Sandor Bodo-Merle 1b7680c6c1 net: bgmac: Fix a BUG triggered by wrong bytes_compl ... On one of our machines we got: kernel BUG at lib/dynamic_queue_limits.c:27! Internal error: Oops - BUG: 0 [#1] PREEMPT SMP ARM CPU: 0 PID: 1166 Comm: irq/41-bgmac Tainted: G W O 4.14.275-rt132 #1 Hardware name: BRCM XGS iProc task: ee3415c0 task.stack: ee32a000 PC is at dql_completed+0x168/0x178 LR is at bgmac_poll+0x18c/0x6d8 pc : [<c03b9430>] lr : [<c04b5a18>] psr: 800a0313 sp : ee32be14 ip : 000005ea fp : 00000bd4 r10: ee558500 r9 : c0116298 r8 : 00000002 r7 : 00000000 r6 : ef128810 r5 : 01993267 r4 : 01993851 r3 : ee558000 r2 : 000070e1 r1 : 00000bd4 r0 : ee52c180 Flags: Nzcv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none Control: 12c5387d Table: 8e88c04a DAC: 00000051 Process irq/41-bgmac (pid: 1166, stack limit = 0xee32a210) Stack: (0xee32be14 to 0xee32c000) be00: ee558520 ee52c100 ef128810 be20: 00000000 00000002 c0116298 c04b5a18 00000000 c0a0c8c4 c0951780 00000040 be40: c0701780 ee558500 ee55d520 ef05b340 ef6f9780 ee558520 00000001 00000040 be60: ffffe000 c0a56878 ef6fa040 c0952040 0000012c c0528744 ef6f97b0 fffcfb6a be80: c0a04104 2eda8000 c0a0c4ec c0a0d368 ee32bf44 c0153534 ee32be98 ee32be98 bea0: ee32bea0 ee32bea0 ee32bea8 ee32bea8 00000000 c01462e4 ffffe000 ef6f22a8 bec0: ffffe000 00000008 ee32bee4 c0147430 ffffe000 c094a2a8 00000003 ffffe000 bee0: c0a54528 00208040 0000000c c0a0c8c4 c0a65980 c0124d3c 00000008 ee558520 bf00: c094a23c c0a02080 00000000 c07a9910 ef136970 ef136970 ee30a440 ef136900 bf20: ee30a440 00000001 ef136900 ee30a440 c016d990 00000000 c0108db0 c012500c bf40: ef136900 c016da14 ee30a464 ffffe000 00000001 c016dd14 00000000 c016db28 bf60: ffffe000 ee21a080 ee30a400 00000000 ee32a000 ee30a440 c016dbfc ee25fd70 bf80: ee21a09c c013edcc ee32a000 ee30a400 c013ec7c 00000000 00000000 00000000 bfa0: 00000000 00000000 00000000 c0108470 00000000 00000000 00000000 00000000 bfc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 bfe0: 00000000 00000000 00000000 00000000 00000013 00000000 00000000 00000000 [<c03b9430>] (dql_completed) from [<c04b5a18>] (bgmac_poll+0x18c/0x6d8) [<c04b5a18>] (bgmac_poll) from [<c0528744>] (net_rx_action+0x1c4/0x494) [<c0528744>] (net_rx_action) from [<c0124d3c>] (do_current_softirqs+0x1ec/0x43c) [<c0124d3c>] (do_current_softirqs) from [<c012500c>] (__local_bh_enable+0x80/0x98) [<c012500c>] (__local_bh_enable) from [<c016da14>] (irq_forced_thread_fn+0x84/0x98) [<c016da14>] (irq_forced_thread_fn) from [<c016dd14>] (irq_thread+0x118/0x1c0) [<c016dd14>] (irq_thread) from [<c013edcc>] (kthread+0x150/0x158) [<c013edcc>] (kthread) from [<c0108470>] (ret_from_fork+0x14/0x24) Code: a83f15e0 0200001a 0630a0e1 c3ffffea (f201f0e7) The issue seems similar to commit 90b3b33936 ("net: hisilicon: Fix a BUG trigered by wrong bytes_compl") and potentially introduced by commit b38c83dd08 ("bgmac: simplify tx ring index handling"). If there is an RX interrupt between setting ring->end and netdev_sent_queue() we can hit the BUG_ON as bgmac_dma_tx_free() can miscalculate the queue size while called from bgmac_poll(). The machine which triggered the BUG runs a v4.14 RT kernel - but the issue seems present in mainline too. Fixes: b38c83dd08 ("bgmac: simplify tx ring index handling") Signed-off-by: Sandor Bodo-Merle <sbodomerle@gmail.com> Reviewed-by: Florian Fainelli <f.fainelli@gmail.com> Link: https://lore.kernel.org/r/20220808173939.193804-1-sbodomerle@gmail.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>		2022-08-09 12:15:44 -07:00
..
bnx2x	net: add skb_[inner_]tcp_all_headers helpers	2022-07-02 16:22:25 +01:00
bnxt	bnxt_en: Remove duplicated include bnxt_devlink.c	2022-08-05 18:53:07 -07:00
genet	net: bcmgenet: Indicate MAC is in charge of PHY PM	2022-08-05 19:02:18 -07:00
b44.c	ethtool: extend ringparam setting/getting API with rx_buf_len	2021-11-22 12:31:49 +00:00
b44.h
bcm63xx_enet.c	bcm63xx: fix Tx cleanup when NAPI poll budget is zero	2022-07-11 11:36:32 -07:00
bcm63xx_enet.h
bcm4908_enet.c	net: switch to netif_napi_add_tx()	2022-05-05 15:54:12 -07:00
bcm4908_enet.h
bcmsysport.c	Bitmap patches for 5.19-rc1	2022-06-04 14:04:27 -07:00
bcmsysport.h	net: systemport: Add global locking for descriptor lifecycle	2021-12-16 08:15:31 -08:00
bgmac-bcma-mdio.c	net: ethernet: bgmac: Fix refcount leak in bcma_mdio_mii_register	2022-06-06 14:38:15 -07:00
bgmac-bcma.c	net: bgmac: Fix an erroneous kfree() in bgmac_remove()	2022-06-14 19:16:36 -07:00
bgmac-platform.c	Revert "net: ethernet: bgmac: Use devm_platform_ioremap_resource_byname"	2022-02-17 08:45:34 -08:00
bgmac.c	net: bgmac: Fix a BUG triggered by wrong bytes_compl	2022-08-09 12:15:44 -07:00
bgmac.h	net: bgmac: remove a copy of the NAPI_POLL_WEIGHT define	2022-04-29 11:56:41 +01:00
bnx2_fw.h
bnx2.c	bnx2: Fix an error message	2022-03-03 14:48:40 +00:00
bnx2.h
cnic_defs.h
cnic_if.h
cnic.c	cnic: Use the bitmap API to allocate bitmaps	2022-07-06 19:55:04 -07:00
cnic.h
Kconfig	ethernet: fix PTP_1588_CLOCK dependencies	2021-08-13 17:49:05 -07:00
Makefile	eth: tg3: silence the GCC 12 array-bounds warning	2022-05-22 22:21:11 +01:00
sb1250-mac.c	eth: switch to netif_napi_add_weight()	2022-05-08 11:33:57 +01:00
tg3.c	net: add skb_[inner_]tcp_all_headers helpers	2022-07-02 16:22:25 +01:00
tg3.h	tg3: Read VPD with pci_vpd_alloc()	2021-08-20 15:49:00 -05:00
unimac.h