Linux CAN drivers development
 help / color / mirror / Atom feed
* [PATCH v12 00/11] can: bcm: collected fixes - final7 \o/ \o/
@ 2026-07-09 20:22 Oliver Hartkopp via B4 Relay
  2026-07-09 20:22 ` [PATCH v12 01/11] can: bcm: defer rx_op deallocation to workqueue to fix thrtimer UAF Oliver Hartkopp via B4 Relay
                   ` (10 more replies)
  0 siblings, 11 replies; 20+ messages in thread
From: Oliver Hartkopp via B4 Relay @ 2026-07-09 20:22 UTC (permalink / raw)
  To: linux-can
  Cc: Oliver Hartkopp, Marc Kleine-Budde, Lee Jones, Feng Xue, Ginger,
	syzbot+75e5e4ae00c3b4bb544e, sashiko-reviews, sashiko-bot

Hi Marc,

as there were different patches flying arround to fix CAN_BCM issues and
AI assisted stuff pop's up again and again, I've created this collection
to be applied.

Fixed issues reported by sashiko-bot for patch 11:

- [High] Race condition between interface unregistration and in-flight packets permanently breaks ANYDEV sockets.
- [Medium] Data race and torn read on 64-bit ktime_t variables bypassing ANYDEV concurrency protection.
  
Best regards,
Oliver

Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
---
Changes in v12:
- patch 11: fixed sashiko-bot issues
  https://lore.kernel.org/linux-can/20260709184351.723F71F000E9@smtp.kernel.org/
- Link to v11: https://patch.msgid.link/20260709-bcm_fixes-v11-0-067ba11bec5c@hartkopp.net

Changes in v11:
- patch 11: new: track a single source interface for ANYDEV timeout/throttle ops
  reported by sashiko-bot
  https://lore.kernel.org/linux-can/20260709105031.1A39C1F000E9@smtp.kernel.org/
- patch 2: added Fixes: tag (mkl)
- Link to v10: https://patch.msgid.link/20260709-bcm_fixes-v10-0-57fff38e34ce@hartkopp.net

Changes in v10:
- patch 4: fixed new issue reported by sashiko-bot
  https://lore.kernel.org/linux-can/20260709083119.015901F00A3D@smtp.kernel.org/
- Link to v9: https://patch.msgid.link/20260709-bcm_fixes-v9-0-6eebb78ccfb2@hartkopp.net

Changes in v9:
- patch 4: fixed two issues reported by sashiko-bot and mkl
  https://lore.kernel.org/linux-can/20260708173935.10D021F000E9@smtp.kernel.org/
  https://lore.kernel.org/linux-can/20260708-beige-tarsier-of-mastery-b73d0d-mkl@pengutronix.de/
- Link to v8: https://patch.msgid.link/20260708-bcm_fixes-v8-0-8c2f5f3bc212@hartkopp.net

Changes in v8:
- patch 9: fixed two issues reported by sashiko-bot:
  https://lore.kernel.org/linux-can/20260708154039.347ED1F000E9@smtp.kernel.org/
- Link to v7: https://patch.msgid.link/20260708-bcm_fixes-v7-0-c78896b342e4@hartkopp.net

Changes in v7:
- patch 9: new: fix stale rx/tx ops after device removal reported by
  sashiko-bot: https://lore.kernel.org/linux-can/20260708094536.DDF821F00A3A@smtp.kernel.org/
- patch 10: formerly patch 9 as new patch 8 & 9 belong together 
- Link to v6: https://patch.msgid.link/20260708-bcm_fixes-v6-0-80710a2bc398@hartkopp.net

Changes in v6:
- patch 1: added Tested-by: tags
- patch 3: changed commit message and comment regarding a wrong claim
  about synchronous delivery from dev_queue_xmit() as remarked by
  https://netdev-ai.bots.linux.dev/ai-review.html?id=6105ebab-87ef-43db-a085-7c190b9f119f
- patch 4: rebased patch 3 comment
- patch 9: new: fix data race on rx_stamp/rx_ifindex in bcm_rx_handler()
  reported by sashiko-bot: https://lore.kernel.org/linux-can/20260707145135.5BC831F00A3A@smtp.kernel.org/
- Link to v5: https://patch.msgid.link/20260707-bcm_fixes-v5-0-c3c74f8d8ff7@hartkopp.net

Changes in v5:
- patch 6: changed comment for bcm_op::bcm_tx_lock (mkl)
- patch 8: new: add missing device refcount for CAN filter removal
- Link to v4: https://patch.msgid.link/20260707-bcm_fixes-v4-0-aa87b8b9d33f@hartkopp.net

Changes in v4:
- incorporated more sashiko-bot concerns from v3
- patch 3: omit hrtimer_forward with zero interval
- patch 4: put bcm_update_stats() under bcm_rx_update_lock
- Link to v3: https://patch.msgid.link/20260707-bcm_fixes-v3-0-84600ca6d889@hartkopp.net

Changes in v3:
- incorporated more sashiko-bot concerns from v2
- patch 3: make snapshot of currframe
- patch 6: add error patch for memcpy_from_msg()
- patch 7: new RTR-reply validation in bcm_rx_setup() from bcm_tx_setup() 
- Link to v2: https://patch.msgid.link/20260707-bcm_fixes-v2-0-96620c534b75@hartkopp.net

Changes in v2:
- incorporated all sashiko-bot concerns from v1
- Link to v1: https://patch.msgid.link/20260612-bcm_fixes-v1-0-ca2fa07ee70f@hartkopp.net

---
Lee Jones (1):
      can: bcm: defer rx_op deallocation to workqueue to fix thrtimer UAF

Oliver Hartkopp (10):
      can: bcm: fix lockless bound/ifindex race and silent RX_SETUP failure
      can: bcm: add locking when updating filter and timer values
      can: bcm: fix CAN frame rx/tx statistics
      can: bcm: add missing rcu list annotations and operations
      can: bcm: extend bcm_tx_lock usage for data and timer updates
      can: bcm: validate frame length in bcm_rx_setup() for RTR replies
      can: bcm: add missing device refcount for CAN filter removal
      can: bcm: fix stale rx/tx ops after device removal
      can: bcm: fix data race on rx_stamp/rx_ifindex in bcm_rx_handler()
      can: bcm: track a single source interface for ANYDEV timeout/throttle ops

 net/can/bcm.c | 578 ++++++++++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 441 insertions(+), 137 deletions(-)
---
base-commit: 0e35b9b6ec0ffcc5e23cbdec09f5c622ad532b53
change-id: 20260612-bcm_fixes-84fb4aa93ac2

Best regards,
--  
Oliver Hartkopp <socketcan@hartkopp.net>



^ permalink raw reply	[flat|nested] 20+ messages in thread

end of thread, other threads:[~2026-07-10  0:40 UTC | newest]

Thread overview: 20+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-07-09 20:22 [PATCH v12 00/11] can: bcm: collected fixes - final7 \o/ \o/ Oliver Hartkopp via B4 Relay
2026-07-09 20:22 ` [PATCH v12 01/11] can: bcm: defer rx_op deallocation to workqueue to fix thrtimer UAF Oliver Hartkopp via B4 Relay
2026-07-09 20:40   ` sashiko-bot
2026-07-09 20:22 ` [PATCH v12 02/11] can: bcm: fix lockless bound/ifindex race and silent RX_SETUP failure Oliver Hartkopp via B4 Relay
2026-07-10  0:40   ` sashiko-bot
2026-07-09 20:22 ` [PATCH v12 03/11] can: bcm: add locking when updating filter and timer values Oliver Hartkopp via B4 Relay
2026-07-09 20:38   ` sashiko-bot
2026-07-09 20:22 ` [PATCH v12 04/11] can: bcm: fix CAN frame rx/tx statistics Oliver Hartkopp via B4 Relay
2026-07-09 20:35   ` sashiko-bot
2026-07-09 20:22 ` [PATCH v12 05/11] can: bcm: add missing rcu list annotations and operations Oliver Hartkopp via B4 Relay
2026-07-09 20:35   ` sashiko-bot
2026-07-09 20:22 ` [PATCH v12 06/11] can: bcm: extend bcm_tx_lock usage for data and timer updates Oliver Hartkopp via B4 Relay
2026-07-09 20:22 ` [PATCH v12 07/11] can: bcm: validate frame length in bcm_rx_setup() for RTR replies Oliver Hartkopp via B4 Relay
2026-07-09 20:22 ` [PATCH v12 08/11] can: bcm: add missing device refcount for CAN filter removal Oliver Hartkopp via B4 Relay
2026-07-09 20:35   ` sashiko-bot
2026-07-09 20:22 ` [PATCH v12 09/11] can: bcm: fix stale rx/tx ops after device removal Oliver Hartkopp via B4 Relay
2026-07-09 20:40   ` sashiko-bot
2026-07-09 20:22 ` [PATCH v12 10/11] can: bcm: fix data race on rx_stamp/rx_ifindex in bcm_rx_handler() Oliver Hartkopp via B4 Relay
2026-07-09 20:44   ` sashiko-bot
2026-07-09 20:22 ` [PATCH v12 11/11] can: bcm: track a single source interface for ANYDEV timeout/throttle ops Oliver Hartkopp via B4 Relay

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox