From d0fbdc3ae9ecc614ddffde55dccbcacef353da0b Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Fri, 25 Oct 2024 16:26:27 +0200 Subject: [PATCH 01/16] mlxsw: pci: Sync Rx buffers for device Non-coherent architectures, like ARM, may require invalidating caches before the device can use the DMA mapped memory, which means that before posting pages to device, drivers should sync the memory for device. Sync for device can be configured as page pool responsibility. Set the relevant flag and define max_len for sync. Cc: Jiri Pirko Fixes: b5b60bb491b2 ("mlxsw: pci: Use page pool for Rx buffers allocation") Signed-off-by: Amit Cohen Reviewed-by: Ido Schimmel Signed-off-by: Petr Machata Link: https://patch.msgid.link/92e01f05c4f506a4f0a9b39c10175dcc01994910.1729866134.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlxsw/pci.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 2320a5f323b4..d6f37456fb31 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -996,12 +996,13 @@ static int mlxsw_pci_cq_page_pool_init(struct mlxsw_pci_queue *q, if (cq_type != MLXSW_PCI_CQ_RDQ) return 0; - pp_params.flags = PP_FLAG_DMA_MAP; + pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV; pp_params.pool_size = MLXSW_PCI_WQE_COUNT * mlxsw_pci->num_sg_entries; pp_params.nid = dev_to_node(&mlxsw_pci->pdev->dev); pp_params.dev = &mlxsw_pci->pdev->dev; pp_params.napi = &q->u.cq.napi; pp_params.dma_dir = DMA_FROM_DEVICE; + pp_params.max_len = PAGE_SIZE; page_pool = page_pool_create(&pp_params); if (IS_ERR(page_pool)) -- 2.51.0 From 12ae97c531fcd3bfd774d4dfeaeac23eafe24280 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 25 Oct 2024 16:26:28 +0200 Subject: [PATCH 02/16] mlxsw: spectrum_ipip: Fix memory leak when changing remote IPv6 address The device stores IPv6 addresses that are used for encapsulation in linear memory that is managed by the driver. Changing the remote address of an ip6gre net device never worked properly, but since cited commit the following reproducer [1] would result in a warning [2] and a memory leak [3]. The problem is that the new remote address is never added by the driver to its hash table (and therefore the device) and the old address is never removed from it. Fix by programming the new address when the configuration of the ip6gre net device changes and removing the old one. If the address did not change, then the above would result in increasing the reference count of the address and then decreasing it. [1] # ip link add name bla up type ip6gre local 2001:db8:1::1 remote 2001:db8:2::1 tos inherit ttl inherit # ip link set dev bla type ip6gre remote 2001:db8:3::1 # ip link del dev bla # devlink dev reload pci/0000:01:00.0 [2] WARNING: CPU: 0 PID: 1682 at drivers/net/ethernet/mellanox/mlxsw/spectrum.c:3002 mlxsw_sp_ipv6_addr_put+0x140/0x1d0 Modules linked in: CPU: 0 UID: 0 PID: 1682 Comm: ip Not tainted 6.12.0-rc3-custom-g86b5b55bc835 #151 Hardware name: Nvidia SN5600/VMOD0013, BIOS 5.13 05/31/2023 RIP: 0010:mlxsw_sp_ipv6_addr_put+0x140/0x1d0 [...] Call Trace: mlxsw_sp_router_netdevice_event+0x55f/0x1240 notifier_call_chain+0x5a/0xd0 call_netdevice_notifiers_info+0x39/0x90 unregister_netdevice_many_notify+0x63e/0x9d0 rtnl_dellink+0x16b/0x3a0 rtnetlink_rcv_msg+0x142/0x3f0 netlink_rcv_skb+0x50/0x100 netlink_unicast+0x242/0x390 netlink_sendmsg+0x1de/0x420 ____sys_sendmsg+0x2bd/0x320 ___sys_sendmsg+0x9a/0xe0 __sys_sendmsg+0x7a/0xd0 do_syscall_64+0x9e/0x1a0 entry_SYSCALL_64_after_hwframe+0x77/0x7f [3] unreferenced object 0xffff898081f597a0 (size 32): comm "ip", pid 1626, jiffies 4294719324 hex dump (first 32 bytes): 20 01 0d b8 00 02 00 00 00 00 00 00 00 00 00 01 ............... 21 49 61 83 80 89 ff ff 00 00 00 00 01 00 00 00 !Ia............. backtrace (crc fd9be911): [<00000000df89c55d>] __kmalloc_cache_noprof+0x1da/0x260 [<00000000ff2a1ddb>] mlxsw_sp_ipv6_addr_kvdl_index_get+0x281/0x340 [<000000009ddd445d>] mlxsw_sp_router_netdevice_event+0x47b/0x1240 [<00000000743e7757>] notifier_call_chain+0x5a/0xd0 [<000000007c7b9e13>] call_netdevice_notifiers_info+0x39/0x90 [<000000002509645d>] register_netdevice+0x5f7/0x7a0 [<00000000c2e7d2a9>] ip6gre_newlink_common.isra.0+0x65/0x130 [<0000000087cd6d8d>] ip6gre_newlink+0x72/0x120 [<000000004df7c7cc>] rtnl_newlink+0x471/0xa20 [<0000000057ed632a>] rtnetlink_rcv_msg+0x142/0x3f0 [<0000000032e0d5b5>] netlink_rcv_skb+0x50/0x100 [<00000000908bca63>] netlink_unicast+0x242/0x390 [<00000000cdbe1c87>] netlink_sendmsg+0x1de/0x420 [<0000000011db153e>] ____sys_sendmsg+0x2bd/0x320 [<000000003b6d53eb>] ___sys_sendmsg+0x9a/0xe0 [<00000000cae27c62>] __sys_sendmsg+0x7a/0xd0 Fixes: cf42911523e0 ("mlxsw: spectrum_ipip: Use common hash table for IPv6 address mapping") Reported-by: Maksym Yaremchuk Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: Petr Machata Link: https://patch.msgid.link/e91012edc5a6cb9df37b78fd377f669381facfcb.1729866134.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski --- .../ethernet/mellanox/mlxsw/spectrum_ipip.c | 26 +++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c index d761a1235994..7ea798a4949e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c @@ -481,11 +481,33 @@ mlxsw_sp_ipip_ol_netdev_change_gre6(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_ipip_entry *ipip_entry, struct netlink_ext_ack *extack) { + u32 new_kvdl_index, old_kvdl_index = ipip_entry->dip_kvdl_index; + struct in6_addr old_addr6 = ipip_entry->parms.daddr.addr6; struct mlxsw_sp_ipip_parms new_parms; + int err; new_parms = mlxsw_sp_ipip_netdev_parms_init_gre6(ipip_entry->ol_dev); - return mlxsw_sp_ipip_ol_netdev_change_gre(mlxsw_sp, ipip_entry, - &new_parms, extack); + + err = mlxsw_sp_ipv6_addr_kvdl_index_get(mlxsw_sp, + &new_parms.daddr.addr6, + &new_kvdl_index); + if (err) + return err; + ipip_entry->dip_kvdl_index = new_kvdl_index; + + err = mlxsw_sp_ipip_ol_netdev_change_gre(mlxsw_sp, ipip_entry, + &new_parms, extack); + if (err) + goto err_change_gre; + + mlxsw_sp_ipv6_addr_put(mlxsw_sp, &old_addr6); + + return 0; + +err_change_gre: + ipip_entry->dip_kvdl_index = old_kvdl_index; + mlxsw_sp_ipv6_addr_put(mlxsw_sp, &new_parms.daddr.addr6); + return err; } static int -- 2.51.0 From d7bd61fa0222db1cdc01d66bec2477c9fdfa6d4f Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Fri, 25 Oct 2024 16:26:29 +0200 Subject: [PATCH 03/16] selftests: forwarding: Add IPv6 GRE remote change tests Test that after changing the remote address of an ip6gre net device traffic is forwarded as expected. Test with both flat and hierarchical topologies and with and without an input / output keys. Signed-off-by: Ido Schimmel Reviewed-by: Petr Machata Signed-off-by: Petr Machata Link: https://patch.msgid.link/02b05246d2cdada0cf2fccffc0faa8a424d0f51b.1729866134.git.petrm@nvidia.com Signed-off-by: Jakub Kicinski --- .../selftests/net/forwarding/ip6gre_flat.sh | 14 ++++ .../net/forwarding/ip6gre_flat_key.sh | 14 ++++ .../net/forwarding/ip6gre_flat_keys.sh | 14 ++++ .../selftests/net/forwarding/ip6gre_hier.sh | 14 ++++ .../net/forwarding/ip6gre_hier_key.sh | 14 ++++ .../net/forwarding/ip6gre_hier_keys.sh | 14 ++++ .../selftests/net/forwarding/ip6gre_lib.sh | 80 +++++++++++++++++++ 7 files changed, 164 insertions(+) diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat.sh index 96c97064f2d3..becc7c3fc809 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_flat.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat.sh @@ -8,6 +8,7 @@ ALL_TESTS=" gre_flat gre_mtu_change + gre_flat_remote_change " NUM_NETIFS=6 @@ -44,6 +45,19 @@ gre_mtu_change() test_mtu_change } +gre_flat_remote_change() +{ + flat_remote_change + + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 (new remote)" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 (new remote)" + + flat_remote_restore + + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 (old remote)" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 (old remote)" +} + cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh index ff9fb0db9bd1..e5335116a2fd 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh @@ -8,6 +8,7 @@ ALL_TESTS=" gre_flat gre_mtu_change + gre_flat_remote_change " NUM_NETIFS=6 @@ -44,6 +45,19 @@ gre_mtu_change() test_mtu_change } +gre_flat_remote_change() +{ + flat_remote_change + + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with key (new remote)" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with key (new remote)" + + flat_remote_restore + + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with key (old remote)" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with key (old remote)" +} + cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh index 12c138785242..7e0cbfdefab0 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh @@ -8,6 +8,7 @@ ALL_TESTS=" gre_flat gre_mtu_change + gre_flat_remote_change " NUM_NETIFS=6 @@ -44,6 +45,19 @@ gre_mtu_change() test_mtu_change gre } +gre_flat_remote_change() +{ + flat_remote_change + + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with ikey/okey (new remote)" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with ikey/okey (new remote)" + + flat_remote_restore + + test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with ikey/okey (old remote)" + test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with ikey/okey (old remote)" +} + cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier.sh index 83b55c30a5c3..e0844495f3d1 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_hier.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier.sh @@ -8,6 +8,7 @@ ALL_TESTS=" gre_hier gre_mtu_change + gre_hier_remote_change " NUM_NETIFS=6 @@ -44,6 +45,19 @@ gre_mtu_change() test_mtu_change gre } +gre_hier_remote_change() +{ + hier_remote_change + + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 (new remote)" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 (new remote)" + + hier_remote_restore + + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 (old remote)" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 (old remote)" +} + cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh index 256607916d92..741bc9c928eb 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh @@ -8,6 +8,7 @@ ALL_TESTS=" gre_hier gre_mtu_change + gre_hier_remote_change " NUM_NETIFS=6 @@ -44,6 +45,19 @@ gre_mtu_change() test_mtu_change gre } +gre_hier_remote_change() +{ + hier_remote_change + + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with key (new remote)" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with key (new remote)" + + hier_remote_restore + + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with key (old remote)" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with key (old remote)" +} + cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh index ad1bcd6334a8..ad9eab4b1367 100755 --- a/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh @@ -8,6 +8,7 @@ ALL_TESTS=" gre_hier gre_mtu_change + gre_hier_remote_change " NUM_NETIFS=6 @@ -44,6 +45,19 @@ gre_mtu_change() test_mtu_change gre } +gre_hier_remote_change() +{ + hier_remote_change + + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with ikey/okey (new remote)" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with ikey/okey (new remote)" + + hier_remote_restore + + test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with ikey/okey (old remote)" + test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with ikey/okey (old remote)" +} + cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/forwarding/ip6gre_lib.sh b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh index 24f4ab328bd2..2d91281dc5b7 100644 --- a/tools/testing/selftests/net/forwarding/ip6gre_lib.sh +++ b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh @@ -436,3 +436,83 @@ test_mtu_change() check_err $? log_test "ping GRE IPv6, packet size 1800 after MTU change" } + +topo_flat_remote_change() +{ + local old1=$1; shift + local new1=$1; shift + local old2=$1; shift + local new2=$1; shift + + ip link set dev g1a type ip6gre local $new1 remote $new2 + __addr_add_del g1a add "$new1/128" + __addr_add_del g1a del "$old1/128" + ip -6 route add $new2/128 via 2001:db8:10::2 + ip -6 route del $old2/128 + + ip link set dev g2a type ip6gre local $new2 remote $new1 + __addr_add_del g2a add "$new2/128" + __addr_add_del g2a del "$old2/128" + ip -6 route add vrf v$ol2 $new1/128 via 2001:db8:10::1 + ip -6 route del vrf v$ol2 $old1/128 +} + +flat_remote_change() +{ + local old1=2001:db8:3::1 + local new1=2001:db8:3::10 + local old2=2001:db8:3::2 + local new2=2001:db8:3::20 + + topo_flat_remote_change $old1 $new1 $old2 $new2 +} + +flat_remote_restore() +{ + local old1=2001:db8:3::10 + local new1=2001:db8:3::1 + local old2=2001:db8:3::20 + local new2=2001:db8:3::2 + + topo_flat_remote_change $old1 $new1 $old2 $new2 +} + +topo_hier_remote_change() +{ + local old1=$1; shift + local new1=$1; shift + local old2=$1; shift + local new2=$1; shift + + __addr_add_del dummy1 del "$old1/64" + __addr_add_del dummy1 add "$new1/64" + ip link set dev g1a type ip6gre local $new1 remote $new2 + ip -6 route add vrf v$ul1 $new2/128 via 2001:db8:10::2 + ip -6 route del vrf v$ul1 $old2/128 + + __addr_add_del dummy2 del "$old2/64" + __addr_add_del dummy2 add "$new2/64" + ip link set dev g2a type ip6gre local $new2 remote $new1 + ip -6 route add vrf v$ul2 $new1/128 via 2001:db8:10::1 + ip -6 route del vrf v$ul2 $old1/128 +} + +hier_remote_change() +{ + local old1=2001:db8:3::1 + local new1=2001:db8:3::10 + local old2=2001:db8:3::2 + local new2=2001:db8:3::20 + + topo_hier_remote_change $old1 $new1 $old2 $new2 +} + +hier_remote_restore() +{ + local old1=2001:db8:3::10 + local new1=2001:db8:3::1 + local old2=2001:db8:3::20 + local new2=2001:db8:3::2 + + topo_hier_remote_change $old1 $new1 $old2 $new2 +} -- 2.51.0 From 637f41476384c76d3cd7dcf5947caf2c8b8d7a9b Mon Sep 17 00:00:00 2001 From: Daniel Golle Date: Sat, 26 Oct 2024 14:52:25 +0100 Subject: [PATCH 04/16] net: ethernet: mtk_wed: fix path of MT7988 WO firmware linux-firmware commit 808cba84 ("mtk_wed: add firmware for mt7988 Wireless Ethernet Dispatcher") added mt7988_wo_{0,1}.bin in the 'mediatek/mt7988' directory while driver current expects the files in the 'mediatek' directory. Change path in the driver header now that the firmware has been added. Fixes: e2f64db13aa1 ("net: ethernet: mtk_wed: introduce WED support for MT7988") Signed-off-by: Daniel Golle Reviewed-by: Andrew Lunn Reviewed-by: AngeloGioacchino Del Regno Link: https://patch.msgid.link/Zxz0GWTR5X5LdWPe@pidgin.makrotopia.org Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mediatek/mtk_wed_wo.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.h b/drivers/net/ethernet/mediatek/mtk_wed_wo.h index 87a67fa3868d..c01b1e8428f6 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_wo.h +++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.h @@ -91,8 +91,8 @@ enum mtk_wed_dummy_cr_idx { #define MT7981_FIRMWARE_WO "mediatek/mt7981_wo.bin" #define MT7986_FIRMWARE_WO0 "mediatek/mt7986_wo_0.bin" #define MT7986_FIRMWARE_WO1 "mediatek/mt7986_wo_1.bin" -#define MT7988_FIRMWARE_WO0 "mediatek/mt7988_wo_0.bin" -#define MT7988_FIRMWARE_WO1 "mediatek/mt7988_wo_1.bin" +#define MT7988_FIRMWARE_WO0 "mediatek/mt7988/mt7988_wo_0.bin" +#define MT7988_FIRMWARE_WO1 "mediatek/mt7988/mt7988_wo_1.bin" #define MTK_WO_MCU_CFG_LS_BASE 0 #define MTK_WO_MCU_CFG_LS_HW_VER_ADDR (MTK_WO_MCU_CFG_LS_BASE + 0x000) -- 2.51.0 From d5953d680f7e96208c29ce4139a0e38de87a57fe Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 30 Oct 2024 23:13:48 +0100 Subject: [PATCH 05/16] netfilter: nft_payload: sanitize offset and length before calling skb_checksum() If access to offset + length is larger than the skbuff length, then skb_checksum() triggers BUG_ON(). skb_checksum() internally subtracts the length parameter while iterating over skbuff, BUG_ON(len) at the end of it checks that the expected length to be included in the checksum calculation is fully consumed. Fixes: 7ec3f7b47b8d ("netfilter: nft_payload: add packet mangling support") Reported-by: Slavin Liu Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_payload.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 330609a76fb2..7dfc5343dae4 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -904,6 +904,9 @@ static void nft_payload_set_eval(const struct nft_expr *expr, ((priv->base != NFT_PAYLOAD_TRANSPORT_HEADER && priv->base != NFT_PAYLOAD_INNER_HEADER) || skb->ip_summed != CHECKSUM_PARTIAL)) { + if (offset + priv->len > skb->len) + goto err; + fsum = skb_checksum(skb, offset, priv->len, 0); tsum = csum_partial(src, priv->len, 0); -- 2.51.0 From e6ab19443b36a45ebfb392775cb17d6a78dd07ea Mon Sep 17 00:00:00 2001 From: Peiyang Wang Date: Fri, 25 Oct 2024 17:29:30 +0800 Subject: [PATCH 06/16] net: hns3: default enable tx bounce buffer when smmu enabled The SMMU engine on HIP09 chip has a hardware issue. SMMU pagetable prefetch features may prefetch and use a invalid PTE even the PTE is valid at that time. This will cause the device trigger fake pagefaults. The solution is to avoid prefetching by adding a SYNC command when smmu mapping a iova. But the performance of nic has a sharp drop. Then we do this workaround, always enable tx bounce buffer, avoid mapping/unmapping on TX path. This issue only affects HNS3, so we always enable tx bounce buffer when smmu enabled to improve performance. Fixes: 295ba232a8c3 ("net: hns3: add device version to replace pci revision") Signed-off-by: Peiyang Wang Signed-off-by: Jian Shen Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni --- .../net/ethernet/hisilicon/hns3/hns3_enet.c | 31 +++++++++++++++++ .../net/ethernet/hisilicon/hns3/hns3_enet.h | 2 ++ .../ethernet/hisilicon/hns3/hns3_ethtool.c | 33 +++++++++++++++++++ 3 files changed, 66 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 4cbc4d069a1f..ac88e301f221 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -1032,6 +1033,8 @@ static bool hns3_can_use_tx_sgl(struct hns3_enet_ring *ring, static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring) { u32 alloc_size = ring->tqp->handle->kinfo.tx_spare_buf_size; + struct net_device *netdev = ring_to_netdev(ring); + struct hns3_nic_priv *priv = netdev_priv(netdev); struct hns3_tx_spare *tx_spare; struct page *page; dma_addr_t dma; @@ -1073,6 +1076,7 @@ static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring) tx_spare->buf = page_address(page); tx_spare->len = PAGE_SIZE << order; ring->tx_spare = tx_spare; + ring->tx_copybreak = priv->tx_copybreak; return; dma_mapping_error: @@ -4868,6 +4872,30 @@ static void hns3_nic_dealloc_vector_data(struct hns3_nic_priv *priv) devm_kfree(&pdev->dev, priv->tqp_vector); } +static void hns3_update_tx_spare_buf_config(struct hns3_nic_priv *priv) +{ +#define HNS3_MIN_SPARE_BUF_SIZE (2 * 1024 * 1024) +#define HNS3_MAX_PACKET_SIZE (64 * 1024) + + struct iommu_domain *domain = iommu_get_domain_for_dev(priv->dev); + struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(priv->ae_handle); + struct hnae3_handle *handle = priv->ae_handle; + + if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3) + return; + + if (!(domain && iommu_is_dma_domain(domain))) + return; + + priv->min_tx_copybreak = HNS3_MAX_PACKET_SIZE; + priv->min_tx_spare_buf_size = HNS3_MIN_SPARE_BUF_SIZE; + + if (priv->tx_copybreak < priv->min_tx_copybreak) + priv->tx_copybreak = priv->min_tx_copybreak; + if (handle->kinfo.tx_spare_buf_size < priv->min_tx_spare_buf_size) + handle->kinfo.tx_spare_buf_size = priv->min_tx_spare_buf_size; +} + static void hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv, unsigned int ring_type) { @@ -5101,6 +5129,7 @@ int hns3_init_all_ring(struct hns3_nic_priv *priv) int i, j; int ret; + hns3_update_tx_spare_buf_config(priv); for (i = 0; i < ring_num; i++) { ret = hns3_alloc_ring_memory(&priv->ring[i]); if (ret) { @@ -5305,6 +5334,8 @@ static int hns3_client_init(struct hnae3_handle *handle) priv->ae_handle = handle; priv->tx_timeout_count = 0; priv->max_non_tso_bd_num = ae_dev->dev_specs.max_non_tso_bd_num; + priv->min_tx_copybreak = 0; + priv->min_tx_spare_buf_size = 0; set_bit(HNS3_NIC_STATE_DOWN, &priv->state); handle->msg_enable = netif_msg_init(debug, DEFAULT_MSG_LEVEL); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index d36c4ed16d8d..caf7a4df8585 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -596,6 +596,8 @@ struct hns3_nic_priv { struct hns3_enet_coalesce rx_coal; u32 tx_copybreak; u32 rx_copybreak; + u32 min_tx_copybreak; + u32 min_tx_spare_buf_size; }; union l3_hdr_info { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index b1e988347347..97eaeec1952b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -1933,6 +1933,31 @@ static int hns3_set_tx_spare_buf_size(struct net_device *netdev, return ret; } +static int hns3_check_tx_copybreak(struct net_device *netdev, u32 copybreak) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + + if (copybreak < priv->min_tx_copybreak) { + netdev_err(netdev, "tx copybreak %u should be no less than %u!\n", + copybreak, priv->min_tx_copybreak); + return -EINVAL; + } + return 0; +} + +static int hns3_check_tx_spare_buf_size(struct net_device *netdev, u32 buf_size) +{ + struct hns3_nic_priv *priv = netdev_priv(netdev); + + if (buf_size < priv->min_tx_spare_buf_size) { + netdev_err(netdev, + "tx spare buf size %u should be no less than %u!\n", + buf_size, priv->min_tx_spare_buf_size); + return -EINVAL; + } + return 0; +} + static int hns3_set_tunable(struct net_device *netdev, const struct ethtool_tunable *tuna, const void *data) @@ -1949,6 +1974,10 @@ static int hns3_set_tunable(struct net_device *netdev, switch (tuna->id) { case ETHTOOL_TX_COPYBREAK: + ret = hns3_check_tx_copybreak(netdev, *(u32 *)data); + if (ret) + return ret; + priv->tx_copybreak = *(u32 *)data; for (i = 0; i < h->kinfo.num_tqps; i++) @@ -1963,6 +1992,10 @@ static int hns3_set_tunable(struct net_device *netdev, break; case ETHTOOL_TX_COPYBREAK_BUF_SIZE: + ret = hns3_check_tx_spare_buf_size(netdev, *(u32 *)data); + if (ret) + return ret; + old_tx_spare_buf_size = h->kinfo.tx_spare_buf_size; new_tx_spare_buf_size = *(u32 *)data; netdev_info(netdev, "request to set tx spare buf size from %u to %u\n", -- 2.51.0 From f2c14899caba76da93ff3fff46b4d5a8f43ce07e Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Fri, 25 Oct 2024 17:29:31 +0800 Subject: [PATCH 07/16] net: hns3: add sync command to sync io-pgtable To avoid errors in pgtable prefectch, add a sync command to sync io-pagtable. This is a supplement for the previous patch. We want all the tx packet can be handled with tx bounce buffer path. But it depends on the remain space of the spare buffer, checked by the hns3_can_use_tx_bounce(). In most cases, maybe 99.99%, it returns true. But once it return false by no available space, the packet will be handled with the former path, which will map/unmap the skb buffer. Then the driver will face the smmu prefetch risk again. So add a sync command in this case to avoid smmu prefectch, just protects corner scenes. Fixes: 295ba232a8c3 ("net: hns3: add device version to replace pci revision") Signed-off-by: Jian Shen Signed-off-by: Peiyang Wang Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni --- .../net/ethernet/hisilicon/hns3/hns3_enet.c | 27 +++++++++++++++++++ 1 file changed, 27 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index ac88e301f221..8760b4e9ade6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -381,6 +381,24 @@ static const struct hns3_rx_ptype hns3_rx_ptype_tbl[] = { #define HNS3_INVALID_PTYPE \ ARRAY_SIZE(hns3_rx_ptype_tbl) +static void hns3_dma_map_sync(struct device *dev, unsigned long iova) +{ + struct iommu_domain *domain = iommu_get_domain_for_dev(dev); + struct iommu_iotlb_gather iotlb_gather; + size_t granule; + + if (!domain || !iommu_is_dma_domain(domain)) + return; + + granule = 1 << __ffs(domain->pgsize_bitmap); + iova = ALIGN_DOWN(iova, granule); + iotlb_gather.start = iova; + iotlb_gather.end = iova + granule - 1; + iotlb_gather.pgsize = granule; + + iommu_iotlb_sync(domain, &iotlb_gather); +} + static irqreturn_t hns3_irq_handle(int irq, void *vector) { struct hns3_enet_tqp_vector *tqp_vector = vector; @@ -1728,7 +1746,9 @@ static int hns3_map_and_fill_desc(struct hns3_enet_ring *ring, void *priv, unsigned int type) { struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use]; + struct hnae3_handle *handle = ring->tqp->handle; struct device *dev = ring_to_dev(ring); + struct hnae3_ae_dev *ae_dev; unsigned int size; dma_addr_t dma; @@ -1760,6 +1780,13 @@ static int hns3_map_and_fill_desc(struct hns3_enet_ring *ring, void *priv, return -ENOMEM; } + /* Add a SYNC command to sync io-pgtale to avoid errors in pgtable + * prefetch + */ + ae_dev = hns3_get_ae_dev(handle); + if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3) + hns3_dma_map_sync(dev, dma); + desc_cb->priv = priv; desc_cb->length = size; desc_cb->dma = dma; -- 2.51.0 From 3e0f7cc887b77603182dceca4d3a6e84f6a40d0a Mon Sep 17 00:00:00 2001 From: Hao Lan Date: Fri, 25 Oct 2024 17:29:32 +0800 Subject: [PATCH 08/16] net: hns3: fixed reset failure issues caused by the incorrect reset type When a reset type that is not supported by the driver is input, a reset pending flag bit of the HNAE3_NONE_RESET type is generated in reset_pending. The driver does not have a mechanism to clear this type of error. As a result, the driver considers that the reset is not complete. This patch provides a mechanism to clear the HNAE3_NONE_RESET flag and the parameter of hnae3_ae_ops.set_default_reset_request is verified. The error message: hns3 0000:39:01.0: cmd failed -16 hns3 0000:39:01.0: hclge device re-init failed, VF is disabled! hns3 0000:39:01.0: failed to reset VF stack hns3 0000:39:01.0: failed to reset VF(4) hns3 0000:39:01.0: prepare reset(2) wait done hns3 0000:39:01.0 eth4: already uninitialized Use the crash tool to view struct hclgevf_dev: struct hclgevf_dev { ... default_reset_request = 0x20, reset_level = HNAE3_NONE_RESET, reset_pending = 0x100, reset_type = HNAE3_NONE_RESET, ... }; Fixes: 720bd5837e37 ("net: hns3: add set_default_reset_request in the hnae3_ae_ops") Signed-off-by: Hao Lan Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni --- .../hisilicon/hns3/hns3pf/hclge_main.c | 33 ++++++++++++++-- .../hisilicon/hns3/hns3vf/hclgevf_main.c | 38 ++++++++++++++++--- 2 files changed, 61 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index bd86efd92a5a..35c618c794be 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -3584,6 +3584,17 @@ static int hclge_set_vf_link_state(struct hnae3_handle *handle, int vf, return ret; } +static void hclge_set_reset_pending(struct hclge_dev *hdev, + enum hnae3_reset_type reset_type) +{ + /* When an incorrect reset type is executed, the get_reset_level + * function generates the HNAE3_NONE_RESET flag. As a result, this + * type do not need to pending. + */ + if (reset_type != HNAE3_NONE_RESET) + set_bit(reset_type, &hdev->reset_pending); +} + static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) { u32 cmdq_src_reg, msix_src_reg, hw_err_src_reg; @@ -3604,7 +3615,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) */ if (BIT(HCLGE_VECTOR0_IMPRESET_INT_B) & msix_src_reg) { dev_info(&hdev->pdev->dev, "IMP reset interrupt\n"); - set_bit(HNAE3_IMP_RESET, &hdev->reset_pending); + hclge_set_reset_pending(hdev, HNAE3_IMP_RESET); set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state); *clearval = BIT(HCLGE_VECTOR0_IMPRESET_INT_B); hdev->rst_stats.imp_rst_cnt++; @@ -3614,7 +3625,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) if (BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B) & msix_src_reg) { dev_info(&hdev->pdev->dev, "global reset interrupt\n"); set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state); - set_bit(HNAE3_GLOBAL_RESET, &hdev->reset_pending); + hclge_set_reset_pending(hdev, HNAE3_GLOBAL_RESET); *clearval = BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B); hdev->rst_stats.global_rst_cnt++; return HCLGE_VECTOR0_EVENT_RST; @@ -4062,7 +4073,7 @@ static void hclge_do_reset(struct hclge_dev *hdev) case HNAE3_FUNC_RESET: dev_info(&pdev->dev, "PF reset requested\n"); /* schedule again to check later */ - set_bit(HNAE3_FUNC_RESET, &hdev->reset_pending); + hclge_set_reset_pending(hdev, HNAE3_FUNC_RESET); hclge_reset_task_schedule(hdev); break; default: @@ -4096,6 +4107,8 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hnae3_ae_dev *ae_dev, clear_bit(HNAE3_FLR_RESET, addr); } + clear_bit(HNAE3_NONE_RESET, addr); + if (hdev->reset_type != HNAE3_NONE_RESET && rst_level < hdev->reset_type) return HNAE3_NONE_RESET; @@ -4237,7 +4250,7 @@ static bool hclge_reset_err_handle(struct hclge_dev *hdev) return false; } else if (hdev->rst_stats.reset_fail_cnt < MAX_RESET_FAIL_CNT) { hdev->rst_stats.reset_fail_cnt++; - set_bit(hdev->reset_type, &hdev->reset_pending); + hclge_set_reset_pending(hdev, hdev->reset_type); dev_info(&hdev->pdev->dev, "re-schedule reset task(%u)\n", hdev->rst_stats.reset_fail_cnt); @@ -4480,8 +4493,20 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle) static void hclge_set_def_reset_request(struct hnae3_ae_dev *ae_dev, enum hnae3_reset_type rst_type) { +#define HCLGE_SUPPORT_RESET_TYPE \ + (BIT(HNAE3_FLR_RESET) | BIT(HNAE3_FUNC_RESET) | \ + BIT(HNAE3_GLOBAL_RESET) | BIT(HNAE3_IMP_RESET)) + struct hclge_dev *hdev = ae_dev->priv; + if (!(BIT(rst_type) & HCLGE_SUPPORT_RESET_TYPE)) { + /* To prevent reset triggered by hclge_reset_event */ + set_bit(HNAE3_NONE_RESET, &hdev->default_reset_request); + dev_warn(&hdev->pdev->dev, "unsupported reset type %d\n", + rst_type); + return; + } + set_bit(rst_type, &hdev->default_reset_request); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 094a7c7b5592..ab54e6155e93 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -1395,6 +1395,17 @@ static int hclgevf_notify_roce_client(struct hclgevf_dev *hdev, return ret; } +static void hclgevf_set_reset_pending(struct hclgevf_dev *hdev, + enum hnae3_reset_type reset_type) +{ + /* When an incorrect reset type is executed, the get_reset_level + * function generates the HNAE3_NONE_RESET flag. As a result, this + * type do not need to pending. + */ + if (reset_type != HNAE3_NONE_RESET) + set_bit(reset_type, &hdev->reset_pending); +} + static int hclgevf_reset_wait(struct hclgevf_dev *hdev) { #define HCLGEVF_RESET_WAIT_US 20000 @@ -1544,7 +1555,7 @@ static void hclgevf_reset_err_handle(struct hclgevf_dev *hdev) hdev->rst_stats.rst_fail_cnt); if (hdev->rst_stats.rst_fail_cnt < HCLGEVF_RESET_MAX_FAIL_CNT) - set_bit(hdev->reset_type, &hdev->reset_pending); + hclgevf_set_reset_pending(hdev, hdev->reset_type); if (hclgevf_is_reset_pending(hdev)) { set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); @@ -1664,6 +1675,8 @@ static enum hnae3_reset_type hclgevf_get_reset_level(unsigned long *addr) clear_bit(HNAE3_FLR_RESET, addr); } + clear_bit(HNAE3_NONE_RESET, addr); + return rst_level; } @@ -1673,14 +1686,15 @@ static void hclgevf_reset_event(struct pci_dev *pdev, struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev); struct hclgevf_dev *hdev = ae_dev->priv; - dev_info(&hdev->pdev->dev, "received reset request from VF enet\n"); - if (hdev->default_reset_request) hdev->reset_level = hclgevf_get_reset_level(&hdev->default_reset_request); else hdev->reset_level = HNAE3_VF_FUNC_RESET; + dev_info(&hdev->pdev->dev, "received reset request from VF enet, reset level is %d\n", + hdev->reset_level); + /* reset of this VF requested */ set_bit(HCLGEVF_RESET_REQUESTED, &hdev->reset_state); hclgevf_reset_task_schedule(hdev); @@ -1691,8 +1705,20 @@ static void hclgevf_reset_event(struct pci_dev *pdev, static void hclgevf_set_def_reset_request(struct hnae3_ae_dev *ae_dev, enum hnae3_reset_type rst_type) { +#define HCLGEVF_SUPPORT_RESET_TYPE \ + (BIT(HNAE3_VF_RESET) | BIT(HNAE3_VF_FUNC_RESET) | \ + BIT(HNAE3_VF_PF_FUNC_RESET) | BIT(HNAE3_VF_FULL_RESET) | \ + BIT(HNAE3_FLR_RESET) | BIT(HNAE3_VF_EXP_RESET)) + struct hclgevf_dev *hdev = ae_dev->priv; + if (!(BIT(rst_type) & HCLGEVF_SUPPORT_RESET_TYPE)) { + /* To prevent reset triggered by hclge_reset_event */ + set_bit(HNAE3_NONE_RESET, &hdev->default_reset_request); + dev_info(&hdev->pdev->dev, "unsupported reset type %d\n", + rst_type); + return; + } set_bit(rst_type, &hdev->default_reset_request); } @@ -1849,14 +1875,14 @@ static void hclgevf_reset_service_task(struct hclgevf_dev *hdev) */ if (hdev->reset_attempts > HCLGEVF_MAX_RESET_ATTEMPTS_CNT) { /* prepare for full reset of stack + pcie interface */ - set_bit(HNAE3_VF_FULL_RESET, &hdev->reset_pending); + hclgevf_set_reset_pending(hdev, HNAE3_VF_FULL_RESET); /* "defer" schedule the reset task again */ set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); } else { hdev->reset_attempts++; - set_bit(hdev->reset_level, &hdev->reset_pending); + hclgevf_set_reset_pending(hdev, hdev->reset_level); set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); } hclgevf_reset_task_schedule(hdev); @@ -1979,7 +2005,7 @@ static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev, rst_ing_reg = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING); dev_info(&hdev->pdev->dev, "receive reset interrupt 0x%x!\n", rst_ing_reg); - set_bit(HNAE3_VF_RESET, &hdev->reset_pending); + hclgevf_set_reset_pending(hdev, HNAE3_VF_RESET); set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state); *clearval = ~(1U << HCLGEVF_VECTOR0_RST_INT_B); -- 2.51.0 From 662ecfc46690e92cf630f51b5d4bbbcffe102980 Mon Sep 17 00:00:00 2001 From: Hao Lan Date: Fri, 25 Oct 2024 17:29:33 +0800 Subject: [PATCH 09/16] net: hns3: fix missing features due to dev->features configuration too early Currently, the netdev->features is configured in hns3_nic_set_features. As a result, __netdev_update_features considers that there is no feature difference, and the procedures of the real features are missing. Fixes: 2a7556bb2b73 ("net: hns3: implement ndo_features_check ops for hns3 driver") Signed-off-by: Hao Lan Signed-off-by: Jian Shen Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni --- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 8760b4e9ade6..b09f0cca34dc 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -2483,7 +2483,6 @@ static int hns3_nic_set_features(struct net_device *netdev, return ret; } - netdev->features = features; return 0; } -- 2.51.0 From 2758f18a83ef283d50c0566d3f672621cc658a1a Mon Sep 17 00:00:00 2001 From: Hao Lan Date: Fri, 25 Oct 2024 17:29:34 +0800 Subject: [PATCH 10/16] net: hns3: Resolved the issue that the debugfs query result is inconsistent. This patch modifies the implementation of debugfs: When the user process stops unexpectedly, not all data of the file system is read. In this case, the save_buf pointer is not released. When the user process is called next time, save_buf is used to copy the cached data to the user space. As a result, the queried data is inconsistent. To solve this problem, determine whether the function is invoked for the first time based on the value of *ppos. If *ppos is 0, obtain the actual data. Fixes: 5e69ea7ee2a6 ("net: hns3: refactor the debugfs process") Signed-off-by: Hao Lan Signed-off-by: Guangwei Zhang Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni --- drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index 807eb3bbb11c..841e5af7b2be 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -1293,8 +1293,10 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer, /* save the buffer addr until the last read operation */ *save_buf = read_buf; + } - /* get data ready for the first time to read */ + /* get data ready for the first time to read */ + if (!*ppos) { ret = hns3_dbg_read_cmd(dbg_data, hns3_dbg_cmd[index].cmd, read_buf, hns3_dbg_cmd[index].buf_len); if (ret) -- 2.51.0 From 5f62009ff10826fefa215da68831f42b0c36b6fb Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Fri, 25 Oct 2024 17:29:35 +0800 Subject: [PATCH 11/16] net: hns3: don't auto enable misc vector Currently, there is a time window between misc irq enabled and service task inited. If an interrupte is reported at this time, it will cause warning like below: [ 16.324639] Call trace: [ 16.324641] __queue_delayed_work+0xb8/0xe0 [ 16.324643] mod_delayed_work_on+0x78/0xd0 [ 16.324655] hclge_errhand_task_schedule+0x58/0x90 [hclge] [ 16.324662] hclge_misc_irq_handle+0x168/0x240 [hclge] [ 16.324666] __handle_irq_event_percpu+0x64/0x1e0 [ 16.324667] handle_irq_event+0x80/0x170 [ 16.324670] handle_fasteoi_edge_irq+0x110/0x2bc [ 16.324671] __handle_domain_irq+0x84/0xfc [ 16.324673] gic_handle_irq+0x88/0x2c0 [ 16.324674] el1_irq+0xb8/0x140 [ 16.324677] arch_cpu_idle+0x18/0x40 [ 16.324679] default_idle_call+0x5c/0x1bc [ 16.324682] cpuidle_idle_call+0x18c/0x1c4 [ 16.324684] do_idle+0x174/0x17c [ 16.324685] cpu_startup_entry+0x30/0x6c [ 16.324687] secondary_start_kernel+0x1a4/0x280 [ 16.324688] ---[ end trace 6aa0bff672a964aa ]--- So don't auto enable misc vector when request irq.. Fixes: 7be1b9f3e99f ("net: hns3: make hclge_service use delayed workqueue") Signed-off-by: Jian Shen Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni --- .../net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 35c618c794be..728f4777e51f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -3780,7 +3781,7 @@ static int hclge_misc_irq_init(struct hclge_dev *hdev) snprintf(hdev->misc_vector.name, HNAE3_INT_NAME_LEN, "%s-misc-%s", HCLGE_NAME, pci_name(hdev->pdev)); ret = request_irq(hdev->misc_vector.vector_irq, hclge_misc_irq_handle, - 0, hdev->misc_vector.name, hdev); + IRQ_NOAUTOEN, hdev->misc_vector.name, hdev); if (ret) { hclge_free_vector(hdev, 0); dev_err(&hdev->pdev->dev, "request misc irq(%d) fail\n", @@ -11916,9 +11917,6 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) hclge_init_rxd_adv_layout(hdev); - /* Enable MISC vector(vector0) */ - hclge_enable_vector(&hdev->misc_vector, true); - ret = hclge_init_wol(hdev); if (ret) dev_warn(&pdev->dev, @@ -11931,6 +11929,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) hclge_state_init(hdev); hdev->last_reset_time = jiffies; + /* Enable MISC vector(vector0) */ + enable_irq(hdev->misc_vector.vector_irq); + hclge_enable_vector(&hdev->misc_vector, true); + dev_info(&hdev->pdev->dev, "%s driver initialization finished.\n", HCLGE_DRIVER_NAME); @@ -12336,7 +12338,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) /* Disable MISC vector(vector0) */ hclge_enable_vector(&hdev->misc_vector, false); - synchronize_irq(hdev->misc_vector.vector_irq); + disable_irq(hdev->misc_vector.vector_irq); /* Disable all hw interrupts */ hclge_config_mac_tnl_int(hdev, false); -- 2.51.0 From d1c2e2961ab460ac2433ff8ad46000582abc573c Mon Sep 17 00:00:00 2001 From: Jian Shen Date: Fri, 25 Oct 2024 17:29:36 +0800 Subject: [PATCH 12/16] net: hns3: initialize reset_timer before hclgevf_misc_irq_init() Currently the misc irq is initialized before reset_timer setup. But it will access the reset_timer in the irq handler. So initialize the reset_timer earlier. Fixes: ff200099d271 ("net: hns3: remove unnecessary work in hclgevf_main") Signed-off-by: Jian Shen Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni --- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index ab54e6155e93..896f1eb172d3 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -2315,6 +2315,7 @@ static void hclgevf_state_init(struct hclgevf_dev *hdev) clear_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state); INIT_DELAYED_WORK(&hdev->service_task, hclgevf_service_task); + timer_setup(&hdev->reset_timer, hclgevf_reset_timer, 0); mutex_init(&hdev->mbx_resp.mbx_mutex); sema_init(&hdev->reset_sem, 1); @@ -3014,7 +3015,6 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) HCLGEVF_DRIVER_NAME); hclgevf_task_schedule(hdev, round_jiffies_relative(HZ)); - timer_setup(&hdev->reset_timer, hclgevf_reset_timer, 0); return 0; -- 2.51.0 From 3e22b7de34cbdb991a2c9c5413eeb8a6fb7da2a5 Mon Sep 17 00:00:00 2001 From: Hao Lan Date: Fri, 25 Oct 2024 17:29:37 +0800 Subject: [PATCH 13/16] net: hns3: fixed hclge_fetch_pf_reg accesses bar space out of bounds issue The TQP BAR space is divided into two segments. TQPs 0-1023 and TQPs 1024-1279 are in different BAR space addresses. However, hclge_fetch_pf_reg does not distinguish the tqp space information when reading the tqp space information. When the number of TQPs is greater than 1024, access bar space overwriting occurs. The problem of different segments has been considered during the initialization of tqp.io_base. Therefore, tqp.io_base is directly used when the queue is read in hclge_fetch_pf_reg. The error message: Unable to handle kernel paging request at virtual address ffff800037200000 pc : hclge_fetch_pf_reg+0x138/0x250 [hclge] lr : hclge_get_regs+0x84/0x1d0 [hclge] Call trace: hclge_fetch_pf_reg+0x138/0x250 [hclge] hclge_get_regs+0x84/0x1d0 [hclge] hns3_get_regs+0x2c/0x50 [hns3] ethtool_get_regs+0xf4/0x270 dev_ethtool+0x674/0x8a0 dev_ioctl+0x270/0x36c sock_do_ioctl+0x110/0x2a0 sock_ioctl+0x2ac/0x530 __arm64_sys_ioctl+0xa8/0x100 invoke_syscall+0x4c/0x124 el0_svc_common.constprop.0+0x140/0x15c do_el0_svc+0x30/0xd0 el0_svc+0x1c/0x2c el0_sync_handler+0xb0/0xb4 el0_sync+0x168/0x180 Fixes: 939ccd107ffc ("net: hns3: move dump regs function to a separate file") Signed-off-by: Hao Lan Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c | 9 +++++---- .../net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c | 9 +++++---- 2 files changed, 10 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c index 43c1c18fa81f..8c057192aae6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_regs.c @@ -510,9 +510,9 @@ out: static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data, struct hnae3_knic_private_info *kinfo) { -#define HCLGE_RING_REG_OFFSET 0x200 #define HCLGE_RING_INT_REG_OFFSET 0x4 + struct hnae3_queue *tqp; int i, j, reg_num; int data_num_sum; u32 *reg = data; @@ -533,10 +533,11 @@ static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data, reg_num = ARRAY_SIZE(ring_reg_addr_list); for (j = 0; j < kinfo->num_tqps; j++) { reg += hclge_reg_get_tlv(HCLGE_REG_TAG_RING, reg_num, reg); + tqp = kinfo->tqp[j]; for (i = 0; i < reg_num; i++) - *reg++ = hclge_read_dev(&hdev->hw, - ring_reg_addr_list[i] + - HCLGE_RING_REG_OFFSET * j); + *reg++ = readl_relaxed(tqp->io_base - + HCLGE_TQP_REG_OFFSET + + ring_reg_addr_list[i]); } data_num_sum += (reg_num + HCLGE_REG_TLV_SPACE) * kinfo->num_tqps; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c index 6db415d8b917..7d9d9dbc7560 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_regs.c @@ -123,10 +123,10 @@ int hclgevf_get_regs_len(struct hnae3_handle *handle) void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version, void *data) { -#define HCLGEVF_RING_REG_OFFSET 0x200 #define HCLGEVF_RING_INT_REG_OFFSET 0x4 struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); + struct hnae3_queue *tqp; int i, j, reg_um; u32 *reg = data; @@ -147,10 +147,11 @@ void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version, reg_um = ARRAY_SIZE(ring_reg_addr_list); for (j = 0; j < hdev->num_tqps; j++) { reg += hclgevf_reg_get_tlv(HCLGEVF_REG_TAG_RING, reg_um, reg); + tqp = &hdev->htqp[j].q; for (i = 0; i < reg_um; i++) - *reg++ = hclgevf_read_dev(&hdev->hw, - ring_reg_addr_list[i] + - HCLGEVF_RING_REG_OFFSET * j); + *reg++ = readl_relaxed(tqp->io_base - + HCLGEVF_TQP_REG_OFFSET + + ring_reg_addr_list[i]); } reg_um = ARRAY_SIZE(tqp_intr_reg_addr_list); -- 2.51.0 From 2cf246143519ecc11dab754385ec42d78b6b6a05 Mon Sep 17 00:00:00 2001 From: Jie Wang Date: Fri, 25 Oct 2024 17:29:38 +0800 Subject: [PATCH 14/16] net: hns3: fix kernel crash when 1588 is sent on HIP08 devices Currently, HIP08 devices does not register the ptp devices, so the hdev->ptp is NULL. But the tx process would still try to set hardware time stamp info with SKBTX_HW_TSTAMP flag and cause a kernel crash. [ 128.087798] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000018 ... [ 128.280251] pc : hclge_ptp_set_tx_info+0x2c/0x140 [hclge] [ 128.286600] lr : hclge_ptp_set_tx_info+0x20/0x140 [hclge] [ 128.292938] sp : ffff800059b93140 [ 128.297200] x29: ffff800059b93140 x28: 0000000000003280 [ 128.303455] x27: ffff800020d48280 x26: ffff0cb9dc814080 [ 128.309715] x25: ffff0cb9cde93fa0 x24: 0000000000000001 [ 128.315969] x23: 0000000000000000 x22: 0000000000000194 [ 128.322219] x21: ffff0cd94f986000 x20: 0000000000000000 [ 128.328462] x19: ffff0cb9d2a166c0 x18: 0000000000000000 [ 128.334698] x17: 0000000000000000 x16: ffffcf1fc523ed24 [ 128.340934] x15: 0000ffffd530a518 x14: 0000000000000000 [ 128.347162] x13: ffff0cd6bdb31310 x12: 0000000000000368 [ 128.353388] x11: ffff0cb9cfbc7070 x10: ffff2cf55dd11e02 [ 128.359606] x9 : ffffcf1f85a212b4 x8 : ffff0cd7cf27dab0 [ 128.365831] x7 : 0000000000000a20 x6 : ffff0cd7cf27d000 [ 128.372040] x5 : 0000000000000000 x4 : 000000000000ffff [ 128.378243] x3 : 0000000000000400 x2 : ffffcf1f85a21294 [ 128.384437] x1 : ffff0cb9db520080 x0 : ffff0cb9db500080 [ 128.390626] Call trace: [ 128.393964] hclge_ptp_set_tx_info+0x2c/0x140 [hclge] [ 128.399893] hns3_nic_net_xmit+0x39c/0x4c4 [hns3] [ 128.405468] xmit_one.constprop.0+0xc4/0x200 [ 128.410600] dev_hard_start_xmit+0x54/0xf0 [ 128.415556] sch_direct_xmit+0xe8/0x634 [ 128.420246] __dev_queue_xmit+0x224/0xc70 [ 128.425101] dev_queue_xmit+0x1c/0x40 [ 128.429608] ovs_vport_send+0xac/0x1a0 [openvswitch] [ 128.435409] do_output+0x60/0x17c [openvswitch] [ 128.440770] do_execute_actions+0x898/0x8c4 [openvswitch] [ 128.446993] ovs_execute_actions+0x64/0xf0 [openvswitch] [ 128.453129] ovs_dp_process_packet+0xa0/0x224 [openvswitch] [ 128.459530] ovs_vport_receive+0x7c/0xfc [openvswitch] [ 128.465497] internal_dev_xmit+0x34/0xb0 [openvswitch] [ 128.471460] xmit_one.constprop.0+0xc4/0x200 [ 128.476561] dev_hard_start_xmit+0x54/0xf0 [ 128.481489] __dev_queue_xmit+0x968/0xc70 [ 128.486330] dev_queue_xmit+0x1c/0x40 [ 128.490856] ip_finish_output2+0x250/0x570 [ 128.495810] __ip_finish_output+0x170/0x1e0 [ 128.500832] ip_finish_output+0x3c/0xf0 [ 128.505504] ip_output+0xbc/0x160 [ 128.509654] ip_send_skb+0x58/0xd4 [ 128.513892] udp_send_skb+0x12c/0x354 [ 128.518387] udp_sendmsg+0x7a8/0x9c0 [ 128.522793] inet_sendmsg+0x4c/0x8c [ 128.527116] __sock_sendmsg+0x48/0x80 [ 128.531609] __sys_sendto+0x124/0x164 [ 128.536099] __arm64_sys_sendto+0x30/0x5c [ 128.540935] invoke_syscall+0x50/0x130 [ 128.545508] el0_svc_common.constprop.0+0x10c/0x124 [ 128.551205] do_el0_svc+0x34/0xdc [ 128.555347] el0_svc+0x20/0x30 [ 128.559227] el0_sync_handler+0xb8/0xc0 [ 128.563883] el0_sync+0x160/0x180 Fixes: 0bf5eb788512 ("net: hns3: add support for PTP") Signed-off-by: Jie Wang Signed-off-by: Jijie Shao Signed-off-by: Paolo Abeni --- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c index 5505caea88e9..bab16c2191b2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c @@ -58,6 +58,9 @@ bool hclge_ptp_set_tx_info(struct hnae3_handle *handle, struct sk_buff *skb) struct hclge_dev *hdev = vport->back; struct hclge_ptp *ptp = hdev->ptp; + if (!ptp) + return false; + if (!test_bit(HCLGE_PTP_FLAG_TX_EN, &ptp->flags) || test_and_set_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state)) { ptp->tx_skipped++; -- 2.51.0 From c40dd8c4732551605712985bc5b7045094c6458d Mon Sep 17 00:00:00 2001 From: =?utf8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= Date: Wed, 30 Oct 2024 11:48:26 +0100 Subject: [PATCH 15/16] bpf, test_run: Fix LIVE_FRAME frame update after a page has been recycled MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit The test_run code detects whether a page has been modified and re-initialises the xdp_frame structure if it has, using xdp_update_frame_from_buff(). However, xdp_update_frame_from_buff() doesn't touch frame->mem, so that wasn't correctly re-initialised, which led to the pages from page_pool not being returned correctly. Syzbot noticed this as a memory leak. Fix this by also copying the frame->mem structure when re-initialising the frame, like we do on initialisation of a new page from page_pool. Fixes: e5995bc7e2ba ("bpf, test_run: fix crashes due to XDP frame overwriting/corruption") Fixes: b530e9e1063e ("bpf: Add "live packet" mode for XDP in BPF_PROG_RUN") Reported-by: syzbot+d121e098da06af416d23@syzkaller.appspotmail.com Signed-off-by: Toke Høiland-Jørgensen Signed-off-by: Daniel Borkmann Tested-by: syzbot+d121e098da06af416d23@syzkaller.appspotmail.com Reviewed-by: Alexander Lobakin Acked-by: Stanislav Fomichev Link: https://lore.kernel.org/bpf/20241030-test-run-mem-fix-v1-1-41e88e8cae43@redhat.com --- net/bpf/test_run.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 6d7a442ceb89..501ec4249fed 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -246,6 +246,7 @@ static void reset_ctx(struct xdp_page_head *head) head->ctx.data_meta = head->orig_ctx.data_meta; head->ctx.data_end = head->orig_ctx.data_end; xdp_update_frame_from_buff(&head->ctx, head->frame); + head->frame->mem = head->orig_ctx.rxq->mem; } static int xdp_recv_frames(struct xdp_frame **frames, int nframes, -- 2.51.0 From badccd49b93bb945bf4e5cc8707db67cdc5e27e5 Mon Sep 17 00:00:00 2001 From: Wei Fang Date: Tue, 29 Oct 2024 17:04:06 +0800 Subject: [PATCH 16/16] net: enetc: set MAC address to the VF net_device The MAC address of VF can be configured through the mailbox mechanism of ENETC, but the previous implementation forgot to set the MAC address in net_device, resulting in the SMAC of the sent frames still being the old MAC address. Since the MAC address in the hardware has been changed, Rx cannot receive frames with the DMAC address as the new MAC address. The most obvious phenomenon is that after changing the MAC address, we can see that the MAC address of eno0vf0 has not changed through the "ifconfig eno0vf0" command and the IP address cannot be obtained . root@ls1028ardb:~# ifconfig eno0vf0 down root@ls1028ardb:~# ifconfig eno0vf0 hw ether 00:04:9f:3a:4d:56 up root@ls1028ardb:~# ifconfig eno0vf0 eno0vf0: flags=4163 mtu 1500 ether 66:36:2c:3b:87:76 txqueuelen 1000 (Ethernet) RX packets 794 bytes 69239 (69.2 KB) RX errors 0 dropped 0 overruns 0 frame 0 TX packets 11 bytes 2226 (2.2 KB) TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0 Fixes: beb74ac878c8 ("enetc: Add vf to pf messaging support") Signed-off-by: Wei Fang Reviewed-by: Vladimir Oltean Reviewed-by: Claudiu Manoil Link: https://patch.msgid.link/20241029090406.841836-1-wei.fang@nxp.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/freescale/enetc/enetc_vf.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c index dfcaac302e24..b15db70769e5 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c @@ -78,11 +78,18 @@ static int enetc_vf_set_mac_addr(struct net_device *ndev, void *addr) { struct enetc_ndev_priv *priv = netdev_priv(ndev); struct sockaddr *saddr = addr; + int err; if (!is_valid_ether_addr(saddr->sa_data)) return -EADDRNOTAVAIL; - return enetc_msg_vsi_set_primary_mac_addr(priv, saddr); + err = enetc_msg_vsi_set_primary_mac_addr(priv, saddr); + if (err) + return err; + + eth_hw_addr_set(ndev, saddr->sa_data); + + return 0; } static int enetc_vf_set_features(struct net_device *ndev, -- 2.51.0