BPF List
 help / color / mirror / Atom feed
From: Khawar Ahemad <ahemadkhawar123@gmail.com>
To: bpf@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: ast@kernel.org, daniel@iogearbox.net, andrii@kernel.org,
	eddyz87@gmail.com, jiayuan.chen@linux.dev, emil@etsalapatis.com
Subject: [PATCH bpf-next v6 0/4] bpf: arena: handle memory.max on fault-in with reclaim/OOM
Date: Tue, 25 Aug 2026 14:49:48 +0530	[thread overview]
Message-ID: <20260825091952.81971-1-ahemadkhawar123@gmail.com> (raw)

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.

Signed-off-by: Khawar Ahemad <ahemadkhawar123@gmail.com>

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)


             reply	other threads:[~2026-08-25  9:19 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-25  9:19 Khawar Ahemad [this message]
2026-08-25  9:19 ` [PATCH v6 1/4] bpf: Add a sleepable page allocator for map memory Khawar Ahemad
2026-08-25  9:32   ` sashiko-bot
2026-08-25  9:19 ` [PATCH v6 2/4] bpf: arena: allocate the fault-in page outside the lock Khawar Ahemad
2026-08-25  9:32   ` sashiko-bot
2026-08-25  9:19 ` [PATCH v6 3/4] selftests/bpf: Add read_cgroup_file() to cgroup_helpers Khawar Ahemad
2026-08-25  9:19 ` [PATCH v6 4/4] selftests/bpf: Add a test for arena fault-in under memory.max Khawar Ahemad
  -- strict thread matches above, loose matches on Subject: below --
2026-08-25  9:49 [PATCH bpf-next v6 0/4] bpf: arena: handle memory.max on fault-in with reclaim/OOM Khawar Ahemad
2026-08-25  9:55 ` Jiayuan Chen
2026-08-25  9:16 Khawar Ahemad

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260825091952.81971-1-ahemadkhawar123@gmail.com \
    --to=ahemadkhawar123@gmail.com \
    --cc=andrii@kernel.org \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=eddyz87@gmail.com \
    --cc=emil@etsalapatis.com \
    --cc=jiayuan.chen@linux.dev \
    --cc=linux-kernel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox