in a panic
* situation. If we want to do crash dump after notifier calls
* and kmsg_dump, we will need architecture dependent extra
* bits in addition to stopping other CPUs, hence we rely on
* crash_smp_send_stop() for that.
*/
if (!crash_kexec)
smp_send_stop();
else
crash_smp_send_stop();
}
/**
* panic - halt the system
* @fmt: The text string to print
*
* Display a message, then perform cleanups.
*
* This function never returns.
*/
void panic(const char *fmt, ...)
{
static char buf[1024];
va_list args;
long i, i_next = 0, len;
int state = 0;
int old_cpu, this_cpu;
bool _crash_kexec_post_notifiers = crash_kexec_post_notifiers;
if (panic_on_warn) {
/*
* This thread may hit another WARN() in the panic path.
* Resetting this prevents additional WARN() from panicking the
* system on this thread. Other threads are blocked by the
* panic_mutex in panic().
*/
panic_on_warn = 0;
}
/*
* Disable local interrupts. This will prevent panic_smp_self_stop
* from deadlocking the first cpu that invokes the panic, since
* there is nothing to prevent an interrupt handler (that runs
* after setting panic_cpu) from invoking panic() again.
*/
local_irq_disable();
preempt_disable_notrace();
/*
* It's possible to come here directly from a panic-assertion and
* not have preempt disabled. Some functions called from here want
* preempt to be disabled. No point enabling it later though...
*
* Only one CPU is allowed to execute the panic code from here. For
* multiple parallel invocations of panic, all other CPUs either
* stop themself or will wait until they are stopped by the 1st CPU
* with smp_send_stop().
*
* cmpxchg success means this is the 1st CPU which comes here,
* so go ahead.
* `old_cpu == this_cpu' means we came from nmi_panic() which sets
* panic_cpu to this CPU. In this case, this is also the 1st CPU.
*/
old_cpu = PANIC_CPU_INVALID;
this_cpu = raw_smp_processor_id();
/* atomic_try_cmpxchg updates old_cpu on failure */
if (atomic_try_cmpxchg(&panic_cpu, &old_cpu, this_cpu)) {
/* go ahead */
} else if (old_cpu != this_cpu)
panic_smp_self_stop();
console_verbose();
bust_spinlocks(1);
va_start(args, fmt);
len = vscnprintf(buf, sizeof(buf), fmt, args);
va_end(args);
if (len && buf[len - 1] == '\n')
buf[len - 1] = '\0';
pr_emerg("Kernel panic - not syncing: %s\n", buf);
#ifdef CONFIG_DEBUG_BUGVERBOSE
/*
* Avoid nested stack-dumping if a panic occurs during oops processing
*/
if (!test_taint(TAINT_DIE) && oops_in_progress <= 1)
dump_stack();
#endif
/*
* If kgdb is enabled, give it a chance to run before we stop all
* the other CPUs or else we won't be able to debug processes left
* running on them.
*/
kgdb_panic(buf);
/*
* If we have crashed and we have a crash kernel loaded let it handle
* everything else.
* If we want to run this after calling panic_notifiers, pass
* the "crash_kexec_post_notifiers" option to the kernel.
*
* Bypass the panic_cpu check and call __crash_kexec directly.
*/
if (!_crash_kexec_post_notifiers)
__crash_kexec(NULL);
panic_other_cpus_shutdown(_crash_kexec_post_notifiers);
printk_legacy_allow_panic_sync();
/*
* Run any panic handlers, including those that might need to
* add information to the kmsg dump output.
*/
atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
panic_print_sys_info(false);
kmsg_dump_desc(KMSG_DUMP_PANIC, buf);
/*
* If you doubt kdump always works fine in any situation,
* "crash_kexec_post_notifiers" offers you a chance to run
* panic_notifiers and dumping kmsg before kdump.
* Note: since some panic_notifiers can make crashed kernel
* more unstable, it can increase risks of the kdump failure too.
*
* Bypass the panic_cpu check and call __crash_kexec directly.
*/
if (_crash_kexec_post_notifiers)
__crash_kexec(NULL);
console_unblank();
/*
* We may have ended up stopping the CPU holding the lock (in
* smp_send_stop()) while still having some valuable data in the console
* buffer. Try to acquire the lock then release it regardless of the
* result. The release will also print the buffers out. Locks debug
* should be disabled to avoid reporting bad unlock balance when
* panic() is not being callled from OOPS.
*/
debug_locks_off();
console_flush_on_panic(CONSOLE_FLUSH_PENDING);
panic_print_sys_info(true);
if (!panic_blink)
panic_blink = no_blink;
if (panic_timeout > 0) {
/*
* Delay timeout seconds before rebooting the machine.
* We can't use the "normal" timers since we just panicked.
*/
pr_emerg("Rebooting in %d seconds..\n", panic_timeout);
for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) {
touch_nmi_watchdog();
if (i >= i_next) {
i += panic_blink(state ^= 1);
i_next = i + 3600 / PANIC_BLINK_SPD;
}
mdelay(PANIC_TIMER_STEP);
}
}
if (panic_timeout != 0) {
/*
* This will not be a clean reboot, with everything
* shutting down. But if there is a chance of
* rebooting the system it will be rebooted.
*/
if (panic_reboot_mode != REBOOT_UNDEFINED)
reboot_mode = panic_reboot_mode;
emergency_restart();
}
#ifdef __sparc__
{
extern int stop_a_enabled;
/* Make sure the user can actually press Stop-A (L1-A) */
stop_a_enabled = 1;
pr_emerg("Press Stop-A (L1-A) from sun keyboard or send break\n"
"twice on console to return to the boot prom\n");
}
#endif
#if defined(CONFIG_S390)
disabled_wait();
#endif
pr_emerg("---[ end Kernel panic - not syncing: %s ]---\n", buf);
/* Do not scroll important messages printed above */
suppress_printk = 1;
/*
* The final messages may not have been printed if in a context that
* defers printing (such as NMI) and irq_work is not available.
* Explicitly flush the kernel log buffer one last time.
*/
console_flush_on_panic(CONSOLE_FLUSH_PENDING);
nbcon_atomic_flush_unsafe();
local_irq_enable();
for (i = 0; ; i += PANIC_TIMER_STEP) {
touch_softlockup_watchdog();
if (i >= i_next) {
i += panic_blink(state ^= 1);
i_next = i + 3600 / PANIC_BLINK_SPD;
}
mdelay(PANIC_TIMER_STEP);
}
}
EXPORT_SYMBOL(panic);
#define TAINT_FLAG(taint, _c_true, _c_false, _module) \
[ TAINT_##taint ] = { \
.c_true = _c_true, .c_false = _c_false, \
.module = _module, \
.desc = #taint, \
}
/*
* TAINT_FORCED_RMMOD could be a per-module flag but the module
* is being removed anyway.
*/
const struct taint_flag taint_flags[TAINT_FLAGS_COUNT] = {
TAINT_FLAG(PROPRIETARY_MODULE, 'P', 'G', true),
TAINT_FLAG(FORCED_MODULE, 'F', ' ', true),
TAINT_FLAG(CPU_OUT_OF_SPEC, 'S', ' ', false),
TAINT_FLAG(FORCED_RMMOD, 'R', ' ', false),
TAINT_FLAG(MACHINE_CHECK, 'M', ' ', false),
TAINT_FLAG(BAD_PAGE, 'B', ' ', false),
TAINT_FLAG(USER, 'U', ' ', false),
TAINT_FLAG(DIE, 'D', ' ', false),
TAINT_FLAG(OVERRIDDEN_ACPI_TABLE, 'A', ' ', false),
TAINT_FLAG(WARN, 'W', ' ', false),
TAINT_FLAG(CRAP, 'C', ' ', true),
TAINT_FLAG(FIRMWARE_WORKAROUND, 'I', ' ', false),
TAINT_FLAG(OOT_MODULE, 'O', ' ', true),
TAINT_FLAG(UNSIGNED_MODULE, 'E', ' ', true),
TAINT_FLAG(SOFTLOCKUP, 'L', ' ', false),
TAINT_FLAG(LIVEPATCH, 'K', ' ', true),
TAINT_FLAG(AUX, 'X', ' ', true),
TAINT_FLAG(RANDSTRUCT, 'T', ' ', true),
TAINT_FLAG(TEST, 'N', ' ', true),
};
#undef TAINT_FLAG
static void print_tainted_seq(struct seq_buf *s, bool verbose)
{
const char *sep = "";
int i;
if (!tainted_mask) {
seq_buf_puts(s, "Not tainted");
return;
}
seq_buf_printf(s, "Tainted: ");
for (i = 0; i < TAINT_FLAGS_COUNT; i++) {
const struct taint_flag *t = &taint_flags[i];
bool is_set = test_bit(i, &tainted_mask);
char c = is_set ? t->c_true : t->c_false;
if (verbose) {
if (is_set) {
seq_buf_printf(s, "%s[%c]=%s", sep, c, t->desc);
sep = ", ";
}
} else {
seq_buf_putc(s, c);
}
}
}
static const char *_print_tainted(bool verbose)
{
/* FIXME: what should the size be? */
static char buf[sizeof(taint_flags)];
struct seq_buf s;
BUILD_BUG_ON(ARRAY_SIZE(taint_flags) != TAINT_FLAGS_COUNT);
seq_buf_init(&s, buf, sizeof(buf));
print_tainted_seq(&s, verbose);
return seq_buf_str(&s);
}
/**
* print_tainted - return a string to represent the kernel taint state.
*
* For individual taint flag meanings, see Documentation/admin-guide/sysctl/kernel.rst
*
* The string is overwritten by the next call to print_tainted(),
* but is always NULL terminated.
*/
const char *print_tainted(void)
{
return _print_tainted(false);
}
/**
* print_tainted_verbose - A more verbose version of print_tainted()
*/
const char *print_tainted_verbose(void)
{
return _print_tainted(true);
}
int test_taint(unsigned flag)
{
return test_bit(flag, &tainted_mask);
}
EXPORT_SYMBOL(test_taint);
unsigned long get_taint(void)
{
return tainted_mask;
}
/**
* add_taint: add a taint flag if not already set.
* @flag: one of the TAINT_* constants.
* @lockdep_ok: whether lock debugging is still OK.
*
* If something bad has gone wrong, you'll want @lockdebug_ok = false, but for
* some notewortht-but-not-corrupting cases, it can be set to true.
*/
void add_taint(unsigned flag, enum lockdep_ok lockdep_ok)
{
if (lockdep_ok == LOCKDEP_NOW_UNRELIABLE && __debug_locks_off())
pr_warn("Disabling lock debugging due to kernel taint\n");
set_bit(flag, &tainted_mask);
if (tainted_mask & panic_on_taint) {
panic_on_taint = 0;
panic("panic_on_taint set ...");
}
}
EXPORT_SYMBOL(add_taint);
static void spin_msec(int msecs)
{
int i;
for (i = 0; i < msecs; i++) {
touch_nmi_watchdog();
mdelay(1);
}
}
/*
* It just happens that oops_enter() and oops_exit() are identically
* implemented...
*/
static void do_oops_enter_exit(void)
{
unsigned long flags;
static int spin_counter;
if (!pause_on_oops)
return;
spin_lock_irqsave(&pause_on_oops_lock, flags);
if (pause_on_oops_flag == 0) {
/* This CPU may now print the oops message */
pause_on_oops_flag = 1;
} else {
/* We need to stall this CPU */
if (!spin_counter) {
/* This CPU gets to do the counting */
spin_counter = pause_on_oops;
do {
spin_unlock(&pause_on_oops_lock);
spin_msec(MSEC_PER_SEC);
spin_lock(&pause_on_oops_lock);
} while (--spin_counter);
pause_on_oops_flag = 0;
} else {
/* This CPU waits for a different one */
while (spin_counter) {
spin_unlock(&pause_on_oops_lock);
spin_msec(1);
spin_lock(&pause_on_oops_lock);
}
}
}
spin_unlock_irqrestore(&pause_on_oops_lock, flags);
}
/*
* Return true if the calling CPU is allowed to print oops-related info.
* This is a bit racy..
*/
bool oops_may_print(void)
{
return pause_on_oops_flag == 0;
}
/*
* Called when the architecture enters its oops handler, before it prints
* anything. If this is the first CPU to oops, and it's oopsing the first
* time then let it proceed.
*
* This is all enabled by the pause_on_oops kernel boot option. We do all
* this to ensure that oopses don't scroll off the screen. It has the
* side-effect of preventing later-oopsing CPUs from mucking up the display,
* too.
*
* It turns out that the CPU which is allowed to print ends up pausing for
* the right duration, whereas all the other CPUs pause for twice as long:
* once in oops_enter(), once in oops_exit().
*/
void oops_enter(void)
{
nbcon_cpu_emergency_enter();
tracing_off();
/* can't trust the integrity of the kernel anymore: */
debug_locks_off();
do_oops_enter_exit();
if (sysctl_oops_all_cpu_backtrace)
trigger_all_cpu_backtrace();
}
static void print_oops_end_marker(void)
{
pr_warn("---[ end trace %016llx ]---\n", 0ULL);
}
/*
* Called when the architecture exits its oops handler, after printing
* everything.
*/
void oops_exit(void)
{
do_oops_enter_exit();
print_oops_end_marker();
nbcon_cpu_emergency_exit();
kmsg_dump(KMSG_DUMP_OOPS);
}
struct warn_args {
const char *fmt;
va_list args;
};
void __warn(const char *file, int line, void *caller, unsigned taint,
struct pt_regs *regs, struct warn_args *args)
{
nbcon_cpu_emergency_enter();
disable_trace_on_warning();
if (file)
pr_warn("WARNING: CPU: %d PID: %d at %s:%d %pS\n",
raw_smp_processor_id(), current->pid, file, line,
caller);
else
pr_warn("WARNING: CPU: %d PID: %d at %pS\n",
raw_smp_processor_id(), current->pid, caller);
#pragma GCC diagnostic push
#ifndef __clang__
#pragma GCC diagnostic ignored "-Wsuggest-attribute=format"
#endif
if (args)
vprintk(args->fmt, args->args);
#pragma GCC diagnostic pop
print_modules();
if (regs)
show_regs(regs);
check_panic_on_warn("kernel");
if (!regs)
dump_stack();
print_irqtrace_events(current);
print_oops_end_marker();
trace_error_report_end(ERROR_DETECTOR_WARN, (unsigned long)caller);
/* Just a warning, don't kill lockdep. */
add_taint(taint, LOCKDEP_STILL_OK);
nbcon_cpu_emergency_exit();
}
#ifdef CONFIG_BUG
#ifndef __WARN_FLAGS
void warn_slowpath_fmt(const char *file, int line, unsigned taint,
const char *fmt, ...)
{
bool rcu = warn_rcu_enter();
struct warn_args args;
pr_warn(CUT_HERE);
if (!fmt) {
__warn(file, line, __builtin_return_address(0), taint,
NULL, NULL);
warn_rcu_exit(rcu);
return;
}
args.fmt = fmt;
va_start(args.args, fmt);
__warn(file, line, __builtin_return_address(0), taint, NULL, &args);
va_end(args.args);
warn_rcu_exit(rcu);
}
EXPORT_SYMBOL(warn_slowpath_fmt);
#else
void __warn_printk(const char *fmt, ...)
{
bool rcu = warn_rcu_enter();
va_list args;
pr_warn(CUT_HERE);
va_start(args, fmt);
vprintk(fmt, args);
va_end(args);
warn_rcu_exit(rcu);
}
EXPORT_SYMBOL(__warn_printk);
#endif
/* Support resetting WARN*_ONCE state */
static int clear_warn_once_set(void *data, u64 val)
{
generic_bug_clear_once();
memset(__start_once, 0, __end_once - __start_once);
return 0;
}
DEFINE_DEBUGFS_ATTRIBUTE(clear_warn_once_fops, NULL, clear_warn_once_set,
"%lld\n");
static __init int register_warn_debugfs(void)
{
/* Don't care about failure */
debugfs_create_file_unsafe("clear_warn_once", 0200, NULL, NULL,
&clear_warn_once_fops);
return 0;
}
device_initcall(register_warn_debugfs);
#endif
#ifdef CONFIG_STACKPROTECTOR
/*
* Called when gcc's -fstack-protector feature is used, and
* gcc detects corruption of the on-stack canary value
*/
__visible noinstr void __stack_chk_fail(void)
{
instrumentation_begin();
panic("stack-protector: Kernel stack is corrupted in: %pB",
__builtin_return_address(0));
instrumentation_end();
}
EXPORT_SYMBOL(__stack_chk_fail);
#endif
core_param(panic, panic_timeout, int, 0644);
core_param(panic_print, panic_print, ulong, 0644);
core_param(pause_on_oops, pause_on_oops, int, 0644);
core_param(panic_on_warn, panic_on_warn, int, 0644);
core_param(crash_kexec_post_notifiers, crash_kexec_post_notifiers, bool, 0644);
static int __init oops_setup(char *s)
{
if (!s)
return -EINVAL;
if (!strcmp(s, "panic"))
panic_on_oops = 1;
return 0;
}
early_param("oops", oops_setup);
static int __init panic_on_taint_setup(char *s)
{
char *taint_str;
if (!s)
return -EINVAL;
taint_str = strsep(&s, ",");
if (kstrtoul(taint_str, 16, &panic_on_taint))
return -EINVAL;
/* make sure panic_on_taint doesn't hold out-of-range TAINT flags */
panic_on_taint &= TAINT_FLAGS_MAX;
if (!panic_on_taint)
return -EINVAL;
if (s && !strcmp(s, "nousertaint"))
panic_on_taint_nousertaint = true;
pr_info("panic_on_taint: bitmask=0x%lx nousertaint_mode=%s\n",
panic_on_taint, str_enabled_disabled(panic_on_taint_nousertaint));
return 0;
}
early_param("panic_on_taint", panic_on_taint_setup);