From: Sasha Levin Date: Sun, 17 Nov 2024 14:35:19 +0000 (-0500) Subject: Fixes for 6.1 X-Git-Tag: v6.12.1~64 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=a0c2664b579a11250cae278812c8cdc14a33f4fe;p=thirdparty%2Fkernel%2Fstable-queue.git Fixes for 6.1 Signed-off-by: Sasha Levin --- diff --git a/queue-6.1/arm-9419-1-mm-fix-kernel-memory-mapping-for-xip-kern.patch b/queue-6.1/arm-9419-1-mm-fix-kernel-memory-mapping-for-xip-kern.patch new file mode 100644 index 00000000000..d31edce4723 --- /dev/null +++ b/queue-6.1/arm-9419-1-mm-fix-kernel-memory-mapping-for-xip-kern.patch @@ -0,0 +1,144 @@ +From 12ca009cc5ac6163370a3cce23f3201b7d1c0975 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 18 Sep 2024 06:57:11 +0100 +Subject: ARM: 9419/1: mm: Fix kernel memory mapping for xip kernels + +From: Harith G + +[ Upstream commit ed6cbe6e5563452f305e89c15846820f2874e431 ] + +The patchset introducing kernel_sec_start/end variables to separate the +kernel/lowmem memory mappings, broke the mapping of the kernel memory +for xipkernels. + +kernel_sec_start/end variables are in RO area before the MMU is switched +on for xipkernels. +So these cannot be set early in boot in head.S. Fix this by setting these +after MMU is switched on. +xipkernels need two different mappings for kernel text (starting at +CONFIG_XIP_PHYS_ADDR) and data (starting at CONFIG_PHYS_OFFSET). +Also, move the kernel code mapping from devicemaps_init() to map_kernel(). + +Fixes: a91da5457085 ("ARM: 9089/1: Define kernel physical section start and end") +Signed-off-by: Harith George +Reviewed-by: Linus Walleij +Signed-off-by: Russell King (Oracle) +Signed-off-by: Sasha Levin +--- + arch/arm/kernel/head.S | 8 ++++++-- + arch/arm/mm/mmu.c | 34 +++++++++++++++++++++------------- + 2 files changed, 27 insertions(+), 15 deletions(-) + +diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S +index 29e2900178a1f..b97da9e069a06 100644 +--- a/arch/arm/kernel/head.S ++++ b/arch/arm/kernel/head.S +@@ -252,11 +252,15 @@ __create_page_tables: + */ + add r0, r4, #KERNEL_OFFSET >> (SECTION_SHIFT - PMD_ENTRY_ORDER) + ldr r6, =(_end - 1) ++ ++ /* For XIP, kernel_sec_start/kernel_sec_end are currently in RO memory */ ++#ifndef CONFIG_XIP_KERNEL + adr_l r5, kernel_sec_start @ _pa(kernel_sec_start) + #if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32 + str r8, [r5, #4] @ Save physical start of kernel (BE) + #else + str r8, [r5] @ Save physical start of kernel (LE) ++#endif + #endif + orr r3, r8, r7 @ Add the MMU flags + add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ENTRY_ORDER) +@@ -264,6 +268,7 @@ __create_page_tables: + add r3, r3, #1 << SECTION_SHIFT + cmp r0, r6 + bls 1b ++#ifndef CONFIG_XIP_KERNEL + eor r3, r3, r7 @ Remove the MMU flags + adr_l r5, kernel_sec_end @ _pa(kernel_sec_end) + #if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32 +@@ -271,8 +276,7 @@ __create_page_tables: + #else + str r3, [r5] @ Save physical end of kernel (LE) + #endif +- +-#ifdef CONFIG_XIP_KERNEL ++#else + /* + * Map the kernel image separately as it is not located in RAM. + */ +diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c +index 463fc2a8448f0..a39a7043f1896 100644 +--- a/arch/arm/mm/mmu.c ++++ b/arch/arm/mm/mmu.c +@@ -1401,18 +1401,6 @@ static void __init devicemaps_init(const struct machine_desc *mdesc) + create_mapping(&map); + } + +- /* +- * Map the kernel if it is XIP. +- * It is always first in the modulearea. +- */ +-#ifdef CONFIG_XIP_KERNEL +- map.pfn = __phys_to_pfn(CONFIG_XIP_PHYS_ADDR & SECTION_MASK); +- map.virtual = MODULES_VADDR; +- map.length = ((unsigned long)_exiprom - map.virtual + ~SECTION_MASK) & SECTION_MASK; +- map.type = MT_ROM; +- create_mapping(&map); +-#endif +- + /* + * Map the cache flushing regions. + */ +@@ -1602,12 +1590,27 @@ static void __init map_kernel(void) + * This will only persist until we turn on proper memory management later on + * and we remap the whole kernel with page granularity. + */ ++#ifdef CONFIG_XIP_KERNEL ++ phys_addr_t kernel_nx_start = kernel_sec_start; ++#else + phys_addr_t kernel_x_start = kernel_sec_start; + phys_addr_t kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE); + phys_addr_t kernel_nx_start = kernel_x_end; ++#endif + phys_addr_t kernel_nx_end = kernel_sec_end; + struct map_desc map; + ++ /* ++ * Map the kernel if it is XIP. ++ * It is always first in the modulearea. ++ */ ++#ifdef CONFIG_XIP_KERNEL ++ map.pfn = __phys_to_pfn(CONFIG_XIP_PHYS_ADDR & SECTION_MASK); ++ map.virtual = MODULES_VADDR; ++ map.length = ((unsigned long)_exiprom - map.virtual + ~SECTION_MASK) & SECTION_MASK; ++ map.type = MT_ROM; ++ create_mapping(&map); ++#else + map.pfn = __phys_to_pfn(kernel_x_start); + map.virtual = __phys_to_virt(kernel_x_start); + map.length = kernel_x_end - kernel_x_start; +@@ -1617,7 +1620,7 @@ static void __init map_kernel(void) + /* If the nx part is small it may end up covered by the tail of the RWX section */ + if (kernel_x_end == kernel_nx_end) + return; +- ++#endif + map.pfn = __phys_to_pfn(kernel_nx_start); + map.virtual = __phys_to_virt(kernel_nx_start); + map.length = kernel_nx_end - kernel_nx_start; +@@ -1762,6 +1765,11 @@ void __init paging_init(const struct machine_desc *mdesc) + { + void *zero_page; + ++#ifdef CONFIG_XIP_KERNEL ++ /* Store the kernel RW RAM region start/end in these variables */ ++ kernel_sec_start = CONFIG_PHYS_OFFSET & SECTION_MASK; ++ kernel_sec_end = round_up(__pa(_end), SECTION_SIZE); ++#endif + pr_debug("physical kernel sections: 0x%08llx-0x%08llx\n", + kernel_sec_start, kernel_sec_end); + +-- +2.43.0 + diff --git a/queue-6.1/bluetooth-hci_core-fix-calling-mgmt_device_connected.patch b/queue-6.1/bluetooth-hci_core-fix-calling-mgmt_device_connected.patch new file mode 100644 index 00000000000..d2d3676398d --- /dev/null +++ b/queue-6.1/bluetooth-hci_core-fix-calling-mgmt_device_connected.patch @@ -0,0 +1,39 @@ +From be82b07c0320a2ef291bb9cde6975924454ecdf7 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 8 Nov 2024 11:19:54 -0500 +Subject: Bluetooth: hci_core: Fix calling mgmt_device_connected + +From: Luiz Augusto von Dentz + +[ Upstream commit 7967dc8f797f454d4f4acec15c7df0cdf4801617 ] + +Since 61a939c68ee0 ("Bluetooth: Queue incoming ACL data until +BT_CONNECTED state is reached") there is no long the need to call +mgmt_device_connected as ACL data will be queued until BT_CONNECTED +state. + +Link: https://bugzilla.kernel.org/show_bug.cgi?id=219458 +Link: https://github.com/bluez/bluez/issues/1014 +Fixes: 333b4fd11e89 ("Bluetooth: L2CAP: Fix uaf in l2cap_connect") +Signed-off-by: Luiz Augusto von Dentz +Signed-off-by: Sasha Levin +--- + net/bluetooth/hci_core.c | 2 -- + 1 file changed, 2 deletions(-) + +diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c +index f93f3e7a3d905..789f7f4a09089 100644 +--- a/net/bluetooth/hci_core.c ++++ b/net/bluetooth/hci_core.c +@@ -3846,8 +3846,6 @@ static void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) + + hci_dev_lock(hdev); + conn = hci_conn_hash_lookup_handle(hdev, handle); +- if (conn && hci_dev_test_flag(hdev, HCI_MGMT)) +- mgmt_device_connected(hdev, conn, NULL, 0); + hci_dev_unlock(hdev); + + if (conn) { +-- +2.43.0 + diff --git a/queue-6.1/bluetooth-hci_event-remove-code-to-removed-config_bt.patch b/queue-6.1/bluetooth-hci_event-remove-code-to-removed-config_bt.patch new file mode 100644 index 00000000000..386373460d8 --- /dev/null +++ b/queue-6.1/bluetooth-hci_event-remove-code-to-removed-config_bt.patch @@ -0,0 +1,206 @@ +From b17dc856b99c631d5e06af11c12aed434bd8660b Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Wed, 7 Feb 2024 14:42:11 +0100 +Subject: Bluetooth: hci_event: Remove code to removed CONFIG_BT_HS + +From: Lukas Bulwahn + +[ Upstream commit f4b0c2b4cd78b75acde56c2ee5aa732b6fb2a6a9 ] + +Commit cec9f3c5561d ("Bluetooth: Remove BT_HS") removes config BT_HS, but +misses two "ifdef BT_HS" blocks in hci_event.c. + +Remove this dead code from this removed config option. + +Signed-off-by: Lukas Bulwahn +Signed-off-by: Luiz Augusto von Dentz +Stable-dep-of: 7967dc8f797f ("Bluetooth: hci_core: Fix calling mgmt_device_connected") +Signed-off-by: Sasha Levin +--- + net/bluetooth/hci_event.c | 163 -------------------------------------- + 1 file changed, 163 deletions(-) + +diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c +index 7c1df481ebe9d..b6fe5e15981f8 100644 +--- a/net/bluetooth/hci_event.c ++++ b/net/bluetooth/hci_event.c +@@ -5648,150 +5648,6 @@ static void hci_remote_oob_data_request_evt(struct hci_dev *hdev, void *edata, + hci_dev_unlock(hdev); + } + +-#if IS_ENABLED(CONFIG_BT_HS) +-static void hci_chan_selected_evt(struct hci_dev *hdev, void *data, +- struct sk_buff *skb) +-{ +- struct hci_ev_channel_selected *ev = data; +- struct hci_conn *hcon; +- +- bt_dev_dbg(hdev, "handle 0x%2.2x", ev->phy_handle); +- +- hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); +- if (!hcon) +- return; +- +- amp_read_loc_assoc_final_data(hdev, hcon); +-} +- +-static void hci_phy_link_complete_evt(struct hci_dev *hdev, void *data, +- struct sk_buff *skb) +-{ +- struct hci_ev_phy_link_complete *ev = data; +- struct hci_conn *hcon, *bredr_hcon; +- +- bt_dev_dbg(hdev, "handle 0x%2.2x status 0x%2.2x", ev->phy_handle, +- ev->status); +- +- hci_dev_lock(hdev); +- +- hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); +- if (!hcon) +- goto unlock; +- +- if (!hcon->amp_mgr) +- goto unlock; +- +- if (ev->status) { +- hci_conn_del(hcon); +- goto unlock; +- } +- +- bredr_hcon = hcon->amp_mgr->l2cap_conn->hcon; +- +- hcon->state = BT_CONNECTED; +- bacpy(&hcon->dst, &bredr_hcon->dst); +- +- hci_conn_hold(hcon); +- hcon->disc_timeout = HCI_DISCONN_TIMEOUT; +- hci_conn_drop(hcon); +- +- hci_debugfs_create_conn(hcon); +- hci_conn_add_sysfs(hcon); +- +- amp_physical_cfm(bredr_hcon, hcon); +- +-unlock: +- hci_dev_unlock(hdev); +-} +- +-static void hci_loglink_complete_evt(struct hci_dev *hdev, void *data, +- struct sk_buff *skb) +-{ +- struct hci_ev_logical_link_complete *ev = data; +- struct hci_conn *hcon; +- struct hci_chan *hchan; +- struct amp_mgr *mgr; +- +- bt_dev_dbg(hdev, "log_handle 0x%4.4x phy_handle 0x%2.2x status 0x%2.2x", +- le16_to_cpu(ev->handle), ev->phy_handle, ev->status); +- +- hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); +- if (!hcon) +- return; +- +- /* Create AMP hchan */ +- hchan = hci_chan_create(hcon); +- if (!hchan) +- return; +- +- hchan->handle = le16_to_cpu(ev->handle); +- hchan->amp = true; +- +- BT_DBG("hcon %p mgr %p hchan %p", hcon, hcon->amp_mgr, hchan); +- +- mgr = hcon->amp_mgr; +- if (mgr && mgr->bredr_chan) { +- struct l2cap_chan *bredr_chan = mgr->bredr_chan; +- +- l2cap_chan_lock(bredr_chan); +- +- bredr_chan->conn->mtu = hdev->block_mtu; +- l2cap_logical_cfm(bredr_chan, hchan, 0); +- hci_conn_hold(hcon); +- +- l2cap_chan_unlock(bredr_chan); +- } +-} +- +-static void hci_disconn_loglink_complete_evt(struct hci_dev *hdev, void *data, +- struct sk_buff *skb) +-{ +- struct hci_ev_disconn_logical_link_complete *ev = data; +- struct hci_chan *hchan; +- +- bt_dev_dbg(hdev, "handle 0x%4.4x status 0x%2.2x", +- le16_to_cpu(ev->handle), ev->status); +- +- if (ev->status) +- return; +- +- hci_dev_lock(hdev); +- +- hchan = hci_chan_lookup_handle(hdev, le16_to_cpu(ev->handle)); +- if (!hchan || !hchan->amp) +- goto unlock; +- +- amp_destroy_logical_link(hchan, ev->reason); +- +-unlock: +- hci_dev_unlock(hdev); +-} +- +-static void hci_disconn_phylink_complete_evt(struct hci_dev *hdev, void *data, +- struct sk_buff *skb) +-{ +- struct hci_ev_disconn_phy_link_complete *ev = data; +- struct hci_conn *hcon; +- +- bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); +- +- if (ev->status) +- return; +- +- hci_dev_lock(hdev); +- +- hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle); +- if (hcon && hcon->type == AMP_LINK) { +- hcon->state = BT_CLOSED; +- hci_disconn_cfm(hcon, ev->reason); +- hci_conn_del(hcon); +- } +- +- hci_dev_unlock(hdev); +-} +-#endif +- + static void le_conn_update_addr(struct hci_conn *conn, bdaddr_t *bdaddr, + u8 bdaddr_type, bdaddr_t *local_rpa) + { +@@ -7473,25 +7329,6 @@ static const struct hci_ev { + /* [0x3e = HCI_EV_LE_META] */ + HCI_EV_REQ_VL(HCI_EV_LE_META, hci_le_meta_evt, + sizeof(struct hci_ev_le_meta), HCI_MAX_EVENT_SIZE), +-#if IS_ENABLED(CONFIG_BT_HS) +- /* [0x40 = HCI_EV_PHY_LINK_COMPLETE] */ +- HCI_EV(HCI_EV_PHY_LINK_COMPLETE, hci_phy_link_complete_evt, +- sizeof(struct hci_ev_phy_link_complete)), +- /* [0x41 = HCI_EV_CHANNEL_SELECTED] */ +- HCI_EV(HCI_EV_CHANNEL_SELECTED, hci_chan_selected_evt, +- sizeof(struct hci_ev_channel_selected)), +- /* [0x42 = HCI_EV_DISCONN_PHY_LINK_COMPLETE] */ +- HCI_EV(HCI_EV_DISCONN_LOGICAL_LINK_COMPLETE, +- hci_disconn_loglink_complete_evt, +- sizeof(struct hci_ev_disconn_logical_link_complete)), +- /* [0x45 = HCI_EV_LOGICAL_LINK_COMPLETE] */ +- HCI_EV(HCI_EV_LOGICAL_LINK_COMPLETE, hci_loglink_complete_evt, +- sizeof(struct hci_ev_logical_link_complete)), +- /* [0x46 = HCI_EV_DISCONN_LOGICAL_LINK_COMPLETE] */ +- HCI_EV(HCI_EV_DISCONN_PHY_LINK_COMPLETE, +- hci_disconn_phylink_complete_evt, +- sizeof(struct hci_ev_disconn_phy_link_complete)), +-#endif + /* [0x48 = HCI_EV_NUM_COMP_BLOCKS] */ + HCI_EV(HCI_EV_NUM_COMP_BLOCKS, hci_num_comp_blocks_evt, + sizeof(struct hci_ev_num_comp_blocks)), +-- +2.43.0 + diff --git a/queue-6.1/bonding-add-ns-target-multicast-address-to-slave-dev.patch b/queue-6.1/bonding-add-ns-target-multicast-address-to-slave-dev.patch new file mode 100644 index 00000000000..2ce7562bd1d --- /dev/null +++ b/queue-6.1/bonding-add-ns-target-multicast-address-to-slave-dev.patch @@ -0,0 +1,237 @@ +From 3fa74edcbfe01432dd5bebaa61e8cc076bd52ca8 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 11 Nov 2024 10:16:49 +0000 +Subject: bonding: add ns target multicast address to slave device +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Hangbin Liu + +[ Upstream commit 8eb36164d1a6769a20ed43033510067ff3dab9ee ] + +Commit 4598380f9c54 ("bonding: fix ns validation on backup slaves") +tried to resolve the issue where backup slaves couldn't be brought up when +receiving IPv6 Neighbor Solicitation (NS) messages. However, this fix only +worked for drivers that receive all multicast messages, such as the veth +interface. + +For standard drivers, the NS multicast message is silently dropped because +the slave device is not a member of the NS target multicast group. + +To address this, we need to make the slave device join the NS target +multicast group, ensuring it can receive these IPv6 NS messages to validate +the slave’s status properly. + +There are three policies before joining the multicast group: +1. All settings must be under active-backup mode (alb and tlb do not support + arp_validate), with backup slaves and slaves supporting multicast. +2. We can add or remove multicast groups when arp_validate changes. +3. Other operations, such as enslaving, releasing, or setting NS targets, + need to be guarded by arp_validate. + +Fixes: 4e24be018eb9 ("bonding: add new parameter ns_targets") +Signed-off-by: Hangbin Liu +Reviewed-by: Nikolay Aleksandrov +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + drivers/net/bonding/bond_main.c | 16 +++++- + drivers/net/bonding/bond_options.c | 82 +++++++++++++++++++++++++++++- + include/net/bond_options.h | 2 + + 3 files changed, 98 insertions(+), 2 deletions(-) + +diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c +index 51d6cf0a3fb4e..26a9f99882e61 100644 +--- a/drivers/net/bonding/bond_main.c ++++ b/drivers/net/bonding/bond_main.c +@@ -919,6 +919,8 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active, + + if (bond->dev->flags & IFF_UP) + bond_hw_addr_flush(bond->dev, old_active->dev); ++ ++ bond_slave_ns_maddrs_add(bond, old_active); + } + + if (new_active) { +@@ -935,6 +937,8 @@ static void bond_hw_addr_swap(struct bonding *bond, struct slave *new_active, + dev_mc_sync(new_active->dev, bond->dev); + netif_addr_unlock_bh(bond->dev); + } ++ ++ bond_slave_ns_maddrs_del(bond, new_active); + } + } + +@@ -2231,6 +2235,11 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, + bond_compute_features(bond); + bond_set_carrier(bond); + ++ /* Needs to be called before bond_select_active_slave(), which will ++ * remove the maddrs if the slave is selected as active slave. ++ */ ++ bond_slave_ns_maddrs_add(bond, new_slave); ++ + if (bond_uses_primary(bond)) { + block_netpoll_tx(); + bond_select_active_slave(bond); +@@ -2240,7 +2249,6 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, + if (bond_mode_can_use_xmit_hash(bond)) + bond_update_slave_arr(bond, NULL); + +- + if (!slave_dev->netdev_ops->ndo_bpf || + !slave_dev->netdev_ops->ndo_xdp_xmit) { + if (bond->xdp_prog) { +@@ -2436,6 +2444,12 @@ static int __bond_release_one(struct net_device *bond_dev, + if (oldcurrent == slave) + bond_change_active_slave(bond, NULL); + ++ /* Must be called after bond_change_active_slave () as the slave ++ * might change from an active slave to a backup slave. Then it is ++ * necessary to clear the maddrs on the backup slave. ++ */ ++ bond_slave_ns_maddrs_del(bond, slave); ++ + if (bond_is_lb(bond)) { + /* Must be called only after the slave has been + * detached from the list and the curr_active_slave +diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c +index 06c4cd0f00024..c8536dc7d860d 100644 +--- a/drivers/net/bonding/bond_options.c ++++ b/drivers/net/bonding/bond_options.c +@@ -15,6 +15,7 @@ + #include + + #include ++#include + + static int bond_option_active_slave_set(struct bonding *bond, + const struct bond_opt_value *newval); +@@ -1230,6 +1231,68 @@ static int bond_option_arp_ip_targets_set(struct bonding *bond, + } + + #if IS_ENABLED(CONFIG_IPV6) ++static bool slave_can_set_ns_maddr(const struct bonding *bond, struct slave *slave) ++{ ++ return BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP && ++ !bond_is_active_slave(slave) && ++ slave->dev->flags & IFF_MULTICAST; ++} ++ ++static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool add) ++{ ++ struct in6_addr *targets = bond->params.ns_targets; ++ char slot_maddr[MAX_ADDR_LEN]; ++ int i; ++ ++ if (!slave_can_set_ns_maddr(bond, slave)) ++ return; ++ ++ for (i = 0; i < BOND_MAX_NS_TARGETS; i++) { ++ if (ipv6_addr_any(&targets[i])) ++ break; ++ ++ if (!ndisc_mc_map(&targets[i], slot_maddr, slave->dev, 0)) { ++ if (add) ++ dev_mc_add(slave->dev, slot_maddr); ++ else ++ dev_mc_del(slave->dev, slot_maddr); ++ } ++ } ++} ++ ++void bond_slave_ns_maddrs_add(struct bonding *bond, struct slave *slave) ++{ ++ if (!bond->params.arp_validate) ++ return; ++ slave_set_ns_maddrs(bond, slave, true); ++} ++ ++void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave) ++{ ++ if (!bond->params.arp_validate) ++ return; ++ slave_set_ns_maddrs(bond, slave, false); ++} ++ ++static void slave_set_ns_maddr(struct bonding *bond, struct slave *slave, ++ struct in6_addr *target, struct in6_addr *slot) ++{ ++ char target_maddr[MAX_ADDR_LEN], slot_maddr[MAX_ADDR_LEN]; ++ ++ if (!bond->params.arp_validate || !slave_can_set_ns_maddr(bond, slave)) ++ return; ++ ++ /* remove the previous maddr from slave */ ++ if (!ipv6_addr_any(slot) && ++ !ndisc_mc_map(slot, slot_maddr, slave->dev, 0)) ++ dev_mc_del(slave->dev, slot_maddr); ++ ++ /* add new maddr on slave if target is set */ ++ if (!ipv6_addr_any(target) && ++ !ndisc_mc_map(target, target_maddr, slave->dev, 0)) ++ dev_mc_add(slave->dev, target_maddr); ++} ++ + static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot, + struct in6_addr *target, + unsigned long last_rx) +@@ -1239,8 +1302,10 @@ static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot, + struct slave *slave; + + if (slot >= 0 && slot < BOND_MAX_NS_TARGETS) { +- bond_for_each_slave(bond, slave, iter) ++ bond_for_each_slave(bond, slave, iter) { + slave->target_last_arp_rx[slot] = last_rx; ++ slave_set_ns_maddr(bond, slave, target, &targets[slot]); ++ } + targets[slot] = *target; + } + } +@@ -1292,15 +1357,30 @@ static int bond_option_ns_ip6_targets_set(struct bonding *bond, + { + return -EPERM; + } ++ ++static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool add) {} ++ ++void bond_slave_ns_maddrs_add(struct bonding *bond, struct slave *slave) {} ++ ++void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave) {} + #endif + + static int bond_option_arp_validate_set(struct bonding *bond, + const struct bond_opt_value *newval) + { ++ bool changed = !!bond->params.arp_validate != !!newval->value; ++ struct list_head *iter; ++ struct slave *slave; ++ + netdev_dbg(bond->dev, "Setting arp_validate to %s (%llu)\n", + newval->string, newval->value); + bond->params.arp_validate = newval->value; + ++ if (changed) { ++ bond_for_each_slave(bond, slave, iter) ++ slave_set_ns_maddrs(bond, slave, !!bond->params.arp_validate); ++ } ++ + return 0; + } + +diff --git a/include/net/bond_options.h b/include/net/bond_options.h +index 69292ecc03257..f631d9f099410 100644 +--- a/include/net/bond_options.h ++++ b/include/net/bond_options.h +@@ -160,5 +160,7 @@ void bond_option_arp_ip_targets_clear(struct bonding *bond); + #if IS_ENABLED(CONFIG_IPV6) + void bond_option_ns_ip6_targets_clear(struct bonding *bond); + #endif ++void bond_slave_ns_maddrs_add(struct bonding *bond, struct slave *slave); ++void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave); + + #endif /* _NET_BOND_OPTIONS_H */ +-- +2.43.0 + diff --git a/queue-6.1/drm-rockchip-vop-fix-a-dereferenced-before-check-war.patch b/queue-6.1/drm-rockchip-vop-fix-a-dereferenced-before-check-war.patch new file mode 100644 index 00000000000..41800c277e4 --- /dev/null +++ b/queue-6.1/drm-rockchip-vop-fix-a-dereferenced-before-check-war.patch @@ -0,0 +1,47 @@ +From c51d6f7b4da8519b0826470c96b313ed18938bc1 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Mon, 21 Oct 2024 15:28:06 +0800 +Subject: drm/rockchip: vop: Fix a dereferenced before check warning + +From: Andy Yan + +[ Upstream commit ab1c793f457f740ab7108cc0b1340a402dbf484d ] + +The 'state' can't be NULL, we should check crtc_state. + +Fix warning: +drivers/gpu/drm/rockchip/rockchip_drm_vop.c:1096 +vop_plane_atomic_async_check() warn: variable dereferenced before check +'state' (see line 1077) + +Fixes: 5ddb0bd4ddc3 ("drm/atomic: Pass the full state to planes async atomic check and update") +Signed-off-by: Andy Yan +Signed-off-by: Heiko Stuebner +Link: https://patchwork.freedesktop.org/patch/msgid/20241021072818.61621-1-andyshrk@163.com +Signed-off-by: Sasha Levin +--- + drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +index b2289a523c408..e5b2112af1381 100644 +--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c ++++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +@@ -1080,10 +1080,10 @@ static int vop_plane_atomic_async_check(struct drm_plane *plane, + if (!plane->state->fb) + return -EINVAL; + +- if (state) +- crtc_state = drm_atomic_get_existing_crtc_state(state, +- new_plane_state->crtc); +- else /* Special case for asynchronous cursor updates. */ ++ crtc_state = drm_atomic_get_existing_crtc_state(state, new_plane_state->crtc); ++ ++ /* Special case for asynchronous cursor updates. */ ++ if (!crtc_state) + crtc_state = plane->crtc->state; + + return drm_atomic_helper_check_plane_state(plane->state, crtc_state, +-- +2.43.0 + diff --git a/queue-6.1/mptcp-error-out-earlier-on-disconnect.patch b/queue-6.1/mptcp-error-out-earlier-on-disconnect.patch new file mode 100644 index 00000000000..89465ccec3f --- /dev/null +++ b/queue-6.1/mptcp-error-out-earlier-on-disconnect.patch @@ -0,0 +1,120 @@ +From e15a0ac941898394f13eb736cb6496824613b06b Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 8 Nov 2024 11:58:16 +0100 +Subject: mptcp: error out earlier on disconnect + +From: Paolo Abeni + +[ Upstream commit 581302298524e9d77c4c44ff5156a6cd112227ae ] + +Eric reported a division by zero splat in the MPTCP protocol: + +Oops: divide error: 0000 [#1] PREEMPT SMP KASAN PTI +CPU: 1 UID: 0 PID: 6094 Comm: syz-executor317 Not tainted +6.12.0-rc5-syzkaller-00291-g05b92660cdfe #0 +Hardware name: Google Google Compute Engine/Google Compute Engine, +BIOS Google 09/13/2024 +RIP: 0010:__tcp_select_window+0x5b4/0x1310 net/ipv4/tcp_output.c:3163 +Code: f6 44 01 e3 89 df e8 9b 75 09 f8 44 39 f3 0f 8d 11 ff ff ff e8 +0d 74 09 f8 45 89 f4 e9 04 ff ff ff e8 00 74 09 f8 44 89 f0 99 7c +24 14 41 29 d6 45 89 f4 e9 ec fe ff ff e8 e8 73 09 f8 48 89 +RSP: 0018:ffffc900041f7930 EFLAGS: 00010293 +RAX: 0000000000017e67 RBX: 0000000000017e67 RCX: ffffffff8983314b +RDX: 0000000000000000 RSI: ffffffff898331b0 RDI: 0000000000000004 +RBP: 00000000005d6000 R08: 0000000000000004 R09: 0000000000017e67 +R10: 0000000000003e80 R11: 0000000000000000 R12: 0000000000003e80 +R13: ffff888031d9b440 R14: 0000000000017e67 R15: 00000000002eb000 +FS: 00007feb5d7f16c0(0000) GS:ffff8880b8700000(0000) knlGS:0000000000000000 +CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +CR2: 00007feb5d8adbb8 CR3: 0000000074e4c000 CR4: 00000000003526f0 +DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 +DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 +Call Trace: + +__tcp_cleanup_rbuf+0x3e7/0x4b0 net/ipv4/tcp.c:1493 +mptcp_rcv_space_adjust net/mptcp/protocol.c:2085 [inline] +mptcp_recvmsg+0x2156/0x2600 net/mptcp/protocol.c:2289 +inet_recvmsg+0x469/0x6a0 net/ipv4/af_inet.c:885 +sock_recvmsg_nosec net/socket.c:1051 [inline] +sock_recvmsg+0x1b2/0x250 net/socket.c:1073 +__sys_recvfrom+0x1a5/0x2e0 net/socket.c:2265 +__do_sys_recvfrom net/socket.c:2283 [inline] +__se_sys_recvfrom net/socket.c:2279 [inline] +__x64_sys_recvfrom+0xe0/0x1c0 net/socket.c:2279 +do_syscall_x64 arch/x86/entry/common.c:52 [inline] +do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83 +entry_SYSCALL_64_after_hwframe+0x77/0x7f +RIP: 0033:0x7feb5d857559 +Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 51 18 00 00 90 48 89 f8 48 +89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d +01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48 +RSP: 002b:00007feb5d7f1208 EFLAGS: 00000246 ORIG_RAX: 000000000000002d +RAX: ffffffffffffffda RBX: 00007feb5d8e1318 RCX: 00007feb5d857559 +RDX: 000000800000000e RSI: 0000000000000000 RDI: 0000000000000003 +RBP: 00007feb5d8e1310 R08: 0000000000000000 R09: ffffffff81000000 +R10: 0000000000000100 R11: 0000000000000246 R12: 00007feb5d8e131c +R13: 00007feb5d8ae074 R14: 000000800000000e R15: 00000000fffffdef + +and provided a nice reproducer. + +The root cause is the current bad handling of racing disconnect. +After the blamed commit below, sk_wait_data() can return (with +error) with the underlying socket disconnected and a zero rcv_mss. + +Catch the error and return without performing any additional +operations on the current socket. + +Reported-by: Eric Dumazet +Fixes: 419ce133ab92 ("tcp: allow again tcp_disconnect() when threads are waiting") +Signed-off-by: Paolo Abeni +Reviewed-by: Matthieu Baerts (NGI0) +Link: https://patch.msgid.link/8c82ecf71662ecbc47bf390f9905de70884c9f2d.1731060874.git.pabeni@redhat.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/mptcp/protocol.c | 13 +++++++++---- + 1 file changed, 9 insertions(+), 4 deletions(-) + +diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c +index d68e93dab88c3..78ac5c538e139 100644 +--- a/net/mptcp/protocol.c ++++ b/net/mptcp/protocol.c +@@ -2180,7 +2180,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + cmsg_flags = MPTCP_CMSG_INQ; + + while (copied < len) { +- int bytes_read; ++ int err, bytes_read; + + bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags, &tss, &cmsg_flags); + if (unlikely(bytes_read < 0)) { +@@ -2245,9 +2245,16 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + } + + pr_debug("block timeout %ld\n", timeo); +- sk_wait_data(sk, &timeo, NULL); ++ mptcp_rcv_space_adjust(msk, copied); ++ err = sk_wait_data(sk, &timeo, NULL); ++ if (err < 0) { ++ err = copied ? : err; ++ goto out_err; ++ } + } + ++ mptcp_rcv_space_adjust(msk, copied); ++ + out_err: + if (cmsg_flags && copied >= 0) { + if (cmsg_flags & MPTCP_CMSG_TS) +@@ -2263,8 +2270,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + pr_debug("msk=%p rx queue empty=%d:%d copied=%d\n", + msk, skb_queue_empty_lockless(&sk->sk_receive_queue), + skb_queue_empty(&msk->receive_queue), copied); +- if (!(flags & MSG_PEEK)) +- mptcp_rcv_space_adjust(msk, copied); + + release_sock(sk); + return copied; +-- +2.43.0 + diff --git a/queue-6.1/net-mlx5-fs-lock-fte-when-checking-if-active.patch b/queue-6.1/net-mlx5-fs-lock-fte-when-checking-if-active.patch new file mode 100644 index 00000000000..ac8f011d3f4 --- /dev/null +++ b/queue-6.1/net-mlx5-fs-lock-fte-when-checking-if-active.patch @@ -0,0 +1,130 @@ +From 4b79a5732cea9509c9e0c315f19f5bbefee3e00e Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 7 Nov 2024 20:35:23 +0200 +Subject: net/mlx5: fs, lock FTE when checking if active + +From: Mark Bloch + +[ Upstream commit 9ca314419930f9135727e39d77e66262d5f7bef6 ] + +The referenced commits introduced a two-step process for deleting FTEs: + +- Lock the FTE, delete it from hardware, set the hardware deletion function + to NULL and unlock the FTE. +- Lock the parent flow group, delete the software copy of the FTE, and + remove it from the xarray. + +However, this approach encounters a race condition if a rule with the same +match value is added simultaneously. In this scenario, fs_core may set the +hardware deletion function to NULL prematurely, causing a panic during +subsequent rule deletions. + +To prevent this, ensure the active flag of the FTE is checked under a lock, +which will prevent the fs_core layer from attaching a new steering rule to +an FTE that is in the process of deletion. + +[ 438.967589] MOSHE: 2496 mlx5_del_flow_rules del_hw_func +[ 438.968205] ------------[ cut here ]------------ +[ 438.968654] refcount_t: decrement hit 0; leaking memory. +[ 438.969249] WARNING: CPU: 0 PID: 8957 at lib/refcount.c:31 refcount_warn_saturate+0xfb/0x110 +[ 438.970054] Modules linked in: act_mirred cls_flower act_gact sch_ingress openvswitch nsh mlx5_vdpa vringh vhost_iotlb vdpa mlx5_ib mlx5_core xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat br_netfilter rpcsec_gss_krb5 auth_rpcgss oid_registry overlay rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm ib_uverbs ib_core zram zsmalloc fuse [last unloaded: cls_flower] +[ 438.973288] CPU: 0 UID: 0 PID: 8957 Comm: tc Not tainted 6.12.0-rc1+ #8 +[ 438.973888] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014 +[ 438.974874] RIP: 0010:refcount_warn_saturate+0xfb/0x110 +[ 438.975363] Code: 40 66 3b 82 c6 05 16 e9 4d 01 01 e8 1f 7c a0 ff 0f 0b c3 cc cc cc cc 48 c7 c7 10 66 3b 82 c6 05 fd e8 4d 01 01 e8 05 7c a0 ff <0f> 0b c3 cc cc cc cc 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 90 +[ 438.976947] RSP: 0018:ffff888124a53610 EFLAGS: 00010286 +[ 438.977446] RAX: 0000000000000000 RBX: ffff888119d56de0 RCX: 0000000000000000 +[ 438.978090] RDX: ffff88852c828700 RSI: ffff88852c81b3c0 RDI: ffff88852c81b3c0 +[ 438.978721] RBP: ffff888120fa0e88 R08: 0000000000000000 R09: ffff888124a534b0 +[ 438.979353] R10: 0000000000000001 R11: 0000000000000001 R12: ffff888119d56de0 +[ 438.979979] R13: ffff888120fa0ec0 R14: ffff888120fa0ee8 R15: ffff888119d56de0 +[ 438.980607] FS: 00007fe6dcc0f800(0000) GS:ffff88852c800000(0000) knlGS:0000000000000000 +[ 438.983984] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +[ 438.984544] CR2: 00000000004275e0 CR3: 0000000186982001 CR4: 0000000000372eb0 +[ 438.985205] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 +[ 438.985842] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 +[ 438.986507] Call Trace: +[ 438.986799] +[ 438.987070] ? __warn+0x7d/0x110 +[ 438.987426] ? refcount_warn_saturate+0xfb/0x110 +[ 438.987877] ? report_bug+0x17d/0x190 +[ 438.988261] ? prb_read_valid+0x17/0x20 +[ 438.988659] ? handle_bug+0x53/0x90 +[ 438.989054] ? exc_invalid_op+0x14/0x70 +[ 438.989458] ? asm_exc_invalid_op+0x16/0x20 +[ 438.989883] ? refcount_warn_saturate+0xfb/0x110 +[ 438.990348] mlx5_del_flow_rules+0x2f7/0x340 [mlx5_core] +[ 438.990932] __mlx5_eswitch_del_rule+0x49/0x170 [mlx5_core] +[ 438.991519] ? mlx5_lag_is_sriov+0x3c/0x50 [mlx5_core] +[ 438.992054] ? xas_load+0x9/0xb0 +[ 438.992407] mlx5e_tc_rule_unoffload+0x45/0xe0 [mlx5_core] +[ 438.993037] mlx5e_tc_del_fdb_flow+0x2a6/0x2e0 [mlx5_core] +[ 438.993623] mlx5e_flow_put+0x29/0x60 [mlx5_core] +[ 438.994161] mlx5e_delete_flower+0x261/0x390 [mlx5_core] +[ 438.994728] tc_setup_cb_destroy+0xb9/0x190 +[ 438.995150] fl_hw_destroy_filter+0x94/0xc0 [cls_flower] +[ 438.995650] fl_change+0x11a4/0x13c0 [cls_flower] +[ 438.996105] tc_new_tfilter+0x347/0xbc0 +[ 438.996503] ? ___slab_alloc+0x70/0x8c0 +[ 438.996929] rtnetlink_rcv_msg+0xf9/0x3e0 +[ 438.997339] ? __netlink_sendskb+0x4c/0x70 +[ 438.997751] ? netlink_unicast+0x286/0x2d0 +[ 438.998171] ? __pfx_rtnetlink_rcv_msg+0x10/0x10 +[ 438.998625] netlink_rcv_skb+0x54/0x100 +[ 438.999020] netlink_unicast+0x203/0x2d0 +[ 438.999421] netlink_sendmsg+0x1e4/0x420 +[ 438.999820] __sock_sendmsg+0xa1/0xb0 +[ 439.000203] ____sys_sendmsg+0x207/0x2a0 +[ 439.000600] ? copy_msghdr_from_user+0x6d/0xa0 +[ 439.001072] ___sys_sendmsg+0x80/0xc0 +[ 439.001459] ? ___sys_recvmsg+0x8b/0xc0 +[ 439.001848] ? generic_update_time+0x4d/0x60 +[ 439.002282] __sys_sendmsg+0x51/0x90 +[ 439.002658] do_syscall_64+0x50/0x110 +[ 439.003040] entry_SYSCALL_64_after_hwframe+0x76/0x7e + +Fixes: 718ce4d601db ("net/mlx5: Consolidate update FTE for all removal changes") +Fixes: cefc23554fc2 ("net/mlx5: Fix FTE cleanup") +Signed-off-by: Mark Bloch +Reviewed-by: Maor Gottlieb +Signed-off-by: Tariq Toukan +Link: https://patch.msgid.link/20241107183527.676877-4-tariqt@nvidia.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 15 ++++++++++++--- + 1 file changed, 12 insertions(+), 3 deletions(-) + +diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +index 164e10b5f9b7f..50fdc3cbb778e 100644 +--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c ++++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +@@ -1880,13 +1880,22 @@ lookup_fte_locked(struct mlx5_flow_group *g, + fte_tmp = NULL; + goto out; + } ++ ++ nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD); ++ + if (!fte_tmp->node.active) { ++ up_write_ref_node(&fte_tmp->node, false); ++ ++ if (take_write) ++ up_write_ref_node(&g->node, false); ++ else ++ up_read_ref_node(&g->node); ++ + tree_put_node(&fte_tmp->node, false); +- fte_tmp = NULL; +- goto out; ++ ++ return NULL; + } + +- nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD); + out: + if (take_write) + up_write_ref_node(&g->node, false); +-- +2.43.0 + diff --git a/queue-6.1/net-mlx5e-ct-fix-null-ptr-deref-in-add-rule-err-flow.patch b/queue-6.1/net-mlx5e-ct-fix-null-ptr-deref-in-add-rule-err-flow.patch new file mode 100644 index 00000000000..bc20fd9b5ac --- /dev/null +++ b/queue-6.1/net-mlx5e-ct-fix-null-ptr-deref-in-add-rule-err-flow.patch @@ -0,0 +1,71 @@ +From 19a574dc355ce7130b5e72b8ac48a782f232ab16 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 7 Nov 2024 20:35:26 +0200 +Subject: net/mlx5e: CT: Fix null-ptr-deref in add rule err flow +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +From: Moshe Shemesh + +[ Upstream commit e99c6873229fe0482e7ceb7d5600e32d623ed9d9 ] + +In error flow of mlx5_tc_ct_entry_add_rule(), in case ct_rule_add() +callback returns error, zone_rule->attr is used uninitiated. Fix it to +use attr which has the needed pointer value. + +Kernel log: + BUG: kernel NULL pointer dereference, address: 0000000000000110 + RIP: 0010:mlx5_tc_ct_entry_add_rule+0x2b1/0x2f0 [mlx5_core] +… + Call Trace: + + ? __die+0x20/0x70 + ? page_fault_oops+0x150/0x3e0 + ? exc_page_fault+0x74/0x140 + ? asm_exc_page_fault+0x22/0x30 + ? mlx5_tc_ct_entry_add_rule+0x2b1/0x2f0 [mlx5_core] + ? mlx5_tc_ct_entry_add_rule+0x1d5/0x2f0 [mlx5_core] + mlx5_tc_ct_block_flow_offload+0xc6a/0xf90 [mlx5_core] + ? nf_flow_offload_tuple+0xd8/0x190 [nf_flow_table] + nf_flow_offload_tuple+0xd8/0x190 [nf_flow_table] + flow_offload_work_handler+0x142/0x320 [nf_flow_table] + ? finish_task_switch.isra.0+0x15b/0x2b0 + process_one_work+0x16c/0x320 + worker_thread+0x28c/0x3a0 + ? __pfx_worker_thread+0x10/0x10 + kthread+0xb8/0xf0 + ? __pfx_kthread+0x10/0x10 + ret_from_fork+0x2d/0x50 + ? __pfx_kthread+0x10/0x10 + ret_from_fork_asm+0x1a/0x30 + + +Fixes: 7fac5c2eced3 ("net/mlx5: CT: Avoid reusing modify header context for natted entries") +Signed-off-by: Moshe Shemesh +Reviewed-by: Cosmin Ratiu +Reviewed-by: Yevgeny Kliteynik +Signed-off-by: Tariq Toukan +Link: https://patch.msgid.link/20241107183527.676877-7-tariqt@nvidia.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +index f01f7dfdbcf88..b011e0d2b620e 100644 +--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c ++++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +@@ -862,7 +862,7 @@ mlx5_tc_ct_entry_add_rule(struct mlx5_tc_ct_priv *ct_priv, + return 0; + + err_rule: +- mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, zone_rule->attr, zone_rule->mh); ++ mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, attr, zone_rule->mh); + mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id); + err_mod_hdr: + kfree(attr); +-- +2.43.0 + diff --git a/queue-6.1/net-mlx5e-ktls-fix-incorrect-page-refcounting.patch b/queue-6.1/net-mlx5e-ktls-fix-incorrect-page-refcounting.patch new file mode 100644 index 00000000000..aaa0ef98e94 --- /dev/null +++ b/queue-6.1/net-mlx5e-ktls-fix-incorrect-page-refcounting.patch @@ -0,0 +1,72 @@ +From 5e823cb7e0f3d53303ed4150512f0fe7b2e8cf79 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 7 Nov 2024 20:35:24 +0200 +Subject: net/mlx5e: kTLS, Fix incorrect page refcounting + +From: Dragos Tatulea + +[ Upstream commit dd6e972cc5890d91d6749bb48e3912721c4e4b25 ] + +The kTLS tx handling code is using a mix of get_page() and +page_ref_inc() APIs to increment the page reference. But on the release +path (mlx5e_ktls_tx_handle_resync_dump_comp()), only put_page() is used. + +This is an issue when using pages from large folios: the get_page() +references are stored on the folio page while the page_ref_inc() +references are stored directly in the given page. On release the folio +page will be dereferenced too many times. + +This was found while doing kTLS testing with sendfile() + ZC when the +served file was read from NFS on a kernel with NFS large folios support +(commit 49b29a573da8 ("nfs: add support for large folios")). + +Fixes: 84d1bb2b139e ("net/mlx5e: kTLS, Limit DUMP wqe size") +Signed-off-by: Dragos Tatulea +Signed-off-by: Tariq Toukan +Link: https://patch.msgid.link/20241107183527.676877-5-tariqt@nvidia.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + .../net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +index 2e0335246967b..6d56d4a9977b0 100644 +--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c ++++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +@@ -665,7 +665,7 @@ tx_sync_info_get(struct mlx5e_ktls_offload_context_tx *priv_tx, + while (remaining > 0) { + skb_frag_t *frag = &record->frags[i]; + +- get_page(skb_frag_page(frag)); ++ page_ref_inc(skb_frag_page(frag)); + remaining -= skb_frag_size(frag); + info->frags[i++] = *frag; + } +@@ -768,7 +768,7 @@ void mlx5e_ktls_tx_handle_resync_dump_comp(struct mlx5e_txqsq *sq, + stats = sq->stats; + + mlx5e_tx_dma_unmap(sq->pdev, dma); +- put_page(wi->resync_dump_frag_page); ++ page_ref_dec(wi->resync_dump_frag_page); + stats->tls_dump_packets++; + stats->tls_dump_bytes += wi->num_bytes; + } +@@ -821,12 +821,12 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx, + + err_out: + for (; i < info.nr_frags; i++) +- /* The put_page() here undoes the page ref obtained in tx_sync_info_get(). ++ /* The page_ref_dec() here undoes the page ref obtained in tx_sync_info_get(). + * Page refs obtained for the DUMP WQEs above (by page_ref_add) will be + * released only upon their completions (or in mlx5e_free_txqsq_descs, + * if channel closes). + */ +- put_page(skb_frag_page(&info.frags[i])); ++ page_ref_dec(skb_frag_page(&info.frags[i])); + + return MLX5E_KTLS_SYNC_FAIL; + } +-- +2.43.0 + diff --git a/queue-6.1/net-sched-cls_u32-fix-u32-s-systematic-failure-to-fr.patch b/queue-6.1/net-sched-cls_u32-fix-u32-s-systematic-failure-to-fr.patch new file mode 100644 index 00000000000..5492ed2983d --- /dev/null +++ b/queue-6.1/net-sched-cls_u32-fix-u32-s-systematic-failure-to-fr.patch @@ -0,0 +1,101 @@ +From 1718701dfdc57c89227a7a785697427b09cc29a4 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Sun, 10 Nov 2024 18:28:36 +0100 +Subject: net: sched: cls_u32: Fix u32's systematic failure to free IDR entries + for hnodes. + +From: Alexandre Ferrieux + +[ Upstream commit 73af53d82076bbe184d9ece9e14b0dc8599e6055 ] + +To generate hnode handles (in gen_new_htid()), u32 uses IDR and +encodes the returned small integer into a structured 32-bit +word. Unfortunately, at disposal time, the needed decoding +is not done. As a result, idr_remove() fails, and the IDR +fills up. Since its size is 2048, the following script ends up +with "Filter already exists": + + tc filter add dev myve $FILTER1 + tc filter add dev myve $FILTER2 + for i in {1..2048} + do + echo $i + tc filter del dev myve $FILTER2 + tc filter add dev myve $FILTER2 + done + +This patch adds the missing decoding logic for handles that +deserve it. + +Fixes: e7614370d6f0 ("net_sched: use idr to allocate u32 filter handles") +Reviewed-by: Eric Dumazet +Acked-by: Jamal Hadi Salim +Signed-off-by: Alexandre Ferrieux +Tested-by: Victor Nogueira +Link: https://patch.msgid.link/20241110172836.331319-1-alexandre.ferrieux@orange.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/sched/cls_u32.c | 18 ++++++++++++++---- + 1 file changed, 14 insertions(+), 4 deletions(-) + +diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c +index adcc8de1d01be..e87d79d043d54 100644 +--- a/net/sched/cls_u32.c ++++ b/net/sched/cls_u32.c +@@ -91,6 +91,16 @@ struct tc_u_common { + long knodes; + }; + ++static u32 handle2id(u32 h) ++{ ++ return ((h & 0x80000000) ? ((h >> 20) & 0x7FF) : h); ++} ++ ++static u32 id2handle(u32 id) ++{ ++ return (id | 0x800U) << 20; ++} ++ + static inline unsigned int u32_hash_fold(__be32 key, + const struct tc_u32_sel *sel, + u8 fshift) +@@ -308,7 +318,7 @@ static u32 gen_new_htid(struct tc_u_common *tp_c, struct tc_u_hnode *ptr) + int id = idr_alloc_cyclic(&tp_c->handle_idr, ptr, 1, 0x7FF, GFP_KERNEL); + if (id < 0) + return 0; +- return (id | 0x800U) << 20; ++ return id2handle(id); + } + + static struct hlist_head *tc_u_common_hash; +@@ -358,7 +368,7 @@ static int u32_init(struct tcf_proto *tp) + return -ENOBUFS; + + refcount_set(&root_ht->refcnt, 1); +- root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : 0x80000000; ++ root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : id2handle(0); + root_ht->prio = tp->prio; + root_ht->is_root = true; + idr_init(&root_ht->handle_idr); +@@ -610,7 +620,7 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, + if (phn == ht) { + u32_clear_hw_hnode(tp, ht, extack); + idr_destroy(&ht->handle_idr); +- idr_remove(&tp_c->handle_idr, ht->handle); ++ idr_remove(&tp_c->handle_idr, handle2id(ht->handle)); + RCU_INIT_POINTER(*hn, ht->next); + kfree_rcu(ht, rcu); + return 0; +@@ -987,7 +997,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, + + err = u32_replace_hw_hnode(tp, ht, userflags, extack); + if (err) { +- idr_remove(&tp_c->handle_idr, handle); ++ idr_remove(&tp_c->handle_idr, handle2id(handle)); + kfree(ht); + return err; + } +-- +2.43.0 + diff --git a/queue-6.1/net-sched-cls_u32-replace-int-refcounts-with-proper-.patch b/queue-6.1/net-sched-cls_u32-replace-int-refcounts-with-proper-.patch new file mode 100644 index 00000000000..cb37cc8fb1f --- /dev/null +++ b/queue-6.1/net-sched-cls_u32-replace-int-refcounts-with-proper-.patch @@ -0,0 +1,200 @@ +From 3b30617cda0beb6630c3289c0e76a73883bfcff3 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 14 Nov 2023 11:18:55 -0300 +Subject: net/sched: cls_u32: replace int refcounts with proper refcounts + +From: Pedro Tammela + +[ Upstream commit 6b78debe1c07e6aa3c91ca0b1384bf3cb8217c50 ] + +Proper refcounts will always warn splat when something goes wrong, +be it underflow, saturation or object resurrection. As these are always +a source of bugs, use it in cls_u32 as a safeguard to prevent/catch issues. +Another benefit is that the refcount API self documents the code, making +clear when transitions to dead are expected. + +For such an update we had to make minor adaptations on u32 to fit the refcount +API. First we set explicitly to '1' when objects are created, then the +objects are alive until a 1 -> 0 happens, which is then released appropriately. + +The above made clear some redundant operations in the u32 code +around the root_ht handling that were removed. The root_ht is created +with a refcnt set to 1. Then when it's associated with tcf_proto it increments the refcnt to 2. +Throughout the entire code the root_ht is an exceptional case and can never be referenced, +therefore the refcnt never incremented/decremented. +Its lifetime is always bound to tcf_proto, meaning if you delete tcf_proto +the root_ht is deleted as well. The code made up for the fact that root_ht refcnt is 2 and did +a double decrement to free it, which is not a fit for the refcount API. + +Even though refcount_t is implemented using atomics, we should observe +a negligible control plane impact. + +Signed-off-by: Pedro Tammela +Acked-by: Jamal Hadi Salim +Link: https://lore.kernel.org/r/20231114141856.974326-2-pctammela@mojatatu.com +Signed-off-by: Jakub Kicinski +Stable-dep-of: 73af53d82076 ("net: sched: cls_u32: Fix u32's systematic failure to free IDR entries for hnodes.") +Signed-off-by: Sasha Levin +--- + net/sched/cls_u32.c | 36 ++++++++++++++++++------------------ + 1 file changed, 18 insertions(+), 18 deletions(-) + +diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c +index 04448bfb4d3db..adcc8de1d01be 100644 +--- a/net/sched/cls_u32.c ++++ b/net/sched/cls_u32.c +@@ -70,7 +70,7 @@ struct tc_u_hnode { + struct tc_u_hnode __rcu *next; + u32 handle; + u32 prio; +- int refcnt; ++ refcount_t refcnt; + unsigned int divisor; + struct idr handle_idr; + bool is_root; +@@ -85,7 +85,7 @@ struct tc_u_hnode { + struct tc_u_common { + struct tc_u_hnode __rcu *hlist; + void *ptr; +- int refcnt; ++ refcount_t refcnt; + struct idr handle_idr; + struct hlist_node hnode; + long knodes; +@@ -357,7 +357,7 @@ static int u32_init(struct tcf_proto *tp) + if (root_ht == NULL) + return -ENOBUFS; + +- root_ht->refcnt++; ++ refcount_set(&root_ht->refcnt, 1); + root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : 0x80000000; + root_ht->prio = tp->prio; + root_ht->is_root = true; +@@ -369,18 +369,20 @@ static int u32_init(struct tcf_proto *tp) + kfree(root_ht); + return -ENOBUFS; + } ++ refcount_set(&tp_c->refcnt, 1); + tp_c->ptr = key; + INIT_HLIST_NODE(&tp_c->hnode); + idr_init(&tp_c->handle_idr); + + hlist_add_head(&tp_c->hnode, tc_u_hash(key)); ++ } else { ++ refcount_inc(&tp_c->refcnt); + } + +- tp_c->refcnt++; + RCU_INIT_POINTER(root_ht->next, tp_c->hlist); + rcu_assign_pointer(tp_c->hlist, root_ht); + +- root_ht->refcnt++; ++ /* root_ht must be destroyed when tcf_proto is destroyed */ + rcu_assign_pointer(tp->root, root_ht); + tp->data = tp_c; + return 0; +@@ -391,7 +393,7 @@ static void __u32_destroy_key(struct tc_u_knode *n) + struct tc_u_hnode *ht = rtnl_dereference(n->ht_down); + + tcf_exts_destroy(&n->exts); +- if (ht && --ht->refcnt == 0) ++ if (ht && refcount_dec_and_test(&ht->refcnt)) + kfree(ht); + kfree(n); + } +@@ -599,8 +601,6 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, + struct tc_u_hnode __rcu **hn; + struct tc_u_hnode *phn; + +- WARN_ON(--ht->refcnt); +- + u32_clear_hnode(tp, ht, extack); + + hn = &tp_c->hlist; +@@ -628,10 +628,10 @@ static void u32_destroy(struct tcf_proto *tp, bool rtnl_held, + + WARN_ON(root_ht == NULL); + +- if (root_ht && --root_ht->refcnt == 1) ++ if (root_ht && refcount_dec_and_test(&root_ht->refcnt)) + u32_destroy_hnode(tp, root_ht, extack); + +- if (--tp_c->refcnt == 0) { ++ if (refcount_dec_and_test(&tp_c->refcnt)) { + struct tc_u_hnode *ht; + + hlist_del(&tp_c->hnode); +@@ -643,7 +643,7 @@ static void u32_destroy(struct tcf_proto *tp, bool rtnl_held, + /* u32_destroy_key() will later free ht for us, if it's + * still referenced by some knode + */ +- if (--ht->refcnt == 0) ++ if (refcount_dec_and_test(&ht->refcnt)) + kfree_rcu(ht, rcu); + } + +@@ -672,7 +672,7 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, + return -EINVAL; + } + +- if (ht->refcnt == 1) { ++ if (refcount_dec_if_one(&ht->refcnt)) { + u32_destroy_hnode(tp, ht, extack); + } else { + NL_SET_ERR_MSG_MOD(extack, "Can not delete in-use filter"); +@@ -680,7 +680,7 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, + } + + out: +- *last = tp_c->refcnt == 1 && tp_c->knodes == 0; ++ *last = refcount_read(&tp_c->refcnt) == 1 && tp_c->knodes == 0; + return ret; + } + +@@ -764,14 +764,14 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, + NL_SET_ERR_MSG_MOD(extack, "Not linking to root node"); + return -EINVAL; + } +- ht_down->refcnt++; ++ refcount_inc(&ht_down->refcnt); + } + + ht_old = rtnl_dereference(n->ht_down); + rcu_assign_pointer(n->ht_down, ht_down); + + if (ht_old) +- ht_old->refcnt--; ++ refcount_dec(&ht_old->refcnt); + } + + if (ifindex >= 0) +@@ -850,7 +850,7 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp, + + /* bump reference count as long as we hold pointer to structure */ + if (ht) +- ht->refcnt++; ++ refcount_inc(&ht->refcnt); + + return new; + } +@@ -930,7 +930,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, + + ht_old = rtnl_dereference(n->ht_down); + if (ht_old) +- ht_old->refcnt++; ++ refcount_inc(&ht_old->refcnt); + } + __u32_destroy_key(new); + return err; +@@ -978,7 +978,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, + return err; + } + } +- ht->refcnt = 1; ++ refcount_set(&ht->refcnt, 1); + ht->divisor = divisor; + ht->handle = handle; + ht->prio = tp->prio; +-- +2.43.0 + diff --git a/queue-6.1/net-vertexcom-mse102x-fix-tx_bytes-calculation.patch b/queue-6.1/net-vertexcom-mse102x-fix-tx_bytes-calculation.patch new file mode 100644 index 00000000000..0581c01403a --- /dev/null +++ b/queue-6.1/net-vertexcom-mse102x-fix-tx_bytes-calculation.patch @@ -0,0 +1,46 @@ +From 4ada504ddf959de38ac5953e35ceb940cc0923c9 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Fri, 8 Nov 2024 12:43:43 +0100 +Subject: net: vertexcom: mse102x: Fix tx_bytes calculation + +From: Stefan Wahren + +[ Upstream commit e68da664d379f352d41d7955712c44e0a738e4ab ] + +The tx_bytes should consider the actual size of the Ethernet frames +without the SPI encapsulation. But we still need to take care of +Ethernet padding. + +Fixes: 2f207cbf0dd4 ("net: vertexcom: Add MSE102x SPI support") +Signed-off-by: Stefan Wahren +Link: https://patch.msgid.link/20241108114343.6174-3-wahrenst@gmx.net +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + drivers/net/ethernet/vertexcom/mse102x.c | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +diff --git a/drivers/net/ethernet/vertexcom/mse102x.c b/drivers/net/ethernet/vertexcom/mse102x.c +index dd766e175f7db..8f67c39f479ee 100644 +--- a/drivers/net/ethernet/vertexcom/mse102x.c ++++ b/drivers/net/ethernet/vertexcom/mse102x.c +@@ -437,13 +437,15 @@ static void mse102x_tx_work(struct work_struct *work) + mse = &mses->mse102x; + + while ((txb = skb_dequeue(&mse->txq))) { ++ unsigned int len = max_t(unsigned int, txb->len, ETH_ZLEN); ++ + mutex_lock(&mses->lock); + ret = mse102x_tx_pkt_spi(mse, txb, work_timeout); + mutex_unlock(&mses->lock); + if (ret) { + mse->ndev->stats.tx_dropped++; + } else { +- mse->ndev->stats.tx_bytes += txb->len; ++ mse->ndev->stats.tx_bytes += len; + mse->ndev->stats.tx_packets++; + } + +-- +2.43.0 + diff --git a/queue-6.1/netlink-terminate-outstanding-dump-on-socket-close.patch b/queue-6.1/netlink-terminate-outstanding-dump-on-socket-close.patch new file mode 100644 index 00000000000..d18ed0be0b4 --- /dev/null +++ b/queue-6.1/netlink-terminate-outstanding-dump-on-socket-close.patch @@ -0,0 +1,142 @@ +From 8b4d7a14abcfd8288c01d7da64867892bfd55df6 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 5 Nov 2024 17:52:34 -0800 +Subject: netlink: terminate outstanding dump on socket close + +From: Jakub Kicinski + +[ Upstream commit 1904fb9ebf911441f90a68e96b22aa73e4410505 ] + +Netlink supports iterative dumping of data. It provides the families +the following ops: + - start - (optional) kicks off the dumping process + - dump - actual dump helper, keeps getting called until it returns 0 + - done - (optional) pairs with .start, can be used for cleanup +The whole process is asynchronous and the repeated calls to .dump +don't actually happen in a tight loop, but rather are triggered +in response to recvmsg() on the socket. + +This gives the user full control over the dump, but also means that +the user can close the socket without getting to the end of the dump. +To make sure .start is always paired with .done we check if there +is an ongoing dump before freeing the socket, and if so call .done. + +The complication is that sockets can get freed from BH and .done +is allowed to sleep. So we use a workqueue to defer the call, when +needed. + +Unfortunately this does not work correctly. What we defer is not +the cleanup but rather releasing a reference on the socket. +We have no guarantee that we own the last reference, if someone +else holds the socket they may release it in BH and we're back +to square one. + +The whole dance, however, appears to be unnecessary. Only the user +can interact with dumps, so we can clean up when socket is closed. +And close always happens in process context. Some async code may +still access the socket after close, queue notification skbs to it etc. +but no dumps can start, end or otherwise make progress. + +Delete the workqueue and flush the dump state directly from the release +handler. Note that further cleanup is possible in -next, for instance +we now always call .done before releasing the main module reference, +so dump doesn't have to take a reference of its own. + +Reported-by: syzkaller +Fixes: ed5d7788a934 ("netlink: Do not schedule work from sk_destruct") +Reviewed-by: Kuniyuki Iwashima +Reviewed-by: Eric Dumazet +Link: https://patch.msgid.link/20241106015235.2458807-1-kuba@kernel.org +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + net/netlink/af_netlink.c | 31 ++++++++----------------------- + net/netlink/af_netlink.h | 2 -- + 2 files changed, 8 insertions(+), 25 deletions(-) + +diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c +index 9eb87f35bc65e..8a74847dacaf1 100644 +--- a/net/netlink/af_netlink.c ++++ b/net/netlink/af_netlink.c +@@ -393,15 +393,6 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk) + + static void netlink_sock_destruct(struct sock *sk) + { +- struct netlink_sock *nlk = nlk_sk(sk); +- +- if (nlk->cb_running) { +- if (nlk->cb.done) +- nlk->cb.done(&nlk->cb); +- module_put(nlk->cb.module); +- kfree_skb(nlk->cb.skb); +- } +- + skb_queue_purge(&sk->sk_receive_queue); + + if (!sock_flag(sk, SOCK_DEAD)) { +@@ -414,14 +405,6 @@ static void netlink_sock_destruct(struct sock *sk) + WARN_ON(nlk_sk(sk)->groups); + } + +-static void netlink_sock_destruct_work(struct work_struct *work) +-{ +- struct netlink_sock *nlk = container_of(work, struct netlink_sock, +- work); +- +- sk_free(&nlk->sk); +-} +- + /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on + * SMP. Look, when several writers sleep and reader wakes them up, all but one + * immediately hit write lock and grab all the cpus. Exclusive sleep solves +@@ -736,12 +719,6 @@ static void deferred_put_nlk_sk(struct rcu_head *head) + if (!refcount_dec_and_test(&sk->sk_refcnt)) + return; + +- if (nlk->cb_running && nlk->cb.done) { +- INIT_WORK(&nlk->work, netlink_sock_destruct_work); +- schedule_work(&nlk->work); +- return; +- } +- + sk_free(sk); + } + +@@ -791,6 +768,14 @@ static int netlink_release(struct socket *sock) + NETLINK_URELEASE, &n); + } + ++ /* Terminate any outstanding dump */ ++ if (nlk->cb_running) { ++ if (nlk->cb.done) ++ nlk->cb.done(&nlk->cb); ++ module_put(nlk->cb.module); ++ kfree_skb(nlk->cb.skb); ++ } ++ + module_put(nlk->module); + + if (netlink_is_kernel(sk)) { +diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h +index b30b8fc760f71..aa430e4d58d80 100644 +--- a/net/netlink/af_netlink.h ++++ b/net/netlink/af_netlink.h +@@ -4,7 +4,6 @@ + + #include + #include +-#include + #include + + /* flags */ +@@ -48,7 +47,6 @@ struct netlink_sock { + + struct rhash_head node; + struct rcu_head rcu; +- struct work_struct work; + }; + + static inline struct netlink_sock *nlk_sk(struct sock *sk) +-- +2.43.0 + diff --git a/queue-6.1/samples-pktgen-correct-dev-to-dev.patch b/queue-6.1/samples-pktgen-correct-dev-to-dev.patch new file mode 100644 index 00000000000..e15de7ca8b2 --- /dev/null +++ b/queue-6.1/samples-pktgen-correct-dev-to-dev.patch @@ -0,0 +1,40 @@ +From 77e4b953c8f58ce9e187ef6a047cdf875a7a6b25 Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Tue, 12 Nov 2024 11:03:47 +0800 +Subject: samples: pktgen: correct dev to DEV + +From: Wei Fang + +[ Upstream commit 3342dc8b4623d835e7dd76a15cec2e5a94fe2f93 ] + +In the pktgen_sample01_simple.sh script, the device variable is uppercase +'DEV' instead of lowercase 'dev'. Because of this typo, the script cannot +enable UDP tx checksum. + +Fixes: 460a9aa23de6 ("samples: pktgen: add UDP tx checksum support") +Signed-off-by: Wei Fang +Reviewed-by: Simon Horman +Acked-by: Jesper Dangaard Brouer +Link: https://patch.msgid.link/20241112030347.1849335-1-wei.fang@nxp.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Sasha Levin +--- + samples/pktgen/pktgen_sample01_simple.sh | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/samples/pktgen/pktgen_sample01_simple.sh b/samples/pktgen/pktgen_sample01_simple.sh +index 09a92ea963f98..c8e75888a9c20 100755 +--- a/samples/pktgen/pktgen_sample01_simple.sh ++++ b/samples/pktgen/pktgen_sample01_simple.sh +@@ -72,7 +72,7 @@ if [ -n "$DST_PORT" ]; then + pg_set $DEV "udp_dst_max $UDP_DST_MAX" + fi + +-[ ! -z "$UDP_CSUM" ] && pg_set $dev "flag UDPCSUM" ++[ ! -z "$UDP_CSUM" ] && pg_set $DEV "flag UDPCSUM" + + # Setup random UDP port src range + pg_set $DEV "flag UDPSRC_RND" +-- +2.43.0 + diff --git a/queue-6.1/series b/queue-6.1/series new file mode 100644 index 00000000000..64b3fcc713e --- /dev/null +++ b/queue-6.1/series @@ -0,0 +1,15 @@ +netlink-terminate-outstanding-dump-on-socket-close.patch +net-vertexcom-mse102x-fix-tx_bytes-calculation.patch +drm-rockchip-vop-fix-a-dereferenced-before-check-war.patch +mptcp-error-out-earlier-on-disconnect.patch +net-mlx5-fs-lock-fte-when-checking-if-active.patch +net-mlx5e-ktls-fix-incorrect-page-refcounting.patch +net-mlx5e-ct-fix-null-ptr-deref-in-add-rule-err-flow.patch +virtio-vsock-fix-accept_queue-memory-leak.patch +bluetooth-hci_event-remove-code-to-removed-config_bt.patch +bluetooth-hci_core-fix-calling-mgmt_device_connected.patch +net-sched-cls_u32-replace-int-refcounts-with-proper-.patch +net-sched-cls_u32-fix-u32-s-systematic-failure-to-fr.patch +samples-pktgen-correct-dev-to-dev.patch +bonding-add-ns-target-multicast-address-to-slave-dev.patch +arm-9419-1-mm-fix-kernel-memory-mapping-for-xip-kern.patch diff --git a/queue-6.1/virtio-vsock-fix-accept_queue-memory-leak.patch b/queue-6.1/virtio-vsock-fix-accept_queue-memory-leak.patch new file mode 100644 index 00000000000..ba2d069742e --- /dev/null +++ b/queue-6.1/virtio-vsock-fix-accept_queue-memory-leak.patch @@ -0,0 +1,93 @@ +From c8e2ffc96d27901bf54c3ec59b567b78033ce0bb Mon Sep 17 00:00:00 2001 +From: Sasha Levin +Date: Thu, 7 Nov 2024 21:46:12 +0100 +Subject: virtio/vsock: Fix accept_queue memory leak + +From: Michal Luczaj + +[ Upstream commit d7b0ff5a866724c3ad21f2628c22a63336deec3f ] + +As the final stages of socket destruction may be delayed, it is possible +that virtio_transport_recv_listen() will be called after the accept_queue +has been flushed, but before the SOCK_DONE flag has been set. As a result, +sockets enqueued after the flush would remain unremoved, leading to a +memory leak. + +vsock_release + __vsock_release + lock + virtio_transport_release + virtio_transport_close + schedule_delayed_work(close_work) + sk_shutdown = SHUTDOWN_MASK +(!) flush accept_queue + release + virtio_transport_recv_pkt + vsock_find_bound_socket + lock + if flag(SOCK_DONE) return + virtio_transport_recv_listen + child = vsock_create_connected + (!) vsock_enqueue_accept(child) + release +close_work + lock + virtio_transport_do_close + set_flag(SOCK_DONE) + virtio_transport_remove_sock + vsock_remove_sock + vsock_remove_bound + release + +Introduce a sk_shutdown check to disallow vsock_enqueue_accept() during +socket destruction. + +unreferenced object 0xffff888109e3f800 (size 2040): + comm "kworker/5:2", pid 371, jiffies 4294940105 + hex dump (first 32 bytes): + 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ + 28 00 0b 40 00 00 00 00 00 00 00 00 00 00 00 00 (..@............ + backtrace (crc 9e5f4e84): + [] kmem_cache_alloc_noprof+0x2c1/0x360 + [] sk_prot_alloc+0x30/0x120 + [] sk_alloc+0x2c/0x4b0 + [] __vsock_create.constprop.0+0x2a/0x310 + [] virtio_transport_recv_pkt+0x4dc/0x9a0 + [] vsock_loopback_work+0xfd/0x140 + [] process_one_work+0x20c/0x570 + [] worker_thread+0x1bf/0x3a0 + [] kthread+0xdd/0x110 + [] ret_from_fork+0x2d/0x50 + [] ret_from_fork_asm+0x1a/0x30 + +Fixes: 3fe356d58efa ("vsock/virtio: discard packets only when socket is really closed") +Reviewed-by: Stefano Garzarella +Signed-off-by: Michal Luczaj +Signed-off-by: Paolo Abeni +Signed-off-by: Sasha Levin +--- + net/vmw_vsock/virtio_transport_common.c | 8 ++++++++ + 1 file changed, 8 insertions(+) + +diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c +index b22dc7bed2182..3bc573cbf8a6e 100644 +--- a/net/vmw_vsock/virtio_transport_common.c ++++ b/net/vmw_vsock/virtio_transport_common.c +@@ -1220,6 +1220,14 @@ virtio_transport_recv_listen(struct sock *sk, struct sk_buff *skb, + return -ENOMEM; + } + ++ /* __vsock_release() might have already flushed accept_queue. ++ * Subsequent enqueues would lead to a memory leak. ++ */ ++ if (sk->sk_shutdown == SHUTDOWN_MASK) { ++ virtio_transport_reset_no_sock(t, skb); ++ return -ESHUTDOWN; ++ } ++ + child = vsock_create_connected(sk); + if (!child) { + virtio_transport_reset_no_sock(t, skb); +-- +2.43.0 +