DPDK-dev Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Marat Khalili <qm2k21@gmail.com>
To: Konstantin Ananyev <konstantin.ananyev@huawei.com>,
	Marat Khalili <qm2k21@gmail.com>
Cc: dev@dpdk.org, stephen@networkplumber.org
Subject: [PATCH 1/9] bpf: document packet callback unload sequence
Date: Sun, 11 Oct 2026 18:21:49 +0000	[thread overview]
Message-ID: <20261011182158.124246-2-qm2k21@gmail.com> (raw)
In-Reply-To: <20261011182158.124246-1-qm2k21@gmail.com>

Add a detailed comment with the sequence diagram to bpf_pkt.c describing
the current de-facto synchronization protocol on BPF program unload
between the control plane and the data plane.

Signed-off-by: Marat Khalili <qm2k21@gmail.com>
---
 lib/bpf/bpf_pkt.c | 65 ++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 64 insertions(+), 1 deletion(-)

diff --git a/lib/bpf/bpf_pkt.c b/lib/bpf/bpf_pkt.c
index f072fdaaed..4223ef624e 100644
--- a/lib/bpf/bpf_pkt.c
+++ b/lib/bpf/bpf_pkt.c
@@ -21,9 +21,72 @@
 #include "bpf_impl.h"
 
 /*
- * information about installed BPF rx/tx callback
+ * CP-DP synchronization mechanism
+ *
+ * After the callback is installed to a port/queue, removing it safely is a non-trivial task.
+ * The `rte_bpf` object can only be destroyed while the callback is not being executed,
+ * while the number of synchronization calls in the packet callback must be minimized.
+ *
+ * APIs `rte_eth_remove_rx_callback` and `rte_eth_remove_tx_callback` remove the callback from
+ * the callback list and upon return guarantee that it will not be called again,
+ * but not that any existing invocation of the callback has completed.
+ *
+ * Current synchronization mechanism relies on the following per-port/queue entities:
+ * 1. List of installed port/queue callbacks ("cbs" on the diagram);
+ * 2. Member `cb` of struct `bpf_eth_cbi`;
+ * 3. Member `use` of struct `bpf_eth_cbi`;
+ *
+ * BPF program is only executed if the first two are set, and increments `use` at the start and
+ * end of the callback execution so that in the safe state its value is even.
+ * This relies on only one thread calling the per-port/queue callback at a time.
+ *
+ * Unload processing starts with clearing the first two entities,
+ * then waits for `use` to become even before destroying the BPF program.
+ * The whole operation is protected by a control-plane-only spinlock (not shown on the diagram).
+ *
+ * Typical sequence of synchronization actions between CP and DP on unload is shown below:
+ * ```
+ *   +----+                +-----+         +-----+        +----+         +-----+          +----+
+ *   | CP |                | cbs |         | use |        | cb |         | bpf |          | DP |
+ *   +----+                +-----+         +-----+        +----+         +-----+          +----+
+ *     |                      |               |              |              |                |
+ *     |                      |<---------------------- fetch callback -----------------------|
+ *     |                      |               |              |              |                |
+ *     |                      |               |<------------- increment to odd --------------|
+ *     |                      |               |              |              |                |
+ *     |-- remove callback -->|               |              |              |       rte_smp_mb()
+ *     |                      |               |              |              |                |
+ *     |                      |               |              |<------ fetch non-NULL --------|
+ *     |                      |               |              |              |                |
+ *     |------------------- store NULL --------------------->|              |                |
+ *     |                      |               |              |              |                |
+ *   rte_smp_mb()             |               |              |              |                |
+ *     |                      |               |              |              |                |
+ *   rte_smp_mb()             |               |              |              |                |
+ *     |                      |               |              |              |                |
+ *     +-if use is odd        |               |              |              | if cb not NULL-+
+ *     | |                    |               |              |              |              | |
+ *     | +------------ fetch odd ------------>|              |              |<-- execute --+ |
+ *     | |                    |               |              |              |  BPF program | |
+ *     | +-while use is same  |               |              |              |              +-+
+ *     | | |                  |               |              |              |                |
+ *     | | +---------- fetch odd ------------>|              |              |      rte_smp_rmb()
+ *     | | |                  |               |              |              |                |
+ *     +-+-+                  |               |<------------- increment to even -------------|
+ *     |                      |               |              |              |                |
+ *     |------------- fetch even ------------>|              |              |                |
+ *     |                      |               |              |              |                |
+ *     |----------------- destroy BPF program and cleanup ----------------->|                |
+ *     |                      |               |              |              |                |
+ *   +----+                +-----+         +-----+        +----+         +-----+          +----+
+ *   | CP |                | cbs |         | use |        | cb |         | bpf |          | DP |
+ *   +----+                +-----+         +-----+        +----+         +-----+          +----+
+ * ```
  */
 
+/*
+ * information about installed BPF rx/tx callback
+ */
 struct __rte_cache_aligned bpf_eth_cbi {
 	/* used by both data & control path */
 	RTE_ATOMIC(uint32_t) use;    /*usage counter */
-- 
2.43.0


  reply	other threads:[~2026-10-11 18:22 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-10-11 18:21 [PATCH 0/9] bpf: clean up and document ethdev callback synchronization Marat Khalili
2026-10-11 18:21 ` Marat Khalili [this message]
2026-10-11 18:21 ` [PATCH 2/9] bpf: document ethdev callback threading limitations Marat Khalili
2026-10-11 18:21 ` [PATCH 3/9] bpf: reject Tx callback installation with MT_LOCKFREE Marat Khalili
2026-10-11 18:21 ` [PATCH 4/9] bpf: add callback flag to skip multi-thread check Marat Khalili
2026-10-11 19:48   ` Stephen Hemminger
2026-10-11 20:12     ` Marat Khalili
2026-10-11 18:21 ` [PATCH 5/9] bpf: remove redundant memory barrier on unload Marat Khalili
2026-10-11 19:50   ` Stephen Hemminger
2026-10-11 20:14     ` Marat Khalili
2026-10-11 18:21 ` [PATCH 6/9] bpf: simplify callback inuse tracking to boolean flag Marat Khalili
2026-10-11 19:51   ` Stephen Hemminger
2026-10-11 20:17     ` Marat Khalili
2026-10-11 18:21 ` [PATCH 7/9] bpf: reformat packet callback unload diagram Marat Khalili
2026-10-11 18:21 ` [PATCH 8/9] bpf: use relaxed stores for callback inuse tracking Marat Khalili
2026-10-11 19:52   ` Stephen Hemminger
2026-10-11 20:24     ` Marat Khalili
2026-10-11 18:21 ` [PATCH 9/9] bpf: make callback handle atomic with relaxed access Marat Khalili
2026-10-11 19:54   ` Stephen Hemminger
2026-10-11 20:31     ` Marat Khalili
2026-10-11 20:29 ` [RFC] bpf: fix callback unload with concurrent Tx burst Stephen Hemminger
2026-10-12 21:09 ` [PATCH v2 0/9] bpf: clean up and document ethdev callback synchronization Marat Khalili
2026-10-12 21:09   ` [PATCH v2 1/9] bpf: document packet callback unload sequence Marat Khalili
2026-10-12 21:09   ` [PATCH v2 2/9] bpf: document ethdev callback threading limitations Marat Khalili
2026-10-12 21:44     ` Stephen Hemminger
2026-10-12 21:09   ` [PATCH v2 3/9] bpf: reject Tx callback installation with MT_LOCKFREE Marat Khalili
2026-10-12 21:09   ` [PATCH v2 4/9] bpf: remove redundant memory barrier on unload Marat Khalili
2026-10-12 21:09   ` [PATCH v2 5/9] bpf: simplify callback inuse tracking to boolean flag Marat Khalili
2026-10-12 21:09   ` [PATCH v2 6/9] bpf: reformat packet callback unload diagram Marat Khalili
2026-10-12 21:09   ` [PATCH v2 7/9] bpf: use relaxed accesses for callback inuse tracking Marat Khalili
2026-10-12 21:09   ` [PATCH v2 8/9] bpf: make callback handle atomic with relaxed access Marat Khalili
2026-10-12 21:09   ` [PATCH v2 9/9] bpf: add callback flag to skip multi-thread check Marat Khalili
2026-10-13 16:55     ` Stephen Hemminger

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=20261011182158.124246-2-qm2k21@gmail.com \
    --to=qm2k21@gmail.com \
    --cc=dev@dpdk.org \
    --cc=konstantin.ananyev@huawei.com \
    --cc=stephen@networkplumber.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