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: Matthew Sakai <msakai@redhat.com>,
	Mikulas Patocka <mpatocka@redhat.com>,
	Sasha Levin <sashal@kernel.org>,
	linux-kernel@vger.kernel.org
Subject: [PATCH AUTOSEL 7.0-6.12] dm vdo slab-depot: validate old zone count on load
Date: Mon, 20 Apr 2026 09:08:04 -0400	[thread overview]
Message-ID: <20260420131539.986432-18-sashal@kernel.org> (raw)
In-Reply-To: <20260420131539.986432-1-sashal@kernel.org>

From: Matthew Sakai <msakai@redhat.com>

[ Upstream commit b3929b2cc2a6003b8e301e6540c651e60d24dcb4 ]

Verify the old zone count has a valid value before using
it to compute slab summary entry offsets.

Signed-off-by: Matthew Sakai <msakai@redhat.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---

LLM Generated explanations, may be completely bogus:

Now I have a thorough understanding. Let me compile my final analysis.

---

## Complete Analysis: dm vdo slab-depot: validate old zone count on load

### PHASE 1: COMMIT MESSAGE FORENSICS

**Step 1.1: Subject Line**
- Subsystem: `dm vdo slab-depot` (device-mapper VDO subsystem, slab
  depot component)
- Action verb: "validate" — implies adding a missing safety check,
  strongly suggests bug fix
- Summary: Validates the `old_zone_count` field read from on-disk
  metadata before using it as an array index.
- Record: [dm vdo slab-depot] [validate] [add bounds check on old zone
  count loaded from disk]

**Step 1.2: Tags**
- `Signed-off-by: Matthew Sakai <msakai@redhat.com>` — author, VDO
  subsystem maintainer
- `Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>` — DM subsystem
  maintainer
- No Fixes: tag, no Reported-by, no Link: tags
- Record: Patch authored by VDO maintainer, signed off by DM maintainer.
  No external bug report; likely found via code audit.

**Step 1.3: Commit Body**
- "Verify the old zone count has a valid value before using it to
  compute slab summary entry offsets."
- This directly describes a missing input validation on data loaded from
  disk. The "old zone count" is deserialized from the VDO super block
  and used to compute array offsets without bounds checking.
- Record: Bug = missing validation of on-disk value used as array index;
  Symptom = potential OOB memory access; Root cause = zone_count from
  disk not validated against MAX_VDO_PHYSICAL_ZONES.

**Step 1.4: Hidden Bug Fix Detection**
- This IS a bug fix. "Validate" = adding a missing safety check. The
  code was using an untrusted on-disk value to compute memory offsets.
- Record: Yes, this is a validation bug fix preventing out-of-bounds
  access.

### PHASE 2: DIFF ANALYSIS

**Step 2.1: Inventory**
- Files: `drivers/md/dm-vdo/slab-depot.c` (+3 lines)
- Function modified: `vdo_decode_slab_depot()`
- Scope: Single-file, surgical 3-line addition
- Record: 1 file, +3 lines, single function, surgical fix.

**Step 2.2: Code Flow Change**
- BEFORE: `state.zone_count` from on-disk metadata was stored as
  `depot->old_zone_count` without any bounds validation. The decode
  function (`decode_slab_depot_state_2_0` in `encodings.c`) reads
  `zone_count` as a raw byte (`buffer[(*offset)++]`) and stores it
  without validation.
- AFTER: `state.zone_count` is checked against `MAX_VDO_PHYSICAL_ZONES`
  (16). If it exceeds 16, `UDS_CORRUPT_DATA` error is returned before
  any allocation.
- The check is placed BEFORE the allocation of the depot structure, so
  no memory leak on this error path.
- Record: Before = raw on-disk byte used unchecked; After = validated
  against maximum before use.

**Step 2.3: Bug Mechanism**
This is an **out-of-bounds memory access** bug:

1. `zone_count` is a `zone_count_t` (u8), so it can be 0-255.
2. `MAX_VDO_PHYSICAL_ZONES` = 16.
3. In `combine_summaries()` (line 4575-4588), `depot->old_zone_count` is
   used to cycle through zones: `entries + (zone * MAX_VDO_SLABS) +
   entry_number`, where `zone` ranges from 0 to `old_zone_count - 1`.
4. The `summary_entries` buffer is allocated with
   `MAXIMUM_VDO_SLAB_SUMMARY_ENTRIES` = `MAX_VDO_SLABS *
   MAX_VDO_PHYSICAL_ZONES` = 8192 * 16 = 131,072 entries.
5. If `old_zone_count` = 17, the maximum offset becomes 16 * 8192 + 8191
   = 139,263, which exceeds the buffer size of 131,072. With
   `old_zone_count` = 255, the max offset is 2,088,959 — massively out
   of bounds.
6. This causes an OOB read (data copied from beyond the buffer boundary)
   and potentially corruption, since `combine_summaries` uses `memcpy`
   both for reading and writing.

Record: [OOB memory access] [corrupt on-disk zone_count > 16 causes
access beyond allocated summary_entries buffer in combine_summaries()]

**Step 2.4: Fix Quality**
- Obviously correct: a simple bounds check against a well-defined
  constant.
- Minimal/surgical: 3 lines, inserted in the right place (before
  allocation and use).
- No regression risk: this only rejects corrupt/invalid data early.
- Placed before allocation, so no resource leak on this new error path.
- Record: Fix is obviously correct, minimal, zero regression risk.

### PHASE 3: GIT HISTORY INVESTIGATION

**Step 3.1: Blame**
- The buggy code (using `state.zone_count` without validation) was
  introduced by `7ce49449ffb940` ("dm vdo: add the slab depot") by
  Matthew Sakai on 2023-11-16.
- This is contained in v6.9-rc1, so it has been present since kernel
  6.9.
- Record: Buggy code introduced in commit 7ce49449ffb940 (v6.9-rc1),
  present since kernel 6.9.

**Step 3.2: Fixes tag** — No Fixes: tag present (expected).

**Step 3.3: File History**
- The file has had moderate recent activity (kerneldoc fixes, refcount
  rework, ring reference removal). No related validation fixes found.
- Record: No prior fix for this issue. Standalone fix.

**Step 3.4: Author**
- Matthew Sakai is the VDO subsystem maintainer and author of the
  original VDO code. Mikulas Patocka is the DM subsystem maintainer who
  signed off.
- Record: Fix from subsystem maintainer, signed off by DM maintainer.
  High confidence.

**Step 3.5: Dependencies**
- This is entirely standalone. It adds a check using
  `MAX_VDO_PHYSICAL_ZONES` and `UDS_CORRUPT_DATA`, both of which already
  exist in all stable trees with dm-vdo.
- Record: No dependencies. Clean standalone fix.

### PHASE 4: MAILING LIST AND EXTERNAL RESEARCH

**Step 4.1-4.5:** Could not find the original mailing list submission
through web search or b4 dig (the commit may be very recent or submitted
through a different channel). The DM tree often takes patches directly.
Both the VDO and DM maintainer signed off, indicating proper review.
- Record: Mailing list thread not found (may be recent/not yet indexed).
  Maintainer sign-offs provide review confidence.

### PHASE 5: CODE SEMANTIC ANALYSIS

**Step 5.1: Key Functions**
- Modified: `vdo_decode_slab_depot()` — the main decoder for VDO slab
  depot on-disk state.

**Step 5.2: Callers**
- `vdo_decode_slab_depot()` is called from `dm-vdo-target.c:1360` during
  VDO volume load/activation. This is triggered when a VDO device is
  started (e.g., `dmsetup create`).
- Record: Called during device activation — any VDO user hits this code
  path.

**Step 5.3-5.4: Impact Path**
- `vdo_decode_slab_depot()` → stores `old_zone_count` →
  `combine_summaries()` uses it to compute offsets into
  `summary_entries` array → OOB access if value > 16.
- The bug is triggered whenever VDO loads a volume with corrupt metadata
  (malicious disk image, bit rot, filesystem corruption).

**Step 5.5: Similar Patterns**
- The `dm-vdo-target.c` already validates `physical_zone_count` at line
  421 (`if (count > MAX_VDO_PHYSICAL_ZONES)`), but the on-disk
  deserialization path in `decode_slab_depot_state_2_0` does NOT
  validate `zone_count`. This is an inconsistency that this fix
  addresses.
- Record: New zone_count validated in dm-vdo-target.c; old zone_count
  from disk was NOT validated. Asymmetric validation = bug.

### PHASE 6: CROSS-REFERENCING

**Step 6.1: Stable Tree Presence**
- dm-vdo was introduced in v6.9-rc1. File does NOT exist in v6.8 or
  earlier.
- Exists in stable trees: 6.12.y, and any other active stable tree >=
  6.9.
- Record: Bug exists in all kernels >= 6.9 (6.12.y stable tree).

**Step 6.2: Backport Complications**
- The v6.9 code is identical to current mainline for this function
  (verified). Patch should apply cleanly.
- Record: Clean apply expected.

**Step 6.3: Related Fixes**
- No related fix found in stable.

### PHASE 7: SUBSYSTEM CONTEXT

**Step 7.1:** dm-vdo (device-mapper Virtual Data Optimizer) is a data
deduplication and compression layer. Classification: IMPORTANT — used in
production storage (Red Hat VDO in RHEL).
- Record: Subsystem: DM/VDO, Criticality: IMPORTANT (production
  storage).

### PHASE 8: IMPACT AND RISK ASSESSMENT

**Step 8.1: Who is affected** — All VDO users loading VDO volumes (dm-
vdo is used in RHEL/Fedora storage stacks).

**Step 8.2: Trigger** — Loading a VDO volume with corrupt on-disk
metadata where zone_count > 16. This can happen from:
- Disk corruption / bit rot
- Malicious crafted disk images
- Record: Triggered on VDO volume load with corrupt metadata.

**Step 8.3: Severity** — OOB memory access → can cause:
- Kernel crash/oops (most likely outcome)
- Memory corruption
- Potential information leak
- Severity: **HIGH** (OOB access from untrusted on-disk data)

**Step 8.4: Risk-Benefit**
- BENEFIT: Prevents OOB memory access from corrupt disk metadata.
  Protects all VDO users.
- RISK: 3 lines, obviously correct bounds check, zero regression risk.
- Record: Very high benefit, very low risk.

### PHASE 9: FINAL SYNTHESIS

**Step 9.1: Evidence**

FOR backporting:
- Fixes out-of-bounds memory access from unvalidated on-disk data
- 3-line surgical fix, obviously correct
- Written by VDO maintainer, signed off by DM maintainer
- Affects all VDO users when loading corrupt volumes
- `zone_count_t` is u8 (0-255) but must be <= 16; no validation existed
- `combine_summaries()` computes `zone * MAX_VDO_SLABS` (up to 254 *
  8192) into a buffer of only 131,072 entries
- Similar validation already exists for new zone_count in dm-vdo-
  target.c
- Code exists in stable trees >= 6.9 (including 6.12.y)

AGAINST backporting:
- No explicit Reported-by or syzbot trigger (likely found by code audit)
- No CVE assigned (yet)
- Requires corrupt/malicious on-disk metadata to trigger

**Step 9.2: Stable Rules Checklist**
1. Obviously correct and tested? **YES** — trivial bounds check
2. Fixes a real bug? **YES** — OOB access from untrusted input
3. Important issue? **YES** — OOB memory access =
   crash/corruption/security
4. Small and contained? **YES** — 3 lines, single file
5. No new features or APIs? **YES** — validation only
6. Can apply to stable? **YES** — code is identical in 6.9+

**Step 9.3: Exception Categories** — N/A (standard bug fix)

**Step 9.4: Decision**
This is a clear-cut missing input validation fix for on-disk data that
can cause out-of-bounds memory access. It's 3 lines, obviously correct,
from the subsystem maintainer, with zero regression risk.

### Verification

- [Phase 1] Parsed commit message: "validate old zone count" = bounds
  check on deserialized data
- [Phase 2] Diff analysis: 3 lines added to `vdo_decode_slab_depot()`,
  validates `state.zone_count <= MAX_VDO_PHYSICAL_ZONES`
- [Phase 2] Confirmed OOB: zone_count=17 → offset 139,263 > buffer
  131,072; zone_count=255 → offset 2,088,959
- [Phase 3] git blame: buggy code introduced in 7ce49449ffb940
  (v6.9-rc1, 2023-11-16)
- [Phase 3] git describe: 7ce49449ffb940 is `v6.9-rc1~148^2~114`
- [Phase 3] Confirmed no Fixes: tag (expected for AUTOSEL candidate)
- [Phase 3] Confirmed standalone fix, no dependencies
- [Phase 4] b4 dig: could not find mailing list thread (UNVERIFIED:
  thread may be too recent)
- [Phase 5] `vdo_decode_slab_depot()` called from `dm-vdo-target.c:1360`
  during VDO volume activation
- [Phase 5] `combine_summaries()` at line 4575-4588 uses
  `old_zone_count` to compute offsets into `summary_entries`
- [Phase 5] `decode_slab_depot_state_2_0()` at line 631 reads
  `zone_count` as raw byte with no validation
- [Phase 5] Confirmed asymmetric validation: new zone_count validated at
  dm-vdo-target.c:421, but not old zone_count from disk
- [Phase 6] File exists in v6.9+ (confirmed `v6.9:drivers/md/dm-
  vdo/slab-depot.c` exists, `v6.8` does not)
- [Phase 6] v6.9 version of `vdo_decode_slab_depot()` is identical —
  clean apply expected
- [Phase 8] Failure mode: OOB memory read/write in `combine_summaries()`
  → crash or corruption, severity HIGH
- UNVERIFIED: Could not locate mailing list discussion; relying on
  maintainer SOBs for review confidence

**YES**

 drivers/md/dm-vdo/slab-depot.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/md/dm-vdo/slab-depot.c b/drivers/md/dm-vdo/slab-depot.c
index 034ecaa51f481..ad00afc2c168d 100644
--- a/drivers/md/dm-vdo/slab-depot.c
+++ b/drivers/md/dm-vdo/slab-depot.c
@@ -4262,6 +4262,10 @@ int vdo_decode_slab_depot(struct slab_depot_state_2_0 state, struct vdo *vdo,
 	}
 	slab_size_shift = ilog2(slab_size);
 
+	if (state.zone_count > MAX_VDO_PHYSICAL_ZONES)
+		return vdo_log_error_strerror(UDS_CORRUPT_DATA,
+					      "invalid zone count");
+
 	result = vdo_allocate_extended(struct slab_depot,
 				       vdo->thread_config.physical_zone_count,
 				       struct block_allocator, __func__, &depot);
-- 
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 ` Sasha Levin [this message]
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 ` [PATCH AUTOSEL 7.0-6.6] bpf, sockmap: Annotate af_unix sock:: Sk_state data-races Sasha Levin
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=20260420131539.986432-18-sashal@kernel.org \
    --to=sashal@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mpatocka@redhat.com \
    --cc=msakai@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.