From: Sasha Levin Date: Sat, 13 Jul 2024 13:26:39 +0000 (-0400) Subject: Fixes for 5.15 X-Git-Tag: v6.1.99~15 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=29a93f203b3c0cda9f835edf2e91897b1b49d543;p=thirdparty%2Fkernel%2Fstable-queue.git Fixes for 5.15 Signed-off-by: Sasha Levin --- diff --git a/queue-5.15/ethtool-netlink-do-not-return-sqi-value-if-link-is-d.patch b/queue-5.15/ethtool-netlink-do-not-return-sqi-value-if-link-is-d.patch new file mode 100644 index 00000000000..0ff0a329e87 --- /dev/null +++ b/queue-5.15/ethtool-netlink-do-not-return-sqi-value-if-link-is-d.patch @@ -0,0 +1,122 @@ +From 41f4c39e13a5a3de0728882b3942de943bfdcf1c Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 9 Jul 2024 08:19:43 +0200 +Subject: ethtool: netlink: do not return SQI value if link is down + +From: Oleksij Rempel + +[ Upstream commit c184cf94e73b04ff7048d045f5413899bc664788 ] + +Do not attach SQI value if link is down. "SQI values are only valid if +link-up condition is present" per OpenAlliance specification of +100Base-T1 Interoperability Test suite [1]. The same rule would apply +for other link types. + +[1] https://opensig.org/automotive-ethernet-specifications/# + +Fixes: 806602191592 ("ethtool: provide UAPI for PHY Signal Quality Index (SQI)") +Signed-off-by: Oleksij Rempel +Reviewed-by: Andrew Lunn +Reviewed-by: Woojung Huh +Link: https://patch.msgid.link/20240709061943.729381-1-o.rempel@pengutronix.de +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/ethtool/linkstate.c | 41 ++++++++++++++++++++++++++++------------- + 1 file changed, 28 insertions(+), 13 deletions(-) + +diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c +index fb676f349455a..470582a70ccbe 100644 +--- a/net/ethtool/linkstate.c ++++ b/net/ethtool/linkstate.c +@@ -36,6 +36,8 @@ static int linkstate_get_sqi(struct net_device *dev) + mutex_lock(&phydev->lock); + if (!phydev->drv || !phydev->drv->get_sqi) + ret = -EOPNOTSUPP; ++ else if (!phydev->link) ++ ret = -ENETDOWN; + else + ret = phydev->drv->get_sqi(phydev); + mutex_unlock(&phydev->lock); +@@ -54,6 +56,8 @@ static int linkstate_get_sqi_max(struct net_device *dev) + mutex_lock(&phydev->lock); + if (!phydev->drv || !phydev->drv->get_sqi_max) + ret = -EOPNOTSUPP; ++ else if (!phydev->link) ++ ret = -ENETDOWN; + else + ret = phydev->drv->get_sqi_max(phydev); + mutex_unlock(&phydev->lock); +@@ -61,6 +65,17 @@ static int linkstate_get_sqi_max(struct net_device *dev) + return ret; + }; + ++static bool linkstate_sqi_critical_error(int sqi) ++{ ++ return sqi < 0 && sqi != -EOPNOTSUPP && sqi != -ENETDOWN; ++} ++ ++static bool linkstate_sqi_valid(struct linkstate_reply_data *data) ++{ ++ return data->sqi >= 0 && data->sqi_max >= 0 && ++ data->sqi <= data->sqi_max; ++} ++ + static int linkstate_get_link_ext_state(struct net_device *dev, + struct linkstate_reply_data *data) + { +@@ -92,12 +107,12 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base, + data->link = __ethtool_get_link(dev); + + ret = linkstate_get_sqi(dev); +- if (ret < 0 && ret != -EOPNOTSUPP) ++ if (linkstate_sqi_critical_error(ret)) + goto out; + data->sqi = ret; + + ret = linkstate_get_sqi_max(dev); +- if (ret < 0 && ret != -EOPNOTSUPP) ++ if (linkstate_sqi_critical_error(ret)) + goto out; + data->sqi_max = ret; + +@@ -122,11 +137,10 @@ static int linkstate_reply_size(const struct ethnl_req_info *req_base, + len = nla_total_size(sizeof(u8)) /* LINKSTATE_LINK */ + + 0; + +- if (data->sqi != -EOPNOTSUPP) +- len += nla_total_size(sizeof(u32)); +- +- if (data->sqi_max != -EOPNOTSUPP) +- len += nla_total_size(sizeof(u32)); ++ if (linkstate_sqi_valid(data)) { ++ len += nla_total_size(sizeof(u32)); /* LINKSTATE_SQI */ ++ len += nla_total_size(sizeof(u32)); /* LINKSTATE_SQI_MAX */ ++ } + + if (data->link_ext_state_provided) + len += nla_total_size(sizeof(u8)); /* LINKSTATE_EXT_STATE */ +@@ -147,13 +161,14 @@ static int linkstate_fill_reply(struct sk_buff *skb, + nla_put_u8(skb, ETHTOOL_A_LINKSTATE_LINK, !!data->link)) + return -EMSGSIZE; + +- if (data->sqi != -EOPNOTSUPP && +- nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI, data->sqi)) +- return -EMSGSIZE; ++ if (linkstate_sqi_valid(data)) { ++ if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI, data->sqi)) ++ return -EMSGSIZE; + +- if (data->sqi_max != -EOPNOTSUPP && +- nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI_MAX, data->sqi_max)) +- return -EMSGSIZE; ++ if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI_MAX, ++ data->sqi_max)) ++ return -EMSGSIZE; ++ } + + if (data->link_ext_state_provided) { + if (nla_put_u8(skb, ETHTOOL_A_LINKSTATE_EXT_STATE, +-- +2.43.0 + diff --git a/queue-5.15/filelock-fix-potential-use-after-free-in-posix_lock_.patch b/queue-5.15/filelock-fix-potential-use-after-free-in-posix_lock_.patch new file mode 100644 index 00000000000..b9c3a1570af --- /dev/null +++ b/queue-5.15/filelock-fix-potential-use-after-free-in-posix_lock_.patch @@ -0,0 +1,50 @@ +From 8989764396ebaac847766289ffc2c78302dc40ba Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 2 Jul 2024 18:44:48 -0400 +Subject: filelock: fix potential use-after-free in posix_lock_inode +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Jeff Layton + +[ Upstream commit 1b3ec4f7c03d4b07bad70697d7e2f4088d2cfe92 ] + +Light Hsieh reported a KASAN UAF warning in trace_posix_lock_inode(). +The request pointer had been changed earlier to point to a lock entry +that was added to the inode's list. However, before the tracepoint could +fire, another task raced in and freed that lock. + +Fix this by moving the tracepoint inside the spinlock, which should +ensure that this doesn't happen. + +Fixes: 74f6f5912693 ("locks: fix KASAN: use-after-free in trace_event_raw_event_filelock_lock") +Link: https://lore.kernel.org/linux-fsdevel/724ffb0a2962e912ea62bb0515deadf39c325112.camel@kernel.org/ +Reported-by: Light Hsieh (謝明燈) +Signed-off-by: Jeff Layton +Link: https://lore.kernel.org/r/20240702-filelock-6-10-v1-1-96e766aadc98@kernel.org +Reviewed-by: Alexander Aring +Signed-off-by: Christian Brauner +Signed-off-by: Sasha Levin +--- + fs/locks.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/fs/locks.c b/fs/locks.c +index 77781b71bcaab..360c348ae6c8f 100644 +--- a/fs/locks.c ++++ b/fs/locks.c +@@ -1392,9 +1392,9 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, + locks_wake_up_blocks(left); + } + out: ++ trace_posix_lock_inode(inode, request, error); + spin_unlock(&ctx->flc_lock); + percpu_up_read(&file_rwsem); +- trace_posix_lock_inode(inode, request, error); + /* + * Free any unused locks. + */ +-- +2.43.0 + diff --git a/queue-5.15/fs-dcache-re-use-value-stored-to-dentry-d_flags-inst.patch b/queue-5.15/fs-dcache-re-use-value-stored-to-dentry-d_flags-inst.patch new file mode 100644 index 00000000000..445113ac90f --- /dev/null +++ b/queue-5.15/fs-dcache-re-use-value-stored-to-dentry-d_flags-inst.patch @@ -0,0 +1,44 @@ +From 1dffc0f2f5300d2ba3e3731677bbbc6c66316ae9 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 3 Apr 2024 10:10:08 +0800 +Subject: fs/dcache: Re-use value stored to dentry->d_flags instead of + re-reading + +From: linke li + +[ Upstream commit 8bfb40be31ddea0cb4664b352e1797cfe6c91976 ] + +Currently, the __d_clear_type_and_inode() writes the value flags to +dentry->d_flags, then immediately re-reads it in order to use it in a if +statement. This re-read is useless because no other update to +dentry->d_flags can occur at this point. + +This commit therefore re-use flags in the if statement instead of +re-reading dentry->d_flags. + +Signed-off-by: linke li +Link: https://lore.kernel.org/r/tencent_5E187BD0A61BA28605E85405F15228254D0A@qq.com +Reviewed-by: Jan Kara +Signed-off-by: Christian Brauner +Stable-dep-of: aabfe57ebaa7 ("vfs: don't mod negative dentry count when on shrinker list") +Signed-off-by: Sasha Levin +--- + fs/dcache.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/fs/dcache.c b/fs/dcache.c +index 422c440b492a5..f2ff73fe2b619 100644 +--- a/fs/dcache.c ++++ b/fs/dcache.c +@@ -331,7 +331,7 @@ static inline void __d_clear_type_and_inode(struct dentry *dentry) + flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); + WRITE_ONCE(dentry->d_flags, flags); + dentry->d_inode = NULL; +- if (dentry->d_flags & DCACHE_LRU_LIST) ++ if (flags & DCACHE_LRU_LIST) + this_cpu_inc(nr_dentry_negative); + } + +-- +2.43.0 + diff --git a/queue-5.15/i40e-fix-xdp-program-unloading-while-removing-the-dr.patch b/queue-5.15/i40e-fix-xdp-program-unloading-while-removing-the-dr.patch new file mode 100644 index 00000000000..e5cb39aa455 --- /dev/null +++ b/queue-5.15/i40e-fix-xdp-program-unloading-while-removing-the-dr.patch @@ -0,0 +1,119 @@ +From 977de632449bea8aabaaffb776eb615688cb51c3 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 8 Jul 2024 16:07:49 -0700 +Subject: i40e: Fix XDP program unloading while removing the driver + +From: Michal Kubiak + +[ Upstream commit 01fc5142ae6b06b61ed51a624f2732d6525d8ea3 ] + +The commit 6533e558c650 ("i40e: Fix reset path while removing +the driver") introduced a new PF state "__I40E_IN_REMOVE" to block +modifying the XDP program while the driver is being removed. +Unfortunately, such a change is useful only if the ".ndo_bpf()" +callback was called out of the rmmod context because unloading the +existing XDP program is also a part of driver removing procedure. +In other words, from the rmmod context the driver is expected to +unload the XDP program without reporting any errors. Otherwise, +the kernel warning with callstack is printed out to dmesg. + +Example failing scenario: + 1. Load the i40e driver. + 2. Load the XDP program. + 3. Unload the i40e driver (using "rmmod" command). + +The example kernel warning log: + +[ +0.004646] WARNING: CPU: 94 PID: 10395 at net/core/dev.c:9290 unregister_netdevice_many_notify+0x7a9/0x870 +[...] +[ +0.010959] RIP: 0010:unregister_netdevice_many_notify+0x7a9/0x870 +[...] +[ +0.002726] Call Trace: +[ +0.002457] +[ +0.002119] ? __warn+0x80/0x120 +[ +0.003245] ? unregister_netdevice_many_notify+0x7a9/0x870 +[ +0.005586] ? report_bug+0x164/0x190 +[ +0.003678] ? handle_bug+0x3c/0x80 +[ +0.003503] ? exc_invalid_op+0x17/0x70 +[ +0.003846] ? asm_exc_invalid_op+0x1a/0x20 +[ +0.004200] ? unregister_netdevice_many_notify+0x7a9/0x870 +[ +0.005579] ? unregister_netdevice_many_notify+0x3cc/0x870 +[ +0.005586] unregister_netdevice_queue+0xf7/0x140 +[ +0.004806] unregister_netdev+0x1c/0x30 +[ +0.003933] i40e_vsi_release+0x87/0x2f0 [i40e] +[ +0.004604] i40e_remove+0x1a1/0x420 [i40e] +[ +0.004220] pci_device_remove+0x3f/0xb0 +[ +0.003943] device_release_driver_internal+0x19f/0x200 +[ +0.005243] driver_detach+0x48/0x90 +[ +0.003586] bus_remove_driver+0x6d/0xf0 +[ +0.003939] pci_unregister_driver+0x2e/0xb0 +[ +0.004278] i40e_exit_module+0x10/0x5f0 [i40e] +[ +0.004570] __do_sys_delete_module.isra.0+0x197/0x310 +[ +0.005153] do_syscall_64+0x85/0x170 +[ +0.003684] ? syscall_exit_to_user_mode+0x69/0x220 +[ +0.004886] ? do_syscall_64+0x95/0x170 +[ +0.003851] ? exc_page_fault+0x7e/0x180 +[ +0.003932] entry_SYSCALL_64_after_hwframe+0x71/0x79 +[ +0.005064] RIP: 0033:0x7f59dc9347cb +[ +0.003648] Code: 73 01 c3 48 8b 0d 65 16 0c 00 f7 d8 64 89 01 48 83 +c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 90 f3 0f 1e fa b8 b0 00 00 00 0f +05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 35 16 0c 00 f7 d8 64 89 01 48 +[ +0.018753] RSP: 002b:00007ffffac99048 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0 +[ +0.007577] RAX: ffffffffffffffda RBX: 0000559b9bb2f6e0 RCX: 00007f59dc9347cb +[ +0.007140] RDX: 0000000000000000 RSI: 0000000000000800 RDI: 0000559b9bb2f748 +[ +0.007146] RBP: 00007ffffac99070 R08: 1999999999999999 R09: 0000000000000000 +[ +0.007133] R10: 00007f59dc9a5ac0 R11: 0000000000000206 R12: 0000000000000000 +[ +0.007141] R13: 00007ffffac992d8 R14: 0000559b9bb2f6e0 R15: 0000000000000000 +[ +0.007151] +[ +0.002204] ---[ end trace 0000000000000000 ]--- + +Fix this by checking if the XDP program is being loaded or unloaded. +Then, block only loading a new program while "__I40E_IN_REMOVE" is set. +Also, move testing "__I40E_IN_REMOVE" flag to the beginning of XDP_SETUP +callback to avoid unnecessary operations and checks. + +Fixes: 6533e558c650 ("i40e: Fix reset path while removing the driver") +Signed-off-by: Michal Kubiak +Reviewed-by: Maciej Fijalkowski +Tested-by: Chandan Kumar Rout (A Contingent Worker at Intel) +Signed-off-by: Tony Nguyen +Link: https://patch.msgid.link/20240708230750.625986-1-anthony.l.nguyen@intel.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/intel/i40e/i40e_main.c | 9 ++++----- + 1 file changed, 4 insertions(+), 5 deletions(-) + +diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c +index 991321b04084a..da4022a211f62 100644 +--- a/drivers/net/ethernet/intel/i40e/i40e_main.c ++++ b/drivers/net/ethernet/intel/i40e/i40e_main.c +@@ -13304,6 +13304,10 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog, + bool need_reset; + int i; + ++ /* VSI shall be deleted in a moment, block loading new programs */ ++ if (prog && test_bit(__I40E_IN_REMOVE, pf->state)) ++ return -EINVAL; ++ + /* Don't allow frames that span over multiple buffers */ + if (frame_size > i40e_calculate_vsi_rx_buf_len(vsi)) { + NL_SET_ERR_MSG_MOD(extack, "MTU too large to enable XDP"); +@@ -13312,14 +13316,9 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog, + + /* When turning XDP on->off/off->on we reset and rebuild the rings. */ + need_reset = (i40e_enabled_xdp_vsi(vsi) != !!prog); +- + if (need_reset) + i40e_prep_for_reset(pf); + +- /* VSI shall be deleted in a moment, just return EINVAL */ +- if (test_bit(__I40E_IN_REMOVE, pf->state)) +- return -EINVAL; +- + old_prog = xchg(&vsi->xdp_prog, prog); + + if (need_reset) { +-- +2.43.0 + diff --git a/queue-5.15/mm-prevent-derefencing-null-ptr-in-pfn_section_valid.patch b/queue-5.15/mm-prevent-derefencing-null-ptr-in-pfn_section_valid.patch new file mode 100644 index 00000000000..52360b16ea5 --- /dev/null +++ b/queue-5.15/mm-prevent-derefencing-null-ptr-in-pfn_section_valid.patch @@ -0,0 +1,44 @@ +From fc7839b7839f0656af821ccd35ae6423c906a00f Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 25 Jun 2024 20:16:39 -0400 +Subject: mm: prevent derefencing NULL ptr in pfn_section_valid() + +From: Waiman Long + +[ Upstream commit 82f0b6f041fad768c28b4ad05a683065412c226e ] + +Commit 5ec8e8ea8b77 ("mm/sparsemem: fix race in accessing +memory_section->usage") changed pfn_section_valid() to add a READ_ONCE() +call around "ms->usage" to fix a race with section_deactivate() where +ms->usage can be cleared. The READ_ONCE() call, by itself, is not enough +to prevent NULL pointer dereference. We need to check its value before +dereferencing it. + +Link: https://lkml.kernel.org/r/20240626001639.1350646-1-longman@redhat.com +Fixes: 5ec8e8ea8b77 ("mm/sparsemem: fix race in accessing memory_section->usage") +Signed-off-by: Waiman Long +Cc: Charan Teja Kalla +Signed-off-by: Andrew Morton +Signed-off-by: Sasha Levin +--- + include/linux/mmzone.h | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h +index 8b8349ffa1cd9..998f10249f136 100644 +--- a/include/linux/mmzone.h ++++ b/include/linux/mmzone.h +@@ -1457,8 +1457,9 @@ static inline int subsection_map_index(unsigned long pfn) + static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) + { + int idx = subsection_map_index(pfn); ++ struct mem_section_usage *usage = READ_ONCE(ms->usage); + +- return test_bit(idx, READ_ONCE(ms->usage)->subsection_map); ++ return usage ? test_bit(idx, usage->subsection_map) : 0; + } + #else + static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) +-- +2.43.0 + diff --git a/queue-5.15/net-ethernet-lantiq_etop-fix-double-free-in-detach.patch b/queue-5.15/net-ethernet-lantiq_etop-fix-double-free-in-detach.patch new file mode 100644 index 00000000000..25abd56f009 --- /dev/null +++ b/queue-5.15/net-ethernet-lantiq_etop-fix-double-free-in-detach.patch @@ -0,0 +1,43 @@ +From 6e779d702a2faf42732588fe96c5c8f2e843bfcf Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 8 Jul 2024 22:58:26 +0200 +Subject: net: ethernet: lantiq_etop: fix double free in detach + +From: Aleksander Jan Bajkowski + +[ Upstream commit e1533b6319ab9c3a97dad314dd88b3783bc41b69 ] + +The number of the currently released descriptor is never incremented +which results in the same skb being released multiple times. + +Fixes: 504d4721ee8e ("MIPS: Lantiq: Add ethernet driver") +Reported-by: Joe Perches +Closes: https://lore.kernel.org/all/fc1bf93d92bb5b2f99c6c62745507cc22f3a7b2d.camel@perches.com/ +Signed-off-by: Aleksander Jan Bajkowski +Reviewed-by: Andrew Lunn +Link: https://patch.msgid.link/20240708205826.5176-1-olek2@wp.pl +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/lantiq_etop.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c +index d9911b3b9172d..c5faeda30c0b4 100644 +--- a/drivers/net/ethernet/lantiq_etop.c ++++ b/drivers/net/ethernet/lantiq_etop.c +@@ -213,9 +213,9 @@ ltq_etop_free_channel(struct net_device *dev, struct ltq_etop_chan *ch) + if (ch->dma.irq) + free_irq(ch->dma.irq, priv); + if (IS_RX(ch->idx)) { +- int desc; ++ struct ltq_dma_channel *dma = &ch->dma; + +- for (desc = 0; desc < LTQ_DESC_NUM; desc++) ++ for (dma->desc = 0; dma->desc < LTQ_DESC_NUM; dma->desc++) + dev_kfree_skb_any(ch->skb[ch->dma.desc]); + } + } +-- +2.43.0 + diff --git a/queue-5.15/net-ethernet-mtk-star-emac-set-mac_managed_pm-when-p.patch b/queue-5.15/net-ethernet-mtk-star-emac-set-mac_managed_pm-when-p.patch new file mode 100644 index 00000000000..1783a6e5a65 --- /dev/null +++ b/queue-5.15/net-ethernet-mtk-star-emac-set-mac_managed_pm-when-p.patch @@ -0,0 +1,55 @@ +From e50bdb2d974d783c05345cba40a42a678e199380 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 8 Jul 2024 14:52:09 +0800 +Subject: net: ethernet: mtk-star-emac: set mac_managed_pm when probing + +From: Jian Hui Lee + +[ Upstream commit 8c6790b5c25dfac11b589cc37346bcf9e23ad468 ] + +The below commit introduced a warning message when phy state is not in +the states: PHY_HALTED, PHY_READY, and PHY_UP. +commit 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state") + +mtk-star-emac doesn't need mdiobus suspend/resume. To fix the warning +message during resume, indicate the phy resume/suspend is managed by the +mac when probing. + +Fixes: 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state") +Signed-off-by: Jian Hui Lee +Reviewed-by: Jacob Keller +Link: https://patch.msgid.link/20240708065210.4178980-1-jianhui.lee@canonical.com +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/mediatek/mtk_star_emac.c | 7 +++++++ + 1 file changed, 7 insertions(+) + +diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c +index 67f9e4415ae92..392648246d8f4 100644 +--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c ++++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c +@@ -1446,6 +1446,7 @@ static int mtk_star_probe(struct platform_device *pdev) + { + struct device_node *of_node; + struct mtk_star_priv *priv; ++ struct phy_device *phydev; + struct net_device *ndev; + struct device *dev; + void __iomem *base; +@@ -1552,6 +1553,12 @@ static int mtk_star_probe(struct platform_device *pdev) + + netif_napi_add(ndev, &priv->napi, mtk_star_poll, NAPI_POLL_WEIGHT); + ++ phydev = of_phy_find_device(priv->phy_node); ++ if (phydev) { ++ phydev->mac_managed_pm = true; ++ put_device(&phydev->mdio.dev); ++ } ++ + return devm_register_netdev(dev, ndev); + } + +-- +2.43.0 + diff --git a/queue-5.15/net-fix-rc7-s-__skb_datagram_iter.patch b/queue-5.15/net-fix-rc7-s-__skb_datagram_iter.patch new file mode 100644 index 00000000000..fbf0d8b5717 --- /dev/null +++ b/queue-5.15/net-fix-rc7-s-__skb_datagram_iter.patch @@ -0,0 +1,45 @@ +From 1516eb61ec3450c003dcc2d8cdd80ca4b8695c22 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 8 Jul 2024 07:46:00 -0700 +Subject: net: fix rc7's __skb_datagram_iter() + +From: Hugh Dickins + +[ Upstream commit f153831097b4435f963e385304cc0f1acba1c657 ] + +X would not start in my old 32-bit partition (and the "n"-handling looks +just as wrong on 64-bit, but for whatever reason did not show up there): +"n" must be accumulated over all pages before it's added to "offset" and +compared with "copy", immediately after the skb_frag_foreach_page() loop. + +Fixes: d2d30a376d9c ("net: allow skb_datagram_iter to be called from any context") +Signed-off-by: Hugh Dickins +Reviewed-by: Sagi Grimberg +Link: https://patch.msgid.link/fef352e8-b89a-da51-f8ce-04bc39ee6481@google.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/core/datagram.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/net/core/datagram.c b/net/core/datagram.c +index 6b7db06eafe68..13f4bf82b2ee8 100644 +--- a/net/core/datagram.c ++++ b/net/core/datagram.c +@@ -447,11 +447,12 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset, + if (copy > len) + copy = len; + ++ n = 0; + skb_frag_foreach_page(frag, + skb_frag_off(frag) + offset - start, + copy, p, p_off, p_len, copied) { + vaddr = kmap_local_page(p); +- n = INDIRECT_CALL_1(cb, simple_copy_to_iter, ++ n += INDIRECT_CALL_1(cb, simple_copy_to_iter, + vaddr + p_off, p_len, data, to); + kunmap_local(vaddr); + } +-- +2.43.0 + diff --git a/queue-5.15/net-lantiq_etop-add-blank-line-after-declaration.patch b/queue-5.15/net-lantiq_etop-add-blank-line-after-declaration.patch new file mode 100644 index 00000000000..dd725999754 --- /dev/null +++ b/queue-5.15/net-lantiq_etop-add-blank-line-after-declaration.patch @@ -0,0 +1,40 @@ +From 6ddeeaf462b97d4b0b535cfd57739f1f154597f6 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 28 Dec 2021 23:00:31 +0100 +Subject: net: lantiq_etop: add blank line after declaration + +From: Aleksander Jan Bajkowski + +[ Upstream commit 4c46625bb586a741b8d0e6bdbddbcb2549fa1d36 ] + +This patch adds a missing line after the declaration and +fixes the checkpatch warning: + +WARNING: Missing a blank line after declarations ++ int desc; ++ for (desc = 0; desc < LTQ_DESC_NUM; desc++) + +Signed-off-by: Aleksander Jan Bajkowski +Link: https://lore.kernel.org/r/20211228220031.71576-1-olek2@wp.pl +Signed-off-by: Jakub Kicinski +Stable-dep-of: e1533b6319ab ("net: ethernet: lantiq_etop: fix double free in detach") +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/lantiq_etop.c | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c +index 057d655d17692..d9911b3b9172d 100644 +--- a/drivers/net/ethernet/lantiq_etop.c ++++ b/drivers/net/ethernet/lantiq_etop.c +@@ -214,6 +214,7 @@ ltq_etop_free_channel(struct net_device *dev, struct ltq_etop_chan *ch) + free_irq(ch->dma.irq, priv); + if (IS_RX(ch->idx)) { + int desc; ++ + for (desc = 0; desc < LTQ_DESC_NUM; desc++) + dev_kfree_skb_any(ch->skb[ch->dma.desc]); + } +-- +2.43.0 + diff --git a/queue-5.15/net-sched-fix-uaf-when-resolving-a-clash.patch b/queue-5.15/net-sched-fix-uaf-when-resolving-a-clash.patch new file mode 100644 index 00000000000..21cd9923173 --- /dev/null +++ b/queue-5.15/net-sched-fix-uaf-when-resolving-a-clash.patch @@ -0,0 +1,131 @@ +From 2410a4a96c3d4e9d903616d5dbe1a5b6300da01b Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 10 Jul 2024 13:37:47 +0800 +Subject: net/sched: Fix UAF when resolving a clash + +From: Chengen Du + +[ Upstream commit 26488172b0292bed837b95a006a3f3431d1898c3 ] + +KASAN reports the following UAF: + + BUG: KASAN: slab-use-after-free in tcf_ct_flow_table_process_conn+0x12b/0x380 [act_ct] + Read of size 1 at addr ffff888c07603600 by task handler130/6469 + + Call Trace: + + dump_stack_lvl+0x48/0x70 + print_address_description.constprop.0+0x33/0x3d0 + print_report+0xc0/0x2b0 + kasan_report+0xd0/0x120 + __asan_load1+0x6c/0x80 + tcf_ct_flow_table_process_conn+0x12b/0x380 [act_ct] + tcf_ct_act+0x886/0x1350 [act_ct] + tcf_action_exec+0xf8/0x1f0 + fl_classify+0x355/0x360 [cls_flower] + __tcf_classify+0x1fd/0x330 + tcf_classify+0x21c/0x3c0 + sch_handle_ingress.constprop.0+0x2c5/0x500 + __netif_receive_skb_core.constprop.0+0xb25/0x1510 + __netif_receive_skb_list_core+0x220/0x4c0 + netif_receive_skb_list_internal+0x446/0x620 + napi_complete_done+0x157/0x3d0 + gro_cell_poll+0xcf/0x100 + __napi_poll+0x65/0x310 + net_rx_action+0x30c/0x5c0 + __do_softirq+0x14f/0x491 + __irq_exit_rcu+0x82/0xc0 + irq_exit_rcu+0xe/0x20 + common_interrupt+0xa1/0xb0 + + + asm_common_interrupt+0x27/0x40 + + Allocated by task 6469: + kasan_save_stack+0x38/0x70 + kasan_set_track+0x25/0x40 + kasan_save_alloc_info+0x1e/0x40 + __kasan_krealloc+0x133/0x190 + krealloc+0xaa/0x130 + nf_ct_ext_add+0xed/0x230 [nf_conntrack] + tcf_ct_act+0x1095/0x1350 [act_ct] + tcf_action_exec+0xf8/0x1f0 + fl_classify+0x355/0x360 [cls_flower] + __tcf_classify+0x1fd/0x330 + tcf_classify+0x21c/0x3c0 + sch_handle_ingress.constprop.0+0x2c5/0x500 + __netif_receive_skb_core.constprop.0+0xb25/0x1510 + __netif_receive_skb_list_core+0x220/0x4c0 + netif_receive_skb_list_internal+0x446/0x620 + napi_complete_done+0x157/0x3d0 + gro_cell_poll+0xcf/0x100 + __napi_poll+0x65/0x310 + net_rx_action+0x30c/0x5c0 + __do_softirq+0x14f/0x491 + + Freed by task 6469: + kasan_save_stack+0x38/0x70 + kasan_set_track+0x25/0x40 + kasan_save_free_info+0x2b/0x60 + ____kasan_slab_free+0x180/0x1f0 + __kasan_slab_free+0x12/0x30 + slab_free_freelist_hook+0xd2/0x1a0 + __kmem_cache_free+0x1a2/0x2f0 + kfree+0x78/0x120 + nf_conntrack_free+0x74/0x130 [nf_conntrack] + nf_ct_destroy+0xb2/0x140 [nf_conntrack] + __nf_ct_resolve_clash+0x529/0x5d0 [nf_conntrack] + nf_ct_resolve_clash+0xf6/0x490 [nf_conntrack] + __nf_conntrack_confirm+0x2c6/0x770 [nf_conntrack] + tcf_ct_act+0x12ad/0x1350 [act_ct] + tcf_action_exec+0xf8/0x1f0 + fl_classify+0x355/0x360 [cls_flower] + __tcf_classify+0x1fd/0x330 + tcf_classify+0x21c/0x3c0 + sch_handle_ingress.constprop.0+0x2c5/0x500 + __netif_receive_skb_core.constprop.0+0xb25/0x1510 + __netif_receive_skb_list_core+0x220/0x4c0 + netif_receive_skb_list_internal+0x446/0x620 + napi_complete_done+0x157/0x3d0 + gro_cell_poll+0xcf/0x100 + __napi_poll+0x65/0x310 + net_rx_action+0x30c/0x5c0 + __do_softirq+0x14f/0x491 + +The ct may be dropped if a clash has been resolved but is still passed to +the tcf_ct_flow_table_process_conn function for further usage. This issue +can be fixed by retrieving ct from skb again after confirming conntrack. + +Fixes: 0cc254e5aa37 ("net/sched: act_ct: Offload connections with commit action") +Co-developed-by: Gerald Yang +Signed-off-by: Gerald Yang +Signed-off-by: Chengen Du +Link: https://patch.msgid.link/20240710053747.13223-1-chengen.du@canonical.com +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/sched/act_ct.c | 8 ++++++++ + 1 file changed, 8 insertions(+) + +diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c +index 5319de38cc6df..c602b0d698f29 100644 +--- a/net/sched/act_ct.c ++++ b/net/sched/act_ct.c +@@ -1046,6 +1046,14 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, + */ + if (nf_conntrack_confirm(skb) != NF_ACCEPT) + goto drop; ++ ++ /* The ct may be dropped if a clash has been resolved, ++ * so it's necessary to retrieve it from skb again to ++ * prevent UAF. ++ */ ++ ct = nf_ct_get(skb, &ctinfo); ++ if (!ct) ++ skip_add = true; + } + + if (!skip_add) +-- +2.43.0 + diff --git a/queue-5.15/octeontx2-af-fix-incorrect-value-output-on-error-pat.patch b/queue-5.15/octeontx2-af-fix-incorrect-value-output-on-error-pat.patch new file mode 100644 index 00000000000..4761d9dc643 --- /dev/null +++ b/queue-5.15/octeontx2-af-fix-incorrect-value-output-on-error-pat.patch @@ -0,0 +1,44 @@ +From 7323342a7aebcdeac7a4918dba7f71d59fdd6e22 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 5 Jul 2024 12:53:17 +0300 +Subject: octeontx2-af: Fix incorrect value output on error path in + rvu_check_rsrc_availability() + +From: Aleksandr Mishin + +[ Upstream commit 442e26af9aa8115c96541026cbfeaaa76c85d178 ] + +In rvu_check_rsrc_availability() in case of invalid SSOW req, an incorrect +data is printed to error log. 'req->sso' value is printed instead of +'req->ssow'. Looks like "copy-paste" mistake. + +Fix this mistake by replacing 'req->sso' with 'req->ssow'. + +Found by Linux Verification Center (linuxtesting.org) with SVACE. + +Fixes: 746ea74241fa ("octeontx2-af: Add RVU block LF provisioning support") +Signed-off-by: Aleksandr Mishin +Reviewed-by: Simon Horman +Link: https://patch.msgid.link/20240705095317.12640-1-amishin@t-argos.ru +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/marvell/octeontx2/af/rvu.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +index bac42e0065c6c..bc8187e3f3393 100644 +--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c ++++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +@@ -1553,7 +1553,7 @@ static int rvu_check_rsrc_availability(struct rvu *rvu, + if (req->ssow > block->lf.max) { + dev_err(&rvu->pdev->dev, + "Func 0x%x: Invalid SSOW req, %d > max %d\n", +- pcifunc, req->sso, block->lf.max); ++ pcifunc, req->ssow, block->lf.max); + return -EINVAL; + } + mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->addr); +-- +2.43.0 + diff --git a/queue-5.15/ppp-reject-claimed-as-lcp-but-actually-malformed-pac.patch b/queue-5.15/ppp-reject-claimed-as-lcp-but-actually-malformed-pac.patch new file mode 100644 index 00000000000..9de5d6ddc80 --- /dev/null +++ b/queue-5.15/ppp-reject-claimed-as-lcp-but-actually-malformed-pac.patch @@ -0,0 +1,67 @@ +From ca2ace34ca355280e51a898890b23be759cf874e Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 8 Jul 2024 14:56:15 +0300 +Subject: ppp: reject claimed-as-LCP but actually malformed packets + +From: Dmitry Antipov + +[ Upstream commit f2aeb7306a898e1cbd03963d376f4b6656ca2b55 ] + +Since 'ppp_async_encode()' assumes valid LCP packets (with code +from 1 to 7 inclusive), add 'ppp_check_packet()' to ensure that +LCP packet has an actual body beyond PPP_LCP header bytes, and +reject claimed-as-LCP but actually malformed data otherwise. + +Reported-by: syzbot+ec0723ba9605678b14bf@syzkaller.appspotmail.com +Closes: https://syzkaller.appspot.com/bug?extid=ec0723ba9605678b14bf +Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") +Signed-off-by: Dmitry Antipov +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + drivers/net/ppp/ppp_generic.c | 15 +++++++++++++++ + 1 file changed, 15 insertions(+) + +diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c +index c1f11d1df4cd6..7a8a717770fcc 100644 +--- a/drivers/net/ppp/ppp_generic.c ++++ b/drivers/net/ppp/ppp_generic.c +@@ -70,6 +70,7 @@ + #define MPHDRLEN_SSN 4 /* ditto with short sequence numbers */ + + #define PPP_PROTO_LEN 2 ++#define PPP_LCP_HDRLEN 4 + + /* + * An instance of /dev/ppp can be associated with either a ppp +@@ -490,6 +491,15 @@ static ssize_t ppp_read(struct file *file, char __user *buf, + return ret; + } + ++static bool ppp_check_packet(struct sk_buff *skb, size_t count) ++{ ++ /* LCP packets must include LCP header which 4 bytes long: ++ * 1-byte code, 1-byte identifier, and 2-byte length. ++ */ ++ return get_unaligned_be16(skb->data) != PPP_LCP || ++ count >= PPP_PROTO_LEN + PPP_LCP_HDRLEN; ++} ++ + static ssize_t ppp_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) + { +@@ -512,6 +522,11 @@ static ssize_t ppp_write(struct file *file, const char __user *buf, + kfree_skb(skb); + goto out; + } ++ ret = -EINVAL; ++ if (unlikely(!ppp_check_packet(skb, count))) { ++ kfree_skb(skb); ++ goto out; ++ } + + switch (pf->kind) { + case INTERFACE: +-- +2.43.0 + diff --git a/queue-5.15/series b/queue-5.15/series index 93a040fe5e6..50ded81c486 100644 --- a/queue-5.15/series +++ b/queue-5.15/series @@ -77,3 +77,19 @@ kbuild-fix-short-log-for-as-in-link-vmlinux.sh.patch nfc-nci-add-the-inconsistency-check-between-the-inpu.patch null_blk-do-not-allow-runt-zone-with-zone-capacity-s.patch nilfs2-fix-incorrect-inode-allocation-from-reserved-inodes.patch +mm-prevent-derefencing-null-ptr-in-pfn_section_valid.patch +filelock-fix-potential-use-after-free-in-posix_lock_.patch +fs-dcache-re-use-value-stored-to-dentry-d_flags-inst.patch +vfs-don-t-mod-negative-dentry-count-when-on-shrinker.patch +tcp-fix-incorrect-undo-caused-by-dsack-of-tlp-retran.patch +skmsg-skip-zero-length-skb-in-sk_msg_recvmsg.patch +octeontx2-af-fix-incorrect-value-output-on-error-pat.patch +net-fix-rc7-s-__skb_datagram_iter.patch +i40e-fix-xdp-program-unloading-while-removing-the-dr.patch +net-lantiq_etop-add-blank-line-after-declaration.patch +net-ethernet-lantiq_etop-fix-double-free-in-detach.patch +net-ethernet-mtk-star-emac-set-mac_managed_pm-when-p.patch +ppp-reject-claimed-as-lcp-but-actually-malformed-pac.patch +ethtool-netlink-do-not-return-sqi-value-if-link-is-d.patch +udp-set-sock_rcu_free-earlier-in-udp_lib_get_port.patch +net-sched-fix-uaf-when-resolving-a-clash.patch diff --git a/queue-5.15/skmsg-skip-zero-length-skb-in-sk_msg_recvmsg.patch b/queue-5.15/skmsg-skip-zero-length-skb-in-sk_msg_recvmsg.patch new file mode 100644 index 00000000000..81d505f543f --- /dev/null +++ b/queue-5.15/skmsg-skip-zero-length-skb-in-sk_msg_recvmsg.patch @@ -0,0 +1,105 @@ +From 78f5573001651795d858bee6a33c33f9314846bb Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 3 Jul 2024 16:39:31 +0800 +Subject: skmsg: Skip zero length skb in sk_msg_recvmsg + +From: Geliang Tang + +[ Upstream commit f0c18025693707ec344a70b6887f7450bf4c826b ] + +When running BPF selftests (./test_progs -t sockmap_basic) on a Loongarch +platform, the following kernel panic occurs: + + [...] + Oops[#1]: + CPU: 22 PID: 2824 Comm: test_progs Tainted: G OE 6.10.0-rc2+ #18 + Hardware name: LOONGSON Dabieshan/Loongson-TC542F0, BIOS Loongson-UDK2018 + ... ... + ra: 90000000048bf6c0 sk_msg_recvmsg+0x120/0x560 + ERA: 9000000004162774 copy_page_to_iter+0x74/0x1c0 + CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE) + PRMD: 0000000c (PPLV0 +PIE +PWE) + EUEN: 00000007 (+FPE +SXE +ASXE -BTE) + ECFG: 00071c1d (LIE=0,2-4,10-12 VS=7) + ESTAT: 00010000 [PIL] (IS= ECode=1 EsubCode=0) + BADV: 0000000000000040 + PRID: 0014c011 (Loongson-64bit, Loongson-3C5000) + Modules linked in: bpf_testmod(OE) xt_CHECKSUM xt_MASQUERADE xt_conntrack + Process test_progs (pid: 2824, threadinfo=0000000000863a31, task=...) + Stack : ... + Call Trace: + [<9000000004162774>] copy_page_to_iter+0x74/0x1c0 + [<90000000048bf6c0>] sk_msg_recvmsg+0x120/0x560 + [<90000000049f2b90>] tcp_bpf_recvmsg_parser+0x170/0x4e0 + [<90000000049aae34>] inet_recvmsg+0x54/0x100 + [<900000000481ad5c>] sock_recvmsg+0x7c/0xe0 + [<900000000481e1a8>] __sys_recvfrom+0x108/0x1c0 + [<900000000481e27c>] sys_recvfrom+0x1c/0x40 + [<9000000004c076ec>] do_syscall+0x8c/0xc0 + [<9000000003731da4>] handle_syscall+0xc4/0x160 + Code: ... + ---[ end trace 0000000000000000 ]--- + Kernel panic - not syncing: Fatal exception + Kernel relocated by 0x3510000 + .text @ 0x9000000003710000 + .data @ 0x9000000004d70000 + .bss @ 0x9000000006469400 + ---[ end Kernel panic - not syncing: Fatal exception ]--- + [...] + +This crash happens every time when running sockmap_skb_verdict_shutdown +subtest in sockmap_basic. + +This crash is because a NULL pointer is passed to page_address() in the +sk_msg_recvmsg(). Due to the different implementations depending on the +architecture, page_address(NULL) will trigger a panic on Loongarch +platform but not on x86 platform. So this bug was hidden on x86 platform +for a while, but now it is exposed on Loongarch platform. The root cause +is that a zero length skb (skb->len == 0) was put on the queue. + +This zero length skb is a TCP FIN packet, which was sent by shutdown(), +invoked in test_sockmap_skb_verdict_shutdown(): + + shutdown(p1, SHUT_WR); + +In this case, in sk_psock_skb_ingress_enqueue(), num_sge is zero, and no +page is put to this sge (see sg_set_page in sg_set_page), but this empty +sge is queued into ingress_msg list. + +And in sk_msg_recvmsg(), this empty sge is used, and a NULL page is got by +sg_page(sge). Pass this NULL page to copy_page_to_iter(), which passes it +to kmap_local_page() and to page_address(), then kernel panics. + +To solve this, we should skip this zero length skb. So in sk_msg_recvmsg(), +if copy is zero, that means it's a zero length skb, skip invoking +copy_page_to_iter(). We are using the EFAULT return triggered by +copy_page_to_iter to check for is_fin in tcp_bpf.c. + +Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") +Suggested-by: John Fastabend +Signed-off-by: Geliang Tang +Signed-off-by: Daniel Borkmann +Reviewed-by: John Fastabend +Link: https://lore.kernel.org/bpf/e3a16eacdc6740658ee02a33489b1b9d4912f378.1719992715.git.tanggeliang@kylinos.cn +Signed-off-by: Sasha Levin +--- + net/core/skmsg.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +diff --git a/net/core/skmsg.c b/net/core/skmsg.c +index ec8671eccae0c..84824f715a2d1 100644 +--- a/net/core/skmsg.c ++++ b/net/core/skmsg.c +@@ -434,7 +434,8 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, + page = sg_page(sge); + if (copied + copy > len) + copy = len - copied; +- copy = copy_page_to_iter(page, sge->offset, copy, iter); ++ if (copy) ++ copy = copy_page_to_iter(page, sge->offset, copy, iter); + if (!copy) { + copied = copied ? copied : -EFAULT; + goto out; +-- +2.43.0 + diff --git a/queue-5.15/tcp-fix-incorrect-undo-caused-by-dsack-of-tlp-retran.patch b/queue-5.15/tcp-fix-incorrect-undo-caused-by-dsack-of-tlp-retran.patch new file mode 100644 index 00000000000..e63634be2e9 --- /dev/null +++ b/queue-5.15/tcp-fix-incorrect-undo-caused-by-dsack-of-tlp-retran.patch @@ -0,0 +1,107 @@ +From 6507b5eda5743003a21189374c1d40509a03a6a0 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 3 Jul 2024 13:12:46 -0400 +Subject: tcp: fix incorrect undo caused by DSACK of TLP retransmit + +From: Neal Cardwell + +[ Upstream commit 0ec986ed7bab6801faed1440e8839dcc710331ff ] + +Loss recovery undo_retrans bookkeeping had a long-standing bug where a +DSACK from a spurious TLP retransmit packet could cause an erroneous +undo of a fast recovery or RTO recovery that repaired a single +really-lost packet (in a sequence range outside that of the TLP +retransmit). Basically, because the loss recovery state machine didn't +account for the fact that it sent a TLP retransmit, the DSACK for the +TLP retransmit could erroneously be implicitly be interpreted as +corresponding to the normal fast recovery or RTO recovery retransmit +that plugged a real hole, thus resulting in an improper undo. + +For example, consider the following buggy scenario where there is a +real packet loss but the congestion control response is improperly +undone because of this bug: + ++ send packets P1, P2, P3, P4 ++ P1 is really lost ++ send TLP retransmit of P4 ++ receive SACK for original P2, P3, P4 ++ enter fast recovery, fast-retransmit P1, increment undo_retrans to 1 ++ receive DSACK for TLP P4, decrement undo_retrans to 0, undo (bug!) ++ receive cumulative ACK for P1-P4 (fast retransmit plugged real hole) + +The fix: when we initialize undo machinery in tcp_init_undo(), if +there is a TLP retransmit in flight, then increment tp->undo_retrans +so that we make sure that we receive a DSACK corresponding to the TLP +retransmit, as well as DSACKs for all later normal retransmits, before +triggering a loss recovery undo. Note that we also have to move the +line that clears tp->tlp_high_seq for RTO recovery, so that upon RTO +we remember the tp->tlp_high_seq value until tcp_init_undo() and clear +it only afterward. + +Also note that the bug dates back to the original 2013 TLP +implementation, commit 6ba8a3b19e76 ("tcp: Tail loss probe (TLP)"). + +However, this patch will only compile and work correctly with kernels +that have tp->tlp_retrans, which was added only in v5.8 in 2020 in +commit 76be93fc0702 ("tcp: allow at most one TLP probe per flight"). +So we associate this fix with that later commit. + +Fixes: 76be93fc0702 ("tcp: allow at most one TLP probe per flight") +Signed-off-by: Neal Cardwell +Reviewed-by: Eric Dumazet +Cc: Yuchung Cheng +Cc: Kevin Yang +Link: https://patch.msgid.link/20240703171246.1739561-1-ncardwell.sw@gmail.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/ipv4/tcp_input.c | 11 ++++++++++- + net/ipv4/tcp_timer.c | 2 -- + 2 files changed, 10 insertions(+), 3 deletions(-) + +diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c +index f37b39350e816..48d45022dedaf 100644 +--- a/net/ipv4/tcp_input.c ++++ b/net/ipv4/tcp_input.c +@@ -2094,8 +2094,16 @@ void tcp_clear_retrans(struct tcp_sock *tp) + static inline void tcp_init_undo(struct tcp_sock *tp) + { + tp->undo_marker = tp->snd_una; ++ + /* Retransmission still in flight may cause DSACKs later. */ +- tp->undo_retrans = tp->retrans_out ? : -1; ++ /* First, account for regular retransmits in flight: */ ++ tp->undo_retrans = tp->retrans_out; ++ /* Next, account for TLP retransmits in flight: */ ++ if (tp->tlp_high_seq && tp->tlp_retrans) ++ tp->undo_retrans++; ++ /* Finally, avoid 0, because undo_retrans==0 means "can undo now": */ ++ if (!tp->undo_retrans) ++ tp->undo_retrans = -1; + } + + static bool tcp_is_rack(const struct sock *sk) +@@ -2174,6 +2182,7 @@ void tcp_enter_loss(struct sock *sk) + + tcp_set_ca_state(sk, TCP_CA_Loss); + tp->high_seq = tp->snd_nxt; ++ tp->tlp_high_seq = 0; + tcp_ecn_queue_cwr(tp); + + /* F-RTO RFC5682 sec 3.1 step 1: retransmit SND.UNA if no previous +diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c +index 40a354dcfec5a..756466816f303 100644 +--- a/net/ipv4/tcp_timer.c ++++ b/net/ipv4/tcp_timer.c +@@ -492,8 +492,6 @@ void tcp_retransmit_timer(struct sock *sk) + if (WARN_ON_ONCE(!skb)) + return; + +- tp->tlp_high_seq = 0; +- + if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) && + !((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) { + /* Receiver dastardly shrinks window. Our retransmits +-- +2.43.0 + diff --git a/queue-5.15/udp-set-sock_rcu_free-earlier-in-udp_lib_get_port.patch b/queue-5.15/udp-set-sock_rcu_free-earlier-in-udp_lib_get_port.patch new file mode 100644 index 00000000000..1855aa1f1c5 --- /dev/null +++ b/queue-5.15/udp-set-sock_rcu_free-earlier-in-udp_lib_get_port.patch @@ -0,0 +1,123 @@ +From 86611b8457c45cb43f95b1eed46081e733056865 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 9 Jul 2024 12:13:56 -0700 +Subject: udp: Set SOCK_RCU_FREE earlier in udp_lib_get_port(). + +From: Kuniyuki Iwashima + +[ Upstream commit 5c0b485a8c6116516f33925b9ce5b6104a6eadfd ] + +syzkaller triggered the warning [0] in udp_v4_early_demux(). + +In udp_v[46]_early_demux() and sk_lookup(), we do not touch the refcount +of the looked-up sk and use sock_pfree() as skb->destructor, so we check +SOCK_RCU_FREE to ensure that the sk is safe to access during the RCU grace +period. + +Currently, SOCK_RCU_FREE is flagged for a bound socket after being put +into the hash table. Moreover, the SOCK_RCU_FREE check is done too early +in udp_v[46]_early_demux() and sk_lookup(), so there could be a small race +window: + + CPU1 CPU2 + ---- ---- + udp_v4_early_demux() udp_lib_get_port() + | |- hlist_add_head_rcu() + |- sk = __udp4_lib_demux_lookup() | + |- DEBUG_NET_WARN_ON_ONCE(sk_is_refcounted(sk)); + `- sock_set_flag(sk, SOCK_RCU_FREE) + +We had the same bug in TCP and fixed it in commit 871019b22d1b ("net: +set SOCK_RCU_FREE before inserting socket into hashtable"). + +Let's apply the same fix for UDP. + +[0]: +WARNING: CPU: 0 PID: 11198 at net/ipv4/udp.c:2599 udp_v4_early_demux+0x481/0xb70 net/ipv4/udp.c:2599 +Modules linked in: +CPU: 0 PID: 11198 Comm: syz-executor.1 Not tainted 6.9.0-g93bda33046e7 #13 +Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 +RIP: 0010:udp_v4_early_demux+0x481/0xb70 net/ipv4/udp.c:2599 +Code: c5 7a 15 fe bb 01 00 00 00 44 89 e9 31 ff d3 e3 81 e3 bf ef ff ff 89 de e8 2c 74 15 fe 85 db 0f 85 02 06 00 00 e8 9f 7a 15 fe <0f> 0b e8 98 7a 15 fe 49 8d 7e 60 e8 4f 39 2f fe 49 c7 46 60 20 52 +RSP: 0018:ffffc9000ce3fa58 EFLAGS: 00010293 +RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffffffff8318c92c +RDX: ffff888036ccde00 RSI: ffffffff8318c2f1 RDI: 0000000000000001 +RBP: ffff88805a2dd6e0 R08: 0000000000000001 R09: 0000000000000000 +R10: 0000000000000000 R11: 0001ffffffffffff R12: ffff88805a2dd680 +R13: 0000000000000007 R14: ffff88800923f900 R15: ffff88805456004e +FS: 00007fc449127640(0000) GS:ffff88807dc00000(0000) knlGS:0000000000000000 +CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +CR2: 00007fc449126e38 CR3: 000000003de4b002 CR4: 0000000000770ef0 +DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 +DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000600 +PKRU: 55555554 +Call Trace: + + ip_rcv_finish_core.constprop.0+0xbdd/0xd20 net/ipv4/ip_input.c:349 + ip_rcv_finish+0xda/0x150 net/ipv4/ip_input.c:447 + NF_HOOK include/linux/netfilter.h:314 [inline] + NF_HOOK include/linux/netfilter.h:308 [inline] + ip_rcv+0x16c/0x180 net/ipv4/ip_input.c:569 + __netif_receive_skb_one_core+0xb3/0xe0 net/core/dev.c:5624 + __netif_receive_skb+0x21/0xd0 net/core/dev.c:5738 + netif_receive_skb_internal net/core/dev.c:5824 [inline] + netif_receive_skb+0x271/0x300 net/core/dev.c:5884 + tun_rx_batched drivers/net/tun.c:1549 [inline] + tun_get_user+0x24db/0x2c50 drivers/net/tun.c:2002 + tun_chr_write_iter+0x107/0x1a0 drivers/net/tun.c:2048 + new_sync_write fs/read_write.c:497 [inline] + vfs_write+0x76f/0x8d0 fs/read_write.c:590 + ksys_write+0xbf/0x190 fs/read_write.c:643 + __do_sys_write fs/read_write.c:655 [inline] + __se_sys_write fs/read_write.c:652 [inline] + __x64_sys_write+0x41/0x50 fs/read_write.c:652 + x64_sys_call+0xe66/0x1990 arch/x86/include/generated/asm/syscalls_64.h:2 + do_syscall_x64 arch/x86/entry/common.c:52 [inline] + do_syscall_64+0x4b/0x110 arch/x86/entry/common.c:83 + entry_SYSCALL_64_after_hwframe+0x4b/0x53 +RIP: 0033:0x7fc44a68bc1f +Code: 89 54 24 18 48 89 74 24 10 89 7c 24 08 e8 e9 cf f5 ff 48 8b 54 24 18 48 8b 74 24 10 41 89 c0 8b 7c 24 08 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 31 44 89 c7 48 89 44 24 08 e8 3c d0 f5 ff 48 +RSP: 002b:00007fc449126c90 EFLAGS: 00000293 ORIG_RAX: 0000000000000001 +RAX: ffffffffffffffda RBX: 00000000004bc050 RCX: 00007fc44a68bc1f +RDX: 0000000000000032 RSI: 00000000200000c0 RDI: 00000000000000c8 +RBP: 00000000004bc050 R08: 0000000000000000 R09: 0000000000000000 +R10: 0000000000000032 R11: 0000000000000293 R12: 0000000000000000 +R13: 000000000000000b R14: 00007fc44a5ec530 R15: 0000000000000000 + + +Fixes: 6acc9b432e67 ("bpf: Add helper to retrieve socket in BPF") +Reported-by: syzkaller +Signed-off-by: Kuniyuki Iwashima +Reviewed-by: Eric Dumazet +Link: https://patch.msgid.link/20240709191356.24010-1-kuniyu@amazon.com +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/ipv4/udp.c | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c +index 53d7a81d62584..138fef35e7071 100644 +--- a/net/ipv4/udp.c ++++ b/net/ipv4/udp.c +@@ -317,6 +317,8 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, + goto fail_unlock; + } + ++ sock_set_flag(sk, SOCK_RCU_FREE); ++ + sk_add_node_rcu(sk, &hslot->head); + hslot->count++; + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); +@@ -333,7 +335,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, + hslot2->count++; + spin_unlock(&hslot2->lock); + } +- sock_set_flag(sk, SOCK_RCU_FREE); ++ + error = 0; + fail_unlock: + spin_unlock_bh(&hslot->lock); +-- +2.43.0 + diff --git a/queue-5.15/vfs-don-t-mod-negative-dentry-count-when-on-shrinker.patch b/queue-5.15/vfs-don-t-mod-negative-dentry-count-when-on-shrinker.patch new file mode 100644 index 00000000000..f17c6b1e8ee --- /dev/null +++ b/queue-5.15/vfs-don-t-mod-negative-dentry-count-when-on-shrinker.patch @@ -0,0 +1,88 @@ +From 88ee1ca735c3041a2b057ddf7ff32590fb1c7930 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 3 Jul 2024 08:13:01 -0400 +Subject: vfs: don't mod negative dentry count when on shrinker list + +From: Brian Foster + +[ Upstream commit aabfe57ebaa75841db47ea59091ec3c5a06d2f52 ] + +The nr_dentry_negative counter is intended to only account negative +dentries that are present on the superblock LRU. Therefore, the LRU +add, remove and isolate helpers modify the counter based on whether +the dentry is negative, but the shrinker list related helpers do not +modify the counter, and the paths that change a dentry between +positive and negative only do so if DCACHE_LRU_LIST is set. + +The problem with this is that a dentry on a shrinker list still has +DCACHE_LRU_LIST set to indicate ->d_lru is in use. The additional +DCACHE_SHRINK_LIST flag denotes whether the dentry is on LRU or a +shrink related list. Therefore if a relevant operation (i.e. unlink) +occurs while a dentry is present on a shrinker list, and the +associated codepath only checks for DCACHE_LRU_LIST, then it is +technically possible to modify the negative dentry count for a +dentry that is off the LRU. Since the shrinker list related helpers +do not modify the negative dentry count (because non-LRU dentries +should not be included in the count) when the dentry is ultimately +removed from the shrinker list, this can cause the negative dentry +count to become permanently inaccurate. + +This problem can be reproduced via a heavy file create/unlink vs. +drop_caches workload. On an 80xcpu system, I start 80 tasks each +running a 1k file create/delete loop, and one task spinning on +drop_caches. After 10 minutes or so of runtime, the idle/clean cache +negative dentry count increases from somewhere in the range of 5-10 +entries to several hundred (and increasingly grows beyond +nr_dentry_unused). + +Tweak the logic in the paths that turn a dentry negative or positive +to filter out the case where the dentry is present on a shrink +related list. This allows the above workload to maintain an accurate +negative dentry count. + +Fixes: af0c9af1b3f6 ("fs/dcache: Track & report number of negative dentries") +Signed-off-by: Brian Foster +Link: https://lore.kernel.org/r/20240703121301.247680-1-bfoster@redhat.com +Acked-by: Ian Kent +Reviewed-by: Josef Bacik +Reviewed-by: Waiman Long +Signed-off-by: Christian Brauner +Signed-off-by: Sasha Levin +--- + fs/dcache.c | 12 +++++++++--- + 1 file changed, 9 insertions(+), 3 deletions(-) + +diff --git a/fs/dcache.c b/fs/dcache.c +index f2ff73fe2b619..9a29cfdaa5416 100644 +--- a/fs/dcache.c ++++ b/fs/dcache.c +@@ -331,7 +331,11 @@ static inline void __d_clear_type_and_inode(struct dentry *dentry) + flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); + WRITE_ONCE(dentry->d_flags, flags); + dentry->d_inode = NULL; +- if (flags & DCACHE_LRU_LIST) ++ /* ++ * The negative counter only tracks dentries on the LRU. Don't inc if ++ * d_lru is on another list. ++ */ ++ if ((flags & (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) + this_cpu_inc(nr_dentry_negative); + } + +@@ -1975,9 +1979,11 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) + + spin_lock(&dentry->d_lock); + /* +- * Decrement negative dentry count if it was in the LRU list. ++ * The negative counter only tracks dentries on the LRU. Don't dec if ++ * d_lru is on another list. + */ +- if (dentry->d_flags & DCACHE_LRU_LIST) ++ if ((dentry->d_flags & ++ (DCACHE_LRU_LIST|DCACHE_SHRINK_LIST)) == DCACHE_LRU_LIST) + this_cpu_dec(nr_dentry_negative); + hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); + raw_write_seqcount_begin(&dentry->d_seq); +-- +2.43.0 +