From: Sasha Levin Date: Sun, 24 Sep 2023 19:27:43 +0000 (-0400) Subject: Fixes for 5.15 X-Git-Tag: v6.5.6~102 X-Git-Url: http://git.ipfire.org/gitweb/index.cgi?a=commitdiff_plain;h=2053b7f646138cbe6cb534d6c54fb7b0a718b127;p=thirdparty%2Fkernel%2Fstable-queue.git Fixes for 5.15 Signed-off-by: Sasha Levin --- diff --git a/queue-5.15/asoc-imx-audmix-fix-return-error-with-devm_clk_get.patch b/queue-5.15/asoc-imx-audmix-fix-return-error-with-devm_clk_get.patch new file mode 100644 index 00000000000..c2f9207f64e --- /dev/null +++ b/queue-5.15/asoc-imx-audmix-fix-return-error-with-devm_clk_get.patch @@ -0,0 +1,41 @@ +From b242c43a4039149bd54b2662bcebbdded8ce500e Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 15 Sep 2023 14:02:11 +0800 +Subject: ASoC: imx-audmix: Fix return error with devm_clk_get() + +From: Shengjiu Wang + +[ Upstream commit b19a5733de255cabba5feecabf6e900638b582d1 ] + +The devm_clk_get() can return -EPROBE_DEFER error, +modify the error code to be -EINVAL is not correct, which +cause the -EPROBE_DEFER error is not correctly handled. + +This patch is to fix the return error code. + +Fixes: b86ef5367761 ("ASoC: fsl: Add Audio Mixer machine driver") +Signed-off-by: Shengjiu Wang +Reviewed-by: Daniel Baluta +Link: https://lore.kernel.org/r/1694757731-18308-1-git-send-email-shengjiu.wang@nxp.com +Signed-off-by: Mark Brown +Signed-off-by: Sasha Levin +--- + sound/soc/fsl/imx-audmix.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/sound/soc/fsl/imx-audmix.c b/sound/soc/fsl/imx-audmix.c +index d991e457060c7..0363255c39ea9 100644 +--- a/sound/soc/fsl/imx-audmix.c ++++ b/sound/soc/fsl/imx-audmix.c +@@ -320,7 +320,7 @@ static int imx_audmix_probe(struct platform_device *pdev) + if (IS_ERR(priv->cpu_mclk)) { + ret = PTR_ERR(priv->cpu_mclk); + dev_err(&cpu_pdev->dev, "failed to get DAI mclk1: %d\n", ret); +- return -EINVAL; ++ return ret; + } + + priv->audmix_pdev = audmix_pdev; +-- +2.40.1 + diff --git a/queue-5.15/asoc-meson-spdifin-start-hw-on-dai-probe.patch b/queue-5.15/asoc-meson-spdifin-start-hw-on-dai-probe.patch new file mode 100644 index 00000000000..70e9a75daed --- /dev/null +++ b/queue-5.15/asoc-meson-spdifin-start-hw-on-dai-probe.patch @@ -0,0 +1,107 @@ +From fda9267d63e671896af83572414ac30f2c1d375c Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 7 Sep 2023 11:05:04 +0200 +Subject: ASoC: meson: spdifin: start hw on dai probe + +From: Jerome Brunet + +[ Upstream commit aedf323b66b2b875137422ecb7d2525179759076 ] + +For spdif input to report the locked rate correctly, even when no capture +is running, the HW and reference clock must be started as soon as +the dai is probed. + +Fixes: 5ce5658375e6 ("ASoC: meson: add axg spdif input") +Signed-off-by: Jerome Brunet +Link: https://lore.kernel.org/r/20230907090504.12700-1-jbrunet@baylibre.com +Signed-off-by: Mark Brown +Signed-off-by: Sasha Levin +--- + sound/soc/meson/axg-spdifin.c | 49 ++++++++++++----------------------- + 1 file changed, 17 insertions(+), 32 deletions(-) + +diff --git a/sound/soc/meson/axg-spdifin.c b/sound/soc/meson/axg-spdifin.c +index d0d09f945b489..7aaded1fc376b 100644 +--- a/sound/soc/meson/axg-spdifin.c ++++ b/sound/soc/meson/axg-spdifin.c +@@ -112,34 +112,6 @@ static int axg_spdifin_prepare(struct snd_pcm_substream *substream, + return 0; + } + +-static int axg_spdifin_startup(struct snd_pcm_substream *substream, +- struct snd_soc_dai *dai) +-{ +- struct axg_spdifin *priv = snd_soc_dai_get_drvdata(dai); +- int ret; +- +- ret = clk_prepare_enable(priv->refclk); +- if (ret) { +- dev_err(dai->dev, +- "failed to enable spdifin reference clock\n"); +- return ret; +- } +- +- regmap_update_bits(priv->map, SPDIFIN_CTRL0, SPDIFIN_CTRL0_EN, +- SPDIFIN_CTRL0_EN); +- +- return 0; +-} +- +-static void axg_spdifin_shutdown(struct snd_pcm_substream *substream, +- struct snd_soc_dai *dai) +-{ +- struct axg_spdifin *priv = snd_soc_dai_get_drvdata(dai); +- +- regmap_update_bits(priv->map, SPDIFIN_CTRL0, SPDIFIN_CTRL0_EN, 0); +- clk_disable_unprepare(priv->refclk); +-} +- + static void axg_spdifin_write_mode_param(struct regmap *map, int mode, + unsigned int val, + unsigned int num_per_reg, +@@ -251,25 +223,38 @@ static int axg_spdifin_dai_probe(struct snd_soc_dai *dai) + ret = axg_spdifin_sample_mode_config(dai, priv); + if (ret) { + dev_err(dai->dev, "mode configuration failed\n"); +- clk_disable_unprepare(priv->pclk); +- return ret; ++ goto pclk_err; + } + ++ ret = clk_prepare_enable(priv->refclk); ++ if (ret) { ++ dev_err(dai->dev, ++ "failed to enable spdifin reference clock\n"); ++ goto pclk_err; ++ } ++ ++ regmap_update_bits(priv->map, SPDIFIN_CTRL0, SPDIFIN_CTRL0_EN, ++ SPDIFIN_CTRL0_EN); ++ + return 0; ++ ++pclk_err: ++ clk_disable_unprepare(priv->pclk); ++ return ret; + } + + static int axg_spdifin_dai_remove(struct snd_soc_dai *dai) + { + struct axg_spdifin *priv = snd_soc_dai_get_drvdata(dai); + ++ regmap_update_bits(priv->map, SPDIFIN_CTRL0, SPDIFIN_CTRL0_EN, 0); ++ clk_disable_unprepare(priv->refclk); + clk_disable_unprepare(priv->pclk); + return 0; + } + + static const struct snd_soc_dai_ops axg_spdifin_ops = { + .prepare = axg_spdifin_prepare, +- .startup = axg_spdifin_startup, +- .shutdown = axg_spdifin_shutdown, + }; + + static int axg_spdifin_iec958_info(struct snd_kcontrol *kcontrol, +-- +2.40.1 + diff --git a/queue-5.15/bnxt_en-flush-xdp-for-bnxt_poll_nitroa0-s-napi.patch b/queue-5.15/bnxt_en-flush-xdp-for-bnxt_poll_nitroa0-s-napi.patch new file mode 100644 index 00000000000..14512deb79f --- /dev/null +++ b/queue-5.15/bnxt_en-flush-xdp-for-bnxt_poll_nitroa0-s-napi.patch @@ -0,0 +1,62 @@ +From 1e409a540871dbd4b7e0ef513e92ed44ac58c075 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 18 Sep 2023 17:36:10 +0200 +Subject: bnxt_en: Flush XDP for bnxt_poll_nitroa0()'s NAPI + +From: Sebastian Andrzej Siewior + +[ Upstream commit edc0140cc3b7b91874ebe70eb7d2a851e8817ccc ] + +bnxt_poll_nitroa0() invokes bnxt_rx_pkt() which can run a XDP program +which in turn can return XDP_REDIRECT. bnxt_rx_pkt() is also used by +__bnxt_poll_work() which flushes (xdp_do_flush()) the packets after each +round. bnxt_poll_nitroa0() lacks this feature. +xdp_do_flush() should be invoked before leaving the NAPI callback. + +Invoke xdp_do_flush() after a redirect in bnxt_poll_nitroa0() NAPI. + +Cc: Michael Chan +Fixes: f18c2b77b2e4e ("bnxt_en: optimized XDP_REDIRECT support") +Reviewed-by: Andy Gospodarek +Signed-off-by: Sebastian Andrzej Siewior +Reviewed-by: Michael Chan +Acked-by: Jesper Dangaard Brouer +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/broadcom/bnxt/bnxt.c | 5 +++++ + 1 file changed, 5 insertions(+) + +diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c +index 931bb40ac05b5..4cb22e4060520 100644 +--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c ++++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c +@@ -2520,6 +2520,7 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget) + struct rx_cmp_ext *rxcmp1; + u32 cp_cons, tmp_raw_cons; + u32 raw_cons = cpr->cp_raw_cons; ++ bool flush_xdp = false; + u32 rx_pkts = 0; + u8 event = 0; + +@@ -2554,6 +2555,8 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget) + rx_pkts++; + else if (rc == -EBUSY) /* partial completion */ + break; ++ if (event & BNXT_REDIRECT_EVENT) ++ flush_xdp = true; + } else if (unlikely(TX_CMP_TYPE(txcmp) == + CMPL_BASE_TYPE_HWRM_DONE)) { + bnxt_hwrm_handler(bp, txcmp); +@@ -2573,6 +2576,8 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget) + + if (event & BNXT_AGG_EVENT) + bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod); ++ if (flush_xdp) ++ xdp_do_flush(); + + if (!bnxt_has_work(bp, cpr) && rx_pkts < budget) { + napi_complete_done(napi, rx_pkts); +-- +2.40.1 + diff --git a/queue-5.15/bpf-avoid-deadlock-when-using-queue-and-stack-maps-f.patch b/queue-5.15/bpf-avoid-deadlock-when-using-queue-and-stack-maps-f.patch new file mode 100644 index 00000000000..37bcf496995 --- /dev/null +++ b/queue-5.15/bpf-avoid-deadlock-when-using-queue-and-stack-maps-f.patch @@ -0,0 +1,79 @@ +From 78c400ffa977e7e69050aaf85fe7f3866a78e2c4 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 11 Sep 2023 15:28:14 +0200 +Subject: bpf: Avoid deadlock when using queue and stack maps from NMI +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Toke Høiland-Jørgensen + +[ Upstream commit a34a9f1a19afe9c60ca0ea61dfeee63a1c2baac8 ] + +Sysbot discovered that the queue and stack maps can deadlock if they are +being used from a BPF program that can be called from NMI context (such as +one that is attached to a perf HW counter event). To fix this, add an +in_nmi() check and use raw_spin_trylock() in NMI context, erroring out if +grabbing the lock fails. + +Fixes: f1a2e44a3aec ("bpf: add queue and stack maps") +Reported-by: Hsin-Wei Hung +Tested-by: Hsin-Wei Hung +Co-developed-by: Hsin-Wei Hung +Signed-off-by: Toke Høiland-Jørgensen +Link: https://lore.kernel.org/r/20230911132815.717240-1-toke@redhat.com +Signed-off-by: Alexei Starovoitov +Signed-off-by: Sasha Levin +--- + kernel/bpf/queue_stack_maps.c | 21 ++++++++++++++++++--- + 1 file changed, 18 insertions(+), 3 deletions(-) + +diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c +index f9c734aaa9902..ef95b796a0fa3 100644 +--- a/kernel/bpf/queue_stack_maps.c ++++ b/kernel/bpf/queue_stack_maps.c +@@ -103,7 +103,12 @@ static int __queue_map_get(struct bpf_map *map, void *value, bool delete) + int err = 0; + void *ptr; + +- raw_spin_lock_irqsave(&qs->lock, flags); ++ if (in_nmi()) { ++ if (!raw_spin_trylock_irqsave(&qs->lock, flags)) ++ return -EBUSY; ++ } else { ++ raw_spin_lock_irqsave(&qs->lock, flags); ++ } + + if (queue_stack_map_is_empty(qs)) { + memset(value, 0, qs->map.value_size); +@@ -133,7 +138,12 @@ static int __stack_map_get(struct bpf_map *map, void *value, bool delete) + void *ptr; + u32 index; + +- raw_spin_lock_irqsave(&qs->lock, flags); ++ if (in_nmi()) { ++ if (!raw_spin_trylock_irqsave(&qs->lock, flags)) ++ return -EBUSY; ++ } else { ++ raw_spin_lock_irqsave(&qs->lock, flags); ++ } + + if (queue_stack_map_is_empty(qs)) { + memset(value, 0, qs->map.value_size); +@@ -198,7 +208,12 @@ static int queue_stack_map_push_elem(struct bpf_map *map, void *value, + if (flags & BPF_NOEXIST || flags > BPF_EXIST) + return -EINVAL; + +- raw_spin_lock_irqsave(&qs->lock, irq_flags); ++ if (in_nmi()) { ++ if (!raw_spin_trylock_irqsave(&qs->lock, irq_flags)) ++ return -EBUSY; ++ } else { ++ raw_spin_lock_irqsave(&qs->lock, irq_flags); ++ } + + if (queue_stack_map_is_full(qs)) { + if (!replace) { +-- +2.40.1 + diff --git a/queue-5.15/dccp-fix-dccp_v4_err-dccp_v6_err-again.patch b/queue-5.15/dccp-fix-dccp_v4_err-dccp_v6_err-again.patch new file mode 100644 index 00000000000..c6cf680a52d --- /dev/null +++ b/queue-5.15/dccp-fix-dccp_v4_err-dccp_v6_err-again.patch @@ -0,0 +1,132 @@ +From 70e8b871c4e8cb6b21d9e4f766428a08c5117f9f Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 15 Sep 2023 19:00:35 +0000 +Subject: dccp: fix dccp_v4_err()/dccp_v6_err() again + +From: Eric Dumazet + +[ Upstream commit 6af289746a636f71f4c0535a9801774118486c7a ] + +dh->dccph_x is the 9th byte (offset 8) in "struct dccp_hdr", +not in the "byte 7" as Jann claimed. + +We need to make sure the ICMP messages are big enough, +using more standard ways (no more assumptions). + +syzbot reported: +BUG: KMSAN: uninit-value in pskb_may_pull_reason include/linux/skbuff.h:2667 [inline] +BUG: KMSAN: uninit-value in pskb_may_pull include/linux/skbuff.h:2681 [inline] +BUG: KMSAN: uninit-value in dccp_v6_err+0x426/0x1aa0 net/dccp/ipv6.c:94 +pskb_may_pull_reason include/linux/skbuff.h:2667 [inline] +pskb_may_pull include/linux/skbuff.h:2681 [inline] +dccp_v6_err+0x426/0x1aa0 net/dccp/ipv6.c:94 +icmpv6_notify+0x4c7/0x880 net/ipv6/icmp.c:867 +icmpv6_rcv+0x19d5/0x30d0 +ip6_protocol_deliver_rcu+0xda6/0x2a60 net/ipv6/ip6_input.c:438 +ip6_input_finish net/ipv6/ip6_input.c:483 [inline] +NF_HOOK include/linux/netfilter.h:304 [inline] +ip6_input+0x15d/0x430 net/ipv6/ip6_input.c:492 +ip6_mc_input+0xa7e/0xc80 net/ipv6/ip6_input.c:586 +dst_input include/net/dst.h:468 [inline] +ip6_rcv_finish+0x5db/0x870 net/ipv6/ip6_input.c:79 +NF_HOOK include/linux/netfilter.h:304 [inline] +ipv6_rcv+0xda/0x390 net/ipv6/ip6_input.c:310 +__netif_receive_skb_one_core net/core/dev.c:5523 [inline] +__netif_receive_skb+0x1a6/0x5a0 net/core/dev.c:5637 +netif_receive_skb_internal net/core/dev.c:5723 [inline] +netif_receive_skb+0x58/0x660 net/core/dev.c:5782 +tun_rx_batched+0x83b/0x920 +tun_get_user+0x564c/0x6940 drivers/net/tun.c:2002 +tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048 +call_write_iter include/linux/fs.h:1985 [inline] +new_sync_write fs/read_write.c:491 [inline] +vfs_write+0x8ef/0x15c0 fs/read_write.c:584 +ksys_write+0x20f/0x4c0 fs/read_write.c:637 +__do_sys_write fs/read_write.c:649 [inline] +__se_sys_write fs/read_write.c:646 [inline] +__x64_sys_write+0x93/0xd0 fs/read_write.c:646 +do_syscall_x64 arch/x86/entry/common.c:50 [inline] +do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 +entry_SYSCALL_64_after_hwframe+0x63/0xcd + +Uninit was created at: +slab_post_alloc_hook+0x12f/0xb70 mm/slab.h:767 +slab_alloc_node mm/slub.c:3478 [inline] +kmem_cache_alloc_node+0x577/0xa80 mm/slub.c:3523 +kmalloc_reserve+0x13d/0x4a0 net/core/skbuff.c:559 +__alloc_skb+0x318/0x740 net/core/skbuff.c:650 +alloc_skb include/linux/skbuff.h:1286 [inline] +alloc_skb_with_frags+0xc8/0xbd0 net/core/skbuff.c:6313 +sock_alloc_send_pskb+0xa80/0xbf0 net/core/sock.c:2795 +tun_alloc_skb drivers/net/tun.c:1531 [inline] +tun_get_user+0x23cf/0x6940 drivers/net/tun.c:1846 +tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048 +call_write_iter include/linux/fs.h:1985 [inline] +new_sync_write fs/read_write.c:491 [inline] +vfs_write+0x8ef/0x15c0 fs/read_write.c:584 +ksys_write+0x20f/0x4c0 fs/read_write.c:637 +__do_sys_write fs/read_write.c:649 [inline] +__se_sys_write fs/read_write.c:646 [inline] +__x64_sys_write+0x93/0xd0 fs/read_write.c:646 +do_syscall_x64 arch/x86/entry/common.c:50 [inline] +do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 +entry_SYSCALL_64_after_hwframe+0x63/0xcd + +CPU: 0 PID: 4995 Comm: syz-executor153 Not tainted 6.6.0-rc1-syzkaller-00014-ga747acc0b752 #0 +Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/04/2023 + +Fixes: 977ad86c2a1b ("dccp: Fix out of bounds access in DCCP error handler") +Reported-by: syzbot +Signed-off-by: Eric Dumazet +Cc: Jann Horn +Reviewed-by: Jann Horn +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/dccp/ipv4.c | 9 ++------- + net/dccp/ipv6.c | 9 ++------- + 2 files changed, 4 insertions(+), 14 deletions(-) + +diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c +index 1490ba960365e..b44e46dc8e040 100644 +--- a/net/dccp/ipv4.c ++++ b/net/dccp/ipv4.c +@@ -250,13 +250,8 @@ static int dccp_v4_err(struct sk_buff *skb, u32 info) + int err; + struct net *net = dev_net(skb->dev); + +- /* For the first __dccp_basic_hdr_len() check, we only need dh->dccph_x, +- * which is in byte 7 of the dccp header. +- * Our caller (icmp_socket_deliver()) already pulled 8 bytes for us. +- * +- * Later on, we want to access the sequence number fields, which are +- * beyond 8 bytes, so we have to pskb_may_pull() ourselves. +- */ ++ if (!pskb_may_pull(skb, offset + sizeof(*dh))) ++ return -EINVAL; + dh = (struct dccp_hdr *)(skb->data + offset); + if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh))) + return -EINVAL; +diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c +index c9f11f86266c0..0ddf64845a06c 100644 +--- a/net/dccp/ipv6.c ++++ b/net/dccp/ipv6.c +@@ -83,13 +83,8 @@ static int dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, + __u64 seq; + struct net *net = dev_net(skb->dev); + +- /* For the first __dccp_basic_hdr_len() check, we only need dh->dccph_x, +- * which is in byte 7 of the dccp header. +- * Our caller (icmpv6_notify()) already pulled 8 bytes for us. +- * +- * Later on, we want to access the sequence number fields, which are +- * beyond 8 bytes, so we have to pskb_may_pull() ourselves. +- */ ++ if (!pskb_may_pull(skb, offset + sizeof(*dh))) ++ return -EINVAL; + dh = (struct dccp_hdr *)(skb->data + offset); + if (!pskb_may_pull(skb, offset + __dccp_basic_hdr_len(dh))) + return -EINVAL; +-- +2.40.1 + diff --git a/queue-5.15/fix-up-backport-of-136191703038-interconnect-teach-l.patch b/queue-5.15/fix-up-backport-of-136191703038-interconnect-teach-l.patch new file mode 100644 index 00000000000..32f5e151ee0 --- /dev/null +++ b/queue-5.15/fix-up-backport-of-136191703038-interconnect-teach-l.patch @@ -0,0 +1,36 @@ +From 16c572ef0646f8b0fa19fbf81b302de8a03127f2 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sun, 24 Sep 2023 14:30:44 -0400 +Subject: Fix up backport of 136191703038 ("interconnect: Teach lockdep about + icc_bw_lock order") + +Add a missing include to fix the following build error: + +drivers/interconnect/core.c: In function 'icc_init': +drivers/interconnect/core.c:1148:9: error: implicit declaration of function 'fs_reclaim_acquire' [-Werror=implicit-function-declaration] + 1148 | fs_reclaim_acquire(GFP_KERNEL); + | ^~~~~~~~~~~~~~~~~~ +drivers/interconnect/core.c:1150:9: error: implicit declaration of function 'fs_reclaim_release' [-Werror=implicit-function-declaration] + 1150 | fs_reclaim_release(GFP_KERNEL); + | ^~~~~~~~~~~~~~~~~~ + +Signed-off-by: Sasha Levin +--- + drivers/interconnect/core.c | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c +index ab654b33f5d24..b7c41bd7409cd 100644 +--- a/drivers/interconnect/core.c ++++ b/drivers/interconnect/core.c +@@ -13,6 +13,7 @@ + #include + #include + #include ++#include + #include + #include + #include +-- +2.40.1 + diff --git a/queue-5.15/i40e-add-vf-vlan-pruning.patch b/queue-5.15/i40e-add-vf-vlan-pruning.patch new file mode 100644 index 00000000000..2fbc409763d --- /dev/null +++ b/queue-5.15/i40e-add-vf-vlan-pruning.patch @@ -0,0 +1,318 @@ +From 0b5a8d44b9fdf130a22a20781c2be973e3f8afb2 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 11 Apr 2022 14:07:14 +0200 +Subject: i40e: Add VF VLAN pruning + +From: Mateusz Palczewski + +[ Upstream commit c87c938f62d8f1f7c24620859d67f2e3eca23afc ] + +VFs by default are able to see all tagged traffic regardless of trust +and VLAN filters configured. + +Add new private flag vf-vlan-pruning that allows changing of default +VF behavior for tagged traffic. When the flag is turned on +untrusted VF will only be able to receive untagged traffic +or traffic with VLAN tags it has created interfaces for + +The flag is off by default and can only be changed if +there are no VFs spawned on the PF. This flag will only be effective +when no PVID is set on VF and VF is not trusted. +Add new function that computes the correct VLAN ID for VF VLAN filters +based on trust, PVID, vf-vlan-prune-disable flag and current VLAN ID. + +Testing Hints: + +Test 1: vf-vlan-pruning == off +============================== +1. Set the private flag +> ethtool --set-priv-flag eth0 vf-vlan-pruning off (default setting) +2. Use scapy to send any VLAN tagged traffic and make sure the VF +receives all VLAN tagged traffic that matches its destination MAC +filters (unicast, multicast, and broadcast). + +Test 2: vf-vlan-pruning == on +============================== +1. Set the private flag +> ethtool --set-priv-flag eth0 vf-vlan-pruning on +2. Use scapy to send any VLAN tagged traffic and make sure the VF does +not receive any VLAN tagged traffic that matches its destination MAC +filters (unicast, multicast, and broadcast). +3. Add a VLAN filter on the VF netdev +> ip link add link eth0v0 name vlan10 type vlan id 10 +4. Bring the VLAN netdev up +> ip link set vlan10 up +4. Use scapy to send traffic with VLAN 10, VLAN 11 (anything not VLAN +10), and untagged traffic. Make sure the VF only receives VLAN 10 +and untagged traffic when the link partner is sending. + +Test 3: vf-vlan-pruning == off && VF is in a port VLAN +============================== +1. Set the private flag +> ethtool --set-priv-flag eth0 vf-vlan-pruning off (default setting) +2. Create a VF +> echo 1 > sriov_numvfs +3. Put the VF in a port VLAN +> ip link set eth0 vf 0 vlan 10 +4. Use scapy to send traffic with VLAN 10 and VLAN 11 (anything not VLAN +10) and make sure the VF only receives untagged traffic when the link +partner is sending VLAN 10 tagged traffic as the VLAN tag is expected +to be stripped by HW for port VLANs and not visible to the VF. + +Test 4: Change vf-vlan-pruning while VFs are created +============================== +echo 0 > sriov_numvfs +ethtool --set-priv-flag eth0 vf-vlan-pruning off +echo 1 > sriov_numvfs +ethtool --set-priv-flag eth0 vf-vlan-pruning on (expect failure) + +Signed-off-by: Sylwester Dziedziuch +Signed-off-by: Przemyslaw Patynowski +Signed-off-by: Mateusz Palczewski +Tested-by: Konrad Jankowski +Signed-off-by: Tony Nguyen +Stable-dep-of: d0d362ffa33d ("i40e: Fix VF VLAN offloading when port VLAN is configured") +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/i40e/i40e.h | 1 + + .../net/ethernet/intel/i40e/i40e_ethtool.c | 9 ++ + drivers/net/ethernet/intel/i40e/i40e_main.c | 135 +++++++++++++++++- + .../ethernet/intel/i40e/i40e_virtchnl_pf.c | 8 +- + 4 files changed, 147 insertions(+), 6 deletions(-) + +diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h +index a42ca847c8f86..b76e6f94edb05 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e.h ++++ b/drivers/net/ethernet/intel/i40e/i40e.h +@@ -566,6 +566,7 @@ struct i40e_pf { + #define I40E_FLAG_DISABLE_FW_LLDP BIT(24) + #define I40E_FLAG_RS_FEC BIT(25) + #define I40E_FLAG_BASE_R_FEC BIT(26) ++#define I40E_FLAG_VF_VLAN_PRUNING BIT(27) + /* TOTAL_PORT_SHUTDOWN + * Allows to physically disable the link on the NIC's port. + * If enabled, (after link down request from the OS) +diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +index d124cb947ffa5..d0b9ee756b306 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c ++++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +@@ -451,6 +451,8 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = { + I40E_PRIV_FLAG("disable-fw-lldp", I40E_FLAG_DISABLE_FW_LLDP, 0), + I40E_PRIV_FLAG("rs-fec", I40E_FLAG_RS_FEC, 0), + I40E_PRIV_FLAG("base-r-fec", I40E_FLAG_BASE_R_FEC, 0), ++ I40E_PRIV_FLAG("vf-vlan-pruning", ++ I40E_FLAG_VF_VLAN_PRUNING, 0), + }; + + #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags) +@@ -5293,6 +5295,13 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags) + return -EOPNOTSUPP; + } + ++ if ((changed_flags & I40E_FLAG_VF_VLAN_PRUNING) && ++ pf->num_alloc_vfs) { ++ dev_warn(&pf->pdev->dev, ++ "Changing vf-vlan-pruning flag while VF(s) are active is not supported\n"); ++ return -EOPNOTSUPP; ++ } ++ + if ((changed_flags & new_flags & + I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED) && + (new_flags & I40E_FLAG_MFP_ENABLED)) +diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c +index d3f3874220a31..76bb1d0de8d1c 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e_main.c ++++ b/drivers/net/ethernet/intel/i40e/i40e_main.c +@@ -1426,6 +1426,114 @@ static int i40e_correct_mac_vlan_filters(struct i40e_vsi *vsi, + return 0; + } + ++/** ++ * i40e_get_vf_new_vlan - Get new vlan id on a vf ++ * @vsi: the vsi to configure ++ * @new_mac: new mac filter to be added ++ * @f: existing mac filter, replaced with new_mac->f if new_mac is not NULL ++ * @vlan_filters: the number of active VLAN filters ++ * @trusted: flag if the VF is trusted ++ * ++ * Get new VLAN id based on current VLAN filters, trust, PVID ++ * and vf-vlan-prune-disable flag. ++ * ++ * Returns the value of the new vlan filter or ++ * the old value if no new filter is needed. ++ */ ++static s16 i40e_get_vf_new_vlan(struct i40e_vsi *vsi, ++ struct i40e_new_mac_filter *new_mac, ++ struct i40e_mac_filter *f, ++ int vlan_filters, ++ bool trusted) ++{ ++ s16 pvid = le16_to_cpu(vsi->info.pvid); ++ struct i40e_pf *pf = vsi->back; ++ bool is_any; ++ ++ if (new_mac) ++ f = new_mac->f; ++ ++ if (pvid && f->vlan != pvid) ++ return pvid; ++ ++ is_any = (trusted || ++ !(pf->flags & I40E_FLAG_VF_VLAN_PRUNING)); ++ ++ if ((vlan_filters && f->vlan == I40E_VLAN_ANY) || ++ (!is_any && !vlan_filters && f->vlan == I40E_VLAN_ANY) || ++ (is_any && !vlan_filters && f->vlan == 0)) { ++ if (is_any) ++ return I40E_VLAN_ANY; ++ else ++ return 0; ++ } ++ ++ return f->vlan; ++} ++ ++/** ++ * i40e_correct_vf_mac_vlan_filters - Correct non-VLAN VF filters if necessary ++ * @vsi: the vsi to configure ++ * @tmp_add_list: list of filters ready to be added ++ * @tmp_del_list: list of filters ready to be deleted ++ * @vlan_filters: the number of active VLAN filters ++ * @trusted: flag if the VF is trusted ++ * ++ * Correct VF VLAN filters based on current VLAN filters, trust, PVID ++ * and vf-vlan-prune-disable flag. ++ * ++ * In case of memory allocation failure return -ENOMEM. Otherwise, return 0. ++ * ++ * This function is only expected to be called from within ++ * i40e_sync_vsi_filters. ++ * ++ * NOTE: This function expects to be called while under the ++ * mac_filter_hash_lock ++ */ ++static int i40e_correct_vf_mac_vlan_filters(struct i40e_vsi *vsi, ++ struct hlist_head *tmp_add_list, ++ struct hlist_head *tmp_del_list, ++ int vlan_filters, ++ bool trusted) ++{ ++ struct i40e_mac_filter *f, *add_head; ++ struct i40e_new_mac_filter *new_mac; ++ struct hlist_node *h; ++ int bkt, new_vlan; ++ ++ hlist_for_each_entry(new_mac, tmp_add_list, hlist) { ++ new_mac->f->vlan = i40e_get_vf_new_vlan(vsi, new_mac, NULL, ++ vlan_filters, trusted); ++ } ++ ++ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { ++ new_vlan = i40e_get_vf_new_vlan(vsi, NULL, f, vlan_filters, ++ trusted); ++ if (new_vlan != f->vlan) { ++ add_head = i40e_add_filter(vsi, f->macaddr, new_vlan); ++ if (!add_head) ++ return -ENOMEM; ++ /* Create a temporary i40e_new_mac_filter */ ++ new_mac = kzalloc(sizeof(*new_mac), GFP_ATOMIC); ++ if (!new_mac) ++ return -ENOMEM; ++ new_mac->f = add_head; ++ new_mac->state = add_head->state; ++ ++ /* Add the new filter to the tmp list */ ++ hlist_add_head(&new_mac->hlist, tmp_add_list); ++ ++ /* Put the original filter into the delete list */ ++ f->state = I40E_FILTER_REMOVE; ++ hash_del(&f->hlist); ++ hlist_add_head(&f->hlist, tmp_del_list); ++ } ++ } ++ ++ vsi->has_vlan_filter = !!vlan_filters; ++ return 0; ++} ++ + /** + * i40e_rm_default_mac_filter - Remove the default MAC filter set by NVM + * @vsi: the PF Main VSI - inappropriate for any other VSI +@@ -2483,10 +2591,14 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) + vlan_filters++; + } + +- retval = i40e_correct_mac_vlan_filters(vsi, +- &tmp_add_list, +- &tmp_del_list, +- vlan_filters); ++ if (vsi->type != I40E_VSI_SRIOV) ++ retval = i40e_correct_mac_vlan_filters ++ (vsi, &tmp_add_list, &tmp_del_list, ++ vlan_filters); ++ else ++ retval = i40e_correct_vf_mac_vlan_filters ++ (vsi, &tmp_add_list, &tmp_del_list, ++ vlan_filters, pf->vf[vsi->vf_id].trusted); + + hlist_for_each_entry(new, &tmp_add_list, hlist) + netdev_hw_addr_refcnt(new->f, vsi->netdev, 1); +@@ -2915,8 +3027,21 @@ int i40e_add_vlan_all_mac(struct i40e_vsi *vsi, s16 vid) + int bkt; + + hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { +- if (f->state == I40E_FILTER_REMOVE) ++ /* If we're asked to add a filter that has been marked for ++ * removal, it is safe to simply restore it to active state. ++ * __i40e_del_filter will have simply deleted any filters which ++ * were previously marked NEW or FAILED, so if it is currently ++ * marked REMOVE it must have previously been ACTIVE. Since we ++ * haven't yet run the sync filters task, just restore this ++ * filter to the ACTIVE state so that the sync task leaves it ++ * in place. ++ */ ++ if (f->state == I40E_FILTER_REMOVE && f->vlan == vid) { ++ f->state = I40E_FILTER_ACTIVE; ++ continue; ++ } else if (f->state == I40E_FILTER_REMOVE) { + continue; ++ } + add_f = i40e_add_filter(vsi, f->macaddr, vid); + if (!add_f) { + dev_info(&vsi->back->pdev->dev, +diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +index 46758bbcb04f4..ce9aa22f82d92 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c ++++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +@@ -4372,6 +4372,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, + /* duplicate request, so just return success */ + goto error_pvid; + ++ i40e_vlan_stripping_enable(vsi); + i40e_vc_reset_vf(vf, true); + /* During reset the VF got a new VSI, so refresh a pointer. */ + vsi = pf->vsi[vf->lan_vsi_idx]; +@@ -4387,7 +4388,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, + * MAC addresses deleted. + */ + if ((!(vlan_id || qos) || +- vlanprio != le16_to_cpu(vsi->info.pvid)) && ++ vlanprio != le16_to_cpu(vsi->info.pvid)) && + vsi->info.pvid) { + ret = i40e_add_vlan_all_mac(vsi, I40E_VLAN_ANY); + if (ret) { +@@ -4750,6 +4751,11 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting) + goto out; + + vf->trusted = setting; ++ ++ /* request PF to sync mac/vlan filters for the VF */ ++ set_bit(__I40E_MACVLAN_SYNC_PENDING, pf->state); ++ pf->vsi[vf->lan_vsi_idx]->flags |= I40E_VSI_FLAG_FILTER_CHANGED; ++ + i40e_vc_reset_vf(vf, true); + dev_info(&pf->pdev->dev, "VF %u is now %strusted\n", + vf_id, setting ? "" : "un"); +-- +2.40.1 + diff --git a/queue-5.15/i40e-fix-vf-vlan-offloading-when-port-vlan-is-config.patch b/queue-5.15/i40e-fix-vf-vlan-offloading-when-port-vlan-is-config.patch new file mode 100644 index 00000000000..21804472d98 --- /dev/null +++ b/queue-5.15/i40e-fix-vf-vlan-offloading-when-port-vlan-is-config.patch @@ -0,0 +1,89 @@ +From 19eda476676e942c8c71dc8a746ca9511203f797 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 7 Sep 2023 17:44:57 +0200 +Subject: i40e: Fix VF VLAN offloading when port VLAN is configured + +From: Ivan Vecera + +[ Upstream commit d0d362ffa33da4acdcf7aee2116ceef8c8fef658 ] + +If port VLAN is configured on a VF then any other VLANs on top of this VF +are broken. + +During i40e_ndo_set_vf_port_vlan() call the i40e driver reset the VF and +iavf driver asks PF (using VIRTCHNL_OP_GET_VF_RESOURCES) for VF capabilities +but this reset occurs too early, prior setting of vf->info.pvid field +and because this field can be zero during i40e_vc_get_vf_resources_msg() +then VIRTCHNL_VF_OFFLOAD_VLAN capability is reported to iavf driver. + +This is wrong because iavf driver should not report VLAN offloading +capability when port VLAN is configured as i40e does not support QinQ +offloading. + +Fix the issue by moving VF reset after setting of vf->port_vlan_id +field. + +Without this patch: +$ echo 1 > /sys/class/net/enp2s0f0/device/sriov_numvfs +$ ip link set enp2s0f0 vf 0 vlan 3 +$ ip link set enp2s0f0v0 up +$ ip link add link enp2s0f0v0 name vlan4 type vlan id 4 +$ ip link set vlan4 up +... +$ ethtool -k enp2s0f0v0 | grep vlan-offload +rx-vlan-offload: on +tx-vlan-offload: on +$ dmesg -l err | grep iavf +[1292500.742914] iavf 0000:02:02.0: Failed to add VLAN filter, error IAVF_ERR_INVALID_QP_ID + +With this patch: +$ echo 1 > /sys/class/net/enp2s0f0/device/sriov_numvfs +$ ip link set enp2s0f0 vf 0 vlan 3 +$ ip link set enp2s0f0v0 up +$ ip link add link enp2s0f0v0 name vlan4 type vlan id 4 +$ ip link set vlan4 up +... +$ ethtool -k enp2s0f0v0 | grep vlan-offload +rx-vlan-offload: off [requested on] +tx-vlan-offload: off [requested on] +$ dmesg -l err | grep iavf + +Fixes: f9b4b6278d51 ("i40e: Reset the VF upon conflicting VLAN configuration") +Signed-off-by: Ivan Vecera +Reviewed-by: Jesse Brandeburg +Tested-by: Rafal Romanowski +Signed-off-by: Tony Nguyen +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 8 +++++--- + 1 file changed, 5 insertions(+), 3 deletions(-) + +diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +index ce9aa22f82d92..7950b18cb7a41 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c ++++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +@@ -4373,9 +4373,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, + goto error_pvid; + + i40e_vlan_stripping_enable(vsi); +- i40e_vc_reset_vf(vf, true); +- /* During reset the VF got a new VSI, so refresh a pointer. */ +- vsi = pf->vsi[vf->lan_vsi_idx]; ++ + /* Locked once because multiple functions below iterate list */ + spin_lock_bh(&vsi->mac_filter_hash_lock); + +@@ -4461,6 +4459,10 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, + */ + vf->port_vlan_id = le16_to_cpu(vsi->info.pvid); + ++ i40e_vc_reset_vf(vf, true); ++ /* During reset the VF got a new VSI, so refresh a pointer. */ ++ vsi = pf->vsi[vf->lan_vsi_idx]; ++ + ret = i40e_config_vf_promiscuous_mode(vf, vsi->id, allmulti, alluni); + if (ret) { + dev_err(&pf->pdev->dev, "Unable to config vf promiscuous mode\n"); +-- +2.40.1 + diff --git a/queue-5.15/iavf-do-not-process-adminq-tasks-when-__iavf_in_remo.patch b/queue-5.15/iavf-do-not-process-adminq-tasks-when-__iavf_in_remo.patch new file mode 100644 index 00000000000..946ef11de20 --- /dev/null +++ b/queue-5.15/iavf-do-not-process-adminq-tasks-when-__iavf_in_remo.patch @@ -0,0 +1,83 @@ +From 9a192631dd77235ace468f918cd52c54e1d4132f Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 7 Aug 2023 14:59:40 +0200 +Subject: iavf: do not process adminq tasks when __IAVF_IN_REMOVE_TASK is set + +From: Radoslaw Tyl + +[ Upstream commit c8de44b577eb540e8bfea55afe1d0904bb571b7a ] + +Prevent schedule operations for adminq during device remove and when +__IAVF_IN_REMOVE_TASK flag is set. Currently, the iavf_down function +adds operations for adminq that shouldn't be processed when the device +is in the __IAVF_REMOVE state. + +Reproduction: + +echo 4 > /sys/bus/pci/devices/0000:17:00.0/sriov_numvfs +ip link set dev ens1f0 vf 0 trust on +ip link set dev ens1f0 vf 1 trust on +ip link set dev ens1f0 vf 2 trust on +ip link set dev ens1f0 vf 3 trust on + +ip link set dev ens1f0 vf 0 mac 00:22:33:44:55:66 +ip link set dev ens1f0 vf 1 mac 00:22:33:44:55:67 +ip link set dev ens1f0 vf 2 mac 00:22:33:44:55:68 +ip link set dev ens1f0 vf 3 mac 00:22:33:44:55:69 + +echo 0000:17:02.0 > /sys/bus/pci/devices/0000\:17\:02.0/driver/unbind +echo 0000:17:02.1 > /sys/bus/pci/devices/0000\:17\:02.1/driver/unbind +echo 0000:17:02.2 > /sys/bus/pci/devices/0000\:17\:02.2/driver/unbind +echo 0000:17:02.3 > /sys/bus/pci/devices/0000\:17\:02.3/driver/unbind +sleep 10 +echo 0000:17:02.0 > /sys/bus/pci/drivers/iavf/bind +echo 0000:17:02.1 > /sys/bus/pci/drivers/iavf/bind +echo 0000:17:02.2 > /sys/bus/pci/drivers/iavf/bind +echo 0000:17:02.3 > /sys/bus/pci/drivers/iavf/bind + +modprobe vfio-pci +echo 8086 154c > /sys/bus/pci/drivers/vfio-pci/new_id + +qemu-system-x86_64 -accel kvm -m 4096 -cpu host \ +-drive file=centos9.qcow2,if=none,id=virtio-disk0 \ +-device virtio-blk-pci,drive=virtio-disk0,bootindex=0 -smp 4 \ +-device vfio-pci,host=17:02.0 -net none \ +-device vfio-pci,host=17:02.1 -net none \ +-device vfio-pci,host=17:02.2 -net none \ +-device vfio-pci,host=17:02.3 -net none \ +-daemonize -vnc :5 + +Current result: +There is a probability that the mac of VF in guest is inconsistent with +it in host + +Expected result: +When passthrough NIC VF to guest, the VF in guest should always get +the same mac as it in host. + +Fixes: 14756b2ae265 ("iavf: Fix __IAVF_RESETTING state usage") +Signed-off-by: Radoslaw Tyl +Tested-by: Rafal Romanowski +Signed-off-by: Tony Nguyen +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/iavf/iavf_main.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c +index a87f4f1ae6845..41b8ff0d4df5e 100644 +--- a/drivers/net/ethernet/intel/iavf/iavf_main.c ++++ b/drivers/net/ethernet/intel/iavf/iavf_main.c +@@ -1142,7 +1142,8 @@ void iavf_down(struct iavf_adapter *adapter) + iavf_clear_fdir_filters(adapter); + iavf_clear_adv_rss_conf(adapter); + +- if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)) { ++ if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) && ++ !(test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))) { + /* cancel any current operation */ + adapter->current_op = VIRTCHNL_OP_UNKNOWN; + /* Schedule operations to close down the HW. Don't wait +-- +2.40.1 + diff --git a/queue-5.15/igc-expose-tx-usecs-coalesce-setting-to-user.patch b/queue-5.15/igc-expose-tx-usecs-coalesce-setting-to-user.patch new file mode 100644 index 00000000000..9e2e41da45f --- /dev/null +++ b/queue-5.15/igc-expose-tx-usecs-coalesce-setting-to-user.patch @@ -0,0 +1,130 @@ +From b9a714a327393b17d9a90a3793a3ad8c6d1f562a Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 19 Sep 2023 10:03:31 -0700 +Subject: igc: Expose tx-usecs coalesce setting to user + +From: Muhammad Husaini Zulkifli + +[ Upstream commit 1703b2e0de653b459ca6230be32ce7f2ea0ae7ee ] + +When users attempt to obtain the coalesce setting using the +ethtool command, current code always returns 0 for tx-usecs. +This is because I225/6 always uses a queue pair setting, hence +tx_coalesce_usecs does not return a value during the +igc_ethtool_get_coalesce() callback process. The pair queue +condition checking in igc_ethtool_get_coalesce() is removed by +this patch so that the user gets information of the value of tx-usecs. + +Even if i225/6 is using queue pair setting, there is no harm in +notifying the user of the tx-usecs. The implementation of the current +code may have previously been a copy of the legacy code i210. +Since I225 has the queue pair setting enabled, tx-usecs will always adhere +to the user-set rx-usecs value. An error message will appear when the user +attempts to set the tx-usecs value for the input parameters because, +by default, they should only set the rx-usecs value. + +This patch also adds the helper function to get the +previous rx coalesce value similar to tx coalesce. + +How to test: +User can get the coalesce value using ethtool command. + +Example command: +Get: ethtool -c + +Previous output: + +rx-usecs: 3 +rx-frames: n/a +rx-usecs-irq: n/a +rx-frames-irq: n/a + +tx-usecs: 0 +tx-frames: n/a +tx-usecs-irq: n/a +tx-frames-irq: n/a + +New output: + +rx-usecs: 3 +rx-frames: n/a +rx-usecs-irq: n/a +rx-frames-irq: n/a + +tx-usecs: 3 +tx-frames: n/a +tx-usecs-irq: n/a +tx-frames-irq: n/a + +Fixes: 8c5ad0dae93c ("igc: Add ethtool support") +Signed-off-by: Muhammad Husaini Zulkifli +Tested-by: Naama Meir +Reviewed-by: Simon Horman +Signed-off-by: Tony Nguyen +Link: https://lore.kernel.org/r/20230919170331.1581031-1-anthony.l.nguyen@intel.com +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/igc/igc_ethtool.c | 31 ++++++++++++-------- + 1 file changed, 19 insertions(+), 12 deletions(-) + +diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c +index 859ddc07fbbfe..17cb4c13d0020 100644 +--- a/drivers/net/ethernet/intel/igc/igc_ethtool.c ++++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c +@@ -861,6 +861,18 @@ static void igc_ethtool_get_stats(struct net_device *netdev, + spin_unlock(&adapter->stats64_lock); + } + ++static int igc_ethtool_get_previous_rx_coalesce(struct igc_adapter *adapter) ++{ ++ return (adapter->rx_itr_setting <= 3) ? ++ adapter->rx_itr_setting : adapter->rx_itr_setting >> 2; ++} ++ ++static int igc_ethtool_get_previous_tx_coalesce(struct igc_adapter *adapter) ++{ ++ return (adapter->tx_itr_setting <= 3) ? ++ adapter->tx_itr_setting : adapter->tx_itr_setting >> 2; ++} ++ + static int igc_ethtool_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, + struct kernel_ethtool_coalesce *kernel_coal, +@@ -868,17 +880,8 @@ static int igc_ethtool_get_coalesce(struct net_device *netdev, + { + struct igc_adapter *adapter = netdev_priv(netdev); + +- if (adapter->rx_itr_setting <= 3) +- ec->rx_coalesce_usecs = adapter->rx_itr_setting; +- else +- ec->rx_coalesce_usecs = adapter->rx_itr_setting >> 2; +- +- if (!(adapter->flags & IGC_FLAG_QUEUE_PAIRS)) { +- if (adapter->tx_itr_setting <= 3) +- ec->tx_coalesce_usecs = adapter->tx_itr_setting; +- else +- ec->tx_coalesce_usecs = adapter->tx_itr_setting >> 2; +- } ++ ec->rx_coalesce_usecs = igc_ethtool_get_previous_rx_coalesce(adapter); ++ ec->tx_coalesce_usecs = igc_ethtool_get_previous_tx_coalesce(adapter); + + return 0; + } +@@ -903,8 +906,12 @@ static int igc_ethtool_set_coalesce(struct net_device *netdev, + ec->tx_coalesce_usecs == 2) + return -EINVAL; + +- if ((adapter->flags & IGC_FLAG_QUEUE_PAIRS) && ec->tx_coalesce_usecs) ++ if ((adapter->flags & IGC_FLAG_QUEUE_PAIRS) && ++ ec->tx_coalesce_usecs != igc_ethtool_get_previous_tx_coalesce(adapter)) { ++ NL_SET_ERR_MSG_MOD(extack, ++ "Queue Pair mode enabled, both Rx and Tx coalescing controlled by rx-usecs"); + return -EINVAL; ++ } + + /* If ITR is disabled, disable DMAC */ + if (ec->rx_coalesce_usecs == 0) { +-- +2.40.1 + diff --git a/queue-5.15/igc-fix-infinite-initialization-loop-with-early-xdp-.patch b/queue-5.15/igc-fix-infinite-initialization-loop-with-early-xdp-.patch new file mode 100644 index 00000000000..a81bac6b1cb --- /dev/null +++ b/queue-5.15/igc-fix-infinite-initialization-loop-with-early-xdp-.patch @@ -0,0 +1,55 @@ +From 40791e0e293682146831d563a7df7c58d6f912b6 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 13 Sep 2023 11:06:15 -0700 +Subject: igc: Fix infinite initialization loop with early XDP redirect + +From: Vinicius Costa Gomes + +[ Upstream commit cb47b1f679c4d83a5fa5f1852e472f844e41a3da ] + +When an XDP redirect happens before the link is ready, that +transmission will not finish and will timeout, causing an adapter +reset. If the redirects do not stop, the adapter will not stop +resetting. + +Wait for the driver to signal that there's a carrier before allowing +transmissions to proceed. + +Previous code was relying that when __IGC_DOWN is cleared, the NIC is +ready to transmit as all the queues are ready, what happens is that +the carrier presence will only be signaled later, after the watchdog +workqueue has a chance to run. And during this interval (between +clearing __IGC_DOWN and the watchdog running) if any transmission +happens the timeout is emitted (detected by igc_tx_timeout()) which +causes the reset, with the potential for the infinite loop. + +Fixes: 4ff320361092 ("igc: Add support for XDP_REDIRECT action") +Reported-by: Ferenc Fejes +Closes: https://lore.kernel.org/netdev/0caf33cf6adb3a5bf137eeaa20e89b167c9986d5.camel@ericsson.com/ +Signed-off-by: Vinicius Costa Gomes +Tested-by: Ferenc Fejes +Reviewed-by: Maciej Fijalkowski +Tested-by: Naama Meir +Signed-off-by: Tony Nguyen +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/igc/igc_main.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c +index a8c24a1c12b43..6185566fbb98c 100644 +--- a/drivers/net/ethernet/intel/igc/igc_main.c ++++ b/drivers/net/ethernet/intel/igc/igc_main.c +@@ -6271,7 +6271,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, + struct igc_ring *ring; + int i, drops; + +- if (unlikely(test_bit(__IGC_DOWN, &adapter->state))) ++ if (unlikely(!netif_carrier_ok(dev))) + return -ENETDOWN; + + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) +-- +2.40.1 + diff --git a/queue-5.15/ionic-fix-16bit-math-issue-when-page_size-64kb.patch b/queue-5.15/ionic-fix-16bit-math-issue-when-page_size-64kb.patch new file mode 100644 index 00000000000..49a7a16e7bc --- /dev/null +++ b/queue-5.15/ionic-fix-16bit-math-issue-when-page_size-64kb.patch @@ -0,0 +1,83 @@ +From 1a7cdefea68193762d727a59434102477ead6d6c Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 14 Sep 2023 18:02:52 -0400 +Subject: ionic: fix 16bit math issue when PAGE_SIZE >= 64KB + +From: David Christensen + +[ Upstream commit 8f6b846b0a86c3cbae8a25b772651cfc2270ad0a ] + +The ionic device supports a maximum buffer length of 16 bits (see +ionic_rxq_desc or ionic_rxq_sg_elem). When adding new buffers to +the receive rings, the function ionic_rx_fill() uses 16bit math when +calculating the number of pages to allocate for an RX descriptor, +given the interface's MTU setting. If the system PAGE_SIZE >= 64KB, +and the buf_info->page_offset is 0, the remain_len value will never +decrement from the original MTU value and the frag_len value will +always be 0, causing additional pages to be allocated as scatter- +gather elements unnecessarily. + +A similar math issue exists in ionic_rx_frags(), but no failures +have been observed here since a 64KB page should not normally +require any scatter-gather elements at any legal Ethernet MTU size. + +Fixes: 4b0a7539a372 ("ionic: implement Rx page reuse") +Signed-off-by: David Christensen +Reviewed-by: Shannon Nelson +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/pensando/ionic/ionic_dev.h | 1 + + drivers/net/ethernet/pensando/ionic/ionic_txrx.c | 10 +++++++--- + 2 files changed, 8 insertions(+), 3 deletions(-) + +diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h +index 922bb6c9e01d5..676c58dc19817 100644 +--- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h ++++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h +@@ -174,6 +174,7 @@ typedef void (*ionic_desc_cb)(struct ionic_queue *q, + struct ionic_desc_info *desc_info, + struct ionic_cq_info *cq_info, void *cb_arg); + ++#define IONIC_MAX_BUF_LEN ((u16)-1) + #define IONIC_PAGE_SIZE PAGE_SIZE + #define IONIC_PAGE_SPLIT_SZ (PAGE_SIZE / 2) + #define IONIC_PAGE_GFP_MASK (GFP_ATOMIC | __GFP_NOWARN |\ +diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +index 376f97b4008bb..6604f5862f892 100644 +--- a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c ++++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c +@@ -151,7 +151,8 @@ static struct sk_buff *ionic_rx_frags(struct ionic_queue *q, + return NULL; + } + +- frag_len = min_t(u16, len, IONIC_PAGE_SIZE - buf_info->page_offset); ++ frag_len = min_t(u16, len, min_t(u32, IONIC_MAX_BUF_LEN, ++ IONIC_PAGE_SIZE - buf_info->page_offset)); + len -= frag_len; + + dma_sync_single_for_cpu(dev, +@@ -388,7 +389,8 @@ void ionic_rx_fill(struct ionic_queue *q) + + /* fill main descriptor - buf[0] */ + desc->addr = cpu_to_le64(buf_info->dma_addr + buf_info->page_offset); +- frag_len = min_t(u16, len, IONIC_PAGE_SIZE - buf_info->page_offset); ++ frag_len = min_t(u16, len, min_t(u32, IONIC_MAX_BUF_LEN, ++ IONIC_PAGE_SIZE - buf_info->page_offset)); + desc->len = cpu_to_le16(frag_len); + remain_len -= frag_len; + buf_info++; +@@ -407,7 +409,9 @@ void ionic_rx_fill(struct ionic_queue *q) + } + + sg_elem->addr = cpu_to_le64(buf_info->dma_addr + buf_info->page_offset); +- frag_len = min_t(u16, remain_len, IONIC_PAGE_SIZE - buf_info->page_offset); ++ frag_len = min_t(u16, remain_len, min_t(u32, IONIC_MAX_BUF_LEN, ++ IONIC_PAGE_SIZE - ++ buf_info->page_offset)); + sg_elem->len = cpu_to_le16(frag_len); + remain_len -= frag_len; + buf_info++; +-- +2.40.1 + diff --git a/queue-5.15/ipv4-fix-null-deref-in-ipv4_link_failure.patch b/queue-5.15/ipv4-fix-null-deref-in-ipv4_link_failure.patch new file mode 100644 index 00000000000..ba6df592fa3 --- /dev/null +++ b/queue-5.15/ipv4-fix-null-deref-in-ipv4_link_failure.patch @@ -0,0 +1,53 @@ +From b9105a29366e34762370af5e1ef10fbe96e58fcd Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 14 Sep 2023 22:12:57 -0700 +Subject: ipv4: fix null-deref in ipv4_link_failure + +From: Kyle Zeng + +[ Upstream commit 0113d9c9d1ccc07f5a3710dac4aa24b6d711278c ] + +Currently, we assume the skb is associated with a device before calling +__ip_options_compile, which is not always the case if it is re-routed by +ipvs. +When skb->dev is NULL, dev_net(skb->dev) will become null-dereference. +This patch adds a check for the edge case and switch to use the net_device +from the rtable when skb->dev is NULL. + +Fixes: ed0de45a1008 ("ipv4: recompile ip options in ipv4_link_failure") +Suggested-by: David Ahern +Signed-off-by: Kyle Zeng +Cc: Stephen Suryaputra +Cc: Vadim Fedorenko +Reviewed-by: David Ahern +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/ipv4/route.c | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +diff --git a/net/ipv4/route.c b/net/ipv4/route.c +index bc6240d327a8f..968cc4aa6e96c 100644 +--- a/net/ipv4/route.c ++++ b/net/ipv4/route.c +@@ -1220,6 +1220,7 @@ EXPORT_INDIRECT_CALLABLE(ipv4_dst_check); + + static void ipv4_send_dest_unreach(struct sk_buff *skb) + { ++ struct net_device *dev; + struct ip_options opt; + int res; + +@@ -1237,7 +1238,8 @@ static void ipv4_send_dest_unreach(struct sk_buff *skb) + opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); + + rcu_read_lock(); +- res = __ip_options_compile(dev_net(skb->dev), &opt, skb, NULL); ++ dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev; ++ res = __ip_options_compile(dev_net(dev), &opt, skb, NULL); + rcu_read_unlock(); + + if (res) +-- +2.40.1 + diff --git a/queue-5.15/locking-seqlock-do-the-lockdep-annotation-before-loc.patch b/queue-5.15/locking-seqlock-do-the-lockdep-annotation-before-loc.patch new file mode 100644 index 00000000000..a81d048d5db --- /dev/null +++ b/queue-5.15/locking-seqlock-do-the-lockdep-annotation-before-loc.patch @@ -0,0 +1,59 @@ +From 3a38391ef588c8a09cb17ac3fd39db696f7d5f2b Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 20 Sep 2023 12:46:27 +0200 +Subject: locking/seqlock: Do the lockdep annotation before locking in + do_write_seqcount_begin_nested() + +From: Sebastian Andrzej Siewior + +[ Upstream commit 41b43b6c6e30a832c790b010a06772e793bca193 ] + +It was brought up by Tetsuo that the following sequence: + + write_seqlock_irqsave() + printk_deferred_enter() + +could lead to a deadlock if the lockdep annotation within +write_seqlock_irqsave() triggers. + +The problem is that the sequence counter is incremented before the lockdep +annotation is performed. The lockdep splat would then attempt to invoke +printk() but the reader side, of the same seqcount, could have a +tty_port::lock acquired waiting for the sequence number to become even again. + +The other lockdep annotations come before the actual locking because "we +want to see the locking error before it happens". There is no reason why +seqcount should be different here. + +Do the lockdep annotation first then perform the locking operation (the +sequence increment). + +Fixes: 1ca7d67cf5d5a ("seqcount: Add lockdep functionality to seqcount/seqlock structures") +Reported-by: Tetsuo Handa +Signed-off-by: Sebastian Andrzej Siewior +Signed-off-by: Ingo Molnar +Link: https://lore.kernel.org/r/20230920104627._DTHgPyA@linutronix.de + +Closes: https://lore.kernel.org/20230621130641.-5iueY1I@linutronix.de +Signed-off-by: Sasha Levin +--- + include/linux/seqlock.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h +index 37ded6b8fee61..2c5d0102315d2 100644 +--- a/include/linux/seqlock.h ++++ b/include/linux/seqlock.h +@@ -516,8 +516,8 @@ do { \ + + static inline void do_write_seqcount_begin_nested(seqcount_t *s, int subclass) + { +- do_raw_write_seqcount_begin(s); + seqcount_acquire(&s->dep_map, subclass, 0, _RET_IP_); ++ do_raw_write_seqcount_begin(s); + } + + /** +-- +2.40.1 + diff --git a/queue-5.15/net-bridge-use-dev_stats_inc.patch b/queue-5.15/net-bridge-use-dev_stats_inc.patch new file mode 100644 index 00000000000..c577af4c64d --- /dev/null +++ b/queue-5.15/net-bridge-use-dev_stats_inc.patch @@ -0,0 +1,139 @@ +From 7a7bb0005708cb863d5d65334b73087ffc61b244 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 18 Sep 2023 09:13:51 +0000 +Subject: net: bridge: use DEV_STATS_INC() + +From: Eric Dumazet + +[ Upstream commit 44bdb313da57322c9b3c108eb66981c6ec6509f4 ] + +syzbot/KCSAN reported data-races in br_handle_frame_finish() [1] +This function can run from multiple cpus without mutual exclusion. + +Adopt SMP safe DEV_STATS_INC() to update dev->stats fields. + +Handles updates to dev->stats.tx_dropped while we are at it. + +[1] +BUG: KCSAN: data-race in br_handle_frame_finish / br_handle_frame_finish + +read-write to 0xffff8881374b2178 of 8 bytes by interrupt on cpu 1: +br_handle_frame_finish+0xd4f/0xef0 net/bridge/br_input.c:189 +br_nf_hook_thresh+0x1ed/0x220 +br_nf_pre_routing_finish_ipv6+0x50f/0x540 +NF_HOOK include/linux/netfilter.h:304 [inline] +br_nf_pre_routing_ipv6+0x1e3/0x2a0 net/bridge/br_netfilter_ipv6.c:178 +br_nf_pre_routing+0x526/0xba0 net/bridge/br_netfilter_hooks.c:508 +nf_hook_entry_hookfn include/linux/netfilter.h:144 [inline] +nf_hook_bridge_pre net/bridge/br_input.c:272 [inline] +br_handle_frame+0x4c9/0x940 net/bridge/br_input.c:417 +__netif_receive_skb_core+0xa8a/0x21e0 net/core/dev.c:5417 +__netif_receive_skb_one_core net/core/dev.c:5521 [inline] +__netif_receive_skb+0x57/0x1b0 net/core/dev.c:5637 +process_backlog+0x21f/0x380 net/core/dev.c:5965 +__napi_poll+0x60/0x3b0 net/core/dev.c:6527 +napi_poll net/core/dev.c:6594 [inline] +net_rx_action+0x32b/0x750 net/core/dev.c:6727 +__do_softirq+0xc1/0x265 kernel/softirq.c:553 +run_ksoftirqd+0x17/0x20 kernel/softirq.c:921 +smpboot_thread_fn+0x30a/0x4a0 kernel/smpboot.c:164 +kthread+0x1d7/0x210 kernel/kthread.c:388 +ret_from_fork+0x48/0x60 arch/x86/kernel/process.c:147 +ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:304 + +read-write to 0xffff8881374b2178 of 8 bytes by interrupt on cpu 0: +br_handle_frame_finish+0xd4f/0xef0 net/bridge/br_input.c:189 +br_nf_hook_thresh+0x1ed/0x220 +br_nf_pre_routing_finish_ipv6+0x50f/0x540 +NF_HOOK include/linux/netfilter.h:304 [inline] +br_nf_pre_routing_ipv6+0x1e3/0x2a0 net/bridge/br_netfilter_ipv6.c:178 +br_nf_pre_routing+0x526/0xba0 net/bridge/br_netfilter_hooks.c:508 +nf_hook_entry_hookfn include/linux/netfilter.h:144 [inline] +nf_hook_bridge_pre net/bridge/br_input.c:272 [inline] +br_handle_frame+0x4c9/0x940 net/bridge/br_input.c:417 +__netif_receive_skb_core+0xa8a/0x21e0 net/core/dev.c:5417 +__netif_receive_skb_one_core net/core/dev.c:5521 [inline] +__netif_receive_skb+0x57/0x1b0 net/core/dev.c:5637 +process_backlog+0x21f/0x380 net/core/dev.c:5965 +__napi_poll+0x60/0x3b0 net/core/dev.c:6527 +napi_poll net/core/dev.c:6594 [inline] +net_rx_action+0x32b/0x750 net/core/dev.c:6727 +__do_softirq+0xc1/0x265 kernel/softirq.c:553 +do_softirq+0x5e/0x90 kernel/softirq.c:454 +__local_bh_enable_ip+0x64/0x70 kernel/softirq.c:381 +__raw_spin_unlock_bh include/linux/spinlock_api_smp.h:167 [inline] +_raw_spin_unlock_bh+0x36/0x40 kernel/locking/spinlock.c:210 +spin_unlock_bh include/linux/spinlock.h:396 [inline] +batadv_tt_local_purge+0x1a8/0x1f0 net/batman-adv/translation-table.c:1356 +batadv_tt_purge+0x2b/0x630 net/batman-adv/translation-table.c:3560 +process_one_work kernel/workqueue.c:2630 [inline] +process_scheduled_works+0x5b8/0xa30 kernel/workqueue.c:2703 +worker_thread+0x525/0x730 kernel/workqueue.c:2784 +kthread+0x1d7/0x210 kernel/kthread.c:388 +ret_from_fork+0x48/0x60 arch/x86/kernel/process.c:147 +ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:304 + +value changed: 0x00000000000d7190 -> 0x00000000000d7191 + +Reported by Kernel Concurrency Sanitizer on: +CPU: 0 PID: 14848 Comm: kworker/u4:11 Not tainted 6.6.0-rc1-syzkaller-00236-gad8a69f361b9 #0 + +Fixes: 1c29fc4989bc ("[BRIDGE]: keep track of received multicast packets") +Reported-by: syzbot +Signed-off-by: Eric Dumazet +Cc: Roopa Prabhu +Cc: Nikolay Aleksandrov +Cc: bridge@lists.linux-foundation.org +Acked-by: Nikolay Aleksandrov +Link: https://lore.kernel.org/r/20230918091351.1356153-1-edumazet@google.com +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/bridge/br_forward.c | 4 ++-- + net/bridge/br_input.c | 4 ++-- + 2 files changed, 4 insertions(+), 4 deletions(-) + +diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c +index 3d69ad5463a9f..011bd3c59da19 100644 +--- a/net/bridge/br_forward.c ++++ b/net/bridge/br_forward.c +@@ -124,7 +124,7 @@ static int deliver_clone(const struct net_bridge_port *prev, + + skb = skb_clone(skb, GFP_ATOMIC); + if (!skb) { +- dev->stats.tx_dropped++; ++ DEV_STATS_INC(dev, tx_dropped); + return -ENOMEM; + } + +@@ -263,7 +263,7 @@ static void maybe_deliver_addr(struct net_bridge_port *p, struct sk_buff *skb, + + skb = skb_copy(skb, GFP_ATOMIC); + if (!skb) { +- dev->stats.tx_dropped++; ++ DEV_STATS_INC(dev, tx_dropped); + return; + } + +diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c +index 6743c8a0fe8e1..54bfcdf692732 100644 +--- a/net/bridge/br_input.c ++++ b/net/bridge/br_input.c +@@ -146,12 +146,12 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb + if ((mdst && mdst->host_joined) || + br_multicast_is_router(brmctx, skb)) { + local_rcv = true; +- br->dev->stats.multicast++; ++ DEV_STATS_INC(br->dev, multicast); + } + mcast_hit = true; + } else { + local_rcv = true; +- br->dev->stats.multicast++; ++ DEV_STATS_INC(br->dev, multicast); + } + break; + case BR_PKT_UNICAST: +-- +2.40.1 + diff --git a/queue-5.15/net-core-fix-eth_p_1588-flow-dissector.patch b/queue-5.15/net-core-fix-eth_p_1588-flow-dissector.patch new file mode 100644 index 00000000000..6dfbdf00c73 --- /dev/null +++ b/queue-5.15/net-core-fix-eth_p_1588-flow-dissector.patch @@ -0,0 +1,123 @@ +From 92d83cb634478dfa0809d666a3e4bce63c6f076b Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 13 Sep 2023 09:39:05 +0300 +Subject: net/core: Fix ETH_P_1588 flow dissector + +From: Sasha Neftin + +[ Upstream commit 75ad80ed88a182ab2ad5513e448cf07b403af5c3 ] + +When a PTP ethernet raw frame with a size of more than 256 bytes followed +by a 0xff pattern is sent to __skb_flow_dissect, nhoff value calculation +is wrong. For example: hdr->message_length takes the wrong value (0xffff) +and it does not replicate real header length. In this case, 'nhoff' value +was overridden and the PTP header was badly dissected. This leads to a +kernel crash. + +net/core: flow_dissector +net/core flow dissector nhoff = 0x0000000e +net/core flow dissector hdr->message_length = 0x0000ffff +net/core flow dissector nhoff = 0x0001000d (u16 overflow) +... +skb linear: 00000000: 00 a0 c9 00 00 00 00 a0 c9 00 00 00 88 +skb frag: 00000000: f7 ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff + +Using the size of the ptp_header struct will allow the corrected +calculation of the nhoff value. + +net/core flow dissector nhoff = 0x0000000e +net/core flow dissector nhoff = 0x00000030 (sizeof ptp_header) +... +skb linear: 00000000: 00 a0 c9 00 00 00 00 a0 c9 00 00 00 88 f7 ff ff +skb linear: 00000010: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff +skb linear: 00000020: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff +skb frag: 00000000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff + +Kernel trace: +[ 74.984279] ------------[ cut here ]------------ +[ 74.989471] kernel BUG at include/linux/skbuff.h:2440! +[ 74.995237] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI +[ 75.001098] CPU: 4 PID: 0 Comm: swapper/4 Tainted: G U 5.15.85-intel-ese-standard-lts #1 +[ 75.011629] Hardware name: Intel Corporation A-Island (CPU:AlderLake)/A-Island (ID:06), BIOS SB_ADLP.01.01.00.01.03.008.D-6A9D9E73-dirty Mar 30 2023 +[ 75.026507] RIP: 0010:eth_type_trans+0xd0/0x130 +[ 75.031594] Code: 03 88 47 78 eb c7 8b 47 68 2b 47 6c 48 8b 97 c0 00 00 00 83 f8 01 7e 1b 48 85 d2 74 06 66 83 3a ff 74 09 b8 00 04 00 00 eb ab <0f> 0b b8 00 01 00 00 eb a2 48 85 ff 74 eb 48 8d 54 24 06 31 f6 b9 +[ 75.052612] RSP: 0018:ffff9948c0228de0 EFLAGS: 00010297 +[ 75.058473] RAX: 00000000000003f2 RBX: ffff8e47047dc300 RCX: 0000000000001003 +[ 75.066462] RDX: ffff8e4e8c9ea040 RSI: ffff8e4704e0a000 RDI: ffff8e47047dc300 +[ 75.074458] RBP: ffff8e4704e2acc0 R08: 00000000000003f3 R09: 0000000000000800 +[ 75.082466] R10: 000000000000000d R11: ffff9948c0228dec R12: ffff8e4715e4e010 +[ 75.090461] R13: ffff9948c0545018 R14: 0000000000000001 R15: 0000000000000800 +[ 75.098464] FS: 0000000000000000(0000) GS:ffff8e4e8fb00000(0000) knlGS:0000000000000000 +[ 75.107530] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +[ 75.113982] CR2: 00007f5eb35934a0 CR3: 0000000150e0a002 CR4: 0000000000770ee0 +[ 75.121980] PKRU: 55555554 +[ 75.125035] Call Trace: +[ 75.127792] +[ 75.130063] ? eth_get_headlen+0xa4/0xc0 +[ 75.134472] igc_process_skb_fields+0xcd/0x150 +[ 75.139461] igc_poll+0xc80/0x17b0 +[ 75.143272] __napi_poll+0x27/0x170 +[ 75.147192] net_rx_action+0x234/0x280 +[ 75.151409] __do_softirq+0xef/0x2f4 +[ 75.155424] irq_exit_rcu+0xc7/0x110 +[ 75.159432] common_interrupt+0xb8/0xd0 +[ 75.163748] +[ 75.166112] +[ 75.168473] asm_common_interrupt+0x22/0x40 +[ 75.173175] RIP: 0010:cpuidle_enter_state+0xe2/0x350 +[ 75.178749] Code: 85 c0 0f 8f 04 02 00 00 31 ff e8 39 6c 67 ff 45 84 ff 74 12 9c 58 f6 c4 02 0f 85 50 02 00 00 31 ff e8 52 b0 6d ff fb 45 85 f6 <0f> 88 b1 00 00 00 49 63 ce 4c 2b 2c 24 48 89 c8 48 6b d1 68 48 c1 +[ 75.199757] RSP: 0018:ffff9948c013bea8 EFLAGS: 00000202 +[ 75.205614] RAX: ffff8e4e8fb00000 RBX: ffffb948bfd23900 RCX: 000000000000001f +[ 75.213619] RDX: 0000000000000004 RSI: ffffffff94206161 RDI: ffffffff94212e20 +[ 75.221620] RBP: 0000000000000004 R08: 000000117568973a R09: 0000000000000001 +[ 75.229622] R10: 000000000000afc8 R11: ffff8e4e8fb29ce4 R12: ffffffff945ae980 +[ 75.237628] R13: 000000117568973a R14: 0000000000000004 R15: 0000000000000000 +[ 75.245635] ? cpuidle_enter_state+0xc7/0x350 +[ 75.250518] cpuidle_enter+0x29/0x40 +[ 75.254539] do_idle+0x1d9/0x260 +[ 75.258166] cpu_startup_entry+0x19/0x20 +[ 75.262582] secondary_startup_64_no_verify+0xc2/0xcb +[ 75.268259] +[ 75.270721] Modules linked in: 8021q snd_sof_pci_intel_tgl snd_sof_intel_hda_common tpm_crb snd_soc_hdac_hda snd_sof_intel_hda snd_hda_ext_core snd_sof_pci snd_sof snd_sof_xtensa_dsp snd_soc_acpi_intel_match snd_soc_acpi snd_soc_core snd_compress iTCO_wdt ac97_bus intel_pmc_bxt mei_hdcp iTCO_vendor_support snd_hda_codec_hdmi pmt_telemetry intel_pmc_core pmt_class snd_hda_intel x86_pkg_temp_thermal snd_intel_dspcfg snd_hda_codec snd_hda_core kvm_intel snd_pcm snd_timer kvm snd mei_me soundcore tpm_tis irqbypass i2c_i801 mei tpm_tis_core pcspkr intel_rapl_msr tpm i2c_smbus intel_pmt thermal sch_fq_codel uio uhid i915 drm_buddy video drm_display_helper drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm fuse configfs +[ 75.342736] ---[ end trace 3785f9f360400e3a ]--- +[ 75.347913] RIP: 0010:eth_type_trans+0xd0/0x130 +[ 75.352984] Code: 03 88 47 78 eb c7 8b 47 68 2b 47 6c 48 8b 97 c0 00 00 00 83 f8 01 7e 1b 48 85 d2 74 06 66 83 3a ff 74 09 b8 00 04 00 00 eb ab <0f> 0b b8 00 01 00 00 eb a2 48 85 ff 74 eb 48 8d 54 24 06 31 f6 b9 +[ 75.373994] RSP: 0018:ffff9948c0228de0 EFLAGS: 00010297 +[ 75.379860] RAX: 00000000000003f2 RBX: ffff8e47047dc300 RCX: 0000000000001003 +[ 75.387856] RDX: ffff8e4e8c9ea040 RSI: ffff8e4704e0a000 RDI: ffff8e47047dc300 +[ 75.395864] RBP: ffff8e4704e2acc0 R08: 00000000000003f3 R09: 0000000000000800 +[ 75.403857] R10: 000000000000000d R11: ffff9948c0228dec R12: ffff8e4715e4e010 +[ 75.411863] R13: ffff9948c0545018 R14: 0000000000000001 R15: 0000000000000800 +[ 75.419875] FS: 0000000000000000(0000) GS:ffff8e4e8fb00000(0000) knlGS:0000000000000000 +[ 75.428946] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +[ 75.435403] CR2: 00007f5eb35934a0 CR3: 0000000150e0a002 CR4: 0000000000770ee0 +[ 75.443410] PKRU: 55555554 +[ 75.446477] Kernel panic - not syncing: Fatal exception in interrupt +[ 75.453738] Kernel Offset: 0x11c00000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) +[ 75.465794] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]--- + +Fixes: 4f1cc51f3488 ("net: flow_dissector: Parse PTP L2 packet header") +Signed-off-by: Sasha Neftin +Reviewed-by: Jiri Pirko +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/core/flow_dissector.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c +index 2596a54c2fe71..a1efbd0f2ad32 100644 +--- a/net/core/flow_dissector.c ++++ b/net/core/flow_dissector.c +@@ -1278,7 +1278,7 @@ bool __skb_flow_dissect(const struct net *net, + break; + } + +- nhoff += ntohs(hdr->message_length); ++ nhoff += sizeof(struct ptp_header); + fdret = FLOW_DISSECT_RET_OUT_GOOD; + break; + } +-- +2.40.1 + diff --git a/queue-5.15/net-ena-flush-xdp-packets-on-error.patch b/queue-5.15/net-ena-flush-xdp-packets-on-error.patch new file mode 100644 index 00000000000..45a2201e2ab --- /dev/null +++ b/queue-5.15/net-ena-flush-xdp-packets-on-error.patch @@ -0,0 +1,48 @@ +From 067c9ec47f0494ce29238d5a763ab8ddc5b2e725 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 18 Sep 2023 17:36:09 +0200 +Subject: net: ena: Flush XDP packets on error. + +From: Sebastian Andrzej Siewior + +[ Upstream commit 6f411fb5ca9419090bee6a0a46425e0a5060b734 ] + +xdp_do_flush() should be invoked before leaving the NAPI poll function +after a XDP-redirect. This is not the case if the driver leaves via +the error path (after having a redirect in one of its previous +iterations). + +Invoke xdp_do_flush() also in the error path. + +Cc: Arthur Kiyanovski +Cc: David Arinzon +Cc: Noam Dagan +Cc: Saeed Bishara +Cc: Shay Agroskin +Fixes: a318c70ad152b ("net: ena: introduce XDP redirect implementation") +Acked-by: Arthur Kiyanovski +Signed-off-by: Sebastian Andrzej Siewior +Acked-by: Jesper Dangaard Brouer +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/amazon/ena/ena_netdev.c | 3 +++ + 1 file changed, 3 insertions(+) + +diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c +index f3673be4fc087..3eba01de95259 100644 +--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c ++++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c +@@ -1788,6 +1788,9 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, + return work_done; + + error: ++ if (xdp_flags & ENA_XDP_REDIRECT) ++ xdp_do_flush(); ++ + adapter = netdev_priv(rx_ring->netdev); + + if (rc == -ENOSPC) { +-- +2.40.1 + diff --git a/queue-5.15/net-hns3-add-5ms-delay-before-clear-firmware-reset-i.patch b/queue-5.15/net-hns3-add-5ms-delay-before-clear-firmware-reset-i.patch new file mode 100644 index 00000000000..86e757038f7 --- /dev/null +++ b/queue-5.15/net-hns3-add-5ms-delay-before-clear-firmware-reset-i.patch @@ -0,0 +1,48 @@ +From 5975d95ac8cc3d3d75bbfa8c60f2a9ff74dd1c45 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 18 Sep 2023 15:48:40 +0800 +Subject: net: hns3: add 5ms delay before clear firmware reset irq source + +From: Jie Wang + +[ Upstream commit 0770063096d5da4a8e467b6e73c1646a75589628 ] + +Currently the reset process in hns3 and firmware watchdog init process is +asynchronous. we think firmware watchdog initialization is completed +before hns3 clear the firmware interrupt source. However, firmware +initialization may not complete early. + +so we add delay before hns3 clear firmware interrupt source and 5 ms delay +is enough to avoid second firmware reset interrupt. + +Fixes: c1a81619d73a ("net: hns3: Add mailbox interrupt handling to PF driver") +Signed-off-by: Jie Wang +Signed-off-by: Jijie Shao +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 5 +++++ + 1 file changed, 5 insertions(+) + +diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +index 0f522daf8e3ab..ca59e1cd992e5 100644 +--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c ++++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +@@ -3391,9 +3391,14 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) + static void hclge_clear_event_cause(struct hclge_dev *hdev, u32 event_type, + u32 regclr) + { ++#define HCLGE_IMP_RESET_DELAY 5 ++ + switch (event_type) { + case HCLGE_VECTOR0_EVENT_PTP: + case HCLGE_VECTOR0_EVENT_RST: ++ if (regclr == BIT(HCLGE_VECTOR0_IMPRESET_INT_B)) ++ mdelay(HCLGE_IMP_RESET_DELAY); ++ + hclge_write_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG, regclr); + break; + case HCLGE_VECTOR0_EVENT_MBX: +-- +2.40.1 + diff --git a/queue-5.15/net-hns3-fix-fail-to-delete-tc-flower-rules-during-r.patch b/queue-5.15/net-hns3-fix-fail-to-delete-tc-flower-rules-during-r.patch new file mode 100644 index 00000000000..1b9584107ad --- /dev/null +++ b/queue-5.15/net-hns3-fix-fail-to-delete-tc-flower-rules-during-r.patch @@ -0,0 +1,43 @@ +From 4afbdef3269c824ea649bd639d6a951e3b15ceba Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 18 Sep 2023 15:48:39 +0800 +Subject: net: hns3: fix fail to delete tc flower rules during reset issue + +From: Jijie Shao + +[ Upstream commit 1a7be66e4685b8541546222c305cce9710718a88 ] + +Firmware does not respond driver commands during reset +Therefore, rule will fail to delete while the firmware is resetting + +So, if failed to delete rule, set rule state to TO_DEL, +and the rule will be deleted when periodic task being scheduled. + +Fixes: 0205ec041ec6 ("net: hns3: add support for hw tc offload of tc flower") +Signed-off-by: Jijie Shao +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 6 ++++++ + 1 file changed, 6 insertions(+) + +diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +index 998ee681b1171..0f522daf8e3ab 100644 +--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c ++++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +@@ -7546,6 +7546,12 @@ static int hclge_del_cls_flower(struct hnae3_handle *handle, + ret = hclge_fd_tcam_config(hdev, HCLGE_FD_STAGE_1, true, rule->location, + NULL, false); + if (ret) { ++ /* if tcam config fail, set rule state to TO_DEL, ++ * so the rule will be deleted when periodic ++ * task being scheduled. ++ */ ++ hclge_update_fd_list(hdev, HCLGE_FD_TO_DEL, rule->location, NULL); ++ set_bit(HCLGE_STATE_FD_TBL_CHANGED, &hdev->state); + spin_unlock_bh(&hdev->fd_rule_lock); + return ret; + } +-- +2.40.1 + diff --git a/queue-5.15/net-hns3-fix-gre-checksum-offload-issue.patch b/queue-5.15/net-hns3-fix-gre-checksum-offload-issue.patch new file mode 100644 index 00000000000..4a67c1a56d8 --- /dev/null +++ b/queue-5.15/net-hns3-fix-gre-checksum-offload-issue.patch @@ -0,0 +1,46 @@ +From c75d88d8cfe21580b456f87538a7e56d0cdca6f9 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 18 Sep 2023 15:48:37 +0800 +Subject: net: hns3: fix GRE checksum offload issue + +From: Jie Wang + +[ Upstream commit f9f651261130cdcb7adc9a3e365b356bc2749ab3 ] + +The device_version V3 hardware can't offload the checksum for IP in GRE +packets, but can do it for NvGRE. So default to disable the checksum and +GSO offload for GRE, but keep the ability to enable it when only using +NvGRE. + +Fixes: 76ad4f0ee747 ("net: hns3: Add support of HNS3 Ethernet Driver for hip08 SoC") +Signed-off-by: Jie Wang +Signed-off-by: Jijie Shao +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 9 +++++++++ + 1 file changed, 9 insertions(+) + +diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +index 3693ff55197dd..fde1ff3580458 100644 +--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c ++++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +@@ -3156,6 +3156,15 @@ static void hns3_set_default_feature(struct net_device *netdev) + NETIF_F_HW_TC); + + netdev->hw_enc_features |= netdev->vlan_features | NETIF_F_TSO_MANGLEID; ++ ++ /* The device_version V3 hardware can't offload the checksum for IP in ++ * GRE packets, but can do it for NvGRE. So default to disable the ++ * checksum and GSO offload for GRE. ++ */ ++ if (ae_dev->dev_version > HNAE3_DEVICE_VERSION_V2) { ++ netdev->features &= ~NETIF_F_GSO_GRE; ++ netdev->features &= ~NETIF_F_GSO_GRE_CSUM; ++ } + } + + static int hns3_alloc_buffer(struct hns3_enet_ring *ring, +-- +2.40.1 + diff --git a/queue-5.15/net-hns3-only-enable-unicast-promisc-when-mac-table-.patch b/queue-5.15/net-hns3-only-enable-unicast-promisc-when-mac-table-.patch new file mode 100644 index 00000000000..87ce74384e0 --- /dev/null +++ b/queue-5.15/net-hns3-only-enable-unicast-promisc-when-mac-table-.patch @@ -0,0 +1,39 @@ +From 8266d6520092624b1bc39212498f741cd7cfe0df Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 18 Sep 2023 15:48:38 +0800 +Subject: net: hns3: only enable unicast promisc when mac table full + +From: Jian Shen + +[ Upstream commit f2ed304922a55690529bcca59678dd92d7466ce8 ] + +Currently, the driver will enable unicast promisc for the function +once configure mac address fail. It's unreasonable when the failure +is caused by using same mac address with other functions. So only +enable unicast promisc when mac table full. + +Fixes: c631c696823c ("net: hns3: refactor the promisc mode setting") +Signed-off-by: Jian Shen +Signed-off-by: Jijie Shao +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +index a415760505ab4..998ee681b1171 100644 +--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c ++++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +@@ -8967,7 +8967,7 @@ static void hclge_update_overflow_flags(struct hclge_vport *vport, + if (mac_type == HCLGE_MAC_ADDR_UC) { + if (is_all_added) + vport->overflow_promisc_flags &= ~HNAE3_OVERFLOW_UPE; +- else ++ else if (hclge_is_umv_space_full(vport, true)) + vport->overflow_promisc_flags |= HNAE3_OVERFLOW_UPE; + } else { + if (is_all_added) +-- +2.40.1 + diff --git a/queue-5.15/net-rds-fix-possible-null-pointer-dereference.patch b/queue-5.15/net-rds-fix-possible-null-pointer-dereference.patch new file mode 100644 index 00000000000..541341edf1e --- /dev/null +++ b/queue-5.15/net-rds-fix-possible-null-pointer-dereference.patch @@ -0,0 +1,48 @@ +From 931460e236e828d8eeb7fd4d4ec7b3cd46667442 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 18 Sep 2023 16:56:23 +0300 +Subject: net: rds: Fix possible NULL-pointer dereference + +From: Artem Chernyshev + +[ Upstream commit f1d95df0f31048f1c59092648997686e3f7d9478 ] + +In rds_rdma_cm_event_handler_cmn() check, if conn pointer exists +before dereferencing it as rdma_set_service_type() argument + +Found by Linux Verification Center (linuxtesting.org) with SVACE. + +Fixes: fd261ce6a30e ("rds: rdma: update rdma transport for tos") +Signed-off-by: Artem Chernyshev +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + net/rds/rdma_transport.c | 12 +++++++----- + 1 file changed, 7 insertions(+), 5 deletions(-) + +diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c +index a9e4ff948a7d6..f71f073fd27ac 100644 +--- a/net/rds/rdma_transport.c ++++ b/net/rds/rdma_transport.c +@@ -86,11 +86,13 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, + break; + + case RDMA_CM_EVENT_ADDR_RESOLVED: +- rdma_set_service_type(cm_id, conn->c_tos); +- rdma_set_min_rnr_timer(cm_id, IB_RNR_TIMER_000_32); +- /* XXX do we need to clean up if this fails? */ +- ret = rdma_resolve_route(cm_id, +- RDS_RDMA_RESOLVE_TIMEOUT_MS); ++ if (conn) { ++ rdma_set_service_type(cm_id, conn->c_tos); ++ rdma_set_min_rnr_timer(cm_id, IB_RNR_TIMER_000_32); ++ /* XXX do we need to clean up if this fails? */ ++ ret = rdma_resolve_route(cm_id, ++ RDS_RDMA_RESOLVE_TIMEOUT_MS); ++ } + break; + + case RDMA_CM_EVENT_ROUTE_RESOLVED: +-- +2.40.1 + diff --git a/queue-5.15/netfilter-ipset-fix-race-between-ipset_cmd_create-an.patch b/queue-5.15/netfilter-ipset-fix-race-between-ipset_cmd_create-an.patch new file mode 100644 index 00000000000..4bd69d9f9b1 --- /dev/null +++ b/queue-5.15/netfilter-ipset-fix-race-between-ipset_cmd_create-an.patch @@ -0,0 +1,64 @@ +From f548f5fc12060efc8b637ce8874adca6000ca921 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 19 Sep 2023 20:04:45 +0200 +Subject: netfilter: ipset: Fix race between IPSET_CMD_CREATE and + IPSET_CMD_SWAP + +From: Jozsef Kadlecsik + +[ Upstream commit 7433b6d2afd512d04398c73aa984d1e285be125b ] + +Kyle Zeng reported that there is a race between IPSET_CMD_ADD and IPSET_CMD_SWAP +in netfilter/ip_set, which can lead to the invocation of `__ip_set_put` on a +wrong `set`, triggering the `BUG_ON(set->ref == 0);` check in it. + +The race is caused by using the wrong reference counter, i.e. the ref counter instead +of ref_netlink. + +Fixes: 24e227896bbf ("netfilter: ipset: Add schedule point in call_ad().") +Reported-by: Kyle Zeng +Closes: https://lore.kernel.org/netfilter-devel/ZPZqetxOmH+w%2Fmyc@westworld/#r +Tested-by: Kyle Zeng +Signed-off-by: Jozsef Kadlecsik +Signed-off-by: Florian Westphal +Signed-off-by: Sasha Levin +--- + net/netfilter/ipset/ip_set_core.c | 12 ++++++++++-- + 1 file changed, 10 insertions(+), 2 deletions(-) + +diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c +index c911fc09f363c..33869db42bb6b 100644 +--- a/net/netfilter/ipset/ip_set_core.c ++++ b/net/netfilter/ipset/ip_set_core.c +@@ -682,6 +682,14 @@ __ip_set_put(struct ip_set *set) + /* set->ref can be swapped out by ip_set_swap, netlink events (like dump) need + * a separate reference counter + */ ++static void ++__ip_set_get_netlink(struct ip_set *set) ++{ ++ write_lock_bh(&ip_set_ref_lock); ++ set->ref_netlink++; ++ write_unlock_bh(&ip_set_ref_lock); ++} ++ + static void + __ip_set_put_netlink(struct ip_set *set) + { +@@ -1695,11 +1703,11 @@ call_ad(struct net *net, struct sock *ctnl, struct sk_buff *skb, + + do { + if (retried) { +- __ip_set_get(set); ++ __ip_set_get_netlink(set); + nfnl_unlock(NFNL_SUBSYS_IPSET); + cond_resched(); + nfnl_lock(NFNL_SUBSYS_IPSET); +- __ip_set_put(set); ++ __ip_set_put_netlink(set); + } + + ip_set_lock(set); +-- +2.40.1 + diff --git a/queue-5.15/netfilter-nf_tables-disable-toggling-dormant-table-s.patch b/queue-5.15/netfilter-nf_tables-disable-toggling-dormant-table-s.patch new file mode 100644 index 00000000000..43e5cdd650e --- /dev/null +++ b/queue-5.15/netfilter-nf_tables-disable-toggling-dormant-table-s.patch @@ -0,0 +1,59 @@ +From 0fb869ed2d0d8eb57f40feb5f988061ac50caff3 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 15 Sep 2023 15:18:11 +0200 +Subject: netfilter: nf_tables: disable toggling dormant table state more than + once + +From: Florian Westphal + +[ Upstream commit c9bd26513b3a11b3adb3c2ed8a31a01a87173ff1 ] + +nft -f -< +Cc: Bing-Jhong Billy Jheng +Cc: info@starlabs.sg +Signed-off-by: Florian Westphal +Signed-off-by: Sasha Levin +--- + net/netfilter/nf_tables_api.c | 4 ++++ + 1 file changed, 4 insertions(+) + +diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c +index 56098859d5b44..2f7d8e0e47de8 100644 +--- a/net/netfilter/nf_tables_api.c ++++ b/net/netfilter/nf_tables_api.c +@@ -1159,6 +1159,10 @@ static int nf_tables_updtable(struct nft_ctx *ctx) + flags & NFT_TABLE_F_OWNER)) + return -EOPNOTSUPP; + ++ /* No dormant off/on/off/on games in single transaction */ ++ if (ctx->table->flags & __NFT_TABLE_F_UPDATE) ++ return -EINVAL; ++ + trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, + sizeof(struct nft_trans_table)); + if (trans == NULL) +-- +2.40.1 + diff --git a/queue-5.15/netfilter-nf_tables-disallow-element-removal-on-anon.patch b/queue-5.15/netfilter-nf_tables-disallow-element-removal-on-anon.patch new file mode 100644 index 00000000000..2c23a85b6af --- /dev/null +++ b/queue-5.15/netfilter-nf_tables-disallow-element-removal-on-anon.patch @@ -0,0 +1,58 @@ +From 2e8edb2ea100ea010be83d46a2ac56ad3e509e24 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sun, 10 Sep 2023 19:04:45 +0200 +Subject: netfilter: nf_tables: disallow element removal on anonymous sets + +From: Pablo Neira Ayuso + +[ Upstream commit 23a3bfd4ba7acd36abf52b78605f61b21bdac216 ] + +Anonymous sets need to be populated once at creation and then they are +bound to rule since 938154b93be8 ("netfilter: nf_tables: reject unbound +anonymous set before commit phase"), otherwise transaction reports +EINVAL. + +Userspace does not need to delete elements of anonymous sets that are +not yet bound, reject this with EOPNOTSUPP. + +From flush command path, skip anonymous sets, they are expected to be +bound already. Otherwise, EINVAL is hit at the end of this transaction +for unbound sets. + +Fixes: 96518518cc41 ("netfilter: add nftables") +Signed-off-by: Pablo Neira Ayuso +Signed-off-by: Sasha Levin +--- + net/netfilter/nf_tables_api.c | 9 +++++---- + 1 file changed, 5 insertions(+), 4 deletions(-) + +diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c +index 4dadb0eebf614..56098859d5b44 100644 +--- a/net/netfilter/nf_tables_api.c ++++ b/net/netfilter/nf_tables_api.c +@@ -1358,8 +1358,7 @@ static int nft_flush_table(struct nft_ctx *ctx) + if (!nft_is_active_next(ctx->net, set)) + continue; + +- if (nft_set_is_anonymous(set) && +- !list_empty(&set->bindings)) ++ if (nft_set_is_anonymous(set)) + continue; + + err = nft_delset(ctx, set); +@@ -6752,8 +6751,10 @@ static int nf_tables_delsetelem(struct sk_buff *skb, + if (IS_ERR(set)) + return PTR_ERR(set); + +- if (!list_empty(&set->bindings) && +- (set->flags & (NFT_SET_CONSTANT | NFT_SET_ANONYMOUS))) ++ if (nft_set_is_anonymous(set)) ++ return -EOPNOTSUPP; ++ ++ if (!list_empty(&set->bindings) && (set->flags & NFT_SET_CONSTANT)) + return -EBUSY; + + nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); +-- +2.40.1 + diff --git a/queue-5.15/platform-x86-intel_scu_ipc-check-status-after-timeou.patch b/queue-5.15/platform-x86-intel_scu_ipc-check-status-after-timeou.patch new file mode 100644 index 00000000000..c8bbc2eaa13 --- /dev/null +++ b/queue-5.15/platform-x86-intel_scu_ipc-check-status-after-timeou.patch @@ -0,0 +1,94 @@ +From 8783908c3100e897a0124e1f063ea8a55ded2865 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 13 Sep 2023 14:27:19 -0700 +Subject: platform/x86: intel_scu_ipc: Check status after timeout in + busy_loop() +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Stephen Boyd + +[ Upstream commit e0b4ab3bb92bda8d12f55842614362989d5b2cb3 ] + +It's possible for the polling loop in busy_loop() to get scheduled away +for a long time. + + status = ipc_read_status(scu); // status = IPC_STATUS_BUSY + + if (!(status & IPC_STATUS_BUSY)) + +If this happens, then the status bit could change while the task is +scheduled away and this function would never read the status again after +timing out. Instead, the function will return -ETIMEDOUT when it's +possible that scheduling didn't work out and the status bit was cleared. +Bit polling code should always check the bit being polled one more time +after the timeout in case this happens. + +Fix this by reading the status once more after the while loop breaks. +The readl_poll_timeout() macro implements all of this, and it is +shorter, so use that macro here to consolidate code and fix this. + +There were some concerns with using readl_poll_timeout() because it uses +timekeeping, and timekeeping isn't running early on or during the late +stages of system suspend or early stages of system resume, but an audit +of the code concluded that this code isn't called during those times so +it is safe to use the macro. + +Cc: Prashant Malani +Reviewed-by: Andy Shevchenko +Reviewed-by: Mika Westerberg +Reviewed-by: Kuppuswamy Sathyanarayanan +Fixes: e7b7ab3847c9 ("platform/x86: intel_scu_ipc: Sleeping is fine when polling") +Signed-off-by: Stephen Boyd +Link: https://lore.kernel.org/r/20230913212723.3055315-2-swboyd@chromium.org +Reviewed-by: Ilpo Järvinen +Reviewed-by: Hans de Goede +Signed-off-by: Hans de Goede +Signed-off-by: Sasha Levin +--- + drivers/platform/x86/intel_scu_ipc.c | 19 ++++++++----------- + 1 file changed, 8 insertions(+), 11 deletions(-) + +diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c +index e7a3e34028178..96675bea88b10 100644 +--- a/drivers/platform/x86/intel_scu_ipc.c ++++ b/drivers/platform/x86/intel_scu_ipc.c +@@ -19,6 +19,7 @@ + #include + #include + #include ++#include + #include + #include + +@@ -232,19 +233,15 @@ static inline u32 ipc_data_readl(struct intel_scu_ipc_dev *scu, u32 offset) + /* Wait till scu status is busy */ + static inline int busy_loop(struct intel_scu_ipc_dev *scu) + { +- unsigned long end = jiffies + IPC_TIMEOUT; +- +- do { +- u32 status; +- +- status = ipc_read_status(scu); +- if (!(status & IPC_STATUS_BUSY)) +- return (status & IPC_STATUS_ERR) ? -EIO : 0; ++ u8 status; ++ int err; + +- usleep_range(50, 100); +- } while (time_before(jiffies, end)); ++ err = readx_poll_timeout(ipc_read_status, scu, status, !(status & IPC_STATUS_BUSY), ++ 100, jiffies_to_usecs(IPC_TIMEOUT)); ++ if (err) ++ return err; + +- return -ETIMEDOUT; ++ return (status & IPC_STATUS_ERR) ? -EIO : 0; + } + + /* Wait till ipc ioc interrupt is received or timeout in 10 HZ */ +-- +2.40.1 + diff --git a/queue-5.15/platform-x86-intel_scu_ipc-check-status-upon-timeout.patch b/queue-5.15/platform-x86-intel_scu_ipc-check-status-upon-timeout.patch new file mode 100644 index 00000000000..2f35f845605 --- /dev/null +++ b/queue-5.15/platform-x86-intel_scu_ipc-check-status-upon-timeout.patch @@ -0,0 +1,64 @@ +From 50a3864d73eee58e5b3ed1e3516b2ad5b2040649 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 13 Sep 2023 14:27:20 -0700 +Subject: platform/x86: intel_scu_ipc: Check status upon timeout in + ipc_wait_for_interrupt() + +From: Stephen Boyd + +[ Upstream commit 427fada620733e6474d783ae6037a66eae42bf8c ] + +It's possible for the completion in ipc_wait_for_interrupt() to timeout, +simply because the interrupt was delayed in being processed. A timeout +in itself is not an error. This driver should check the status register +upon a timeout to ensure that scheduling or interrupt processing delays +don't affect the outcome of the IPC return value. + + CPU0 SCU + ---- --- + ipc_wait_for_interrupt() + wait_for_completion_timeout(&scu->cmd_complete) + [TIMEOUT] status[IPC_STATUS_BUSY]=0 + +Fix this problem by reading the status bit in all cases, regardless of +the timeout. If the completion times out, we'll assume the problem was +that the IPC_STATUS_BUSY bit was still set, but if the status bit is +cleared in the meantime we know that we hit some scheduling delay and we +should just check the error bit. + +Cc: Prashant Malani +Reviewed-by: Kuppuswamy Sathyanarayanan +Reviewed-by: Andy Shevchenko +Reviewed-by: Mika Westerberg +Fixes: ed12f295bfd5 ("ipc: Added support for IPC interrupt mode") +Signed-off-by: Stephen Boyd +Link: https://lore.kernel.org/r/20230913212723.3055315-3-swboyd@chromium.org +Reviewed-by: Hans de Goede +Signed-off-by: Hans de Goede +Signed-off-by: Sasha Levin +--- + drivers/platform/x86/intel_scu_ipc.c | 6 ++++-- + 1 file changed, 4 insertions(+), 2 deletions(-) + +diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c +index 96675bea88b10..be97cfae4b0f3 100644 +--- a/drivers/platform/x86/intel_scu_ipc.c ++++ b/drivers/platform/x86/intel_scu_ipc.c +@@ -249,10 +249,12 @@ static inline int ipc_wait_for_interrupt(struct intel_scu_ipc_dev *scu) + { + int status; + +- if (!wait_for_completion_timeout(&scu->cmd_complete, IPC_TIMEOUT)) +- return -ETIMEDOUT; ++ wait_for_completion_timeout(&scu->cmd_complete, IPC_TIMEOUT); + + status = ipc_read_status(scu); ++ if (status & IPC_STATUS_BUSY) ++ return -ETIMEDOUT; ++ + if (status & IPC_STATUS_ERR) + return -EIO; + +-- +2.40.1 + diff --git a/queue-5.15/platform-x86-intel_scu_ipc-don-t-override-scu-in-int.patch b/queue-5.15/platform-x86-intel_scu_ipc-don-t-override-scu-in-int.patch new file mode 100644 index 00000000000..8b9f9a92170 --- /dev/null +++ b/queue-5.15/platform-x86-intel_scu_ipc-don-t-override-scu-in-int.patch @@ -0,0 +1,52 @@ +From 0e887f54ac2ee5e45bb0a64f674a76c422cecd75 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 13 Sep 2023 14:27:21 -0700 +Subject: platform/x86: intel_scu_ipc: Don't override scu in + intel_scu_ipc_dev_simple_command() +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Stephen Boyd + +[ Upstream commit efce78584e583226e9a1f6cb2fb555d6ff47c3e7 ] + +Andy discovered this bug during patch review. The 'scu' argument to this +function shouldn't be overridden by the function itself. It doesn't make +any sense. Looking at the commit history, we see that commit +f57fa18583f5 ("platform/x86: intel_scu_ipc: Introduce new SCU IPC API") +removed the setting of the scu to ipcdev in other functions, but not +this one. That was an oversight. Remove this line so that we stop +overriding the scu instance that is used by this function. + +Reported-by: Andy Shevchenko +Closes: https://lore.kernel.org/r/ZPjdZ3xNmBEBvNiS@smile.fi.intel.com +Cc: Prashant Malani +Reviewed-by: Andy Shevchenko +Reviewed-by: Mika Westerberg +Fixes: f57fa18583f5 ("platform/x86: intel_scu_ipc: Introduce new SCU IPC API") +Signed-off-by: Stephen Boyd +Link: https://lore.kernel.org/r/20230913212723.3055315-4-swboyd@chromium.org +Reviewed-by: Ilpo Järvinen +Reviewed-by: Hans de Goede +Signed-off-by: Hans de Goede +Signed-off-by: Sasha Levin +--- + drivers/platform/x86/intel_scu_ipc.c | 1 - + 1 file changed, 1 deletion(-) + +diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c +index be97cfae4b0f3..dfe010f1ee084 100644 +--- a/drivers/platform/x86/intel_scu_ipc.c ++++ b/drivers/platform/x86/intel_scu_ipc.c +@@ -444,7 +444,6 @@ int intel_scu_ipc_dev_simple_command(struct intel_scu_ipc_dev *scu, int cmd, + mutex_unlock(&ipclock); + return -ENODEV; + } +- scu = ipcdev; + cmdval = sub << 12 | cmd; + ipc_command(scu, cmdval); + err = intel_scu_ipc_check_status(scu); +-- +2.40.1 + diff --git a/queue-5.15/platform-x86-intel_scu_ipc-fail-ipc-send-if-still-bu.patch b/queue-5.15/platform-x86-intel_scu_ipc-fail-ipc-send-if-still-bu.patch new file mode 100644 index 00000000000..a3254c1da42 --- /dev/null +++ b/queue-5.15/platform-x86-intel_scu_ipc-fail-ipc-send-if-still-bu.patch @@ -0,0 +1,123 @@ +From dab768bb89fbad4590afa42e31ae7d2d8303a65f Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 13 Sep 2023 14:27:22 -0700 +Subject: platform/x86: intel_scu_ipc: Fail IPC send if still busy +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Stephen Boyd + +[ Upstream commit 85e654c9f722853a595fa941dca60c157b707b86 ] + +It's possible for interrupts to get significantly delayed to the point +that callers of intel_scu_ipc_dev_command() and friends can call the +function once, hit a timeout, and call it again while the interrupt +still hasn't been processed. This driver will get seriously confused if +the interrupt is finally processed after the second IPC has been sent +with ipc_command(). It won't know which IPC has been completed. This +could be quite disastrous if calling code assumes something has happened +upon return from intel_scu_ipc_dev_simple_command() when it actually +hasn't. + +Let's avoid this scenario by simply returning -EBUSY in this case. +Hopefully higher layers will know to back off or fail gracefully when +this happens. It's all highly unlikely anyway, but it's better to be +correct here as we have no way to know which IPC the status register is +telling us about if we send a second IPC while the previous IPC is still +processing. + +Cc: Prashant Malani +Cc: Kuppuswamy Sathyanarayanan +Reviewed-by: Andy Shevchenko +Reviewed-by: Mika Westerberg +Fixes: ed12f295bfd5 ("ipc: Added support for IPC interrupt mode") +Signed-off-by: Stephen Boyd +Link: https://lore.kernel.org/r/20230913212723.3055315-5-swboyd@chromium.org +Reviewed-by: Ilpo Järvinen +Reviewed-by: Hans de Goede +Signed-off-by: Hans de Goede +Signed-off-by: Sasha Levin +--- + drivers/platform/x86/intel_scu_ipc.c | 40 +++++++++++++++++++--------- + 1 file changed, 28 insertions(+), 12 deletions(-) + +diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c +index dfe010f1ee084..189c5460edd81 100644 +--- a/drivers/platform/x86/intel_scu_ipc.c ++++ b/drivers/platform/x86/intel_scu_ipc.c +@@ -266,6 +266,24 @@ static int intel_scu_ipc_check_status(struct intel_scu_ipc_dev *scu) + return scu->irq > 0 ? ipc_wait_for_interrupt(scu) : busy_loop(scu); + } + ++static struct intel_scu_ipc_dev *intel_scu_ipc_get(struct intel_scu_ipc_dev *scu) ++{ ++ u8 status; ++ ++ if (!scu) ++ scu = ipcdev; ++ if (!scu) ++ return ERR_PTR(-ENODEV); ++ ++ status = ipc_read_status(scu); ++ if (status & IPC_STATUS_BUSY) { ++ dev_dbg(&scu->dev, "device is busy\n"); ++ return ERR_PTR(-EBUSY); ++ } ++ ++ return scu; ++} ++ + /* Read/Write power control(PMIC in Langwell, MSIC in PenWell) registers */ + static int pwr_reg_rdwr(struct intel_scu_ipc_dev *scu, u16 *addr, u8 *data, + u32 count, u32 op, u32 id) +@@ -279,11 +297,10 @@ static int pwr_reg_rdwr(struct intel_scu_ipc_dev *scu, u16 *addr, u8 *data, + memset(cbuf, 0, sizeof(cbuf)); + + mutex_lock(&ipclock); +- if (!scu) +- scu = ipcdev; +- if (!scu) { ++ scu = intel_scu_ipc_get(scu); ++ if (IS_ERR(scu)) { + mutex_unlock(&ipclock); +- return -ENODEV; ++ return PTR_ERR(scu); + } + + for (nc = 0; nc < count; nc++, offset += 2) { +@@ -438,12 +455,12 @@ int intel_scu_ipc_dev_simple_command(struct intel_scu_ipc_dev *scu, int cmd, + int err; + + mutex_lock(&ipclock); +- if (!scu) +- scu = ipcdev; +- if (!scu) { ++ scu = intel_scu_ipc_get(scu); ++ if (IS_ERR(scu)) { + mutex_unlock(&ipclock); +- return -ENODEV; ++ return PTR_ERR(scu); + } ++ + cmdval = sub << 12 | cmd; + ipc_command(scu, cmdval); + err = intel_scu_ipc_check_status(scu); +@@ -483,11 +500,10 @@ int intel_scu_ipc_dev_command_with_size(struct intel_scu_ipc_dev *scu, int cmd, + return -EINVAL; + + mutex_lock(&ipclock); +- if (!scu) +- scu = ipcdev; +- if (!scu) { ++ scu = intel_scu_ipc_get(scu); ++ if (IS_ERR(scu)) { + mutex_unlock(&ipclock); +- return -ENODEV; ++ return PTR_ERR(scu); + } + + memcpy(inbuf, in, inlen); +-- +2.40.1 + diff --git a/queue-5.15/powerpc-perf-hv-24x7-update-domain-value-check.patch b/queue-5.15/powerpc-perf-hv-24x7-update-domain-value-check.patch new file mode 100644 index 00000000000..ea8a5411e69 --- /dev/null +++ b/queue-5.15/powerpc-perf-hv-24x7-update-domain-value-check.patch @@ -0,0 +1,63 @@ +From 40917e9373039f228b21ea4e318fa7e8c0e26711 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 25 Aug 2023 11:26:01 +0530 +Subject: powerpc/perf/hv-24x7: Update domain value check + +From: Kajol Jain + +[ Upstream commit 4ff3ba4db5943cac1045e3e4a3c0463ea10f6930 ] + +Valid domain value is in range 1 to HV_PERF_DOMAIN_MAX. Current code has +check for domain value greater than or equal to HV_PERF_DOMAIN_MAX. But +the check for domain value 0 is missing. + +Fix this issue by adding check for domain value 0. + +Before: + # ./perf stat -v -e hv_24x7/CPM_ADJUNCT_INST,domain=0,core=1/ sleep 1 + Using CPUID 00800200 + Control descriptor is not initialized + Error: + The sys_perf_event_open() syscall returned with 5 (Input/output error) for + event (hv_24x7/CPM_ADJUNCT_INST,domain=0,core=1/). + /bin/dmesg | grep -i perf may provide additional information. + + Result from dmesg: + [ 37.819387] hv-24x7: hcall failed: [0 0x60040000 0x100 0] => ret + 0xfffffffffffffffc (-4) detail=0x2000000 failing ix=0 + +After: + # ./perf stat -v -e hv_24x7/CPM_ADJUNCT_INST,domain=0,core=1/ sleep 1 + Using CPUID 00800200 + Control descriptor is not initialized + Warning: + hv_24x7/CPM_ADJUNCT_INST,domain=0,core=1/ event is not supported by the kernel. + failed to read counter hv_24x7/CPM_ADJUNCT_INST,domain=0,core=1/ + +Fixes: ebd4a5a3ebd9 ("powerpc/perf/hv-24x7: Minor improvements") +Reported-by: Krishan Gopal Sarawast +Signed-off-by: Kajol Jain +Tested-by: Disha Goel +Signed-off-by: Michael Ellerman +Link: https://msgid.link/20230825055601.360083-1-kjain@linux.ibm.com +Signed-off-by: Sasha Levin +--- + arch/powerpc/perf/hv-24x7.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c +index 1816f560a4652..284ccc90fb11c 100644 +--- a/arch/powerpc/perf/hv-24x7.c ++++ b/arch/powerpc/perf/hv-24x7.c +@@ -1431,7 +1431,7 @@ static int h_24x7_event_init(struct perf_event *event) + } + + domain = event_get_domain(event); +- if (domain >= HV_PERF_DOMAIN_MAX) { ++ if (domain == 0 || domain >= HV_PERF_DOMAIN_MAX) { + pr_devel("invalid domain %d\n", domain); + return -EINVAL; + } +-- +2.40.1 + diff --git a/queue-5.15/selftests-tls-swap-the-tx-and-rx-sockets-in-some-tes.patch b/queue-5.15/selftests-tls-swap-the-tx-and-rx-sockets-in-some-tes.patch new file mode 100644 index 00000000000..f3a72abef5f --- /dev/null +++ b/queue-5.15/selftests-tls-swap-the-tx-and-rx-sockets-in-some-tes.patch @@ -0,0 +1,55 @@ +From 787fafdf366387f8ea8ec5696c5171bd29f3466d Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 12 Sep 2023 16:16:25 +0200 +Subject: selftests: tls: swap the TX and RX sockets in some tests + +From: Sabrina Dubroca + +[ Upstream commit c326ca98446e0ae4fee43a40acf79412b74cfedb ] + +tls.sendmsg_large and tls.sendmsg_multiple are trying to send through +the self->cfd socket (only configured with TLS_RX) and to receive through +the self->fd socket (only configured with TLS_TX), so they're not using +kTLS at all. Swap the sockets. + +Fixes: 7f657d5bf507 ("selftests: tls: add selftests for TLS sockets") +Signed-off-by: Sabrina Dubroca +Signed-off-by: David S. Miller +Signed-off-by: Sasha Levin +--- + tools/testing/selftests/net/tls.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c +index 97fceb9be9ed3..3bdb093731358 100644 +--- a/tools/testing/selftests/net/tls.c ++++ b/tools/testing/selftests/net/tls.c +@@ -441,11 +441,11 @@ TEST_F(tls, sendmsg_large) + + msg.msg_iov = &vec; + msg.msg_iovlen = 1; +- EXPECT_EQ(sendmsg(self->cfd, &msg, 0), send_len); ++ EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len); + } + + while (recvs++ < sends) { +- EXPECT_NE(recv(self->fd, mem, send_len, 0), -1); ++ EXPECT_NE(recv(self->cfd, mem, send_len, 0), -1); + } + + free(mem); +@@ -474,9 +474,9 @@ TEST_F(tls, sendmsg_multiple) + msg.msg_iov = vec; + msg.msg_iovlen = iov_len; + +- EXPECT_EQ(sendmsg(self->cfd, &msg, 0), total_len); ++ EXPECT_EQ(sendmsg(self->fd, &msg, 0), total_len); + buf = malloc(total_len); +- EXPECT_NE(recv(self->fd, buf, total_len, 0), -1); ++ EXPECT_NE(recv(self->cfd, buf, total_len, 0), -1); + for (i = 0; i < iov_len; i++) { + EXPECT_EQ(memcmp(test_strs[i], buf + len_cmp, + strlen(test_strs[i])), +-- +2.40.1 + diff --git a/queue-5.15/series b/queue-5.15/series index b6356061f21..8890aa994c4 100644 --- a/queue-5.15/series +++ b/queue-5.15/series @@ -31,3 +31,37 @@ netfilter-nft_set_pipapo-call-nft_trans_gc_queue_syn.patch netfilter-nft_set_pipapo-stop-gc-iteration-if-gc-tra.patch netfilter-nft_set_hash-try-later-when-gc-hits-eagain.patch netfilter-nf_tables-fix-memleak-when-more-than-255-e.patch +asoc-meson-spdifin-start-hw-on-dai-probe.patch +netfilter-nf_tables-disallow-element-removal-on-anon.patch +bpf-avoid-deadlock-when-using-queue-and-stack-maps-f.patch +selftests-tls-swap-the-tx-and-rx-sockets-in-some-tes.patch +net-core-fix-eth_p_1588-flow-dissector.patch +asoc-imx-audmix-fix-return-error-with-devm_clk_get.patch +iavf-do-not-process-adminq-tasks-when-__iavf_in_remo.patch +i40e-add-vf-vlan-pruning.patch +i40e-fix-vf-vlan-offloading-when-port-vlan-is-config.patch +ionic-fix-16bit-math-issue-when-page_size-64kb.patch +igc-fix-infinite-initialization-loop-with-early-xdp-.patch +ipv4-fix-null-deref-in-ipv4_link_failure.patch +powerpc-perf-hv-24x7-update-domain-value-check.patch +dccp-fix-dccp_v4_err-dccp_v6_err-again.patch +platform-x86-intel_scu_ipc-check-status-after-timeou.patch +platform-x86-intel_scu_ipc-check-status-upon-timeout.patch +platform-x86-intel_scu_ipc-don-t-override-scu-in-int.patch +platform-x86-intel_scu_ipc-fail-ipc-send-if-still-bu.patch +x86-srso-fix-srso_show_state-side-effect.patch +x86-srso-fix-sbpb-enablement-for-spec_rstack_overflo.patch +net-hns3-fix-gre-checksum-offload-issue.patch +net-hns3-only-enable-unicast-promisc-when-mac-table-.patch +net-hns3-fix-fail-to-delete-tc-flower-rules-during-r.patch +net-hns3-add-5ms-delay-before-clear-firmware-reset-i.patch +net-bridge-use-dev_stats_inc.patch +team-fix-null-ptr-deref-when-team-device-type-is-cha.patch +net-rds-fix-possible-null-pointer-dereference.patch +netfilter-nf_tables-disable-toggling-dormant-table-s.patch +netfilter-ipset-fix-race-between-ipset_cmd_create-an.patch +locking-seqlock-do-the-lockdep-annotation-before-loc.patch +net-ena-flush-xdp-packets-on-error.patch +bnxt_en-flush-xdp-for-bnxt_poll_nitroa0-s-napi.patch +igc-expose-tx-usecs-coalesce-setting-to-user.patch +fix-up-backport-of-136191703038-interconnect-teach-l.patch diff --git a/queue-5.15/team-fix-null-ptr-deref-when-team-device-type-is-cha.patch b/queue-5.15/team-fix-null-ptr-deref-when-team-device-type-is-cha.patch new file mode 100644 index 00000000000..1a7c768e7d5 --- /dev/null +++ b/queue-5.15/team-fix-null-ptr-deref-when-team-device-type-is-cha.patch @@ -0,0 +1,121 @@ +From 623c68f955985ec3002836c98f0409b8a455bdc1 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 18 Sep 2023 20:30:11 +0800 +Subject: team: fix null-ptr-deref when team device type is changed + +From: Ziyang Xuan + +[ Upstream commit 492032760127251e5540a5716a70996bacf2a3fd ] + +Get a null-ptr-deref bug as follows with reproducer [1]. + +BUG: kernel NULL pointer dereference, address: 0000000000000228 +... +RIP: 0010:vlan_dev_hard_header+0x35/0x140 [8021q] +... +Call Trace: + + ? __die+0x24/0x70 + ? page_fault_oops+0x82/0x150 + ? exc_page_fault+0x69/0x150 + ? asm_exc_page_fault+0x26/0x30 + ? vlan_dev_hard_header+0x35/0x140 [8021q] + ? vlan_dev_hard_header+0x8e/0x140 [8021q] + neigh_connected_output+0xb2/0x100 + ip6_finish_output2+0x1cb/0x520 + ? nf_hook_slow+0x43/0xc0 + ? ip6_mtu+0x46/0x80 + ip6_finish_output+0x2a/0xb0 + mld_sendpack+0x18f/0x250 + mld_ifc_work+0x39/0x160 + process_one_work+0x1e6/0x3f0 + worker_thread+0x4d/0x2f0 + ? __pfx_worker_thread+0x10/0x10 + kthread+0xe5/0x120 + ? __pfx_kthread+0x10/0x10 + ret_from_fork+0x34/0x50 + ? __pfx_kthread+0x10/0x10 + ret_from_fork_asm+0x1b/0x30 + +[1] +$ teamd -t team0 -d -c '{"runner": {"name": "loadbalance"}}' +$ ip link add name t-dummy type dummy +$ ip link add link t-dummy name t-dummy.100 type vlan id 100 +$ ip link add name t-nlmon type nlmon +$ ip link set t-nlmon master team0 +$ ip link set t-nlmon nomaster +$ ip link set t-dummy up +$ ip link set team0 up +$ ip link set t-dummy.100 down +$ ip link set t-dummy.100 master team0 + +When enslave a vlan device to team device and team device type is changed +from non-ether to ether, header_ops of team device is changed to +vlan_header_ops. That is incorrect and will trigger null-ptr-deref +for vlan->real_dev in vlan_dev_hard_header() because team device is not +a vlan device. + +Cache eth_header_ops in team_setup(), then assign cached header_ops to +header_ops of team net device when its type is changed from non-ether +to ether to fix the bug. + +Fixes: 1d76efe1577b ("team: add support for non-ethernet devices") +Suggested-by: Hangbin Liu +Reviewed-by: Hangbin Liu +Signed-off-by: Ziyang Xuan +Reviewed-by: Jiri Pirko +Reviewed-by: Eric Dumazet +Link: https://lore.kernel.org/r/20230918123011.1884401-1-william.xuanziyang@huawei.com +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + drivers/net/team/team.c | 10 +++++++++- + include/linux/if_team.h | 2 ++ + 2 files changed, 11 insertions(+), 1 deletion(-) + +diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c +index f99df92d211e2..44275094906c0 100644 +--- a/drivers/net/team/team.c ++++ b/drivers/net/team/team.c +@@ -2122,7 +2122,12 @@ static const struct ethtool_ops team_ethtool_ops = { + static void team_setup_by_port(struct net_device *dev, + struct net_device *port_dev) + { +- dev->header_ops = port_dev->header_ops; ++ struct team *team = netdev_priv(dev); ++ ++ if (port_dev->type == ARPHRD_ETHER) ++ dev->header_ops = team->header_ops_cache; ++ else ++ dev->header_ops = port_dev->header_ops; + dev->type = port_dev->type; + dev->hard_header_len = port_dev->hard_header_len; + dev->needed_headroom = port_dev->needed_headroom; +@@ -2169,8 +2174,11 @@ static int team_dev_type_check_change(struct net_device *dev, + + static void team_setup(struct net_device *dev) + { ++ struct team *team = netdev_priv(dev); ++ + ether_setup(dev); + dev->max_mtu = ETH_MAX_MTU; ++ team->header_ops_cache = dev->header_ops; + + dev->netdev_ops = &team_netdev_ops; + dev->ethtool_ops = &team_ethtool_ops; +diff --git a/include/linux/if_team.h b/include/linux/if_team.h +index 5dd1657947b75..762c77d13e7dd 100644 +--- a/include/linux/if_team.h ++++ b/include/linux/if_team.h +@@ -189,6 +189,8 @@ struct team { + struct net_device *dev; /* associated netdevice */ + struct team_pcpu_stats __percpu *pcpu_stats; + ++ const struct header_ops *header_ops_cache; ++ + struct mutex lock; /* used for overall locking, e.g. port lists write */ + + /* +-- +2.40.1 + diff --git a/queue-5.15/x86-srso-fix-sbpb-enablement-for-spec_rstack_overflo.patch b/queue-5.15/x86-srso-fix-sbpb-enablement-for-spec_rstack_overflo.patch new file mode 100644 index 00000000000..bdb7b09c011 --- /dev/null +++ b/queue-5.15/x86-srso-fix-sbpb-enablement-for-spec_rstack_overflo.patch @@ -0,0 +1,39 @@ +From a9c6d4187abc74dee98b1e6566b0d928120bb64a Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 4 Sep 2023 22:04:48 -0700 +Subject: x86/srso: Fix SBPB enablement for spec_rstack_overflow=off + +From: Josh Poimboeuf + +[ Upstream commit 01b057b2f4cc2d905a0bd92195657dbd9a7005ab ] + +If the user has requested no SRSO mitigation, other mitigations can use +the lighter-weight SBPB instead of IBPB. + +Fixes: fb3bd914b3ec ("x86/srso: Add a Speculative RAS Overflow mitigation") +Signed-off-by: Josh Poimboeuf +Signed-off-by: Ingo Molnar +Signed-off-by: Borislav Petkov (AMD) +Acked-by: Borislav Petkov (AMD) +Link: https://lore.kernel.org/r/b20820c3cfd1003171135ec8d762a0b957348497.1693889988.git.jpoimboe@kernel.org +Signed-off-by: Sasha Levin +--- + arch/x86/kernel/cpu/bugs.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c +index 78a57737f1ba1..6322a08edbba5 100644 +--- a/arch/x86/kernel/cpu/bugs.c ++++ b/arch/x86/kernel/cpu/bugs.c +@@ -2414,7 +2414,7 @@ static void __init srso_select_mitigation(void) + + switch (srso_cmd) { + case SRSO_CMD_OFF: +- return; ++ goto pred_cmd; + + case SRSO_CMD_MICROCODE: + if (has_microcode) { +-- +2.40.1 + diff --git a/queue-5.15/x86-srso-fix-srso_show_state-side-effect.patch b/queue-5.15/x86-srso-fix-srso_show_state-side-effect.patch new file mode 100644 index 00000000000..38905dfb5dc --- /dev/null +++ b/queue-5.15/x86-srso-fix-srso_show_state-side-effect.patch @@ -0,0 +1,44 @@ +From 29cc9e3da821774dcc2980c380692ec865abb491 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 4 Sep 2023 22:04:45 -0700 +Subject: x86/srso: Fix srso_show_state() side effect + +From: Josh Poimboeuf + +[ Upstream commit a8cf700c17d9ca6cb8ee7dc5c9330dbac3948237 ] + +Reading the 'spec_rstack_overflow' sysfs file can trigger an unnecessary +MSR write, and possibly even a (handled) exception if the microcode +hasn't been updated. + +Avoid all that by just checking X86_FEATURE_IBPB_BRTYPE instead, which +gets set by srso_select_mitigation() if the updated microcode exists. + +Fixes: fb3bd914b3ec ("x86/srso: Add a Speculative RAS Overflow mitigation") +Signed-off-by: Josh Poimboeuf +Signed-off-by: Ingo Molnar +Signed-off-by: Borislav Petkov (AMD) +Reviewed-by: Nikolay Borisov +Acked-by: Borislav Petkov (AMD) +Link: https://lore.kernel.org/r/27d128899cb8aee9eb2b57ddc996742b0c1d776b.1693889988.git.jpoimboe@kernel.org +Signed-off-by: Sasha Levin +--- + arch/x86/kernel/cpu/bugs.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c +index 0d2c5fe841414..78a57737f1ba1 100644 +--- a/arch/x86/kernel/cpu/bugs.c ++++ b/arch/x86/kernel/cpu/bugs.c +@@ -2692,7 +2692,7 @@ static ssize_t srso_show_state(char *buf) + + return sysfs_emit(buf, "%s%s\n", + srso_strings[srso_mitigation], +- (cpu_has_ibpb_brtype_microcode() ? "" : ", no microcode")); ++ boot_cpu_has(X86_FEATURE_IBPB_BRTYPE) ? "" : ", no microcode"); + } + + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, +-- +2.40.1 +