[PATCH AUTOSEL for 4.9 127/190] bnx2x: Align RX buffers
From: Scott Wood[ Upstream commit 9b70de6d0266888b3743f03802502e43131043c8 ] The bnx2x driver is not providing proper alignment on the receive buffers it passes to build_skb(), causing skb_shared_info to be misaligned. skb_shared_info contains an atomic, and while PPC normally supports unaligned accesses, it does not support unaligned atomics. Aligning the size of rx buffers will ensure that page_frag_alloc() returns aligned addresses. This can be reproduced on PPC by setting the network MTU to 1450 (or other non-multiple-of-4) and then generating sufficient inbound network traffic (one or two large "wget"s usually does it), producing the following oops: Unable to handle kernel paging request for unaligned access at address 0xc0ffc43af656 Faulting instruction address: 0xc080ef8c Oops: Kernel access of bad area, sig: 7 [#1] SMP NR_CPUS=2048 NUMA PowerNV Modules linked in: vmx_crypto powernv_rng rng_core powernv_op_panel leds_powernv led_class nfsd ip_tables x_tables autofs4 xfs lpfc bnx2x mdio libcrc32c crc_t10dif crct10dif_generic crct10dif_common CPU: 104 PID: 0 Comm: swapper/104 Not tainted 4.11.0-rc8-00088-g4c761da #2 task: c0ffd4892400 task.stack: c0ffd492 NIP: c080ef8c LR: c080eee8 CTR: c01f8320 REGS: c0c33710 TRAP: 0600 Not tainted (4.11.0-rc8-00088-g4c761da) MSR: 90009033 CR: 24082042 XER: CFAR: c080eea0 DAR: c0ffc43af656 DSISR: SOFTE: 1 GPR00: c0907f64 c0c33990 c0dd3b00 c0ffcaf22100 GPR04: c0ffcaf22e00 GPR08: 00b80008 c0ffc43af636 c0ffc43af656 GPR12: c01f6f00 cfe1a000 049f c51f GPR16: ef33 8a43 0001 GPR20: c0ffc58a90c0 dd86 GPR24: c07fd0ed10c0 0158 014a GPR28: c0ffc43af010 c0ffc9144000 c0ffcaf22e00 c0ffcaf22100 NIP [c080ef8c] __skb_clone+0xdc/0x140 LR [c080eee8] __skb_clone+0x38/0x140 Call Trace: [c0c33990] [c080fb74] skb_clone+0x74/0x110 (unreliable) [c0c339c0] [c0907f64] packet_rcv+0x144/0x510 [c0c33a40] [c0827b64] __netif_receive_skb_core+0x5b4/0xd80 [c0c33b00] [c082b2bc] netif_receive_skb_internal+0x2c/0xc0 [c0c33b40] [c082c49c] napi_gro_receive+0x11c/0x260 [c0c33b80] [d00066483d68] bnx2x_poll+0xcf8/0x17b0 [bnx2x] [c0c33d00] [c082babc] net_rx_action+0x31c/0x480 [c0c33e10] [c00d5a44] __do_softirq+0x164/0x3d0 [c0c33f00] [c00d60a8] irq_exit+0x108/0x120 [c0c33f20] [c0015b98] __do_irq+0x98/0x200 [c0c33f90] [c0027f14] call_do_irq+0x14/0x24 [c0ffd4923a90] [c0015d94] do_IRQ+0x94/0x110 [c0ffd4923ae0] [c0008d90] hardware_interrupt_common+0x150/0x160 Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 0a5ee1d973ac..857fdfb0197b 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -2026,6 +2026,7 @@ static void bnx2x_set_rx_buf_size(struct bnx2x *bp) ETH_OVREHEAD + mtu + BNX2X_FW_RX_ALIGN_END; + fp->rx_buf_size = SKB_DATA_ALIGN(fp->rx_buf_size); /* Note : rx_buf_size doesn't take into account NET_SKB_PAD */ if (fp->rx_buf_size + NET_SKB_PAD <= PAGE_SIZE) fp->rx_frag_size = fp->rx_buf_size + NET_SKB_PAD; -- 2.14.1
[PATCH AUTOSEL for 4.9 127/190] bnx2x: Align RX buffers
From: Scott Wood [ Upstream commit 9b70de6d0266888b3743f03802502e43131043c8 ] The bnx2x driver is not providing proper alignment on the receive buffers it passes to build_skb(), causing skb_shared_info to be misaligned. skb_shared_info contains an atomic, and while PPC normally supports unaligned accesses, it does not support unaligned atomics. Aligning the size of rx buffers will ensure that page_frag_alloc() returns aligned addresses. This can be reproduced on PPC by setting the network MTU to 1450 (or other non-multiple-of-4) and then generating sufficient inbound network traffic (one or two large "wget"s usually does it), producing the following oops: Unable to handle kernel paging request for unaligned access at address 0xc0ffc43af656 Faulting instruction address: 0xc080ef8c Oops: Kernel access of bad area, sig: 7 [#1] SMP NR_CPUS=2048 NUMA PowerNV Modules linked in: vmx_crypto powernv_rng rng_core powernv_op_panel leds_powernv led_class nfsd ip_tables x_tables autofs4 xfs lpfc bnx2x mdio libcrc32c crc_t10dif crct10dif_generic crct10dif_common CPU: 104 PID: 0 Comm: swapper/104 Not tainted 4.11.0-rc8-00088-g4c761da #2 task: c0ffd4892400 task.stack: c0ffd492 NIP: c080ef8c LR: c080eee8 CTR: c01f8320 REGS: c0c33710 TRAP: 0600 Not tainted (4.11.0-rc8-00088-g4c761da) MSR: 90009033 CR: 24082042 XER: CFAR: c080eea0 DAR: c0ffc43af656 DSISR: SOFTE: 1 GPR00: c0907f64 c0c33990 c0dd3b00 c0ffcaf22100 GPR04: c0ffcaf22e00 GPR08: 00b80008 c0ffc43af636 c0ffc43af656 GPR12: c01f6f00 cfe1a000 049f c51f GPR16: ef33 8a43 0001 GPR20: c0ffc58a90c0 dd86 GPR24: c07fd0ed10c0 0158 014a GPR28: c0ffc43af010 c0ffc9144000 c0ffcaf22e00 c0ffcaf22100 NIP [c080ef8c] __skb_clone+0xdc/0x140 LR [c080eee8] __skb_clone+0x38/0x140 Call Trace: [c0c33990] [c080fb74] skb_clone+0x74/0x110 (unreliable) [c0c339c0] [c0907f64] packet_rcv+0x144/0x510 [c0c33a40] [c0827b64] __netif_receive_skb_core+0x5b4/0xd80 [c0c33b00] [c082b2bc] netif_receive_skb_internal+0x2c/0xc0 [c0c33b40] [c082c49c] napi_gro_receive+0x11c/0x260 [c0c33b80] [d00066483d68] bnx2x_poll+0xcf8/0x17b0 [bnx2x] [c0c33d00] [c082babc] net_rx_action+0x31c/0x480 [c0c33e10] [c00d5a44] __do_softirq+0x164/0x3d0 [c0c33f00] [c00d60a8] irq_exit+0x108/0x120 [c0c33f20] [c0015b98] __do_irq+0x98/0x200 [c0c33f90] [c0027f14] call_do_irq+0x14/0x24 [c0ffd4923a90] [c0015d94] do_IRQ+0x94/0x110 [c0ffd4923ae0] [c0008d90] hardware_interrupt_common+0x150/0x160 Signed-off-by: David S. Miller Signed-off-by: Sasha Levin --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 0a5ee1d973ac..857fdfb0197b 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -2026,6 +2026,7 @@ static void bnx2x_set_rx_buf_size(struct bnx2x *bp) ETH_OVREHEAD + mtu + BNX2X_FW_RX_ALIGN_END; + fp->rx_buf_size = SKB_DATA_ALIGN(fp->rx_buf_size); /* Note : rx_buf_size doesn't take into account NET_SKB_PAD */ if (fp->rx_buf_size + NET_SKB_PAD <= PAGE_SIZE) fp->rx_frag_size = fp->rx_buf_size + NET_SKB_PAD; -- 2.14.1