Needed observability on in field devices can be collected with minimal overhead and can be toggled on and off. Event driven telemetry can be done with tracepoint BPF programs.
The process comm is provided for aggregation across devices and tgid is to enable per-process aggregation per device.
This allows for observing the distribution of such problems in the field, to deduce if there are legitimate bugs or if a bump to the limit is warranted.
Cc: Andrew Morton akpm@linux-foundation.org Cc: David Hildenbrand david@redhat.com Cc: "Liam R. Howlett" Liam.Howlett@oracle.com Cc: Lorenzo Stoakes lorenzo.stoakes@oracle.com Cc: Mike Rapoport rppt@kernel.org Cc: Minchan Kim minchan@kernel.org Cc: Pedro Falcato pfalcato@suse.de Signed-off-by: Kalesh Singh kaleshsingh@google.com
---
Changes in v3: - capture the mm pointer as the unique identifier and capture the vma_count as well, instead of current task tgid, per Steve - Add include/trace/events/vma.h to MEMORY MAPPING section in MAINTAINERS, per Lorenzo - rename trace_max_vma_count_exceeded() to trace_mm_insufficient_vma_slots(), since this is a preemptive check, per Lorenzo - Fix tools/testing/vma build errors, per Lorenzo
MAINTAINERS | 1 + include/trace/events/vma.h | 32 ++++++++++++++++++++++++++++++++ mm/mmap.c | 5 ++++- mm/mremap.c | 10 ++++++++-- mm/vma.c | 9 +++++++-- mm/vma_internal.h | 2 ++ tools/testing/vma/vma_internal.h | 5 +++++ 7 files changed, 59 insertions(+), 5 deletions(-) create mode 100644 include/trace/events/vma.h
diff --git a/MAINTAINERS b/MAINTAINERS index aa83e5893e16..d37215a8a829 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16566,6 +16566,7 @@ S: Maintained W: http://www.linux-mm.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm F: include/trace/events/mmap.h +F: include/trace/events/vma.h F: mm/interval_tree.c F: mm/mincore.c F: mm/mlock.c diff --git a/include/trace/events/vma.h b/include/trace/events/vma.h new file mode 100644 index 000000000000..4540fa607f66 --- /dev/null +++ b/include/trace/events/vma.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM vma + +#if !defined(_TRACE_VMA_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_VMA_H + +#include <linux/tracepoint.h> + +TRACE_EVENT(mm_insufficient_vma_slots, + + TP_PROTO(struct mm_struct *mm), + + TP_ARGS(mm), + + TP_STRUCT__entry( + __field(void *, mm) + __field(int, vma_count) + ), + + TP_fast_assign( + __entry->mm = mm; + __entry->vma_count = mm->vma_count; + ), + + TP_printk("mm=%p vma_count=%d", __entry->mm, __entry->vma_count) +); + +#endif /* _TRACE_VMA_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/mm/mmap.c b/mm/mmap.c index b4eda47b88d8..4035f49ac963 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -56,6 +56,7 @@
#define CREATE_TRACE_POINTS #include <trace/events/mmap.h> +#include <trace/events/vma.h>
#include "internal.h"
@@ -374,8 +375,10 @@ unsigned long do_mmap(struct file *file, unsigned long addr, return -EOVERFLOW;
/* Too many mappings? */ - if (!vma_count_remaining(mm)) + if (!vma_count_remaining(mm)) { + trace_mm_insufficient_vma_slots(mm); return -ENOMEM; + }
/* * addr is returned from get_unmapped_area, diff --git a/mm/mremap.c b/mm/mremap.c index 14d35d87e89b..a7f440a3737f 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -30,6 +30,8 @@ #include <asm/tlb.h> #include <asm/pgalloc.h>
+#include <trace/events/vma.h> + #include "internal.h"
/* Classify the kind of remap operation being performed. */ @@ -1040,8 +1042,10 @@ static unsigned long prep_move_vma(struct vma_remap_struct *vrm) * We'd prefer to avoid failure later on in do_munmap: * which may split one vma into three before unmapping. */ - if (vma_count_remaining(current->mm) < 4) + if (vma_count_remaining(current->mm) < 4) { + trace_mm_insufficient_vma_slots(current->mm); return -ENOMEM; + }
if (vma->vm_ops && vma->vm_ops->may_split) { if (vma->vm_start != old_addr) @@ -1817,8 +1821,10 @@ static unsigned long check_mremap_params(struct vma_remap_struct *vrm) * the threshold. In other words, is the current map count + 6 at or * below the threshold? Otherwise return -ENOMEM here to be more safe. */ - if (vma_count_remaining(current->mm) < 6) + if (vma_count_remaining(current->mm) < 6) { + trace_mm_insufficient_vma_slots(current->mm); return -ENOMEM; + }
return 0; } diff --git a/mm/vma.c b/mm/vma.c index b35a4607cde4..6d8cef7f4d5f 100644 --- a/mm/vma.c +++ b/mm/vma.c @@ -592,8 +592,10 @@ __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, static int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long addr, int new_below) { - if (!vma_count_remaining(vma->vm_mm)) + if (!vma_count_remaining(vma->vm_mm)) { + trace_mm_insufficient_vma_slots(vma->vm_mm); return -ENOMEM; + }
return __split_vma(vmi, vma, addr, new_below); } @@ -1346,6 +1348,7 @@ static int vms_gather_munmap_vmas(struct vma_munmap_struct *vms, */ if (vms->end < vms->vma->vm_end && !vma_count_remaining(vms->vma->vm_mm)) { + trace_mm_insufficient_vma_slots(vms->vma->vm_mm); error = -ENOMEM; goto vma_count_exceeded; } @@ -2797,8 +2800,10 @@ int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma, if (!may_expand_vm(mm, vm_flags, len >> PAGE_SHIFT)) return -ENOMEM;
- if (!vma_count_remaining(mm)) + if (!vma_count_remaining(mm)) { + trace_mm_insufficient_vma_slots(mm); return -ENOMEM; + }
if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT)) return -ENOMEM; diff --git a/mm/vma_internal.h b/mm/vma_internal.h index 2f05735ff190..86823ca6857b 100644 --- a/mm/vma_internal.h +++ b/mm/vma_internal.h @@ -52,4 +52,6 @@
#include "internal.h"
+#include <trace/events/vma.h> + #endif /* __MM_VMA_INTERNAL_H */ diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h index 84760d901656..57e36d82b4c8 100644 --- a/tools/testing/vma/vma_internal.h +++ b/tools/testing/vma/vma_internal.h @@ -1493,4 +1493,9 @@ static int vma_count_remaining(const struct mm_struct *mm) return (max_count > vma_count) ? (max_count - vma_count) : 0; }
+/* Stub for trace_mm_insufficient_vma_slots */ +static inline void trace_mm_insufficient_vma_slots(struct mm_struct *mm) +{ +} + #endif /* __MM_VMA_INTERNAL_H */