Files
linux/include/ras/ras_event.h
Linus Torvalds 7203ca412f Merge tag 'mm-stable-2025-12-03-21-26' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton:

  "__vmalloc()/kvmalloc() and no-block support" (Uladzislau Rezki)
     Rework the vmalloc() code to support non-blocking allocations
     (GFP_ATOIC, GFP_NOWAIT)

  "ksm: fix exec/fork inheritance" (xu xin)
     Fix a rare case where the KSM MMF_VM_MERGE_ANY prctl state is not
     inherited across fork/exec

  "mm/zswap: misc cleanup of code and documentations" (SeongJae Park)
     Some light maintenance work on the zswap code

  "mm/page_owner: add debugfs files 'show_handles' and 'show_stacks_handles'" (Mauricio Faria de Oliveira)
     Enhance the /sys/kernel/debug/page_owner debug feature by adding
     unique identifiers to differentiate the various stack traces so
     that userspace monitoring tools can better match stack traces over
     time

  "mm/page_alloc: pcp->batch cleanups" (Joshua Hahn)
     Minor alterations to the page allocator's per-cpu-pages feature

  "Improve UFFDIO_MOVE scalability by removing anon_vma lock" (Lokesh Gidra)
     Address a scalability issue in userfaultfd's UFFDIO_MOVE operation

  "kasan: cleanups for kasan_enabled() checks" (Sabyrzhan Tasbolatov)

  "drivers/base/node: fold node register and unregister functions" (Donet Tom)
     Clean up the NUMA node handling code a little

  "mm: some optimizations for prot numa" (Kefeng Wang)
     Cleanups and small optimizations to the NUMA allocation hinting
     code

  "mm/page_alloc: Batch callers of free_pcppages_bulk" (Joshua Hahn)
     Address long lock hold times at boot on large machines. These were
     causing (harmless) softlockup warnings

  "optimize the logic for handling dirty file folios during reclaim" (Baolin Wang)
     Remove some now-unnecessary work from page reclaim

  "mm/damon: allow DAMOS auto-tuned for per-memcg per-node memory usage" (SeongJae Park)
     Enhance the DAMOS auto-tuning feature

  "mm/damon: fixes for address alignment issues in DAMON_LRU_SORT and DAMON_RECLAIM" (Quanmin Yan)
     Fix DAMON_LRU_SORT and DAMON_RECLAIM with certain userspace
     configuration

  "expand mmap_prepare functionality, port more users" (Lorenzo Stoakes)
     Enhance the new(ish) file_operations.mmap_prepare() method and port
     additional callsites from the old ->mmap() over to ->mmap_prepare()

  "Fix stale IOTLB entries for kernel address space" (Lu Baolu)
     Fix a bug (and possible security issue on non-x86) in the IOMMU
     code. In some situations the IOMMU could be left hanging onto a
     stale kernel pagetable entry

  "mm/huge_memory: cleanup __split_unmapped_folio()" (Wei Yang)
     Clean up and optimize the folio splitting code

  "mm, swap: misc cleanup and bugfix" (Kairui Song)
     Some cleanups and a minor fix in the swap discard code

  "mm/damon: misc documentation fixups" (SeongJae Park)

  "mm/damon: support pin-point targets removal" (SeongJae Park)
     Permit userspace to remove a specific monitoring target in the
     middle of the current targets list

  "mm: MISC follow-up patches for linux/pgalloc.h" (Harry Yoo)
     A couple of cleanups related to mm header file inclusion

  "mm/swapfile.c: select swap devices of default priority round robin" (Baoquan He)
     improve the selection of swap devices for NUMA machines

  "mm: Convert memory block states (MEM_*) macros to enums" (Israel Batista)
     Change the memory block labels from macros to enums so they will
     appear in kernel debug info

  "ksm: perform a range-walk to jump over holes in break_ksm" (Pedro Demarchi Gomes)
     Address an inefficiency when KSM unmerges an address range

  "mm/damon/tests: fix memory bugs in kunit tests" (SeongJae Park)
     Fix leaks and unhandled malloc() failures in DAMON userspace unit
     tests

  "some cleanups for pageout()" (Baolin Wang)
     Clean up a couple of minor things in the page scanner's
     writeback-for-eviction code

  "mm/hugetlb: refactor sysfs/sysctl interfaces" (Hui Zhu)
     Move hugetlb's sysfs/sysctl handling code into a new file

  "introduce VM_MAYBE_GUARD and make it sticky" (Lorenzo Stoakes)
     Make the VMA guard regions available in /proc/pid/smaps and
     improves the mergeability of guarded VMAs

  "mm: perform guard region install/remove under VMA lock" (Lorenzo Stoakes)
     Reduce mmap lock contention for callers performing VMA guard region
     operations

  "vma_start_write_killable" (Matthew Wilcox)
     Start work on permitting applications to be killed when they are
     waiting on a read_lock on the VMA lock

  "mm/damon/tests: add more tests for online parameters commit" (SeongJae Park)
     Add additional userspace testing of DAMON's "commit" feature

  "mm/damon: misc cleanups" (SeongJae Park)

  "make VM_SOFTDIRTY a sticky VMA flag" (Lorenzo Stoakes)
     Address the possible loss of a VMA's VM_SOFTDIRTY flag when that
     VMA is merged with another

  "mm: support device-private THP" (Balbir Singh)
     Introduce support for Transparent Huge Page (THP) migration in zone
     device-private memory

  "Optimize folio split in memory failure" (Zi Yan)

  "mm/huge_memory: Define split_type and consolidate split support checks" (Wei Yang)
     Some more cleanups in the folio splitting code

  "mm: remove is_swap_[pte, pmd]() + non-swap entries, introduce leaf entries" (Lorenzo Stoakes)
     Clean up our handling of pagetable leaf entries by introducing the
     concept of 'software leaf entries', of type softleaf_t

  "reparent the THP split queue" (Muchun Song)
     Reparent the THP split queue to its parent memcg. This is in
     preparation for addressing the long-standing "dying memcg" problem,
     wherein dead memcg's linger for too long, consuming memory
     resources

  "unify PMD scan results and remove redundant cleanup" (Wei Yang)
     A little cleanup in the hugepage collapse code

  "zram: introduce writeback bio batching" (Sergey Senozhatsky)
     Improve zram writeback efficiency by introducing batched bio
     writeback support

  "memcg: cleanup the memcg stats interfaces" (Shakeel Butt)
     Clean up our handling of the interrupt safety of some memcg stats

  "make vmalloc gfp flags usage more apparent" (Vishal Moola)
     Clean up vmalloc's handling of incoming GFP flags

  "mm: Add soft-dirty and uffd-wp support for RISC-V" (Chunyan Zhang)
     Teach soft dirty and userfaultfd write protect tracking to use
     RISC-V's Svrsw60t59b extension

  "mm: swap: small fixes and comment cleanups" (Youngjun Park)
     Fix a small bug and clean up some of the swap code

  "initial work on making VMA flags a bitmap" (Lorenzo Stoakes)
     Start work on converting the vma struct's flags to a bitmap, so we
     stop running out of them, especially on 32-bit

  "mm/swapfile: fix and cleanup swap list iterations" (Youngjun Park)
     Address a possible bug in the swap discard code and clean things
     up a little

[ This merge also reverts commit ebb9aeb980 ("vfio/nvgrace-gpu:
  register device memory for poison handling") because it looks
  broken to me, I've asked for clarification   - Linus ]

* tag 'mm-stable-2025-12-03-21-26' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (321 commits)
  mm: fix vma_start_write_killable() signal handling
  mm/swapfile: use plist_for_each_entry in __folio_throttle_swaprate
  mm/swapfile: fix list iteration when next node is removed during discard
  fs/proc/task_mmu.c: fix make_uffd_wp_huge_pte() huge pte handling
  mm/kfence: add reboot notifier to disable KFENCE on shutdown
  memcg: remove inc/dec_lruvec_kmem_state helpers
  selftests/mm/uffd: initialize char variable to Null
  mm: fix DEBUG_RODATA_TEST indentation in Kconfig
  mm: introduce VMA flags bitmap type
  tools/testing/vma: eliminate dependency on vma->__vm_flags
  mm: simplify and rename mm flags function for clarity
  mm: declare VMA flags by bit
  zram: fix a spelling mistake
  mm/page_alloc: optimize lowmem_reserve max lookup using its semantic monotonicity
  mm/vmscan: skip increasing kswapd_failures when reclaim was boosted
  pagemap: update BUDDY flag documentation
  mm: swap: remove scan_swap_map_slots() references from comments
  mm: swap: change swap_alloc_slow() to void
  mm, swap: remove redundant comment for read_swap_cache_async
  mm, swap: use SWP_SOLIDSTATE to determine if swap is rotational
  ...
2025-12-05 13:52:43 -08:00

384 lines
11 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#undef TRACE_SYSTEM
#define TRACE_SYSTEM ras
#define TRACE_INCLUDE_FILE ras_event
#if !defined(_TRACE_HW_EVENT_MC_H) || defined(TRACE_HEADER_MULTI_READ)
#define _TRACE_HW_EVENT_MC_H
#include <linux/tracepoint.h>
#include <linux/edac.h>
#include <linux/ktime.h>
#include <linux/pci.h>
#include <linux/aer.h>
#include <linux/cper.h>
/*
* MCE Extended Error Log trace event
*
* These events are generated when hardware detects a corrected or
* uncorrected event.
*/
/* memory trace event */
#if defined(CONFIG_ACPI_EXTLOG) || defined(CONFIG_ACPI_EXTLOG_MODULE)
TRACE_EVENT(extlog_mem_event,
TP_PROTO(struct cper_sec_mem_err *mem,
u32 err_seq,
const guid_t *fru_id,
const char *fru_text,
u8 sev),
TP_ARGS(mem, err_seq, fru_id, fru_text, sev),
TP_STRUCT__entry(
__field(u32, err_seq)
__field(u8, etype)
__field(u8, sev)
__field(u64, pa)
__field(u8, pa_mask_lsb)
__field_struct(guid_t, fru_id)
__string(fru_text, fru_text)
__field_struct(struct cper_mem_err_compact, data)
),
TP_fast_assign(
__entry->err_seq = err_seq;
if (mem->validation_bits & CPER_MEM_VALID_ERROR_TYPE)
__entry->etype = mem->error_type;
else
__entry->etype = ~0;
__entry->sev = sev;
if (mem->validation_bits & CPER_MEM_VALID_PA)
__entry->pa = mem->physical_addr;
else
__entry->pa = ~0ull;
if (mem->validation_bits & CPER_MEM_VALID_PA_MASK)
__entry->pa_mask_lsb = (u8)__ffs64(mem->physical_addr_mask);
else
__entry->pa_mask_lsb = ~0;
__entry->fru_id = *fru_id;
__assign_str(fru_text);
cper_mem_err_pack(mem, &__entry->data);
),
TP_printk("{%d} %s error: %s physical addr: %016llx (mask lsb: %x) %sFRU: %pUl %.20s",
__entry->err_seq,
cper_severity_str(__entry->sev),
cper_mem_err_type_str(__entry->etype),
__entry->pa,
__entry->pa_mask_lsb,
cper_mem_err_unpack(p, &__entry->data),
&__entry->fru_id,
__get_str(fru_text))
);
#endif
/*
* Hardware Events Report
*
* Those events are generated when hardware detected a corrected or
* uncorrected event, and are meant to replace the current API to report
* errors defined on both EDAC and MCE subsystems.
*
* FIXME: Add events for handling memory errors originated from the
* MCE subsystem.
*/
/*
* Hardware-independent Memory Controller specific events
*/
/*
* Default error mechanisms for Memory Controller errors (CE and UE)
*/
TRACE_EVENT(mc_event,
TP_PROTO(const unsigned int err_type,
const char *error_msg,
const char *label,
const int error_count,
const u8 mc_index,
const s8 top_layer,
const s8 mid_layer,
const s8 low_layer,
unsigned long address,
const u8 grain_bits,
unsigned long syndrome,
const char *driver_detail),
TP_ARGS(err_type, error_msg, label, error_count, mc_index,
top_layer, mid_layer, low_layer, address, grain_bits,
syndrome, driver_detail),
TP_STRUCT__entry(
__field( unsigned int, error_type )
__string( msg, error_msg )
__string( label, label )
__field( u16, error_count )
__field( u8, mc_index )
__field( s8, top_layer )
__field( s8, middle_layer )
__field( s8, lower_layer )
__field( long, address )
__field( u8, grain_bits )
__field( long, syndrome )
__string( driver_detail, driver_detail )
),
TP_fast_assign(
__entry->error_type = err_type;
__assign_str(msg);
__assign_str(label);
__entry->error_count = error_count;
__entry->mc_index = mc_index;
__entry->top_layer = top_layer;
__entry->middle_layer = mid_layer;
__entry->lower_layer = low_layer;
__entry->address = address;
__entry->grain_bits = grain_bits;
__entry->syndrome = syndrome;
__assign_str(driver_detail);
),
TP_printk("%d %s error%s:%s%s on %s (mc:%d location:%d:%d:%d address:0x%08lx grain:%d syndrome:0x%08lx%s%s)",
__entry->error_count,
mc_event_error_type(__entry->error_type),
__entry->error_count > 1 ? "s" : "",
__get_str(msg)[0] ? " " : "",
__get_str(msg),
__get_str(label),
__entry->mc_index,
__entry->top_layer,
__entry->middle_layer,
__entry->lower_layer,
__entry->address,
1 << __entry->grain_bits,
__entry->syndrome,
__get_str(driver_detail)[0] ? " " : "",
__get_str(driver_detail))
);
/*
* ARM Processor Events Report
*
* This event is generated when hardware detects an ARM processor error
* has occurred. UEFI 2.6 spec section N.2.4.4.
*/
#define APEIL "ARM Processor Err Info data len"
#define APEID "ARM Processor Err Info raw data"
#define APECIL "ARM Processor Err Context Info data len"
#define APECID "ARM Processor Err Context Info raw data"
#define VSEIL "Vendor Specific Err Info data len"
#define VSEID "Vendor Specific Err Info raw data"
TRACE_EVENT(arm_event,
TP_PROTO(const struct cper_sec_proc_arm *proc,
const u8 *pei_err,
const u32 pei_len,
const u8 *ctx_err,
const u32 ctx_len,
const u8 *oem,
const u32 oem_len,
u8 sev,
int cpu),
TP_ARGS(proc, pei_err, pei_len, ctx_err, ctx_len, oem, oem_len, sev, cpu),
TP_STRUCT__entry(
__field(u64, mpidr)
__field(u64, midr)
__field(u32, running_state)
__field(u32, psci_state)
__field(u8, affinity)
__field(u32, pei_len)
__dynamic_array(u8, pei_buf, pei_len)
__field(u32, ctx_len)
__dynamic_array(u8, ctx_buf, ctx_len)
__field(u32, oem_len)
__dynamic_array(u8, oem_buf, oem_len)
__field(u8, sev)
__field(int, cpu)
),
TP_fast_assign(
if (proc->validation_bits & CPER_ARM_VALID_AFFINITY_LEVEL)
__entry->affinity = proc->affinity_level;
else
__entry->affinity = ~0;
if (proc->validation_bits & CPER_ARM_VALID_MPIDR)
__entry->mpidr = proc->mpidr;
else
__entry->mpidr = 0ULL;
__entry->midr = proc->midr;
if (proc->validation_bits & CPER_ARM_VALID_RUNNING_STATE) {
__entry->running_state = proc->running_state;
__entry->psci_state = proc->psci_state;
} else {
__entry->running_state = ~0;
__entry->psci_state = ~0;
}
__entry->pei_len = pei_len;
memcpy(__get_dynamic_array(pei_buf), pei_err, pei_len);
__entry->ctx_len = ctx_len;
memcpy(__get_dynamic_array(ctx_buf), ctx_err, ctx_len);
__entry->oem_len = oem_len;
memcpy(__get_dynamic_array(oem_buf), oem, oem_len);
__entry->sev = sev;
__entry->cpu = cpu;
),
TP_printk("cpu: %d; error: %d; affinity level: %d; MPIDR: %016llx; MIDR: %016llx; "
"running state: %d; PSCI state: %d; "
"%s: %d; %s: %s; %s: %d; %s: %s; %s: %d; %s: %s",
__entry->cpu,
__entry->sev,
__entry->affinity, __entry->mpidr, __entry->midr,
__entry->running_state, __entry->psci_state,
APEIL, __entry->pei_len, APEID,
__print_hex(__get_dynamic_array(pei_buf), __entry->pei_len),
APECIL, __entry->ctx_len, APECID,
__print_hex(__get_dynamic_array(ctx_buf), __entry->ctx_len),
VSEIL, __entry->oem_len, VSEID,
__print_hex(__get_dynamic_array(oem_buf), __entry->oem_len))
);
/*
* Non-Standard Section Report
*
* This event is generated when hardware detected a hardware
* error event, which may be of non-standard section as defined
* in UEFI spec appendix "Common Platform Error Record", or may
* be of sections for which TRACE_EVENT is not defined.
*
*/
TRACE_EVENT(non_standard_event,
TP_PROTO(const guid_t *sec_type,
const guid_t *fru_id,
const char *fru_text,
const u8 sev,
const u8 *err,
const u32 len),
TP_ARGS(sec_type, fru_id, fru_text, sev, err, len),
TP_STRUCT__entry(
__array(char, sec_type, UUID_SIZE)
__array(char, fru_id, UUID_SIZE)
__string(fru_text, fru_text)
__field(u8, sev)
__field(u32, len)
__dynamic_array(u8, buf, len)
),
TP_fast_assign(
memcpy(__entry->sec_type, sec_type, UUID_SIZE);
memcpy(__entry->fru_id, fru_id, UUID_SIZE);
__assign_str(fru_text);
__entry->sev = sev;
__entry->len = len;
memcpy(__get_dynamic_array(buf), err, len);
),
TP_printk("severity: %d; sec type:%pU; FRU: %pU %s; data len:%d; raw data:%s",
__entry->sev, __entry->sec_type,
__entry->fru_id, __get_str(fru_text),
__entry->len,
__print_hex(__get_dynamic_array(buf), __entry->len))
);
#ifdef CONFIG_PCIEAER
/*
* PCIe AER Trace event
*
* These events are generated when hardware detects a corrected or
* uncorrected event on a PCIe device. The event report has
* the following structure:
*
* char * dev_name - The name of the slot where the device resides
* ([domain:]bus:device.function).
* u32 status - Either the correctable or uncorrectable register
* indicating what error or errors have been seen
* u8 severity - error severity 0:NONFATAL 1:FATAL 2:CORRECTED
*/
#define aer_correctable_errors \
{PCI_ERR_COR_RCVR, "Receiver Error"}, \
{PCI_ERR_COR_BAD_TLP, "Bad TLP"}, \
{PCI_ERR_COR_BAD_DLLP, "Bad DLLP"}, \
{PCI_ERR_COR_REP_ROLL, "RELAY_NUM Rollover"}, \
{PCI_ERR_COR_REP_TIMER, "Replay Timer Timeout"}, \
{PCI_ERR_COR_ADV_NFAT, "Advisory Non-Fatal Error"}, \
{PCI_ERR_COR_INTERNAL, "Corrected Internal Error"}, \
{PCI_ERR_COR_LOG_OVER, "Header Log Overflow"}
#define aer_uncorrectable_errors \
{PCI_ERR_UNC_UND, "Undefined"}, \
{PCI_ERR_UNC_DLP, "Data Link Protocol Error"}, \
{PCI_ERR_UNC_SURPDN, "Surprise Down Error"}, \
{PCI_ERR_UNC_POISON_TLP,"Poisoned TLP"}, \
{PCI_ERR_UNC_FCP, "Flow Control Protocol Error"}, \
{PCI_ERR_UNC_COMP_TIME, "Completion Timeout"}, \
{PCI_ERR_UNC_COMP_ABORT,"Completer Abort"}, \
{PCI_ERR_UNC_UNX_COMP, "Unexpected Completion"}, \
{PCI_ERR_UNC_RX_OVER, "Receiver Overflow"}, \
{PCI_ERR_UNC_MALF_TLP, "Malformed TLP"}, \
{PCI_ERR_UNC_ECRC, "ECRC Error"}, \
{PCI_ERR_UNC_UNSUP, "Unsupported Request Error"}, \
{PCI_ERR_UNC_ACSV, "ACS Violation"}, \
{PCI_ERR_UNC_INTN, "Uncorrectable Internal Error"},\
{PCI_ERR_UNC_MCBTLP, "MC Blocked TLP"}, \
{PCI_ERR_UNC_ATOMEG, "AtomicOp Egress Blocked"}, \
{PCI_ERR_UNC_TLPPRE, "TLP Prefix Blocked Error"}
TRACE_EVENT(aer_event,
TP_PROTO(const char *dev_name,
const u32 status,
const u8 severity,
const u8 tlp_header_valid,
struct pcie_tlp_log *tlp),
TP_ARGS(dev_name, status, severity, tlp_header_valid, tlp),
TP_STRUCT__entry(
__string( dev_name, dev_name )
__field( u32, status )
__field( u8, severity )
__field( u8, tlp_header_valid)
__array( u32, tlp_header, PCIE_STD_MAX_TLP_HEADERLOG)
),
TP_fast_assign(
__assign_str(dev_name);
__entry->status = status;
__entry->severity = severity;
__entry->tlp_header_valid = tlp_header_valid;
if (tlp_header_valid) {
int i;
for (i = 0; i < PCIE_STD_MAX_TLP_HEADERLOG; i++)
__entry->tlp_header[i] = tlp->dw[i];
}
),
TP_printk("%s PCIe Bus Error: severity=%s, %s, TLP Header=%s\n",
__get_str(dev_name),
__entry->severity == AER_CORRECTABLE ? "Corrected" :
__entry->severity == AER_FATAL ?
"Fatal" : "Uncorrected, non-fatal",
__entry->severity == AER_CORRECTABLE ?
__print_flags(__entry->status, "|", aer_correctable_errors) :
__print_flags(__entry->status, "|", aer_uncorrectable_errors),
__entry->tlp_header_valid ?
__print_array(__entry->tlp_header, PCIE_STD_MAX_TLP_HEADERLOG, 4) :
"Not available")
);
#endif /* CONFIG_PCIEAER */
#endif /* _TRACE_HW_EVENT_MC_H */
/* This part must be outside protection */
#include <trace/define_trace.h>