All of lore.kernel.org
 help / color / mirror / Atom feed
From: Sasha Levin <sashal@kernel.org>
To: patches@lists.linux.dev, stable@vger.kernel.org
Cc: Michal Luczaj <mhal@rbox.co>,
	Kuniyuki Iwashima <kuniyu@google.com>,
	Martin KaFai Lau <martin.lau@linux.dev>,
	Martin KaFai Lau <martin.lau@kernel.org>,
	Jiayuan Chen <jiayuan.chen@linux.dev>,
	Sasha Levin <sashal@kernel.org>,
	john.fastabend@gmail.com, jakub@cloudflare.com,
	davem@davemloft.net, edumazet@google.com, kuba@kernel.org,
	pabeni@redhat.com, netdev@vger.kernel.org, bpf@vger.kernel.org,
	linux-kernel@vger.kernel.org
Subject: [PATCH AUTOSEL 7.0-6.6] bpf, sockmap: Annotate af_unix sock:: Sk_state data-races
Date: Mon, 20 Apr 2026 09:08:19 -0400	[thread overview]
Message-ID: <20260420131539.986432-33-sashal@kernel.org> (raw)
In-Reply-To: <20260420131539.986432-1-sashal@kernel.org>

From: Michal Luczaj <mhal@rbox.co>

[ Upstream commit a25566084e391348385a72dd507e0cc0c268dd5d ]

sock_map_sk_state_allowed() and sock_map_redirect_allowed() read af_unix
socket sk_state locklessly.

Use READ_ONCE(). Note that for sock_map_redirect_allowed() change affects
not only af_unix, but all non-TCP sockets (UDP, af_vsock).

Suggested-by: Kuniyuki Iwashima <kuniyu@google.com>
Suggested-by: Martin KaFai Lau <martin.lau@linux.dev>
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260414-unix-proto-update-null-ptr-deref-v4-1-2af6fe97918e@rbox.co
Signed-off-by: Sasha Levin <sashal@kernel.org>
---

LLM Generated explanations, may be completely bogus:

Now I have enough context. Let me compile my analysis.

## Phase 1: Commit Message Forensics

**Step 1.1 - Subject Line Parse:**
- Subsystem: `bpf, sockmap:`
- Action verb: "Annotate" (not "fix")
- Summary: Adds READ_ONCE() to two lockless reads of af_unix sk_state in
  sock_map.c

Record: bpf/sockmap subsystem, annotation (data race), adds READ_ONCE()
to sk_state reads

**Step 1.2 - Tags:**
- `Suggested-by: Kuniyuki Iwashima` (networking/af_unix expert)
- `Suggested-by: Martin KaFai Lau` (BPF maintainer)
- `Signed-off-by: Michal Luczaj` (original author)
- `Signed-off-by: Martin KaFai Lau` (maintainer applied)
- `Reviewed-by: Jiayuan Chen`
- `Reviewed-by: Kuniyuki Iwashima`
- `Link:` to v4 on patch.msgid.link
- **No** Fixes: tag
- **No** Cc: stable
- **No** syzbot/KCSAN report

Record: Strong review endorsement (both suggesters are reviewers); no
Fixes:/stable tags; no concrete bug report cited.

**Step 1.3 - Body Text:**
The commit explicitly acknowledges that `sock_map_sk_state_allowed()`
and `sock_map_redirect_allowed()` read sk_state "locklessly". Change
uses READ_ONCE(). Notes the redirect_allowed change also affects UDP and
af_vsock. No crash/panic/reproducer described in body — it's purely a
data race annotation.

Record: Describes data race (paired writer uses WRITE_ONCE); no user-
visible symptom documented.

**Step 1.4 - Hidden fix?**
"Annotate data-races" is standard kernel terminology for adding
READ_ONCE/WRITE_ONCE pairings. This is a recognized synchronization bug
fix pattern per KCSAN/C11 memory model, even without a concrete crash.

## Phase 2: Diff Analysis

**Step 2.1 - Inventory:** Single file `net/core/sock_map.c`, 2 lines
changed (2 insertions, 2 deletions). Two functions modified:
`sock_map_redirect_allowed()` and `sock_map_sk_state_allowed()`. Minimal
surgical scope.

**Step 2.2 - Code flow:** Before/after behavior is identical modulo
compiler: READ_ONCE prevents load tearing/reordering/fusion by the
compiler for lockless reads.

**Step 2.3 - Bug mechanism:** Category (b) Synchronization. This is a
completion of a WRITE_ONCE/READ_ONCE pair: writer side at
`net/unix/af_unix.c:1775` uses `WRITE_ONCE(sk->sk_state,
TCP_ESTABLISHED)` in `unix_stream_connect()`, but sock_map.c readers
were plain reads — a data race per kernel/C11 rules.

**Step 2.4 - Fix quality:** Obviously correct. Zero regression risk —
READ_ONCE is a compiler barrier with no runtime cost on aligned reads.

## Phase 3: Git History

**Step 3.1 - Blame:** The affected lines originated from:
- `sock_map_redirect_allowed`: commit `122e6c79efe1c2` (Cong Wang, 2021)
- `sock_map_sk_state_allowed` af_unix branch: commit `8d6650646ce49e`
  (John Fastabend, Dec 2023 - fixing syzkaller null ptr deref in
  unix_bpf)

The af_unix branch of sock_map_sk_state_allowed was added in v6.8 (Dec
2023).

**Step 3.2 - Fixes tag:** No Fixes: tag on this patch. The series' patch
5/5 has `Fixes: c63829182c37 ("af_unix: Implement
->psock_update_sk_prot()")` — the null-ptr-deref is fixed there, not
here.

**Step 3.3 - File history:** Recent active development on sock_map.c.
This is patch 1/5 of a series fixing a null-ptr-deref that crashes via
`unix_stream_bpf_update_proto+0xa0`. Patch 5/5 is the actual crash fix.

**Step 3.4 - Author's role:** Michal Luczaj is an active vsock/unix
contributor. Martin KaFai Lau (BPF maintainer) applied it. Kuniyuki
Iwashima is the af_unix expert.

**Step 3.5 - Dependencies:** This patch is independent of the rest of
the series — it touches separate code than patches 2-5. No dependencies.

## Phase 4: Mailing List Research

**Step 4.1 - Original submission:** Found v3 on lore/yhbt and v4
referenced in the commit (20260414-unix-proto-update-null-ptr-deref-v4).
Series: `[PATCH bpf v3 0/5] bpf, sockmap: Fix af_unix null-ptr-deref in
proto update`.

**Step 4.2 - Reviewers:** Networking maintainers (Paolo, Jakub,
Kuniyuki, Eric Dumazet), BPF maintainers (Martin, Alexei, Daniel),
af_unix expert Kuniyuki explicitly reviewed and ACKed this patch.

**Step 4.3 - Bug report:** The series is motivated by a NULL ptr deref
crash (shown in patch 5/5's commit message) but THIS specific patch has
no explicit crash reporter. Kuniyuki notes: "Actually TCP path also
needs READ_ONCE(), but I think it's okay for now since this series
focuses on AF_UNIX" — confirming this is the known-pattern data race
annotation.

**Step 4.4 - Series context:** This is 1/5 of a series:
1. (this one) READ_ONCE annotations
2. Refactor to sock_map_sk_{acquire,release}() helpers
3. Fix af_unix iter deadlock (has Fixes: tag)
4. Selftest
5. Adapt sockmap for af_unix locking (has Fixes: tag — the actual null-
   ptr-deref fix)

**Step 4.5 - Stable discussion:** No explicit stable nomination. Author
himself noted patch 5/5's locking would make this READ_ONCE redundant
for the af_unix path, but the patch was kept as a minimal standalone
hardening.

## Phase 5: Code Semantic Analysis

**Step 5.1 - Functions modified:** `sock_map_redirect_allowed()`,
`sock_map_sk_state_allowed()`

**Step 5.2 - Callers:**
- `sock_map_redirect_allowed()`: 4 callers — `bpf_sk_redirect_map`,
  `bpf_msg_redirect_map`, `bpf_sk_redirect_hash`,
  `bpf_msg_redirect_hash`. Called from BPF programs at runtime (hot
  path).
- `sock_map_sk_state_allowed()`: 2 callers in `sock_map_update_elem_sys`
  and `sock_map_update_elem` — invoked on BPF_MAP_UPDATE_ELEM syscall.

**Step 5.3 - Callees:** Just reads sk->sk_state and does bitmask
comparison.

**Step 5.4 - Reachability:** Reachable from userspace via bpf() syscall
(BPF_MAP_UPDATE_ELEM) and from BPF programs redirecting sockets —
CONFIRMED reachable.

**Step 5.5 - Similar patterns:** Found the same pattern in
`net/unix/diag.c` (commit `0aa3be7b3e1f8 "af_unix: Annotate data-races
around sk->sk_state in UNIX_DIAG"`) — had Fixes: tags and went to
**ALL** stable trees: 5.10, 5.15, 6.1, 6.6, 6.12, 6.17, 6.18. Strong
precedent.

## Phase 6: Cross-referencing Stable Trees

**Step 6.1 - Code in stable:**
- `sock_map_redirect_allowed()`: Present in ALL active stable trees
  (5.10, 5.15, 6.1, 6.6, 6.12, 6.17, 6.18)
- `sock_map_sk_state_allowed()` af_unix branch (hunk 2): Only in 6.6.y
  and newer (added in v6.8 by backport of 8d6650646ce49)

**Step 6.2 - Backport complications:** Hunk 1
(sock_map_redirect_allowed) applies to all trees. Hunk 2
(sock_map_sk_state_allowed af_unix branch) only applies to 6.6+ where
the af_unix branch exists. Minor adjustment for older trees (drop hunk
2). Clean for 6.6+.

**Step 6.3 - Related fixes in stable:** Precedent 0aa3be7b3e1f8 is in
ALL stable trees — shows the same type of annotation is routinely
accepted.

## Phase 7: Subsystem Context

**Step 7.1 - Subsystem:** `net/core/sock_map.c` = networking core + BPF.
IMPORTANT criticality (BPF sockmap used in user-space networking stacks
like Cilium).

**Step 7.2 - Activity:** Actively developed subsystem with recent bug
fixes.

## Phase 8: Impact Assessment

**Step 8.1 - Affected users:** BPF sockmap users on systems with af_unix
BPF usage, and any users with BPF programs using
sk_redirect/msg_redirect on non-TCP sockets.

**Step 8.2 - Trigger:** Concurrent BPF_MAP_UPDATE_ELEM on a socket
that's undergoing state change (e.g., unix_stream_connect). On most
archs with aligned int reads, load tearing is unlikely, but compiler
fusion/reordering is possible. KCSAN would flag this.

**Step 8.3 - Failure mode:** Without READ_ONCE alone, theoretical
compiler-induced mis-behavior (torn/fused reads of sk_state leading to
wrong state checks). The concrete null-ptr-deref described in the series
is NOT fixed by this patch alone — that's fixed by patch 5/5. Severity:
LOW-MEDIUM for this patch in isolation.

**Step 8.4 - Risk/benefit:**
- Risk: ~zero (READ_ONCE is a compiler barrier; no runtime change on
  aligned reads)
- Benefit: Completes WRITE_ONCE/READ_ONCE pair, silences KCSAN, hardens
  against compiler edge cases

## Phase 9: Final Synthesis

**Evidence FOR backporting:**
- Fixes a genuine data race (plain read paired with WRITE_ONCE on the
  writer)
- Very small, surgical, obviously correct (2 lines)
- Strong reviewer endorsement (Kuniyuki, Jiayuan, Martin)
- Strong precedent: `0aa3be7b3e1f8` (identical pattern) was accepted
  into ALL stable trees with Fixes: tags
- Zero regression risk

**Evidence AGAINST backporting:**
- No Fixes: tag on THIS specific patch
- No Cc: stable tag
- No concrete syzbot/KCSAN report cited
- By itself, does NOT fix the null-ptr-deref (that's patch 5/5)
- Author acknowledged patch 5/5's proper locking would make this
  redundant on af_unix path
- "Annotation only" — preventive rather than curative for the crash

**Stable Rules checklist:**
1. Obviously correct and tested? YES (trivial READ_ONCE; reviewed by
   multiple maintainers)
2. Fixes a real bug? YES (data race per C11/kernel rules) but not a
   user-visible crash alone
3. Important issue? MEDIUM (data race without concrete trigger)
4. Small and contained? YES (2 lines)
5. No new features/APIs? YES
6. Applies to stable? Mostly — hunk 2 needs 6.6+ but hunk 1 applies
   everywhere

**Decision analysis:** This is a borderline case. The patch itself is
pure annotation with no concrete user-visible crash fix in isolation.
However, the precedent (0aa3be7b3e1f8) strongly shows this annotation
pattern IS routinely accepted into stable, including down to 5.10.y. The
patch is 2 lines, zero-risk, and completes a real WRITE_ONCE/READ_ONCE
pair. The Kuniyuki review noting "TCP path also needs READ_ONCE()"
indicates this is a recognized pattern.

Given:
- The precedent of identical-pattern commits going to all stable trees
- Zero regression risk
- Real (if benign) data race being fixed
- Strong review from domain experts

## Verification

- [Phase 1] Parsed tags: no Fixes:, no Cc: stable, but strong Reviewed-
  by from networking maintainer Kuniyuki and BPF maintainer Martin KaFai
  Lau
- [Phase 2] Diff analysis: exactly 2 lines changed, adds READ_ONCE() to
  2 lockless sk_state reads
- [Phase 2] Verified writer pairs with WRITE_ONCE at
  net/unix/af_unix.c:1556, 1775 in unix_stream_connect
- [Phase 3] git blame: affected code introduced by 122e6c79efe1c2 (2021)
  and 8d6650646ce49e (Dec 2023, v6.8)
- [Phase 3] git show c63829182c37: confirmed Fixes: target from patch
  5/5 is from 2021 (widely in stable)
- [Phase 4] Found lore discussion on yhbt.net showing full series thread
- [Phase 4] Confirmed this is patch 1/5; real null-ptr-deref crash is
  fixed by patch 5/5
- [Phase 4] Kuniyuki review comment: "Actually TCP path also needs
  READ_ONCE()" — confirms this is an incremental fix of a broader race
  pattern
- [Phase 5] grep sock_map_redirect_allowed: 4 callers in sockmap BPF
  redirect hooks
- [Phase 5] grep sock_map_sk_state_allowed: 2 callers in
  BPF_MAP_UPDATE_ELEM paths
- [Phase 5] Found precedent commit 0aa3be7b3e1f8 ("af_unix: Annotate
  data-races around sk->sk_state in UNIX_DIAG") — same pattern
- [Phase 6] Verified code presence in stable trees: redirect_allowed
  exists in all; state_allowed af_unix branch only in 6.6+ (6.6, 6.12,
  6.17, 6.18 checked)
- [Phase 6] Confirmed precedent 0aa3be7b3e1f8 backported to
  linux-5.10.y, 5.15.y, 6.1.y, 6.6.y, 6.12.y, 6.17.y, 6.18.y — all
  active stable trees
- [Phase 8] Failure mode: data race (compiler-level), severity LOW-
  MEDIUM in isolation
- UNVERIFIED: Whether the v4 of the series has been applied to mainline
  (appears not yet, as I couldn't locate the commit SHA in local
  mainline snapshot — checked bpf-next and linus-next/master)
- UNVERIFIED: Whether the rest of the series (patches 2-5) will also go
  through autoselection

The patch is 2 lines of low-risk data race annotation with strong
precedent for acceptance into all active stable trees. While it doesn't
fix the null-ptr-deref in isolation (that's patch 5/5), it genuinely
completes a WRITE_ONCE/READ_ONCE pair and silences KCSAN. Stable
maintainers routinely accept these annotations, as evidenced by
`0aa3be7b3e1f8` being in every active stable tree including 5.10.y.

**YES**

 net/core/sock_map.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index b0e96337a2698..02a68be3002a2 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -530,7 +530,7 @@ static bool sock_map_redirect_allowed(const struct sock *sk)
 	if (sk_is_tcp(sk))
 		return sk->sk_state != TCP_LISTEN;
 	else
-		return sk->sk_state == TCP_ESTABLISHED;
+		return READ_ONCE(sk->sk_state) == TCP_ESTABLISHED;
 }
 
 static bool sock_map_sk_is_suitable(const struct sock *sk)
@@ -543,7 +543,7 @@ static bool sock_map_sk_state_allowed(const struct sock *sk)
 	if (sk_is_tcp(sk))
 		return (1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_LISTEN);
 	if (sk_is_stream_unix(sk))
-		return (1 << sk->sk_state) & TCPF_ESTABLISHED;
+		return (1 << READ_ONCE(sk->sk_state)) & TCPF_ESTABLISHED;
 	if (sk_is_vsock(sk) &&
 	    (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET))
 		return (1 << sk->sk_state) & TCPF_ESTABLISHED;
-- 
2.53.0


  parent reply	other threads:[~2026-04-20 13:16 UTC|newest]

Thread overview: 96+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-04-20 13:07 [PATCH AUTOSEL 6.18] ALSA: hda/realtek: add quirk for Lenovo Yoga 7 2-in-1 16AKP10 Sasha Levin
2026-04-20 13:07 ` [PATCH AUTOSEL 6.18] net: stmmac: Fix PTP ref clock for Tegra234 Sasha Levin
2026-04-20 13:07 ` [PATCH AUTOSEL 7.0-6.12] ring-buffer: Enforce read ordering of trace_buffer cpumask and buffers Sasha Levin
2026-04-20 13:07 ` [PATCH AUTOSEL 7.0-6.6] PCI: Prevent assignment to unsupported bridge windows Sasha Levin
2026-04-20 13:07 ` [PATCH AUTOSEL 7.0-5.10] smb: client: fix integer underflow in receive_encrypted_read() Sasha Levin
2026-04-20 13:07 ` [PATCH AUTOSEL 7.0-5.10] gpio: lp873x: normalize return value of gpio_get Sasha Levin
2026-04-20 13:07 ` [PATCH AUTOSEL 7.0-6.12] ALSA: hda: cs35l41: Fix boost type for HP Dragonfly 13.5 inch G4 Sasha Levin
2026-04-20 13:07 ` [PATCH AUTOSEL 7.0-6.18] wifi: mt76: don't return TXQ when exceeding max non-AQL packets Sasha Levin
2026-04-20 13:07 ` [PATCH AUTOSEL 6.18] arm64: dts: imx91-tqma9131: improve eMMC pad configuration Sasha Levin
2026-04-20 13:07 ` [PATCH AUTOSEL 6.18] ASoC: amd: acp: add ASUS HN7306EA quirk for legacy SDW machine Sasha Levin
2026-04-20 13:07 ` [PATCH AUTOSEL 7.0-6.12] wifi: mac80211: properly handle error in ieee80211_add_virtual_monitor Sasha Levin
2026-04-20 13:07 ` [PATCH AUTOSEL 7.0-5.10] net: qrtr: fix endian handling of confirm_rx field Sasha Levin
2026-04-20 13:07 ` [PATCH AUTOSEL 7.0-6.18] mmc: sdhci-esdhc-imx: wait for data transfer completion before reset Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 6.18] tracing/probe: reject non-closed empty immediate strings Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.18] media: rc: fix race between unregister and urb/irq callbacks Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 6.18] netfilter: xt_multiport: validate range encoding in checkentry Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 6.18] arm64: dts: imx93-tqma9352: improve eMMC pad configuration Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.12] dm vdo slab-depot: validate old zone count on load Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.6] wifi: mt76: mt792x: Fix a potential deadlock in high-load situations Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.12] orangefs: add usercopy whitelist to orangefs_op_cache Sasha Levin
2026-04-20 13:08 ` [Intel-wired-lan] [PATCH AUTOSEL 6.18] ice: ptp: don't WARN when controlling PF is unavailable Sasha Levin
2026-04-20 13:08   ` Sasha Levin
2026-04-20 13:08 ` [Intel-wired-lan] [PATCH AUTOSEL 6.18] e1000: check return value of e1000_read_eeprom Sasha Levin
2026-04-20 13:08   ` Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.19] ALSA: usb-audio: Add quirks for Arturia AF16Rig Sasha Levin
2026-04-20 13:27   ` Philip Willoughby
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.12] ALSA: asihpi: detect truncated control names Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.18] ALSA: hda/realtek: Add support for ASUS 2026 Commercial laptops using CS35L41 HDA Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-5.10] jfs: Set the lbmDone flag at the end of lbmIODone Sasha Levin
2026-04-20 14:10   ` Edward Adam Davis
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.19] ASoC: SDCA: Add CS47L47 to class driver Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-5.10] media: renesas: vsp1: rpf: Fix crop left and top clamping Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 6.18] ASoC: amd: yc: Add DMI entry for HP Laptop 15-fc0xxx Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-5.10] media: au0828: Fix green screen in analog Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 6.18] ASoC: Intel: avs: Fix memory leak in avs_register_i2s_test_boards() Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.6] nvme-loop: do not cancel I/O and admin tagset during ctrl reset/shutdown Sasha Levin
2026-04-20 13:08 ` Sasha Levin [this message]
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.18] net: wangxun: reorder timer and work sync cancellations Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-5.10] PCI: tegra194: Assert CLKREQ# explicitly by default Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-5.15] net: mvneta: support EPROBE_DEFER when reading MAC address Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 6.18] ALSA: hda/realtek: add quirk for Framework F111:000F Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-5.10] jfs: add dmapctl integrity check to prevent invalid operations Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.6] wifi: mac80211: Remove deleted sta links in ieee80211_ml_reconf_work() Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.6] HID: logitech-hidpp: fix race condition when accessing stale stack pointer Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.1] net/mlx5e: XSK, Increase size for chunk_size param Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.18] PCI: dwc: Proceed with system suspend even if the endpoint doesn't respond with PME_TO_Ack message Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-5.10] ACPI: processor: idle: Fix NULL pointer dereference in hotplug path Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-5.10] ppp: disconnect channel before nullifying pch->chan Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.1] wifi: iwlwifi: mvm: zero iwl_geo_tx_power_profiles_cmd before sending Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-5.15] ALSA: pcm: Serialize snd_pcm_suspend_all() with open_mutex Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.1] Bluetooth: hci_qca: disable power control for WCN7850 when bt_en is not defined Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.6] Bluetooth: hci_qca: Fix missing wakeup during SSR memdump handling Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 6.18] pinctrl: intel: Fix the revision for new features (1kOhm PD, HW debouncer) Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-5.10] fbdev: viafb: check ioremap return value in viafb_lcd_get_mobile_state Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.19] drm/panel-edp: Add BOE NV153WUM-N42, CMN N153JCA-ELK, CSW MNF307QS3-2 Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0] drm/amdgpu/userq: remove queue from doorbell xarray Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.1] memory: brcmstb_memc: Expand LPDDR4 check to cover for LPDDR5 Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.12] nouveau: pci: quiesce GPU on shutdown Sasha Levin
2026-04-20 13:08   ` Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-5.10] perf/amd/ibs: Avoid race between event add and NMI Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.12] drm/amd/display: Fix dcn401_optimize_bandwidth Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.18] wifi: rtw88: coex: Ignore BT info byte 5 from RTL8821A Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 6.18] btrfs: tracepoints: get correct superblock from dentry in event btrfs_sync_file() Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.18] ALSA: hda/realtek: Add quirk for CSL Unity BF24B Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-5.10] media: stm32: dcmi: stop the dma transfer on overrun Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-5.10] ALSA: aoa/onyx: Fix OF node leak on probe failure Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.18] drm/bridge: waveshare-dsi: Register and attach our DSI device at probe Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.1] wifi: rtw89: retry efuse physical map dump on transient failure Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 6.18] netfilter: nfnetlink_queue: make hash table per queue Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.18] gpio: cgbc: normalize return value of gpio_get Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.18] HID: logitech-hidpp: Check bounds when deleting force-feedback effects Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 6.18] x86: shadow stacks: proper error handling for mmap lock Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.1] sched: Fix incorrect schedstats for rt and dl thread Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.18] wifi: iwlwifi: pcie: don't dump on reset handshake in dump Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 6.18] net: sfp: add quirks for Hisense and HSGQ GPON ONT SFP modules Sasha Levin
2026-04-20 13:08 ` [Intel-wired-lan] [PATCH AUTOSEL 6.18] ixgbevf: add missing negotiate_features op to Hyper-V ops table Sasha Levin
2026-04-20 13:08   ` Sasha Levin
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-6.18] hwmon: (pmbus/isl68137) Add support for Renesas RAA228942 and RAA228943 Sasha Levin
2026-04-20 18:32   ` sashiko-bot
2026-04-20 13:08 ` [PATCH AUTOSEL 7.0-5.15] btrfs: use BTRFS_FS_UPDATE_UUID_TREE_GEN flag for UUID tree rescan check Sasha Levin
2026-04-20 13:09 ` [PATCH AUTOSEL 7.0-6.19] Bluetooth: hci_ll: Enable BROKEN_ENHANCED_SETUP_SYNC_CONN for WL183x Sasha Levin
2026-04-20 13:09 ` [PATCH AUTOSEL 7.0-6.18] wifi: mt76: abort ROC on chanctx changes Sasha Levin
2026-04-20 13:09 ` [PATCH AUTOSEL 7.0-6.18] perf/amd/ibs: Limit ldlat->l3missonly dependency to Zen5 Sasha Levin
2026-04-20 13:09 ` [PATCH AUTOSEL 6.18] drm/amdkfd: Fix queue preemption/eviction failures by aligning control stack size to GPU page size Sasha Levin
2026-04-20 13:09 ` [PATCH AUTOSEL 6.18] clockevents: Prevent timer interrupt starvation Sasha Levin
2026-04-20 14:12   ` Thomas Gleixner
2026-04-21  6:26     ` [PATCH stable backport] clockevents: Add missing resets of the next_event_forced flag Thomas Gleixner
2026-04-21  7:44       ` Patch "clockevents: Add missing resets of the next_event_forced flag" has been added to the 7.0-stable tree gregkh
2026-04-20 13:09 ` [PATCH AUTOSEL 7.0-5.10] ASoC: tas2552: Allow audio enable GPIO to sleep Sasha Levin
2026-04-20 13:09 ` [PATCH AUTOSEL 7.0-6.18] wifi: ath12k: Fix the assignment of logical link index Sasha Levin
2026-04-20 13:09 ` [PATCH AUTOSEL 7.0-6.12] drm/amdgpu: fix DF NULL pointer issue for soc24 Sasha Levin
2026-04-20 13:09 ` [PATCH AUTOSEL 7.0-6.18] drm/ttm: Avoid invoking the OOM killer when reading back swapped content Sasha Levin
2026-04-20 13:09 ` [PATCH AUTOSEL 6.18] drm/vc4: Release runtime PM reference after binding V3D Sasha Levin
2026-04-20 13:09 ` [PATCH AUTOSEL 7.0-5.10] media: i2c: mt9p031: Check return value of devm_gpiod_get_optional() in mt9p031_probe() Sasha Levin
2026-04-20 13:09 ` [PATCH AUTOSEL 6.18] Bluetooth: hci_sync: annotate data-races around hdev->req_status Sasha Levin
2026-04-20 13:09 ` [PATCH AUTOSEL 7.0-5.10] ASoC: Intel: bytcr_rt5651: Fix MCLK leak on platform_clock_control error Sasha Levin

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=20260420131539.986432-33-sashal@kernel.org \
    --to=sashal@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=jakub@cloudflare.com \
    --cc=jiayuan.chen@linux.dev \
    --cc=john.fastabend@gmail.com \
    --cc=kuba@kernel.org \
    --cc=kuniyu@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=martin.lau@kernel.org \
    --cc=martin.lau@linux.dev \
    --cc=mhal@rbox.co \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=patches@lists.linux.dev \
    --cc=stable@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.