[PATCH bpf-next v6 0/4] bpf: arena: handle memory.max on fault-in with reclaim/OOM

Khawar Ahemad posted 4 patches 1 month ago
There is a newer version of this series
include/linux/bpf.h                           |   1 +
kernel/bpf/arena.c                            |  90 +++++++---
kernel/bpf/syscall.c                          |  21 ++-
tools/testing/selftests/bpf/cgroup_helpers.c  |  67 ++++++++
tools/testing/selftests/bpf/cgroup_helpers.h  |   4 +
.../selftests/bpf/prog_tests/arena_memcg.c    | 158 ++++++++++++++++++
.../testing/selftests/bpf/progs/arena_memcg.c |  24 +++
7 files changed, 340 insertions(+), 25 deletions(-)
create mode 100644 tools/testing/selftests/bpf/prog_tests/arena_memcg.c
create mode 100644 tools/testing/selftests/bpf/progs/arena_memcg.c
[PATCH bpf-next v6 0/4] bpf: arena: handle memory.max on fault-in with reclaim/OOM
Posted by Khawar Ahemad 1 month ago
This series fixes an issue where accessing a valid BPF arena page under
memory pressure (e.g. hitting a cgroup's memory.max limit) incorrectly
results in a SIGSEGV crash rather than invoking memory reclaim or the
memcg OOM killer.

Problem:
========
arena_vm_fault() previously performed page allocation while holding
arena->spinlock (with interrupts disabled). This restricted the allocation
path to the non-blocking alloc_pages_nolock() path, which cannot sleep,
reclaim memory, or invoke the memcg OOM killer. When the cgroup's
memory.max limit was reached, the allocation returned -ENOMEM, which
arena_vm_fault() converted to VM_FAULT_SIGSEGV, killing the process on a
valid virtual address.

Solution:
=========
1. Introduce bpf_map_alloc_page_sleepable() using BPF_PAGE_GFP
   (GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT | __GFP_NOWARN) for sleepable
   contexts.
2. Rework arena_vm_fault() to preallocate the page outside arena->spinlock
   with bpf_map_alloc_page_sleepable(), allowing reclaim and OOM handling.
3. Use a lockless probe (vmalloc_to_page) before allocation to avoid
   redundant allocations in the hot path.
4. Replace misleading VM_FAULT_SIGSEGV returns with VM_FAULT_SIGBUS for
   non-recoverable internal errors, reserving SIGSEGV strictly for true
   addressing violations under BPF_F_SEGV_ON_FAULT.
5. Add a BPF selftest (arena_memcg) to validate fault-in behavior and
   proper OOM handling under cgroup memory.max constraints.

Jiayuan Chen (4):
  bpf: Add a sleepable page allocator for map memory
  bpf: arena: allocate the fault-in page outside the lock
  selftests/bpf: Add read_cgroup_file() to cgroup_helpers
  selftests/bpf: Add a test for arena fault-in under memory.max

 include/linux/bpf.h                           |   1 +
 kernel/bpf/arena.c                            |  90 +++++++---
 kernel/bpf/syscall.c                          |  21 ++-
 tools/testing/selftests/bpf/cgroup_helpers.c  |  67 ++++++++
 tools/testing/selftests/bpf/cgroup_helpers.h  |   4 +
 .../selftests/bpf/prog_tests/arena_memcg.c    | 158 ++++++++++++++++++
 .../testing/selftests/bpf/progs/arena_memcg.c |  24 +++
 7 files changed, 340 insertions(+), 25 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/arena_memcg.c
 create mode 100644 tools/testing/selftests/bpf/progs/arena_memcg.c

-- 
2.54.0 (Apple Git-157)