- Kernel - mailweb.openeuler.org

[PATCH OLK-6.6] Bluetooth: MGMT: Fix possible deadlocks
by dinglongwei 06 Jan '25

06 Jan '25

From: Luiz Augusto von Dentz <luiz.von.dentz(a)intel.com> stable inclusion from stable-v6.6.64 commit 5703fb1d85f653e35b327b14de4db7da239e4fd9 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBA6RL Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit a66dfaf18fd61bb75ef8cee83db46b2aadf153d0 ] This fixes possible deadlocks like the following caused by hci_cmd_sync_dequeue causing the destroy function to run: INFO: task kworker/u19:0:143 blocked for more than 120 seconds. Tainted: G W O 6.8.0-2024-03-19-intel-next-iLS-24ww14 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:kworker/u19:0 state:D stack:0 pid:143 tgid:143 ppid:2 flags:0x00004000 Workqueue: hci0 hci_cmd_sync_work [bluetooth] Call Trace: <TASK> __schedule+0x374/0xaf0 schedule+0x3c/0xf0 schedule_preempt_disabled+0x1c/0x30 __mutex_lock.constprop.0+0x3ef/0x7a0 __mutex_lock_slowpath+0x13/0x20 mutex_lock+0x3c/0x50 mgmt_set_connectable_complete+0xa4/0x150 [bluetooth] ? kfree+0x211/0x2a0 hci_cmd_sync_dequeue+0xae/0x130 [bluetooth] ? __pfx_cmd_complete_rsp+0x10/0x10 [bluetooth] cmd_complete_rsp+0x26/0x80 [bluetooth] mgmt_pending_foreach+0x4d/0x70 [bluetooth] __mgmt_power_off+0x8d/0x180 [bluetooth] ? _raw_spin_unlock_irq+0x23/0x40 hci_dev_close_sync+0x445/0x5b0 [bluetooth] hci_set_powered_sync+0x149/0x250 [bluetooth] set_powered_sync+0x24/0x60 [bluetooth] hci_cmd_sync_work+0x90/0x150 [bluetooth] process_one_work+0x13e/0x300 worker_thread+0x2f7/0x420 ? __pfx_worker_thread+0x10/0x10 kthread+0x107/0x140 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x3d/0x60 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1b/0x30 </TASK> Tested-by: Kiran K <kiran.k(a)intel.com> Fixes: f53e1c9c726d ("Bluetooth: MGMT: Fix possible crash on mgmt_index_removed") Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz(a)intel.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> Signed-off-by: dinglongwei <dinglongwei1(a)huawei.com> --- net/bluetooth/mgmt.c | 27 ++++++++++++++++++--------- 1 file changed, 18 insertions(+), 9 deletions(-) diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index 1f3a39c20a91..2238f431858a 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1503,7 +1503,8 @@ static void mgmt_set_discoverable_complete(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "err %d", err); /* Make sure cmd still outstanding. */ - if (cmd != pending_find(MGMT_OP_SET_DISCOVERABLE, hdev)) + if (err == -ECANCELED || + cmd != pending_find(MGMT_OP_SET_DISCOVERABLE, hdev)) return; hci_dev_lock(hdev); @@ -1677,7 +1678,8 @@ static void mgmt_set_connectable_complete(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "err %d", err); /* Make sure cmd still outstanding. */ - if (cmd != pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) + if (err == -ECANCELED || + cmd != pending_find(MGMT_OP_SET_CONNECTABLE, hdev)) return; hci_dev_lock(hdev); @@ -1910,7 +1912,7 @@ static void set_ssp_complete(struct hci_dev *hdev, void *data, int err) bool changed; /* Make sure cmd still outstanding. */ - if (cmd != pending_find(MGMT_OP_SET_SSP, hdev)) + if (err == -ECANCELED || cmd != pending_find(MGMT_OP_SET_SSP, hdev)) return; if (err) { @@ -3775,7 +3777,8 @@ static void set_name_complete(struct hci_dev *hdev, void *data, int err) bt_dev_dbg(hdev, "err %d", err); - if (cmd != pending_find(MGMT_OP_SET_LOCAL_NAME, hdev)) + if (err == -ECANCELED || + cmd != pending_find(MGMT_OP_SET_LOCAL_NAME, hdev)) return; if (status) { @@ -3950,7 +3953,8 @@ static void set_default_phy_complete(struct hci_dev *hdev, void *data, int err) struct sk_buff *skb = cmd->skb; u8 status = mgmt_status(err); - if (cmd != pending_find(MGMT_OP_SET_PHY_CONFIGURATION, hdev)) + if (err == -ECANCELED || + cmd != pending_find(MGMT_OP_SET_PHY_CONFIGURATION, hdev)) return; if (!status) { @@ -5841,13 +5845,16 @@ static void start_discovery_complete(struct hci_dev *hdev, void *data, int err) { struct mgmt_pending_cmd *cmd = data; + bt_dev_dbg(hdev, "err %d", err); + + if (err == -ECANCELED) + return; + if (cmd != pending_find(MGMT_OP_START_DISCOVERY, hdev) && cmd != pending_find(MGMT_OP_START_LIMITED_DISCOVERY, hdev) && cmd != pending_find(MGMT_OP_START_SERVICE_DISCOVERY, hdev)) return; - bt_dev_dbg(hdev, "err %d", err); - mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode, mgmt_status(err), cmd->param, 1); mgmt_pending_remove(cmd); @@ -6080,7 +6087,8 @@ static void stop_discovery_complete(struct hci_dev *hdev, void *data, int err) { struct mgmt_pending_cmd *cmd = data; - if (cmd != pending_find(MGMT_OP_STOP_DISCOVERY, hdev)) + if (err == -ECANCELED || + cmd != pending_find(MGMT_OP_STOP_DISCOVERY, hdev)) return; bt_dev_dbg(hdev, "err %d", err); @@ -8025,7 +8033,8 @@ static void read_local_oob_ext_data_complete(struct hci_dev *hdev, void *data, u8 status = mgmt_status(err); u16 eir_len; - if (cmd != pending_find(MGMT_OP_READ_LOCAL_OOB_EXT_DATA, hdev)) + if (err == -ECANCELED || + cmd != pending_find(MGMT_OP_READ_LOCAL_OOB_EXT_DATA, hdev)) return; if (!status) { -- 2.22.0

2 1

[PATCH OLK-6.6] arm64: probes: Disable kprobes/uprobes on MOPS instructions
by Chen Zhongjin 06 Jan '25

06 Jan '25

From: Kristina Martsenko <kristina.martsenko(a)arm.com> stable inclusion from stable-v6.6.64 commit 0dd9a53bb9b2562c7f73edbca2f399828700b7a6 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBA6RL Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit c56c599d9002d44f559be3852b371db46adac87c ] FEAT_MOPS instructions require that all three instructions (prologue, main and epilogue) appear consecutively in memory. Placing a kprobe/uprobe on one of them doesn't work as only a single instruction gets executed out-of-line or simulated. So don't allow placing a probe on a MOPS instruction. Fixes: b7564127ffcb ("arm64: mops: detect and enable FEAT_MOPS") Signed-off-by: Kristina Martsenko <kristina.martsenko(a)arm.com> Link: https://lore.kernel.org/r/20240930161051.3777828-2-kristina.martsenko@arm.c… Signed-off-by: Catalin Marinas <catalin.marinas(a)arm.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Chen Zhongjin <chenzhongjin(a)huawei.com> --- arch/arm64/include/asm/insn.h | 1 + arch/arm64/kernel/probes/decode-insn.c | 7 +++++-- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index db1aeacd4cd9..0ccf51afde31 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -347,6 +347,7 @@ __AARCH64_INSN_FUNCS(ldrsw_lit, 0xFF000000, 0x98000000) __AARCH64_INSN_FUNCS(exclusive, 0x3F800000, 0x08000000) __AARCH64_INSN_FUNCS(load_ex, 0x3F400000, 0x08400000) __AARCH64_INSN_FUNCS(store_ex, 0x3F400000, 0x08000000) +__AARCH64_INSN_FUNCS(mops, 0x3B200C00, 0x19000400) __AARCH64_INSN_FUNCS(stp, 0x7FC00000, 0x29000000) __AARCH64_INSN_FUNCS(ldp, 0x7FC00000, 0x29400000) __AARCH64_INSN_FUNCS(stp_post, 0x7FC00000, 0x28800000) diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c index 3496d6169e59..42b69936cee3 100644 --- a/arch/arm64/kernel/probes/decode-insn.c +++ b/arch/arm64/kernel/probes/decode-insn.c @@ -58,10 +58,13 @@ static bool __kprobes aarch64_insn_is_steppable(u32 insn) * Instructions which load PC relative literals are not going to work * when executed from an XOL slot. Instructions doing an exclusive * load/store are not going to complete successfully when single-step - * exception handling happens in the middle of the sequence. + * exception handling happens in the middle of the sequence. Memory + * copy/set instructions require that all three instructions be placed + * consecutively in memory. */ if (aarch64_insn_uses_literal(insn) || - aarch64_insn_is_exclusive(insn)) + aarch64_insn_is_exclusive(insn) || + aarch64_insn_is_mops(insn)) return false; return true; -- 2.25.1

2 1

[PATCH OLK-6.6] [Backport] btrfs: fix use-after-free in btrfs_encoded_read_endio()
by Yongjian Sun 06 Jan '25

06 Jan '25

From: Johannes Thumshirn <johannes.thumshirn(a)wdc.com> mainline inclusion from mainline-v6.12-rc3 commit 05b36b04d74a517d6675bf2f90829ff1ac7e28dc category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAOP CVE: CVE-2024-56582 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Shinichiro reported the following use-after free that sometimes is happening in our CI system when running fstests' btrfs/284 on a TCMU runner device: BUG: KASAN: slab-use-after-free in lock_release+0x708/0x780 Read of size 8 at addr ffff888106a83f18 by task kworker/u80:6/219 CPU: 8 UID: 0 PID: 219 Comm: kworker/u80:6 Not tainted 6.12.0-rc6-kts+ #15 Hardware name: Supermicro Super Server/X11SPi-TF, BIOS 3.3 02/21/2020 Workqueue: btrfs-endio btrfs_end_bio_work [btrfs] Call Trace: <TASK> dump_stack_lvl+0x6e/0xa0 ? lock_release+0x708/0x780 print_report+0x174/0x505 ? lock_release+0x708/0x780 ? __virt_addr_valid+0x224/0x410 ? lock_release+0x708/0x780 kasan_report+0xda/0x1b0 ? lock_release+0x708/0x780 ? __wake_up+0x44/0x60 lock_release+0x708/0x780 ? __pfx_lock_release+0x10/0x10 ? __pfx_do_raw_spin_lock+0x10/0x10 ? lock_is_held_type+0x9a/0x110 _raw_spin_unlock_irqrestore+0x1f/0x60 __wake_up+0x44/0x60 btrfs_encoded_read_endio+0x14b/0x190 [btrfs] btrfs_check_read_bio+0x8d9/0x1360 [btrfs] ? lock_release+0x1b0/0x780 ? trace_lock_acquire+0x12f/0x1a0 ? __pfx_btrfs_check_read_bio+0x10/0x10 [btrfs] ? process_one_work+0x7e3/0x1460 ? lock_acquire+0x31/0xc0 ? process_one_work+0x7e3/0x1460 process_one_work+0x85c/0x1460 ? __pfx_process_one_work+0x10/0x10 ? assign_work+0x16c/0x240 worker_thread+0x5e6/0xfc0 ? __pfx_worker_thread+0x10/0x10 kthread+0x2c3/0x3a0 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x31/0x70 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1a/0x30 </TASK> Allocated by task 3661: kasan_save_stack+0x30/0x50 kasan_save_track+0x14/0x30 __kasan_kmalloc+0xaa/0xb0 btrfs_encoded_read_regular_fill_pages+0x16c/0x6d0 [btrfs] send_extent_data+0xf0f/0x24a0 [btrfs] process_extent+0x48a/0x1830 [btrfs] changed_cb+0x178b/0x2ea0 [btrfs] btrfs_ioctl_send+0x3bf9/0x5c20 [btrfs] _btrfs_ioctl_send+0x117/0x330 [btrfs] btrfs_ioctl+0x184a/0x60a0 [btrfs] __x64_sys_ioctl+0x12e/0x1a0 do_syscall_64+0x95/0x180 entry_SYSCALL_64_after_hwframe+0x76/0x7e Freed by task 3661: kasan_save_stack+0x30/0x50 kasan_save_track+0x14/0x30 kasan_save_free_info+0x3b/0x70 __kasan_slab_free+0x4f/0x70 kfree+0x143/0x490 btrfs_encoded_read_regular_fill_pages+0x531/0x6d0 [btrfs] send_extent_data+0xf0f/0x24a0 [btrfs] process_extent+0x48a/0x1830 [btrfs] changed_cb+0x178b/0x2ea0 [btrfs] btrfs_ioctl_send+0x3bf9/0x5c20 [btrfs] _btrfs_ioctl_send+0x117/0x330 [btrfs] btrfs_ioctl+0x184a/0x60a0 [btrfs] __x64_sys_ioctl+0x12e/0x1a0 do_syscall_64+0x95/0x180 entry_SYSCALL_64_after_hwframe+0x76/0x7e The buggy address belongs to the object at ffff888106a83f00 which belongs to the cache kmalloc-rnd-07-96 of size 96 The buggy address is located 24 bytes inside of freed 96-byte region [ffff888106a83f00, ffff888106a83f60) The buggy address belongs to the physical page: page: refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff888106a83800 pfn:0x106a83 flags: 0x17ffffc0000000(node=0|zone=2|lastcpupid=0x1fffff) page_type: f5(slab) raw: 0017ffffc0000000 ffff888100053680 ffffea0004917200 0000000000000004 raw: ffff888106a83800 0000000080200019 00000001f5000000 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888106a83e00: fa fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc ffff888106a83e80: fa fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc >ffff888106a83f00: fa fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc ^ ffff888106a83f80: fa fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc ffff888106a84000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ================================================================== Further analyzing the trace and the crash dump's vmcore file shows that the wake_up() call in btrfs_encoded_read_endio() is calling wake_up() on the wait_queue that is in the private data passed to the end_io handler. Commit 4ff47df40447 ("btrfs: move priv off stack in btrfs_encoded_read_regular_fill_pages()") moved 'struct btrfs_encoded_read_private' off the stack. Before that commit one can see a corruption of the private data when analyzing the vmcore after a crash: *(struct btrfs_encoded_read_private *)0xffff88815626eec8 = { .wait = (wait_queue_head_t){ .lock = (spinlock_t){ .rlock = (struct raw_spinlock){ .raw_lock = (arch_spinlock_t){ .val = (atomic_t){ .counter = (int)-2005885696, }, .locked = (u8)0, .pending = (u8)157, .locked_pending = (u16)40192, .tail = (u16)34928, }, .magic = (unsigned int)536325682, .owner_cpu = (unsigned int)29, .owner = (void *)__SCT__tp_func_btrfs_transaction_commit+0x0 = 0x0, .dep_map = (struct lockdep_map){ .key = (struct lock_class_key *)0xffff8881575a3b6c, .class_cache = (struct lock_class *[2]){ 0xffff8882a71985c0, 0xffffea00066f5d40 }, .name = (const char *)0xffff88815626f100 = "", .wait_type_outer = (u8)37, .wait_type_inner = (u8)178, .lock_type = (u8)154, }, }, .__padding = (u8 [24]){ 0, 157, 112, 136, 50, 174, 247, 31, 29 }, .dep_map = (struct lockdep_map){ .key = (struct lock_class_key *)0xffff8881575a3b6c, .class_cache = (struct lock_class *[2]){ 0xffff8882a71985c0, 0xffffea00066f5d40 }, .name = (const char *)0xffff88815626f100 = "", .wait_type_outer = (u8)37, .wait_type_inner = (u8)178, .lock_type = (u8)154, }, }, .head = (struct list_head){ .next = (struct list_head *)0x112cca, .prev = (struct list_head *)0x47, }, }, .pending = (atomic_t){ .counter = (int)-1491499288, }, .status = (blk_status_t)130, } Here we can see several indicators of in-memory data corruption, e.g. the large negative atomic values of ->pending or ->wait->lock->rlock->raw_lock->val, as well as the bogus spinlock magic 0x1ff7ae32 (decimal 536325682 above) instead of 0xdead4ead or the bogus pointer values for ->wait->head. To fix this, change atomic_dec_return() to atomic_dec_and_test() to fix the corruption, as atomic_dec_return() is defined as two instructions on x86_64, whereas atomic_dec_and_test() is defined as a single atomic operation. This can lead to a situation where counter value is already decremented but the if statement in btrfs_encoded_read_endio() is not completely processed, i.e. the 0 test has not completed. If another thread continues executing btrfs_encoded_read_regular_fill_pages() the atomic_dec_return() there can see an already updated ->pending counter and continues by freeing the private data. Continuing in the endio handler the test for 0 succeeds and the wait_queue is woken up, resulting in a use-after-free. Reported-by: Shinichiro Kawasaki <shinichiro.kawasaki(a)wdc.com> Suggested-by: Damien Le Moal <Damien.LeMoal(a)wdc.com> Fixes: 1881fba89bd5 ("btrfs: add BTRFS_IOC_ENCODED_READ ioctl") CC: stable(a)vger.kernel.org # 6.1+ Reviewed-by: Filipe Manana <fdmanana(a)suse.com> Reviewed-by: Qu Wenruo <wqu(a)suse.com> Signed-off-by: Johannes Thumshirn <johannes.thumshirn(a)wdc.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> Signed-off-by: Sun Yongjian <sunyongjian1(a)huawei.com> Signed-off-by: Yongjian Sun <sunyongjian1(a)huawei.com> --- fs/btrfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index fae45b8d485e..1511405abfe0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9974,7 +9974,7 @@ static void btrfs_encoded_read_endio(struct btrfs_bio *bbio) */ WRITE_ONCE(priv->status, bbio->bio.bi_status); } - if (!atomic_dec_return(&priv->pending)) + if (!atomic_dec_and_test(&priv->pending)) wake_up(&priv->wait); bio_put(&bbio->bio); } -- 2.39.2

2 1

[PATCH OLK-6.6 0/6] LoongArch: fix some issue
by Hongchen Zhang 06 Jan '25

06 Jan '25

Zhao Qunqin (3): pci/quirks: LS7A2000: fix pm transition of devices under pcie port net: stmmac: dwmac-loongson: fix Mac DMA reset drivers/char: add ACPI firmware support for Loongson SE driver wanghongliang (3): LoongArch: fix i2c related issues LoongArch: eiointc: fix ext irq route error LoongArch: adjust the calc method of number of packages. arch/loongarch/configs/loongson3_defconfig | 2 + arch/loongarch/include/asm/topology.h | 4 + arch/loongarch/kernel/setup.c | 1 + arch/loongarch/kernel/smp.c | 3 + drivers/char/loongson_se.c | 440 +++++++----------- drivers/char/lsse_sdf_cdev.c | 310 ++++++------ drivers/gpio/gpio-loongson-64bit.c | 298 ++++++++++-- drivers/i2c/busses/i2c-ls2x.c | 12 +- drivers/irqchip/irq-loongson-eiointc.c | 47 +- .../ethernet/stmicro/stmmac/dwmac-loongson.c | 14 + drivers/pci/quirks.c | 30 ++ drivers/platform/loongarch/cpu_hwmon.c | 3 +- include/linux/pci.h | 1 + .../include/asm => include/soc/loongson}/se.h | 52 +-- 14 files changed, 710 insertions(+), 507 deletions(-) rename {arch/loongarch/include/asm => include/soc/loongson}/se.h (68%) -- 2.33.0

2 7

[PATCH openEuler-1.0-LTS 1/1] 9p/xen: fix release of IRQ
by Ze Zuo 06 Jan '25

06 Jan '25

From: Alex Zenla <alex(a)edera.dev> stable inclusion from stable-v4.19.325 commit 692eb06703afc3e24d889d77e94a0e20229f6a4a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEDPA CVE: CVE-2024-56704 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit e43c608f40c065b30964f0a806348062991b802d ] Kernel logs indicate an IRQ was double-freed. Pass correct device ID during IRQ release. Fixes: 71ebd71921e45 ("xen/9pfs: connect to the backend") Signed-off-by: Alex Zenla <alex(a)edera.dev> Signed-off-by: Alexander Merritt <alexander(a)edera.dev> Signed-off-by: Ariadne Conill <ariadne(a)ariadne.space> Reviewed-by: Juergen Gross <jgross(a)suse.com> Message-ID: <20241121225100.5736-1-alexander(a)edera.dev> [Dominique: remove confusing variable reset to 0] Signed-off-by: Dominique Martinet <asmadeus(a)codewreck.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> (cherry picked from commit 692eb06703afc3e24d889d77e94a0e20229f6a4a) Signed-off-by: Ze Zuo <zuoze1(a)huawei.com> --- net/9p/trans_xen.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index 8e158f09cba8..4096cfc7efc6 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -297,7 +297,7 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv) if (!priv->rings[i].intf) break; if (priv->rings[i].irq > 0) - unbind_from_irqhandler(priv->rings[i].irq, priv->dev); + unbind_from_irqhandler(priv->rings[i].irq, ring); if (priv->rings[i].data.in) { for (j = 0; j < (1 << XEN_9PFS_RING_ORDER); j++) { grant_ref_t ref; -- 2.25.1

2 1

[PATCH OLK-5.10 0/2] CVE-2024-56724
by Liao Chen 06 Jan '25

06 Jan '25

fix CVE-2024-56724 Andy Shevchenko (2): [Backport] mfd: intel_soc_pmic_bxtwc: Use IRQ domain for USB Type-C device [Backport] mfd: intel_soc_pmic_bxtwc: Use IRQ domain for TMU device drivers/mfd/intel_soc_pmic_bxtwc.c | 85 ++++++++++++++++---------- drivers/platform/x86/intel_bxtwc_tmu.c | 22 ++----- drivers/usb/typec/tcpm/wcove.c | 4 -- 3 files changed, 59 insertions(+), 52 deletions(-) -- 2.34.1

2 3

[PATCH openEuler-22.03-LTS-SP1 0/2] CVE-2024-56724
by Liao Chen 06 Jan '25

06 Jan '25

fix CVE-2024-56724 Andy Shevchenko (2): [Backport] mfd: intel_soc_pmic_bxtwc: Use IRQ domain for USB Type-C device [Backport] mfd: intel_soc_pmic_bxtwc: Use IRQ domain for TMU device drivers/mfd/intel_soc_pmic_bxtwc.c | 85 ++++++++++++++++---------- drivers/platform/x86/intel_bxtwc_tmu.c | 22 ++----- drivers/usb/typec/tcpm/wcove.c | 4 -- 3 files changed, 59 insertions(+), 52 deletions(-) -- 2.34.1

2 3

[PATCH OLK-6.6 0/2] CVE-2024-56724
by Liao Chen 06 Jan '25

06 Jan '25

fix CVE-2024-56724 Andy Shevchenko (2): [Backport] mfd: intel_soc_pmic_bxtwc: Use IRQ domain for USB Type-C device [Backport] mfd: intel_soc_pmic_bxtwc: Use IRQ domain for TMU device drivers/mfd/intel_soc_pmic_bxtwc.c | 85 ++++++++++++++++---------- drivers/platform/x86/intel_bxtwc_tmu.c | 22 ++----- drivers/usb/typec/tcpm/wcove.c | 4 -- 3 files changed, 59 insertions(+), 52 deletions(-) -- 2.34.1

2 3

[PATCH openEuler-22.03-LTS-SP1 0/2] CVE-2024-56604_openEuler-22.03-LTS-SP1
by dinglongwei 06 Jan '25

06 Jan '25

CVE-2024-56604_openEuler-22.03-LTS-SP1 Ignat Korchagin (1): Bluetooth: RFCOMM: avoid leaving dangling sk pointer in rfcomm_sock_alloc() Luiz Augusto von Dentz (1): Bluetooth: Consolidate code around sk_alloc into a helper function include/net/bluetooth/bluetooth.h | 2 ++ net/bluetooth/af_bluetooth.c | 21 +++++++++++++++++++++ net/bluetooth/bnep/sock.c | 10 +--------- net/bluetooth/hci_sock.c | 10 ++-------- net/bluetooth/l2cap_sock.c | 10 +--------- net/bluetooth/rfcomm/sock.c | 21 +++++++-------------- net/bluetooth/sco.c | 10 +--------- 7 files changed, 35 insertions(+), 49 deletions(-) -- 2.22.0

2 3

[PATCH openEuler-22.03-LTS-SP1] crypto: hisilicon/qm - inject error before stopping queue
by Guo Mengqi 06 Jan '25

06 Jan '25

From: Weili Qian <qianweili(a)huawei.com> stable inclusion from stable-v6.1.113 commit 98d3be34c9153eceadb56de50d9f9347e88d86e4 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAYQSI CVE: CVE-2024-47730 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit b04f06fc0243600665b3b50253869533b7938468 ] The master ooo cannot be completely closed when the accelerator core reports memory error. Therefore, the driver needs to inject the qm error to close the master ooo. Currently, the qm error is injected after stopping queue, memory may be released immediately after stopping queue, causing the device to access the released memory. Therefore, error is injected to close master ooo before stopping queue to ensure that the device does not access the released memory. Fixes: 6c6dd5802c2d ("crypto: hisilicon/qm - add controller reset interface") Signed-off-by: Weili Qian <qianweili(a)huawei.com> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: drivers/crypto/hisilicon/qm.c [context conflict] Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> --- drivers/crypto/hisilicon/qm.c | 51 +++++++++++++++++------------------ 1 file changed, 24 insertions(+), 27 deletions(-) diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 382e54406510..179ec9710d8c 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -5058,6 +5058,28 @@ static int qm_set_vf_mse(struct hisi_qm *qm, bool set) return -ETIMEDOUT; } +static void qm_dev_ecc_mbit_handle(struct hisi_qm *qm) +{ + u32 nfe_enb = 0; + + /* Kunpeng930 hardware automatically close master ooo when NFE occurs */ + if (qm->ver >= QM_HW_V3) + return; + + if (!qm->err_status.is_dev_ecc_mbit && + qm->err_status.is_qm_ecc_mbit && + qm->err_ini->close_axi_master_ooo) { + qm->err_ini->close_axi_master_ooo(qm); + } else if (qm->err_status.is_dev_ecc_mbit && + !qm->err_status.is_qm_ecc_mbit && + !qm->err_ini->close_axi_master_ooo) { + nfe_enb = readl(qm->io_base + QM_RAS_NFE_ENABLE); + writel(nfe_enb & QM_RAS_NFE_MBIT_DISABLE, + qm->io_base + QM_RAS_NFE_ENABLE); + writel(QM_ECC_MBIT, qm->io_base + QM_ABNORMAL_INT_SET); + } +} + static int qm_vf_reset_prepare(struct hisi_qm *qm, enum qm_stop_reason stop_reason) { @@ -5122,6 +5144,8 @@ static int qm_controller_reset_prepare(struct hisi_qm *qm) return ret; } + qm_dev_ecc_mbit_handle(qm); + /* PF obtains the information of VF by querying the register. */ qm_cmd_uninit(qm); @@ -5146,31 +5170,6 @@ static int qm_controller_reset_prepare(struct hisi_qm *qm) return 0; } -static void qm_dev_ecc_mbit_handle(struct hisi_qm *qm) -{ - u32 nfe_enb = 0; - - /* Kunpeng930 hardware automatically close master ooo when NFE occurs */ - if (qm->ver >= QM_HW_V3) - return; - - if (!qm->err_status.is_dev_ecc_mbit && - qm->err_status.is_qm_ecc_mbit && - qm->err_ini->close_axi_master_ooo) { - - qm->err_ini->close_axi_master_ooo(qm); - - } else if (qm->err_status.is_dev_ecc_mbit && - !qm->err_status.is_qm_ecc_mbit && - !qm->err_ini->close_axi_master_ooo) { - - nfe_enb = readl(qm->io_base + QM_RAS_NFE_ENABLE); - writel(nfe_enb & QM_RAS_NFE_MBIT_DISABLE, - qm->io_base + QM_RAS_NFE_ENABLE); - writel(QM_ECC_MBIT, qm->io_base + QM_ABNORMAL_INT_SET); - } -} - static int qm_soft_reset(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; @@ -5196,8 +5195,6 @@ static int qm_soft_reset(struct hisi_qm *qm) return ret; } - qm_dev_ecc_mbit_handle(qm); - /* OOO register set and check */ writel(ACC_MASTER_GLOBAL_CTRL_SHUTDOWN, qm->io_base + ACC_MASTER_GLOBAL_CTRL); -- 2.22.0

2 1

[PATCH OLK-5.10] iio: adc: ad7923: Fix buffer overflow for tx_buf and ring_xfer
by Yi Yang 06 Jan '25

06 Jan '25

From: Nuno Sa <nuno.sa(a)analog.com> mainline inclusion from mainline-v6.13-rc1 commit 3a4187ec454e19903fd15f6e1825a4b84e59a4cd category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAMO CVE: CVE-2024-56557 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- The AD7923 was updated to support devices with 8 channels, but the size of tx_buf and ring_xfer was not increased accordingly, leading to a potential buffer overflow in ad7923_update_scan_mode(). Fixes: 851644a60d20 ("iio: adc: ad7923: Add support for the ad7908/ad7918/ad7928") Cc: stable(a)vger.kernel.org Signed-off-by: Nuno Sa <nuno.sa(a)analog.com> Signed-off-by: Zicheng Qu <quzicheng(a)huawei.com> Link: https://patch.msgid.link/20241029134637.2261336-1-quzicheng@huawei.com Signed-off-by: Jonathan Cameron <Jonathan.Cameron(a)huawei.com> Conflicts: drivers/iio/adc/ad7923.c [conflicts due to not mergered 908af45d70573 ("iio: adc: ad7923: Fix alignment for DMA safety")] Signed-off-by: Yi Yang <yiyang13(a)huawei.com> --- drivers/iio/adc/ad7923.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iio/adc/ad7923.c b/drivers/iio/adc/ad7923.c index 96eeda433ad6..b44a853a8390 100644 --- a/drivers/iio/adc/ad7923.c +++ b/drivers/iio/adc/ad7923.c @@ -47,7 +47,7 @@ struct ad7923_state { struct spi_device *spi; - struct spi_transfer ring_xfer[5]; + struct spi_transfer ring_xfer[9]; struct spi_transfer scan_single_xfer[2]; struct spi_message ring_msg; struct spi_message scan_single_msg; @@ -63,7 +63,7 @@ struct ad7923_state { * Length = 8 channels + 4 extra for 8 byte timestamp */ __be16 rx_buf[12] ____cacheline_aligned; - __be16 tx_buf[4]; + __be16 tx_buf[8]; }; struct ad7923_chip_info { -- 2.25.1

2 1

[PATCH OLK-6.6 0/1] CVE-2024-56701
by Liao Chen 06 Jan '25

06 Jan '25

fix CVE-2024-56701 Michael Ellerman (1): powerpc/pseries: Fix dtl_access_lock to be a rw_semaphore arch/powerpc/include/asm/dtl.h | 4 ++-- arch/powerpc/platforms/pseries/dtl.c | 8 ++++---- arch/powerpc/platforms/pseries/lpar.c | 8 ++++---- 3 files changed, 10 insertions(+), 10 deletions(-) -- 2.34.1

2 2

[PATCH OLK-6.6 0/1] CVE-2024-56567
by Liao Chen 06 Jan '25

06 Jan '25

fix CVE-2024-56567 Zicheng Qu (1): ad7780: fix division by zero in ad7780_write_raw() drivers/iio/adc/ad7780.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) -- 2.34.1

2 2

[PATCH OLK-6.6 0/1] CVE-2024-56677
by Liao Chen 06 Jan '25

06 Jan '25

fix CVE-2024-56677 Ritesh Harjani (IBM) (1): powerpc/fadump: Move fadump_cma_init to setup_arch() after initmem_init() arch/powerpc/include/asm/fadump.h | 7 +++++++ arch/powerpc/kernel/fadump.c | 6 +----- arch/powerpc/kernel/setup-common.c | 6 ++++-- 3 files changed, 12 insertions(+), 7 deletions(-) -- 2.34.1

2 2

[PATCH OLK-5.10] drm/amd/display: Fix null check for pipe_ctx->plane_state in dcn20_program_pipe
by Xiongfeng Wang 06 Jan '25

06 Jan '25

From: Zicheng Qu <quzicheng(a)huawei.com> mainline inclusion from mainline-v6.13-rc1 commit 6a057072ddd127255350357dd880903e8fa23f36 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAEI CVE: CVE-2024-53201 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- This commit addresses a null pointer dereference issue in dcn20_program_pipe(). Previously, commit 8e4ed3cf1642 ("drm/amd/display: Add null check for pipe_ctx->plane_state in dcn20_program_pipe") partially fixed the null pointer dereference issue. However, in dcn20_update_dchubp_dpp(), the variable pipe_ctx is passed in, and plane_state is accessed again through pipe_ctx. Multiple if statements directly call attributes of plane_state, leading to potential null pointer dereference issues. This patch adds necessary null checks to ensure stability. Fixes: 8e4ed3cf1642 ("drm/amd/display: Add null check for pipe_ctx->plane_state in dcn20_program_pipe") Reviewed-by: Tom Chung <chiahsuan.chung(a)amd.com> Signed-off-by: Zicheng Qu <quzicheng(a)huawei.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Conflicts: drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c [wangxiongfeng: Fix conflicts because file path is changed] Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index ebb8a0c63fcc8..8c257a4e3c03b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1601,9 +1601,9 @@ static void dcn20_program_pipe( dc->res_pool->hubbub->funcs->force_wm_propagate_to_pipes(dc->res_pool->hubbub); } - if (pipe_ctx->update_flags.raw || - (pipe_ctx->plane_state && pipe_ctx->plane_state->update_flags.raw) || - pipe_ctx->stream->update_flags.raw) + if (pipe_ctx->plane_state && (pipe_ctx->update_flags.raw || + pipe_ctx->plane_state->update_flags.raw || + pipe_ctx->stream->update_flags.raw)) dcn20_update_dchubp_dpp(dc, pipe_ctx, context); if (pipe_ctx->plane_state && (pipe_ctx->update_flags.bits.enable || -- 2.20.1

2 1

[PATCH openEuler-22.03-LTS-SP1] drm/amd/display: Fix null check for pipe_ctx->plane_state in dcn20_program_pipe
by Xiongfeng Wang 06 Jan '25

06 Jan '25

From: Zicheng Qu <quzicheng(a)huawei.com> mainline inclusion from mainline-v6.13-rc1 commit 6a057072ddd127255350357dd880903e8fa23f36 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAEI CVE: CVE-2024-53201 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- This commit addresses a null pointer dereference issue in dcn20_program_pipe(). Previously, commit 8e4ed3cf1642 ("drm/amd/display: Add null check for pipe_ctx->plane_state in dcn20_program_pipe") partially fixed the null pointer dereference issue. However, in dcn20_update_dchubp_dpp(), the variable pipe_ctx is passed in, and plane_state is accessed again through pipe_ctx. Multiple if statements directly call attributes of plane_state, leading to potential null pointer dereference issues. This patch adds necessary null checks to ensure stability. Fixes: 8e4ed3cf1642 ("drm/amd/display: Add null check for pipe_ctx->plane_state in dcn20_program_pipe") Reviewed-by: Tom Chung <chiahsuan.chung(a)amd.com> Signed-off-by: Zicheng Qu <quzicheng(a)huawei.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Conflicts: drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c [wangxiongfeng: Fix conflicts because file path is changed] Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index ebb8a0c63fcc8..8c257a4e3c03b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1601,9 +1601,9 @@ static void dcn20_program_pipe( dc->res_pool->hubbub->funcs->force_wm_propagate_to_pipes(dc->res_pool->hubbub); } - if (pipe_ctx->update_flags.raw || - (pipe_ctx->plane_state && pipe_ctx->plane_state->update_flags.raw) || - pipe_ctx->stream->update_flags.raw) + if (pipe_ctx->plane_state && (pipe_ctx->update_flags.raw || + pipe_ctx->plane_state->update_flags.raw || + pipe_ctx->stream->update_flags.raw)) dcn20_update_dchubp_dpp(dc, pipe_ctx, context); if (pipe_ctx->plane_state && (pipe_ctx->update_flags.bits.enable || -- 2.20.1

2 1

[PATCH OLK-6.6] drm/amd/display: Fix null check for pipe_ctx->plane_state in dcn20_program_pipe
by Xiongfeng Wang 06 Jan '25

06 Jan '25

From: Zicheng Qu <quzicheng(a)huawei.com> mainline inclusion from mainline-v6.13-rc1 commit 6a057072ddd127255350357dd880903e8fa23f36 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAEI CVE: CVE-2024-53201 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- This commit addresses a null pointer dereference issue in dcn20_program_pipe(). Previously, commit 8e4ed3cf1642 ("drm/amd/display: Add null check for pipe_ctx->plane_state in dcn20_program_pipe") partially fixed the null pointer dereference issue. However, in dcn20_update_dchubp_dpp(), the variable pipe_ctx is passed in, and plane_state is accessed again through pipe_ctx. Multiple if statements directly call attributes of plane_state, leading to potential null pointer dereference issues. This patch adds necessary null checks to ensure stability. Fixes: 8e4ed3cf1642 ("drm/amd/display: Add null check for pipe_ctx->plane_state in dcn20_program_pipe") Reviewed-by: Tom Chung <chiahsuan.chung(a)amd.com> Signed-off-by: Zicheng Qu <quzicheng(a)huawei.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Conflicts: drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c [wangxiongfeng: Fix conflicts because file path is changed] Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> --- drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c index c6c465b46e19..509e0fd52491 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hwseq.c @@ -1733,9 +1733,9 @@ static void dcn20_program_pipe( dc->res_pool->hubbub->funcs->program_det_size( dc->res_pool->hubbub, pipe_ctx->plane_res.hubp->inst, pipe_ctx->det_buffer_size_kb); - if (pipe_ctx->update_flags.raw || - (pipe_ctx->plane_state && pipe_ctx->plane_state->update_flags.raw) || - pipe_ctx->stream->update_flags.raw) + if (pipe_ctx->plane_state && (pipe_ctx->update_flags.raw || + pipe_ctx->plane_state->update_flags.raw || + pipe_ctx->stream->update_flags.raw)) dcn20_update_dchubp_dpp(dc, pipe_ctx, context); if (pipe_ctx->plane_state && (pipe_ctx->update_flags.bits.enable || -- 2.20.1

2 1

[PATCH openEuler-22.03-LTS-SP1] wifi: ath10k: avoid NULL pointer error during sdio remove
by Liu Mingrui 06 Jan '25

06 Jan '25

From: Kang Yang <quic_kangyang(a)quicinc.com> mainline inclusion from mainline-v6.13-rc1 commit 95c38953cb1ecf40399a676a1f85dfe2b5780a9a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAPA CVE: CVE-2024-56599 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- When running 'rmmod ath10k', ath10k_sdio_remove() will free sdio workqueue by destroy_workqueue(). But if CONFIG_INIT_ON_FREE_DEFAULT_ON is set to yes, kernel panic will happen: Call trace: destroy_workqueue+0x1c/0x258 ath10k_sdio_remove+0x84/0x94 sdio_bus_remove+0x50/0x16c device_release_driver_internal+0x188/0x25c device_driver_detach+0x20/0x2c This is because during 'rmmod ath10k', ath10k_sdio_remove() will call ath10k_core_destroy() before destroy_workqueue(). wiphy_dev_release() will finally be called in ath10k_core_destroy(). This function will free struct cfg80211_registered_device *rdev and all its members, including wiphy, dev and the pointer of sdio workqueue. Then the pointer of sdio workqueue will be set to NULL due to CONFIG_INIT_ON_FREE_DEFAULT_ON. After device release, destroy_workqueue() will use NULL pointer then the kernel panic happen. Call trace: ath10k_sdio_remove ->ath10k_core_unregister …… ->ath10k_core_stop ->ath10k_hif_stop ->ath10k_sdio_irq_disable ->ath10k_hif_power_down ->del_timer_sync(&ar_sdio->sleep_timer) ->ath10k_core_destroy ->ath10k_mac_destroy ->ieee80211_free_hw ->wiphy_free …… ->wiphy_dev_release ->destroy_workqueue Need to call destroy_workqueue() before ath10k_core_destroy(), free the work queue buffer first and then free pointer of work queue by ath10k_core_destroy(). This order matches the error path order in ath10k_sdio_probe(). No work will be queued on sdio workqueue between it is destroyed and ath10k_core_destroy() is called. Based on the call_stack above, the reason is: Only ath10k_sdio_sleep_timer_handler(), ath10k_sdio_hif_tx_sg() and ath10k_sdio_irq_disable() will queue work on sdio workqueue. Sleep timer will be deleted before ath10k_core_destroy() in ath10k_hif_power_down(). ath10k_sdio_irq_disable() only be called in ath10k_hif_stop(). ath10k_core_unregister() will call ath10k_hif_power_down() to stop hif bus, so ath10k_sdio_hif_tx_sg() won't be called anymore. Tested-on: QCA6174 hw3.2 SDIO WLAN.RMH.4.4.1-00189 Signed-off-by: Kang Yang <quic_kangyang(a)quicinc.com> Tested-by: David Ruth <druth(a)chromium.org> Reviewed-by: David Ruth <druth(a)chromium.org> Link: https://patch.msgid.link/20241008022246.1010-1-quic_kangyang@quicinc.com Signed-off-by: Jeff Johnson <quic_jjohnson(a)quicinc.com> Conflicts: drivers/net/wireless/ath/ath10k/sdio.c [Context conflicts, no function change] Signed-off-by: Liu Mingrui <liumingrui(a)huawei.com> --- drivers/net/wireless/ath/ath10k/sdio.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c index 0fe639710a8b..7f2bd4889bb5 100644 --- a/drivers/net/wireless/ath/ath10k/sdio.c +++ b/drivers/net/wireless/ath/ath10k/sdio.c @@ -2649,10 +2649,10 @@ static void ath10k_sdio_remove(struct sdio_func *func) netif_napi_del(&ar->napi); - ath10k_core_destroy(ar); - flush_workqueue(ar_sdio->workqueue); destroy_workqueue(ar_sdio->workqueue); + + ath10k_core_destroy(ar); } static const struct sdio_device_id ath10k_sdio_devices[] = { -- 2.25.1

2 1

[PATCH OLK-5.10] wifi: ath10k: avoid NULL pointer error during sdio remove
by Liu Mingrui 06 Jan '25

06 Jan '25

From: Kang Yang <quic_kangyang(a)quicinc.com> mainline inclusion from mainline-v6.13-rc1 commit 95c38953cb1ecf40399a676a1f85dfe2b5780a9a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAPA CVE: CVE-2024-56599 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- When running 'rmmod ath10k', ath10k_sdio_remove() will free sdio workqueue by destroy_workqueue(). But if CONFIG_INIT_ON_FREE_DEFAULT_ON is set to yes, kernel panic will happen: Call trace: destroy_workqueue+0x1c/0x258 ath10k_sdio_remove+0x84/0x94 sdio_bus_remove+0x50/0x16c device_release_driver_internal+0x188/0x25c device_driver_detach+0x20/0x2c This is because during 'rmmod ath10k', ath10k_sdio_remove() will call ath10k_core_destroy() before destroy_workqueue(). wiphy_dev_release() will finally be called in ath10k_core_destroy(). This function will free struct cfg80211_registered_device *rdev and all its members, including wiphy, dev and the pointer of sdio workqueue. Then the pointer of sdio workqueue will be set to NULL due to CONFIG_INIT_ON_FREE_DEFAULT_ON. After device release, destroy_workqueue() will use NULL pointer then the kernel panic happen. Call trace: ath10k_sdio_remove ->ath10k_core_unregister …… ->ath10k_core_stop ->ath10k_hif_stop ->ath10k_sdio_irq_disable ->ath10k_hif_power_down ->del_timer_sync(&ar_sdio->sleep_timer) ->ath10k_core_destroy ->ath10k_mac_destroy ->ieee80211_free_hw ->wiphy_free …… ->wiphy_dev_release ->destroy_workqueue Need to call destroy_workqueue() before ath10k_core_destroy(), free the work queue buffer first and then free pointer of work queue by ath10k_core_destroy(). This order matches the error path order in ath10k_sdio_probe(). No work will be queued on sdio workqueue between it is destroyed and ath10k_core_destroy() is called. Based on the call_stack above, the reason is: Only ath10k_sdio_sleep_timer_handler(), ath10k_sdio_hif_tx_sg() and ath10k_sdio_irq_disable() will queue work on sdio workqueue. Sleep timer will be deleted before ath10k_core_destroy() in ath10k_hif_power_down(). ath10k_sdio_irq_disable() only be called in ath10k_hif_stop(). ath10k_core_unregister() will call ath10k_hif_power_down() to stop hif bus, so ath10k_sdio_hif_tx_sg() won't be called anymore. Tested-on: QCA6174 hw3.2 SDIO WLAN.RMH.4.4.1-00189 Signed-off-by: Kang Yang <quic_kangyang(a)quicinc.com> Tested-by: David Ruth <druth(a)chromium.org> Reviewed-by: David Ruth <druth(a)chromium.org> Link: https://patch.msgid.link/20241008022246.1010-1-quic_kangyang@quicinc.com Signed-off-by: Jeff Johnson <quic_jjohnson(a)quicinc.com> Conflicts: drivers/net/wireless/ath/ath10k/sdio.c [Context conflicts, no function change] Signed-off-by: Liu Mingrui <liumingrui(a)huawei.com> --- drivers/net/wireless/ath/ath10k/sdio.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c index 0fe639710a8b..7f2bd4889bb5 100644 --- a/drivers/net/wireless/ath/ath10k/sdio.c +++ b/drivers/net/wireless/ath/ath10k/sdio.c @@ -2649,10 +2649,10 @@ static void ath10k_sdio_remove(struct sdio_func *func) netif_napi_del(&ar->napi); - ath10k_core_destroy(ar); - flush_workqueue(ar_sdio->workqueue); destroy_workqueue(ar_sdio->workqueue); + + ath10k_core_destroy(ar); } static const struct sdio_device_id ath10k_sdio_devices[] = { -- 2.25.1

2 1

[PATCH OLK-5.10] BEAEC[Backport] ALSA: 6fire: Release resources at card release
by Lin Ruifeng 06 Jan '25

06 Jan '25

From: Takashi Iwai <tiwai(a)suse.de> stable inclusion from stable-v5.10.231 commit f2d06d4e129e2508e356136f99bb20a332ff1a00 bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAEC CVE: CVE-2024-53239 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit a0810c3d6dd2d29a9b92604d682eacd2902ce947 ] The current 6fire code tries to release the resources right after the call of usb6fire_chip_abort(). But at this moment, the card object might be still in use (as we're calling snd_card_free_when_closed()). For avoid potential UAFs, move the release of resources to the card's private_free instead of the manual call of usb6fire_chip_destroy() at the USB disconnect callback. Fixes: c6d43ba816d1 ("ALSA: usb/6fire - Driver for TerraTec DMX 6Fire USB") Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Link: https://patch.msgid.link/20241113111042.15058-6-tiwai@suse.de Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Lin Ruifeng <linruifeng4(a)huawei.com> --- sound/usb/6fire/chip.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/sound/usb/6fire/chip.c b/sound/usb/6fire/chip.c index 08c6e6a52eb9..ad6f89845a5c 100644 --- a/sound/usb/6fire/chip.c +++ b/sound/usb/6fire/chip.c @@ -62,8 +62,10 @@ static void usb6fire_chip_abort(struct sfire_chip *chip) } } -static void usb6fire_chip_destroy(struct sfire_chip *chip) +static void usb6fire_card_free(struct snd_card *card) { + struct sfire_chip *chip = card->private_data; + if (chip) { if (chip->pcm) usb6fire_pcm_destroy(chip); @@ -73,8 +75,6 @@ static void usb6fire_chip_destroy(struct sfire_chip *chip) usb6fire_comm_destroy(chip); if (chip->control) usb6fire_control_destroy(chip); - if (chip->card) - snd_card_free(chip->card); } } @@ -137,6 +137,7 @@ static int usb6fire_chip_probe(struct usb_interface *intf, chip->regidx = regidx; chip->intf_count = 1; chip->card = card; + card->private_free = usb6fire_card_free; ret = usb6fire_comm_init(chip); if (ret < 0) @@ -163,7 +164,7 @@ static int usb6fire_chip_probe(struct usb_interface *intf, return 0; destroy_chip: - usb6fire_chip_destroy(chip); + snd_card_free(card); return ret; } @@ -182,7 +183,6 @@ static void usb6fire_chip_disconnect(struct usb_interface *intf) chip->shutdown = true; usb6fire_chip_abort(chip); - usb6fire_chip_destroy(chip); } } } -- 2.22.0

2 1

[PATCH OLK-6.6] [Backport] ALSA: 6fire: Release resources at card release
by Lin Ruifeng 06 Jan '25

06 Jan '25

From: Takashi Iwai <tiwai(a)suse.de> stable inclusion from stable-v6.6.64 commit b754e831a94f82f2593af806741392903f359168 bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAEC CVE: CVE-2024-53239 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit a0810c3d6dd2d29a9b92604d682eacd2902ce947 ] The current 6fire code tries to release the resources right after the call of usb6fire_chip_abort(). But at this moment, the card object might be still in use (as we're calling snd_card_free_when_closed()). For avoid potential UAFs, move the release of resources to the card's private_free instead of the manual call of usb6fire_chip_destroy() at the USB disconnect callback. Fixes: c6d43ba816d1 ("ALSA: usb/6fire - Driver for TerraTec DMX 6Fire USB") Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Link: https://patch.msgid.link/20241113111042.15058-6-tiwai@suse.de Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Lin Ruifeng <linruifeng4(a)huawei.com> --- sound/usb/6fire/chip.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/sound/usb/6fire/chip.c b/sound/usb/6fire/chip.c index 33e962178c93..d562a30b087f 100644 --- a/sound/usb/6fire/chip.c +++ b/sound/usb/6fire/chip.c @@ -61,8 +61,10 @@ static void usb6fire_chip_abort(struct sfire_chip *chip) } } -static void usb6fire_chip_destroy(struct sfire_chip *chip) +static void usb6fire_card_free(struct snd_card *card) { + struct sfire_chip *chip = card->private_data; + if (chip) { if (chip->pcm) usb6fire_pcm_destroy(chip); @@ -72,8 +74,6 @@ static void usb6fire_chip_destroy(struct sfire_chip *chip) usb6fire_comm_destroy(chip); if (chip->control) usb6fire_control_destroy(chip); - if (chip->card) - snd_card_free(chip->card); } } @@ -136,6 +136,7 @@ static int usb6fire_chip_probe(struct usb_interface *intf, chip->regidx = regidx; chip->intf_count = 1; chip->card = card; + card->private_free = usb6fire_card_free; ret = usb6fire_comm_init(chip); if (ret < 0) @@ -162,7 +163,7 @@ static int usb6fire_chip_probe(struct usb_interface *intf, return 0; destroy_chip: - usb6fire_chip_destroy(chip); + snd_card_free(card); return ret; } @@ -181,7 +182,6 @@ static void usb6fire_chip_disconnect(struct usb_interface *intf) chip->shutdown = true; usb6fire_chip_abort(chip); - usb6fire_chip_destroy(chip); } } } -- 2.22.0

2 1

[PATCH openEuler-1.0-LTS] BEAEC[Backport] ALSA: 6fire: Release resources at card release
by Lin Ruifeng 06 Jan '25

06 Jan '25

From: Takashi Iwai <tiwai(a)suse.de> stable inclusion from stable-v4.19.325 commit 74357d0b5cd3ef544752bc9f21cbeee4902fae6c bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAEC CVE: CVE-2024-53239 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit a0810c3d6dd2d29a9b92604d682eacd2902ce947 ] The current 6fire code tries to release the resources right after the call of usb6fire_chip_abort(). But at this moment, the card object might be still in use (as we're calling snd_card_free_when_closed()). For avoid potential UAFs, move the release of resources to the card's private_free instead of the manual call of usb6fire_chip_destroy() at the USB disconnect callback. Fixes: c6d43ba816d1 ("ALSA: usb/6fire - Driver for TerraTec DMX 6Fire USB") Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Link: https://patch.msgid.link/20241113111042.15058-6-tiwai@suse.de Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Lin Ruifeng <linruifeng4(a)huawei.com> --- sound/usb/6fire/chip.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/sound/usb/6fire/chip.c b/sound/usb/6fire/chip.c index 17d5e3ee6d73..f5a9b7a0b585 100644 --- a/sound/usb/6fire/chip.c +++ b/sound/usb/6fire/chip.c @@ -66,8 +66,10 @@ static void usb6fire_chip_abort(struct sfire_chip *chip) } } -static void usb6fire_chip_destroy(struct sfire_chip *chip) +static void usb6fire_card_free(struct snd_card *card) { + struct sfire_chip *chip = card->private_data; + if (chip) { if (chip->pcm) usb6fire_pcm_destroy(chip); @@ -77,8 +79,6 @@ static void usb6fire_chip_destroy(struct sfire_chip *chip) usb6fire_comm_destroy(chip); if (chip->control) usb6fire_control_destroy(chip); - if (chip->card) - snd_card_free(chip->card); } } @@ -141,6 +141,7 @@ static int usb6fire_chip_probe(struct usb_interface *intf, chip->regidx = regidx; chip->intf_count = 1; chip->card = card; + card->private_free = usb6fire_card_free; ret = usb6fire_comm_init(chip); if (ret < 0) @@ -167,7 +168,7 @@ static int usb6fire_chip_probe(struct usb_interface *intf, return 0; destroy_chip: - usb6fire_chip_destroy(chip); + snd_card_free(card); return ret; } @@ -186,7 +187,6 @@ static void usb6fire_chip_disconnect(struct usb_interface *intf) chip->shutdown = true; usb6fire_chip_abort(chip); - usb6fire_chip_destroy(chip); } } } -- 2.22.0

2 1

[PATCH OLK-6.6] [Backport] Bluetooth: L2CAP: do not leave dangling sk pointer on error in l2cap_sock_create()
by Lin Ruifeng 06 Jan '25

06 Jan '25

From: Ignat Korchagin <ignat(a)cloudflare.com> stable inclusion from stable-v6.6.66 commit 8ad09ddc63ace3950ac43db6fbfe25b40f589dd6 bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEANO CVE: CVE-2024-56605 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 7c4f78cdb8e7501e9f92d291a7d956591bf73be9 ] bt_sock_alloc() allocates the sk object and attaches it to the provided sock object. On error l2cap_sock_alloc() frees the sk object, but the dangling pointer is still attached to the sock object, which may create use-after-free in other code. Signed-off-by: Ignat Korchagin <ignat(a)cloudflare.com> Reviewed-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Link: https://patch.msgid.link/20241014153808.51894-3-ignat@cloudflare.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Lin Ruifeng <linruifeng4(a)huawei.com> --- net/bluetooth/l2cap_sock.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index f04ce8426798..379ca86c41cd 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1885,6 +1885,7 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, chan = l2cap_chan_create(); if (!chan) { sk_free(sk); + sock->sk = NULL; return NULL; } -- 2.22.0

2 1

[PATCH openEuler-22.03-LTS-SP1] [Backport] Bluetooth: L2CAP: do not leave dangling sk pointer on error in l2cap_sock_create()
by Lin Ruifeng 06 Jan '25

06 Jan '25

From: Ignat Korchagin <ignat(a)cloudflare.com> stable inclusion from stable-v5.10.231 commit daa13175a6dea312a76099066cb4cbd4fc959a84 bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEANO CVE: CVE-2024-56605 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 7c4f78cdb8e7501e9f92d291a7d956591bf73be9 ] bt_sock_alloc() allocates the sk object and attaches it to the provided sock object. On error l2cap_sock_alloc() frees the sk object, but the dangling pointer is still attached to the sock object, which may create use-after-free in other code. Signed-off-by: Ignat Korchagin <ignat(a)cloudflare.com> Reviewed-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Link: https://patch.msgid.link/20241014153808.51894-3-ignat@cloudflare.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Lin Ruifeng <linruifeng4(a)huawei.com> --- net/bluetooth/l2cap_sock.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 51927765473b..87be9d294773 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1863,6 +1863,7 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, chan = l2cap_chan_create(); if (!chan) { sk_free(sk); + sock->sk = NULL; return NULL; } -- 2.22.0

2 1

[PATCH OLK-5.10] [Backport] Bluetooth: L2CAP: do not leave dangling sk pointer on error in l2cap_sock_create()
by Lin Ruifeng 06 Jan '25

06 Jan '25

From: Ignat Korchagin <ignat(a)cloudflare.com> stable inclusion from stable-v5.10.231 commit daa13175a6dea312a76099066cb4cbd4fc959a84 bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEANO CVE: CVE-2024-56605 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 7c4f78cdb8e7501e9f92d291a7d956591bf73be9 ] bt_sock_alloc() allocates the sk object and attaches it to the provided sock object. On error l2cap_sock_alloc() frees the sk object, but the dangling pointer is still attached to the sock object, which may create use-after-free in other code. Signed-off-by: Ignat Korchagin <ignat(a)cloudflare.com> Reviewed-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Link: https://patch.msgid.link/20241014153808.51894-3-ignat@cloudflare.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Lin Ruifeng <linruifeng4(a)huawei.com> --- net/bluetooth/l2cap_sock.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index f7240442bde6..27223e43aff2 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1872,6 +1872,7 @@ static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, chan = l2cap_chan_create(); if (!chan) { sk_free(sk); + sock->sk = NULL; return NULL; } -- 2.22.0

2 1

[PATCH OLK-6.6] sched: fix warning in sched_setaffinity
by Zicheng Qu 06 Jan '25

06 Jan '25

From: Josh Don <joshdon(a)google.com> mainline inclusion from mainline-6.13-rc3 commit 70ee7947a29029736a1a06c73a48ff37674a851b category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBD13G Reference: https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/commit/?id=70ee… -------------------------------- Commit 8f9ea86fdf99b added some logic to sched_setaffinity that included a WARN when a per-task affinity assignment races with a cpuset update. Specifically, we can have a race where a cpuset update results in the task affinity no longer being a subset of the cpuset. That's fine; we have a fallback to instead use the cpuset mask. However, we have a WARN set up that will trigger if the cpuset mask has no overlap at all with the requested task affinity. This shouldn't be a warning condition; its trivial to create this condition. Reproduced the warning by the following setup: - $PID inside a cpuset cgroup - another thread repeatedly switching the cpuset cpus from 1-2 to just 1 - another thread repeatedly setting the $PID affinity (via taskset) to 2 Fixes: 8f9ea86fdf99b ("sched: Always preserve the user requested cpumask") Signed-off-by: Josh Don <joshdon(a)google.com> Acked-and-tested-by: Vincent Guittot <vincent.guittot(a)linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Acked-by: Waiman Long <longman(a)redhat.com> Tested-by: Madadi Vineeth Reddy <vineethr(a)linux.ibm.com> Link: https://lkml.kernel.org/r/20241111182738.1832953-1-joshdon@google.com Conflicts: kernel/sched/core.c kernel/sched/syscalls.c [The linux stable 6.6 lacks this commit 70ee7947a290 ("sched: fix warning in sched_setaffinity"), so pick from linux mainline, this function "__sched_setaffinity" has been moved from core to syscall in mainline.] Signed-off-by: Zicheng Qu <quzicheng(a)huawei.com> --- kernel/sched/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7a9aff1dbb3c..5569c89bbaf3 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8415,7 +8415,7 @@ __sched_setaffinity(struct task_struct *p, struct affinity_context *ctx) bool empty = !cpumask_and(new_mask, new_mask, ctx->user_mask); - if (WARN_ON_ONCE(empty)) + if (empty) cpumask_copy(new_mask, cpus_allowed); } __set_cpus_allowed_ptr(p, ctx); -- 2.34.1

2 1

[PATCH OLK-6.6] [Backport] Bluetooth: btmtk: avoid UAF in btmtk_process_coredump
by Lin Ruifeng 06 Jan '25

06 Jan '25

From: Thadeu Lima de Souza Cascardo <cascardo(a)igalia.com> stable inclusion from stable-v6.6.67 commit ecdcaea0e4057171ea4c3783e1cc1c900ad99125 bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAOV CVE: CVE-2024-56653 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit b548f5e9456c568155499d9ebac675c0d7a296e8 ] hci_devcd_append may lead to the release of the skb, so it cannot be accessed once it is called. ================================================================== BUG: KASAN: slab-use-after-free in btmtk_process_coredump+0x2a7/0x2d0 [btmtk] Read of size 4 at addr ffff888033cfabb0 by task kworker/0:3/82 CPU: 0 PID: 82 Comm: kworker/0:3 Tainted: G U 6.6.40-lockdep-03464-g1d8b4eb3060e #1 b0b3c1cc0c842735643fb411799d97921d1f688c Hardware name: Google Yaviks_Ufs/Yaviks_Ufs, BIOS Google_Yaviks_Ufs.15217.552.0 05/07/2024 Workqueue: events btusb_rx_work [btusb] Call Trace: <TASK> dump_stack_lvl+0xfd/0x150 print_report+0x131/0x780 kasan_report+0x177/0x1c0 btmtk_process_coredump+0x2a7/0x2d0 [btmtk 03edd567dd71a65958807c95a65db31d433e1d01] btusb_recv_acl_mtk+0x11c/0x1a0 [btusb 675430d1e87c4f24d0c1f80efe600757a0f32bec] btusb_rx_work+0x9e/0xe0 [btusb 675430d1e87c4f24d0c1f80efe600757a0f32bec] worker_thread+0xe44/0x2cc0 kthread+0x2ff/0x3a0 ret_from_fork+0x51/0x80 ret_from_fork_asm+0x1b/0x30 </TASK> Allocated by task 82: stack_trace_save+0xdc/0x190 kasan_set_track+0x4e/0x80 __kasan_slab_alloc+0x4e/0x60 kmem_cache_alloc+0x19f/0x360 skb_clone+0x132/0xf70 btusb_recv_acl_mtk+0x104/0x1a0 [btusb] btusb_rx_work+0x9e/0xe0 [btusb] worker_thread+0xe44/0x2cc0 kthread+0x2ff/0x3a0 ret_from_fork+0x51/0x80 ret_from_fork_asm+0x1b/0x30 Freed by task 1733: stack_trace_save+0xdc/0x190 kasan_set_track+0x4e/0x80 kasan_save_free_info+0x28/0xb0 ____kasan_slab_free+0xfd/0x170 kmem_cache_free+0x183/0x3f0 hci_devcd_rx+0x91a/0x2060 [bluetooth] worker_thread+0xe44/0x2cc0 kthread+0x2ff/0x3a0 ret_from_fork+0x51/0x80 ret_from_fork_asm+0x1b/0x30 The buggy address belongs to the object at ffff888033cfab40 which belongs to the cache skbuff_head_cache of size 232 The buggy address is located 112 bytes inside of freed 232-byte region [ffff888033cfab40, ffff888033cfac28) The buggy address belongs to the physical page: page:00000000a174ba93 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x33cfa head:00000000a174ba93 order:1 entire_mapcount:0 nr_pages_mapped:0 pincount:0 anon flags: 0x4000000000000840(slab|head|zone=1) page_type: 0xffffffff() raw: 4000000000000840 ffff888100848a00 0000000000000000 0000000000000001 raw: 0000000000000000 0000000080190019 00000001ffffffff 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff888033cfaa80: fb fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc ffff888033cfab00: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb >ffff888033cfab80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff888033cfac00: fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc ffff888033cfac80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ================================================================== Check if we need to call hci_devcd_complete before calling hci_devcd_append. That requires that we check data->cd_info.cnt >= MTK_COREDUMP_NUM instead of data->cd_info.cnt > MTK_COREDUMP_NUM, as we increment data->cd_info.cnt only once the call to hci_devcd_append succeeds. Fixes: 0b7015132878 ("Bluetooth: btusb: mediatek: add MediaTek devcoredump support") Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo(a)igalia.com> Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz(a)intel.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Lin Ruifeng <linruifeng4(a)huawei.com> --- drivers/bluetooth/btmtk.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c index 812fd2a8f853..4c53ab22d09b 100644 --- a/drivers/bluetooth/btmtk.c +++ b/drivers/bluetooth/btmtk.c @@ -371,6 +371,7 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb) { struct btmediatek_data *data = hci_get_priv(hdev); int err; + bool complete = false; if (!IS_ENABLED(CONFIG_DEV_COREDUMP)) { kfree_skb(skb); @@ -392,19 +393,22 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb) fallthrough; case HCI_DEVCOREDUMP_ACTIVE: default: + /* Mediatek coredump data would be more than MTK_COREDUMP_NUM */ + if (data->cd_info.cnt >= MTK_COREDUMP_NUM && + skb->len > MTK_COREDUMP_END_LEN) + if (!memcmp((char *)&skb->data[skb->len - MTK_COREDUMP_END_LEN], + MTK_COREDUMP_END, MTK_COREDUMP_END_LEN - 1)) + complete = true; + err = hci_devcd_append(hdev, skb); if (err < 0) break; data->cd_info.cnt++; - /* Mediatek coredump data would be more than MTK_COREDUMP_NUM */ - if (data->cd_info.cnt > MTK_COREDUMP_NUM && - skb->len > MTK_COREDUMP_END_LEN) - if (!memcmp((char *)&skb->data[skb->len - MTK_COREDUMP_END_LEN], - MTK_COREDUMP_END, MTK_COREDUMP_END_LEN - 1)) { - bt_dev_info(hdev, "Mediatek coredump end"); - hci_devcd_complete(hdev); - } + if (complete) { + bt_dev_info(hdev, "Mediatek coredump end"); + hci_devcd_complete(hdev); + } break; } -- 2.22.0

2 1

[PATCH openEuler-22.03-LTS-SP1] [Backport] ALSA: 6fire: Release resources at card release
by Lin Ruifeng 06 Jan '25

06 Jan '25

From: Takashi Iwai <tiwai(a)suse.de> stable inclusion from stable-v5.10.231 commit f2d06d4e129e2508e356136f99bb20a332ff1a00 bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAEC CVE: CVE-2024-53239 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit a0810c3d6dd2d29a9b92604d682eacd2902ce947 ] The current 6fire code tries to release the resources right after the call of usb6fire_chip_abort(). But at this moment, the card object might be still in use (as we're calling snd_card_free_when_closed()). For avoid potential UAFs, move the release of resources to the card's private_free instead of the manual call of usb6fire_chip_destroy() at the USB disconnect callback. Fixes: c6d43ba816d1 ("ALSA: usb/6fire - Driver for TerraTec DMX 6Fire USB") Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Link: https://patch.msgid.link/20241113111042.15058-6-tiwai@suse.de Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Lin Ruifeng <linruifeng4(a)huawei.com> --- sound/usb/6fire/chip.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/sound/usb/6fire/chip.c b/sound/usb/6fire/chip.c index 08c6e6a52eb9..ad6f89845a5c 100644 --- a/sound/usb/6fire/chip.c +++ b/sound/usb/6fire/chip.c @@ -62,8 +62,10 @@ static void usb6fire_chip_abort(struct sfire_chip *chip) } } -static void usb6fire_chip_destroy(struct sfire_chip *chip) +static void usb6fire_card_free(struct snd_card *card) { + struct sfire_chip *chip = card->private_data; + if (chip) { if (chip->pcm) usb6fire_pcm_destroy(chip); @@ -73,8 +75,6 @@ static void usb6fire_chip_destroy(struct sfire_chip *chip) usb6fire_comm_destroy(chip); if (chip->control) usb6fire_control_destroy(chip); - if (chip->card) - snd_card_free(chip->card); } } @@ -137,6 +137,7 @@ static int usb6fire_chip_probe(struct usb_interface *intf, chip->regidx = regidx; chip->intf_count = 1; chip->card = card; + card->private_free = usb6fire_card_free; ret = usb6fire_comm_init(chip); if (ret < 0) @@ -163,7 +164,7 @@ static int usb6fire_chip_probe(struct usb_interface *intf, return 0; destroy_chip: - usb6fire_chip_destroy(chip); + snd_card_free(card); return ret; } @@ -182,7 +183,6 @@ static void usb6fire_chip_disconnect(struct usb_interface *intf) chip->shutdown = true; usb6fire_chip_abort(chip); - usb6fire_chip_destroy(chip); } } } -- 2.22.0

2 1

[PATCH OLK-6.6 v2 0/2] CVE-2024-53224
by Pu Lehui 06 Jan '25

06 Jan '25

Jianbo Liu (1): IB/mlx5: Allocate resources just before first QP/SRQ is created Patrisious Haddad (1): RDMA/mlx5: Move events notifier registration to be after device registration drivers/infiniband/hw/mlx5/main.c | 185 ++++++++++++++++++--------- drivers/infiniband/hw/mlx5/mlx5_ib.h | 6 +- drivers/infiniband/hw/mlx5/qp.c | 4 + drivers/infiniband/hw/mlx5/srq.c | 4 + 4 files changed, 136 insertions(+), 63 deletions(-) -- 2.34.1

2 3

[PATCH OLK-5.10] xsk: Add generic xdp multi-buffer send support
by Yue Haibing 06 Jan '25

06 Jan '25

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/IAOZOH ---------------------------------------------- This is partialy backport from mainline xdp multi-buffer send support for generic xsk. Signed-off-by: Yue Haibing <yuehaibing(a)huawei.com> --- net/xdp/xsk.c | 237 ++++++++++++++++++++++++++++++++++++++++++++ net/xdp/xsk_queue.h | 14 +++ 2 files changed, 251 insertions(+) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 34d210a08393..eca562d20ddc 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -528,6 +528,231 @@ static void xsk_destruct_skb(struct sk_buff *skb) sock_wfree(skb); } +#ifdef CONFIG_XSK_MULTI_BUF +static int xsk_cq_reserve_addr_locked(struct xdp_sock *xs, u64 addr) +{ + unsigned long flags; + int ret; + + spin_lock_irqsave(&xs->pool->cq_lock, flags); + ret = xskq_prod_reserve_addr(xs->pool->cq, addr); + spin_unlock_irqrestore(&xs->pool->cq_lock, flags); + + return ret; +} + +static void xsk_cq_submit_locked(struct xdp_sock *xs, u32 n) +{ + unsigned long flags; + + spin_lock_irqsave(&xs->pool->cq_lock, flags); + xskq_prod_submit_n(xs->pool->cq, n); + spin_unlock_irqrestore(&xs->pool->cq_lock, flags); +} + +static void xsk_cq_cancel_locked(struct xdp_sock *xs, u32 n) +{ + unsigned long flags; + + spin_lock_irqsave(&xs->pool->cq_lock, flags); + xskq_prod_cancel_n(xs->pool->cq, n); + spin_unlock_irqrestore(&xs->pool->cq_lock, flags); +} + +static u32 xsk_get_num_desc(struct sk_buff *skb) +{ + return skb ? (long)skb_shinfo(skb)->destructor_arg : 0; +} + +static void xsk_destruct_skb_multi(struct sk_buff *skb) +{ + xsk_cq_submit_locked(xdp_sk(skb->sk), xsk_get_num_desc(skb)); + sock_wfree(skb); +} + +static void xsk_set_destructor_arg(struct sk_buff *skb) +{ + long num = xsk_get_num_desc(xdp_sk(skb->sk)->skb) + 1; + + skb_shinfo(skb)->destructor_arg = (void *)num; +} + +static void xsk_consume_skb(struct sk_buff *skb) +{ + struct xdp_sock *xs = xdp_sk(skb->sk); + + skb->destructor = sock_wfree; + xsk_cq_cancel_locked(xs, xsk_get_num_desc(skb)); + /* Free skb without triggering the perf drop trace */ + consume_skb(skb); + xs->skb = NULL; +} + +static void xsk_drop_skb(struct sk_buff *skb) +{ + xdp_sk(skb->sk)->tx->invalid_descs += xsk_get_num_desc(skb); + xsk_consume_skb(skb); +} + +static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, + struct xdp_desc *desc) +{ + struct net_device *dev = xs->dev; + struct sk_buff *skb = xs->skb; + int err; + + if (dev->priv_flags & IFF_TX_SKB_NO_LINEAR) { + err = -EOPNOTSUPP; + goto free_err; + } else { + u32 hr, tr, len; + void *buffer; + + buffer = xsk_buff_raw_get_data(xs->pool, desc->addr); + len = desc->len; + + if (!skb) { + hr = max(NET_SKB_PAD, L1_CACHE_ALIGN(dev->needed_headroom)); + tr = dev->needed_tailroom; + skb = sock_alloc_send_skb(&xs->sk, hr + len + tr, 1, &err); + if (unlikely(!skb)) + goto free_err; + + skb_reserve(skb, hr); + skb_put(skb, len); + + err = skb_store_bits(skb, 0, buffer, len); + if (unlikely(err)) { + kfree_skb(skb); + goto free_err; + } + } else { + int nr_frags = skb_shinfo(skb)->nr_frags; + struct page *page; + u8 *vaddr; + + if (unlikely(nr_frags == (MAX_SKB_FRAGS - 1) && xp_mb_desc(desc))) { + err = -EOVERFLOW; + goto free_err; + } + + page = alloc_page(xs->sk.sk_allocation); + if (unlikely(!page)) { + err = -EAGAIN; + goto free_err; + } + + vaddr = kmap(page); + memcpy(vaddr, buffer, len); + kunmap(page); + + skb_add_rx_frag(skb, nr_frags, page, 0, len, PAGE_SIZE); + refcount_add(PAGE_SIZE, &xs->sk.sk_wmem_alloc); + } + } + + skb->dev = dev; + skb->priority = xs->sk.sk_priority; + skb->mark = xs->sk.sk_mark; + skb->destructor = xsk_destruct_skb_multi; + xsk_set_destructor_arg(skb); + + return skb; +free_err: + if (err == -EOVERFLOW) { + /* Drop the packet */ + xsk_set_destructor_arg(xs->skb); + xsk_drop_skb(xs->skb); + xskq_cons_release(xs->tx); + } else { + /* Let application retry */ + xsk_cq_cancel_locked(xs, 1); + } + + return ERR_PTR(err); +} + +static int xsk_generic_xmit_multi(struct sock *sk) +{ + struct xdp_sock *xs = xdp_sk(sk); + u32 max_batch = TX_BATCH_SIZE; + bool sent_frame = false; + struct xdp_desc desc; + struct sk_buff *skb; + int err = 0; + + mutex_lock(&xs->mutex); + + if (xs->queue_id >= xs->dev->real_num_tx_queues) + goto out; + + while (xskq_cons_peek_desc(xs->tx, &desc, xs->pool)) { + if (max_batch-- == 0) { + err = -EAGAIN; + goto out; + } + + /* This is the backpressure mechanism for the Tx path. + * Reserve space in the completion queue and only proceed + * if there is space in it. This avoids having to implement + * any buffering in the Tx path. + */ + if (xsk_cq_reserve_addr_locked(xs, desc.addr)) + goto out; + + skb = xsk_build_skb(xs, &desc); + if (IS_ERR(skb)) { + err = PTR_ERR(skb); + if (err != -EOVERFLOW) + goto out; + err = 0; + continue; + } + + xskq_cons_release(xs->tx); + + if (xp_mb_desc(&desc)) { + xs->skb = skb; + continue; + } + + err = __dev_direct_xmit(skb, xs->queue_id); + if (err == NETDEV_TX_BUSY) { + /* Tell user-space to retry the send */ + xskq_cons_cancel_n(xs->tx, xsk_get_num_desc(skb)); + xsk_consume_skb(skb); + err = -EAGAIN; + goto out; + } + + /* Ignore NET_XMIT_CN as packet might have been sent */ + if (err == NET_XMIT_DROP) { + /* SKB completed but not sent */ + err = -EBUSY; + xs->skb = NULL; + goto out; + } + + sent_frame = true; + xs->skb = NULL; + } + + if (xskq_has_descs(xs->tx)) { + if (xs->skb) + xsk_drop_skb(xs->skb); + xskq_cons_release(xs->tx); + } + +out: + if (sent_frame) + if (xsk_tx_writeable(xs)) + sk->sk_write_space(sk); + + mutex_unlock(&xs->mutex); + return err; +} +#endif + static int xsk_generic_xmit(struct sock *sk) { struct xdp_sock *xs = xdp_sk(sk); @@ -631,7 +856,14 @@ static int __xsk_sendmsg(struct sock *sk) if (unlikely(!xs->tx)) return -ENOBUFS; +#ifdef CONFIG_XSK_MULTI_BUF + if (xs->zc) + return xsk_zc_xmit(xs); + else + return xs->sg ? xsk_generic_xmit_multi(sk) : xsk_generic_xmit(sk); +#else return xs->zc ? xsk_zc_xmit(xs) : xsk_generic_xmit(sk); +#endif } static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) @@ -769,6 +1001,11 @@ static int xsk_release(struct socket *sock) net = sock_net(sk); +#ifdef CONFIG_XSK_MULTI_BUF + if (xs->skb) + xsk_drop_skb(xs->skb); +#endif + mutex_lock(&net->xdp.lock); sk_del_node_init_rcu(sk); mutex_unlock(&net->xdp.lock); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 75d6fe2ae32d..419cd38d635f 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -186,6 +186,13 @@ static inline bool xp_validate_desc(struct xsk_buff_pool *pool, xp_aligned_validate_desc(pool, desc); } +#ifdef CONFIG_XSK_MULTI_BUF +static inline bool xskq_has_descs(struct xsk_queue *q) +{ + return q->cached_cons != q->cached_prod; +} +#endif + static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d, struct xsk_buff_pool *pool) @@ -282,6 +289,13 @@ static inline bool xskq_cons_is_full(struct xsk_queue *q) q->nentries; } +#ifdef CONFIG_XSK_MULTI_BUF +static inline void xskq_cons_cancel_n(struct xsk_queue *q, u32 cnt) +{ + q->cached_cons -= cnt; +} +#endif + static inline u32 xskq_cons_present_entries(struct xsk_queue *q) { /* No barriers needed since data is not accessed */ -- 2.34.1

2 1

[PATCH OLK-6.6] sched: fix warning in sched_setaffinity
by Zicheng Qu 06 Jan '25

06 Jan '25

From: Josh Don <joshdon(a)google.com> mainline inclusion from mainline-6.13-rc3 commit 70ee7947a29029736a1a06c73a48ff37674a851b category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBD13G Reference: https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/commit/?id=70ee… -------------------------------- Commit 8f9ea86fdf99b added some logic to sched_setaffinity that included a WARN when a per-task affinity assignment races with a cpuset update. Specifically, we can have a race where a cpuset update results in the task affinity no longer being a subset of the cpuset. That's fine; we have a fallback to instead use the cpuset mask. However, we have a WARN set up that will trigger if the cpuset mask has no overlap at all with the requested task affinity. This shouldn't be a warning condition; its trivial to create this condition. Reproduced the warning by the following setup: - $PID inside a cpuset cgroup - another thread repeatedly switching the cpuset cpus from 1-2 to just 1 - another thread repeatedly setting the $PID affinity (via taskset) to 2 Fixes: 8f9ea86fdf99b ("sched: Always preserve the user requested cpumask") Signed-off-by: Josh Don <joshdon(a)google.com> Acked-and-tested-by: Vincent Guittot <vincent.guittot(a)linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Acked-by: Waiman Long <longman(a)redhat.com> Tested-by: Madadi Vineeth Reddy <vineethr(a)linux.ibm.com> Link: https://lkml.kernel.org/r/20241111182738.1832953-1-joshdon@google.com iConflicts: kernel/sched/core.c kernel/sched/syscalls.c [The linux stable 6.6 lacks this commit 70ee7947a290 ("sched: fix warning in sched_setaffinity"), so pick from linux mainline, this function "__sched_setaffinity" has been moved from core to syscall in mainline.] Signed-off-by: Zicheng Qu <quzicheng(a)huawei.com> --- kernel/sched/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7a9aff1dbb3c..5569c89bbaf3 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8415,7 +8415,7 @@ __sched_setaffinity(struct task_struct *p, struct affinity_context *ctx) bool empty = !cpumask_and(new_mask, new_mask, ctx->user_mask); - if (WARN_ON_ONCE(empty)) + if (empty) cpumask_copy(new_mask, cpus_allowed); } __set_cpus_allowed_ptr(p, ctx); -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] firmware: arm_scpi: Check the DVFS OPP count returned by the firmware
by Yi Yang 06 Jan '25

06 Jan '25

From: Luo Qiu <luoqiu(a)kylinsec.com.cn> stable inclusion from stable-v4.19.325 commit 12e2c520a0a4202575e4a45ea41f06a8e9aa3417 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBDHGL CVE: CVE-2024-53157 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 109aa654f85c5141e813b2cd1bd36d90be678407 ] Fix a kernel crash with the below call trace when the SCPI firmware returns OPP count of zero. dvfs_info.opp_count may be zero on some platforms during the reboot test, and the kernel will crash after dereferencing the pointer to kcalloc(info->count, sizeof(*opp), GFP_KERNEL). | Unable to handle kernel NULL pointer dereference at virtual address 0000000000000028 | Mem abort info: | ESR = 0x96000004 | Exception class = DABT (current EL), IL = 32 bits | SET = 0, FnV = 0 | EA = 0, S1PTW = 0 | Data abort info: | ISV = 0, ISS = 0x00000004 | CM = 0, WnR = 0 | user pgtable: 4k pages, 48-bit VAs, pgdp = 00000000faefa08c | [0000000000000028] pgd=0000000000000000 | Internal error: Oops: 96000004 [#1] SMP | scpi-hwmon: probe of PHYT000D:00 failed with error -110 | Process systemd-udevd (pid: 1701, stack limit = 0x00000000aaede86c) | CPU: 2 PID: 1701 Comm: systemd-udevd Not tainted 4.19.90+ #1 | Hardware name: PHYTIUM LTD Phytium FT2000/4/Phytium FT2000/4, BIOS | pstate: 60000005 (nZCv daif -PAN -UAO) | pc : scpi_dvfs_recalc_rate+0x40/0x58 [clk_scpi] | lr : clk_register+0x438/0x720 | Call trace: | scpi_dvfs_recalc_rate+0x40/0x58 [clk_scpi] | devm_clk_hw_register+0x50/0xa0 | scpi_clk_ops_init.isra.2+0xa0/0x138 [clk_scpi] | scpi_clocks_probe+0x528/0x70c [clk_scpi] | platform_drv_probe+0x58/0xa8 | really_probe+0x260/0x3d0 | driver_probe_device+0x12c/0x148 | device_driver_attach+0x74/0x98 | __driver_attach+0xb4/0xe8 | bus_for_each_dev+0x88/0xe0 | driver_attach+0x30/0x40 | bus_add_driver+0x178/0x2b0 | driver_register+0x64/0x118 | __platform_driver_register+0x54/0x60 | scpi_clocks_driver_init+0x24/0x1000 [clk_scpi] | do_one_initcall+0x54/0x220 | do_init_module+0x54/0x1c8 | load_module+0x14a4/0x1668 | __se_sys_finit_module+0xf8/0x110 | __arm64_sys_finit_module+0x24/0x30 | el0_svc_common+0x78/0x170 | el0_svc_handler+0x38/0x78 | el0_svc+0x8/0x340 | Code: 937d7c00 a94153f3 a8c27bfd f9400421 (b8606820) | ---[ end trace 06feb22469d89fa8 ]--- | Kernel panic - not syncing: Fatal exception | SMP: stopping secondary CPUs | Kernel Offset: disabled | CPU features: 0x10,a0002008 | Memory Limit: none Fixes: 8cb7cf56c9fe ("firmware: add support for ARM System Control and Power Interface(SCPI) protocol") Signed-off-by: Luo Qiu <luoqiu(a)kylinsec.com.cn> Message-Id: <55A2F7A784391686+20241101032115.275977-1-luoqiu(a)kylinsec.com.cn> Signed-off-by: Sudeep Holla <sudeep.holla(a)arm.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yi Yang <yiyang13(a)huawei.com> --- drivers/firmware/arm_scpi.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/firmware/arm_scpi.c b/drivers/firmware/arm_scpi.c index baa7280eccb3..e3fff7b29045 100644 --- a/drivers/firmware/arm_scpi.c +++ b/drivers/firmware/arm_scpi.c @@ -638,6 +638,9 @@ static struct scpi_dvfs_info *scpi_dvfs_get_info(u8 domain) if (ret) return ERR_PTR(ret); + if (!buf.opp_count) + return ERR_PTR(-ENOENT); + info = kmalloc(sizeof(*info), GFP_KERNEL); if (!info) return ERR_PTR(-ENOMEM); -- 2.25.1

2 1

[PATCH OLK-5.10] firmware: arm_scpi: Check the DVFS OPP count returned by the firmware
by Yi Yang 06 Jan '25

06 Jan '25

From: Luo Qiu <luoqiu(a)kylinsec.com.cn> stable inclusion from stable-v5.10.231 commit 380c0e1d96f3b522f3170c18ee5e0f1a28fec5d6 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBDHGL CVE: CVE-2024-53157 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 109aa654f85c5141e813b2cd1bd36d90be678407 ] Fix a kernel crash with the below call trace when the SCPI firmware returns OPP count of zero. dvfs_info.opp_count may be zero on some platforms during the reboot test, and the kernel will crash after dereferencing the pointer to kcalloc(info->count, sizeof(*opp), GFP_KERNEL). | Unable to handle kernel NULL pointer dereference at virtual address 0000000000000028 | Mem abort info: | ESR = 0x96000004 | Exception class = DABT (current EL), IL = 32 bits | SET = 0, FnV = 0 | EA = 0, S1PTW = 0 | Data abort info: | ISV = 0, ISS = 0x00000004 | CM = 0, WnR = 0 | user pgtable: 4k pages, 48-bit VAs, pgdp = 00000000faefa08c | [0000000000000028] pgd=0000000000000000 | Internal error: Oops: 96000004 [#1] SMP | scpi-hwmon: probe of PHYT000D:00 failed with error -110 | Process systemd-udevd (pid: 1701, stack limit = 0x00000000aaede86c) | CPU: 2 PID: 1701 Comm: systemd-udevd Not tainted 4.19.90+ #1 | Hardware name: PHYTIUM LTD Phytium FT2000/4/Phytium FT2000/4, BIOS | pstate: 60000005 (nZCv daif -PAN -UAO) | pc : scpi_dvfs_recalc_rate+0x40/0x58 [clk_scpi] | lr : clk_register+0x438/0x720 | Call trace: | scpi_dvfs_recalc_rate+0x40/0x58 [clk_scpi] | devm_clk_hw_register+0x50/0xa0 | scpi_clk_ops_init.isra.2+0xa0/0x138 [clk_scpi] | scpi_clocks_probe+0x528/0x70c [clk_scpi] | platform_drv_probe+0x58/0xa8 | really_probe+0x260/0x3d0 | driver_probe_device+0x12c/0x148 | device_driver_attach+0x74/0x98 | __driver_attach+0xb4/0xe8 | bus_for_each_dev+0x88/0xe0 | driver_attach+0x30/0x40 | bus_add_driver+0x178/0x2b0 | driver_register+0x64/0x118 | __platform_driver_register+0x54/0x60 | scpi_clocks_driver_init+0x24/0x1000 [clk_scpi] | do_one_initcall+0x54/0x220 | do_init_module+0x54/0x1c8 | load_module+0x14a4/0x1668 | __se_sys_finit_module+0xf8/0x110 | __arm64_sys_finit_module+0x24/0x30 | el0_svc_common+0x78/0x170 | el0_svc_handler+0x38/0x78 | el0_svc+0x8/0x340 | Code: 937d7c00 a94153f3 a8c27bfd f9400421 (b8606820) | ---[ end trace 06feb22469d89fa8 ]--- | Kernel panic - not syncing: Fatal exception | SMP: stopping secondary CPUs | Kernel Offset: disabled | CPU features: 0x10,a0002008 | Memory Limit: none Fixes: 8cb7cf56c9fe ("firmware: add support for ARM System Control and Power Interface(SCPI) protocol") Signed-off-by: Luo Qiu <luoqiu(a)kylinsec.com.cn> Message-Id: <55A2F7A784391686+20241101032115.275977-1-luoqiu(a)kylinsec.com.cn> Signed-off-by: Sudeep Holla <sudeep.holla(a)arm.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yi Yang <yiyang13(a)huawei.com> --- drivers/firmware/arm_scpi.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/firmware/arm_scpi.c b/drivers/firmware/arm_scpi.c index 36391cb5130e..3a1d77b882f7 100644 --- a/drivers/firmware/arm_scpi.c +++ b/drivers/firmware/arm_scpi.c @@ -627,6 +627,9 @@ static struct scpi_dvfs_info *scpi_dvfs_get_info(u8 domain) if (ret) return ERR_PTR(ret); + if (!buf.opp_count) + return ERR_PTR(-ENOENT); + info = kmalloc(sizeof(*info), GFP_KERNEL); if (!info) return ERR_PTR(-ENOMEM); -- 2.25.1

2 1

[PATCH OLK-6.6] firmware: arm_scpi: Check the DVFS OPP count returned by the firmware
by Yi Yang 06 Jan '25

06 Jan '25

From: Luo Qiu <luoqiu(a)kylinsec.com.cn> stable inclusion from stable-v6.6.64 commit 025067eeb945aa17c7dd483a63960125b7efb577 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBDHGL CVE: CVE-2024-53157 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 109aa654f85c5141e813b2cd1bd36d90be678407 ] Fix a kernel crash with the below call trace when the SCPI firmware returns OPP count of zero. dvfs_info.opp_count may be zero on some platforms during the reboot test, and the kernel will crash after dereferencing the pointer to kcalloc(info->count, sizeof(*opp), GFP_KERNEL). | Unable to handle kernel NULL pointer dereference at virtual address 0000000000000028 | Mem abort info: | ESR = 0x96000004 | Exception class = DABT (current EL), IL = 32 bits | SET = 0, FnV = 0 | EA = 0, S1PTW = 0 | Data abort info: | ISV = 0, ISS = 0x00000004 | CM = 0, WnR = 0 | user pgtable: 4k pages, 48-bit VAs, pgdp = 00000000faefa08c | [0000000000000028] pgd=0000000000000000 | Internal error: Oops: 96000004 [#1] SMP | scpi-hwmon: probe of PHYT000D:00 failed with error -110 | Process systemd-udevd (pid: 1701, stack limit = 0x00000000aaede86c) | CPU: 2 PID: 1701 Comm: systemd-udevd Not tainted 4.19.90+ #1 | Hardware name: PHYTIUM LTD Phytium FT2000/4/Phytium FT2000/4, BIOS | pstate: 60000005 (nZCv daif -PAN -UAO) | pc : scpi_dvfs_recalc_rate+0x40/0x58 [clk_scpi] | lr : clk_register+0x438/0x720 | Call trace: | scpi_dvfs_recalc_rate+0x40/0x58 [clk_scpi] | devm_clk_hw_register+0x50/0xa0 | scpi_clk_ops_init.isra.2+0xa0/0x138 [clk_scpi] | scpi_clocks_probe+0x528/0x70c [clk_scpi] | platform_drv_probe+0x58/0xa8 | really_probe+0x260/0x3d0 | driver_probe_device+0x12c/0x148 | device_driver_attach+0x74/0x98 | __driver_attach+0xb4/0xe8 | bus_for_each_dev+0x88/0xe0 | driver_attach+0x30/0x40 | bus_add_driver+0x178/0x2b0 | driver_register+0x64/0x118 | __platform_driver_register+0x54/0x60 | scpi_clocks_driver_init+0x24/0x1000 [clk_scpi] | do_one_initcall+0x54/0x220 | do_init_module+0x54/0x1c8 | load_module+0x14a4/0x1668 | __se_sys_finit_module+0xf8/0x110 | __arm64_sys_finit_module+0x24/0x30 | el0_svc_common+0x78/0x170 | el0_svc_handler+0x38/0x78 | el0_svc+0x8/0x340 | Code: 937d7c00 a94153f3 a8c27bfd f9400421 (b8606820) | ---[ end trace 06feb22469d89fa8 ]--- | Kernel panic - not syncing: Fatal exception | SMP: stopping secondary CPUs | Kernel Offset: disabled | CPU features: 0x10,a0002008 | Memory Limit: none Fixes: 8cb7cf56c9fe ("firmware: add support for ARM System Control and Power Interface(SCPI) protocol") Signed-off-by: Luo Qiu <luoqiu(a)kylinsec.com.cn> Message-Id: <55A2F7A784391686+20241101032115.275977-1-luoqiu(a)kylinsec.com.cn> Signed-off-by: Sudeep Holla <sudeep.holla(a)arm.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yi Yang <yiyang13(a)huawei.com> --- drivers/firmware/arm_scpi.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/firmware/arm_scpi.c b/drivers/firmware/arm_scpi.c index 435d0e2658a4..3de25e9d18ef 100644 --- a/drivers/firmware/arm_scpi.c +++ b/drivers/firmware/arm_scpi.c @@ -627,6 +627,9 @@ static struct scpi_dvfs_info *scpi_dvfs_get_info(u8 domain) if (ret) return ERR_PTR(ret); + if (!buf.opp_count) + return ERR_PTR(-ENOENT); + info = kmalloc(sizeof(*info), GFP_KERNEL); if (!info) return ERR_PTR(-ENOMEM); -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS] ALSA: us122l: Use snd_card_free_when_closed() at disconnection
by Li Nan 06 Jan '25

06 Jan '25

From: Takashi Iwai <tiwai(a)suse.de> stable inclusion from stable-v4.19.325 commit 020cbc4d7414f0962004213e2b7bc5cc607e9ec7 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAG2 CVE: CVE-2024-56532 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit b7df09bb348016943f56b09dcaafe221e3f73947 ] The USB disconnect callback is supposed to be short and not too-long waiting. OTOH, the current code uses snd_card_free() at disconnection, but this waits for the close of all used fds, hence it can take long. It eventually blocks the upper layer USB ioctls, which may trigger a soft lockup. An easy workaround is to replace snd_card_free() with snd_card_free_when_closed(). This variant returns immediately while the release of resources is done asynchronously by the card device release at the last close. The loop of us122l->mmap_count check is dropped as well. The check is useless for the asynchronous operation with *_when_closed(). Fixes: 030a07e44129 ("ALSA: Add USB US122L driver") Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Link: https://patch.msgid.link/20241113111042.15058-3-tiwai@suse.de Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Li Nan <linan122(a)huawei.com> --- sound/usb/usx2y/us122l.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/sound/usb/usx2y/us122l.c b/sound/usb/usx2y/us122l.c index 8082f7b077f1..eac2e4d0e7d9 100644 --- a/sound/usb/usx2y/us122l.c +++ b/sound/usb/usx2y/us122l.c @@ -649,10 +649,7 @@ static void snd_us122l_disconnect(struct usb_interface *intf) usb_put_intf(usb_ifnum_to_if(us122l->dev, 1)); usb_put_dev(us122l->dev); - while (atomic_read(&us122l->mmap_count)) - msleep(500); - - snd_card_free(card); + snd_card_free_when_closed(card); } static int snd_us122l_suspend(struct usb_interface *intf, pm_message_t message) -- 2.39.2

2 1

[PATCH OLK-5.10] iio: adc: ad7923: Fix buffer overflow for tx_buf and ring_xfer
by Yi Yang 06 Jan '25

06 Jan '25

From: Nuno Sa <nuno.sa(a)analog.com> mainline inclusion from mainline-v6.13-rc1 commit 3a4187ec454e19903fd15f6e1825a4b84e59a4cd category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAMO CVE: CVE-2024-56557 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- The AD7923 was updated to support devices with 8 channels, but the size of tx_buf and ring_xfer was not increased accordingly, leading to a potential buffer overflow in ad7923_update_scan_mode(). Fixes: 851644a60d20 ("iio: adc: ad7923: Add support for the ad7908/ad7918/ad7928") Cc: stable(a)vger.kernel.org Signed-off-by: Nuno Sa <nuno.sa(a)analog.com> Signed-off-by: Zicheng Qu <quzicheng(a)huawei.com> Link: https://patch.msgid.link/20241029134637.2261336-1-quzicheng@huawei.com Signed-off-by: Jonathan Cameron <Jonathan.Cameron(a)huawei.com> Conflicts: drivers/iio/adc/ad7923.c [conflicts due to not mergered 908af45d70573 ("iio: adc: ad7923: Fix alignment for DMA safety")] Signed-off-by: Yi Yang <yiyang13(a)huawei.com> --- drivers/iio/adc/ad7923.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iio/adc/ad7923.c b/drivers/iio/adc/ad7923.c index 96eeda433ad6..b44a853a8390 100644 --- a/drivers/iio/adc/ad7923.c +++ b/drivers/iio/adc/ad7923.c @@ -47,7 +47,7 @@ struct ad7923_state { struct spi_device *spi; - struct spi_transfer ring_xfer[5]; + struct spi_transfer ring_xfer[9]; struct spi_transfer scan_single_xfer[2]; struct spi_message ring_msg; struct spi_message scan_single_msg; @@ -63,7 +63,7 @@ struct ad7923_state { * Length = 8 channels + 4 extra for 8 byte timestamp */ __be16 rx_buf[12] ____cacheline_aligned; - __be16 tx_buf[4]; + __be16 tx_buf[8]; }; struct ad7923_chip_info { -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS 1/1] 9p/xen: fix release of IRQ
by Ze Zuo 06 Jan '25

06 Jan '25

From: Alex Zenla <alex(a)edera.dev> stable inclusion from stable-v4.19.325 commit 692eb06703afc3e24d889d77e94a0e20229f6a4a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEDPA CVE: CVE-2024-56704 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit e43c608f40c065b30964f0a806348062991b802d ] Kernel logs indicate an IRQ was double-freed. Pass correct device ID during IRQ release. Fixes: 71ebd71921e45 ("xen/9pfs: connect to the backend") Signed-off-by: Alex Zenla <alex(a)edera.dev> Signed-off-by: Alexander Merritt <alexander(a)edera.dev> Signed-off-by: Ariadne Conill <ariadne(a)ariadne.space> Reviewed-by: Juergen Gross <jgross(a)suse.com> Message-ID: <20241121225100.5736-1-alexander(a)edera.dev> [Dominique: remove confusing variable reset to 0] Signed-off-by: Dominique Martinet <asmadeus(a)codewreck.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> (cherry picked from commit 692eb06703afc3e24d889d77e94a0e20229f6a4a) Signed-off-by: Ze Zuo <zuoze1(a)huawei.com> --- net/9p/trans_xen.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index 8e158f09cba8..4096cfc7efc6 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -297,7 +297,7 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv) if (!priv->rings[i].intf) break; if (priv->rings[i].irq > 0) - unbind_from_irqhandler(priv->rings[i].irq, priv->dev); + unbind_from_irqhandler(priv->rings[i].irq, ring); if (priv->rings[i].data.in) { for (j = 0; j < (1 << XEN_9PFS_RING_ORDER); j++) { grant_ref_t ref; -- 2.25.1

2 1

[PATCH OLK-6.6] iio: adc: ad7923: Fix buffer overflow for tx_buf and ring_xfer
by Yi Yang 06 Jan '25

06 Jan '25

From: Nuno Sa <nuno.sa(a)analog.com> stable inclusion from stable-v6.6.64 commit e5cac32721997cb8bcb208a29f4598b3faf46338 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAMO CVE: CVE-2024-56557 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 3a4187ec454e19903fd15f6e1825a4b84e59a4cd upstream. The AD7923 was updated to support devices with 8 channels, but the size of tx_buf and ring_xfer was not increased accordingly, leading to a potential buffer overflow in ad7923_update_scan_mode(). Fixes: 851644a60d20 ("iio: adc: ad7923: Add support for the ad7908/ad7918/ad7928") Cc: stable(a)vger.kernel.org Signed-off-by: Nuno Sa <nuno.sa(a)analog.com> Signed-off-by: Zicheng Qu <quzicheng(a)huawei.com> Link: https://patch.msgid.link/20241029134637.2261336-1-quzicheng@huawei.com Signed-off-by: Jonathan Cameron <Jonathan.Cameron(a)huawei.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yi Yang <yiyang13(a)huawei.com> --- drivers/iio/adc/ad7923.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iio/adc/ad7923.c b/drivers/iio/adc/ad7923.c index 9d6bf6d0927a..709ce2a50097 100644 --- a/drivers/iio/adc/ad7923.c +++ b/drivers/iio/adc/ad7923.c @@ -48,7 +48,7 @@ struct ad7923_state { struct spi_device *spi; - struct spi_transfer ring_xfer[5]; + struct spi_transfer ring_xfer[9]; struct spi_transfer scan_single_xfer[2]; struct spi_message ring_msg; struct spi_message scan_single_msg; @@ -64,7 +64,7 @@ struct ad7923_state { * Length = 8 channels + 4 extra for 8 byte timestamp */ __be16 rx_buf[12] __aligned(IIO_DMA_MINALIGN); - __be16 tx_buf[4]; + __be16 tx_buf[8]; }; struct ad7923_chip_info { -- 2.25.1

2 1

[PATCH OLK-6.6] vfio/mlx5: Fix an unwind issue in mlx5vf_add_migration_pages()
by Yi Yang 06 Jan '25

06 Jan '25

From: Yishai Hadas <yishaih(a)nvidia.com> mainline inclusion from mainline-v6.13-rc1 commit 22e87bf3f77c18f5982c19ffe2732ef0c7a25f16 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEGF7 CVE: CVE-2024-56742 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Fix an unwind issue in mlx5vf_add_migration_pages(). If a set of pages is allocated but fails to be added to the SG table, they need to be freed to prevent a memory leak. Any pages successfully added to the SG table will be freed as part of mlx5vf_free_data_buffer(). Fixes: 6fadb021266d ("vfio/mlx5: Implement vfio_pci driver for mlx5 devices") Signed-off-by: Yishai Hadas <yishaih(a)nvidia.com> Reviewed-by: Jason Gunthorpe <jgg(a)nvidia.com> Link: https://lore.kernel.org/r/20241114095318.16556-2-yishaih@nvidia.com Signed-off-by: Alex Williamson <alex.williamson(a)redhat.com> Conflicts: drivers/vfio/pci/mlx5/main.c drivers/vfio/pci/mlx5/cmd.c [conflicts due to not mergered 821b8f6bf8489 ("vfio/mlx5: Enforce PRE_COPY support")] Signed-off-by: Yi Yang <yiyang13(a)huawei.com> --- drivers/vfio/pci/mlx5/main.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c index 5cf2b491d15a..54bb74433ec1 100644 --- a/drivers/vfio/pci/mlx5/main.c +++ b/drivers/vfio/pci/mlx5/main.c @@ -71,6 +71,7 @@ int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf, unsigned long filled; unsigned int to_fill; int ret; + int i; to_fill = min_t(unsigned int, npages, PAGE_SIZE / sizeof(*page_list)); page_list = kvzalloc(to_fill * sizeof(*page_list), GFP_KERNEL_ACCOUNT); @@ -91,7 +92,7 @@ int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf, GFP_KERNEL_ACCOUNT); if (ret) - goto err; + goto err_append; buf->allocated_length += filled * PAGE_SIZE; /* clean input for another bulk allocation */ memset(page_list, 0, filled * sizeof(*page_list)); @@ -102,6 +103,9 @@ int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf, kvfree(page_list); return 0; +err_append: + for (i = filled - 1; i >= 0; i--) + __free_page(page_list[i]); err: kvfree(page_list); return ret; -- 2.25.1

2 1

[PATCH OLK-6.6] wifi: ath10k: avoid NULL pointer error during sdio remove
by Liu Mingrui 06 Jan '25

06 Jan '25

From: Kang Yang <quic_kangyang(a)quicinc.com> mainline inclusion from mainline-v6.13-rc1 commit 95c38953cb1ecf40399a676a1f85dfe2b5780a9a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAPA CVE: CVE-2024-56599 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- When running 'rmmod ath10k', ath10k_sdio_remove() will free sdio workqueue by destroy_workqueue(). But if CONFIG_INIT_ON_FREE_DEFAULT_ON is set to yes, kernel panic will happen: Call trace: destroy_workqueue+0x1c/0x258 ath10k_sdio_remove+0x84/0x94 sdio_bus_remove+0x50/0x16c device_release_driver_internal+0x188/0x25c device_driver_detach+0x20/0x2c This is because during 'rmmod ath10k', ath10k_sdio_remove() will call ath10k_core_destroy() before destroy_workqueue(). wiphy_dev_release() will finally be called in ath10k_core_destroy(). This function will free struct cfg80211_registered_device *rdev and all its members, including wiphy, dev and the pointer of sdio workqueue. Then the pointer of sdio workqueue will be set to NULL due to CONFIG_INIT_ON_FREE_DEFAULT_ON. After device release, destroy_workqueue() will use NULL pointer then the kernel panic happen. Call trace: ath10k_sdio_remove ->ath10k_core_unregister …… ->ath10k_core_stop ->ath10k_hif_stop ->ath10k_sdio_irq_disable ->ath10k_hif_power_down ->del_timer_sync(&ar_sdio->sleep_timer) ->ath10k_core_destroy ->ath10k_mac_destroy ->ieee80211_free_hw ->wiphy_free …… ->wiphy_dev_release ->destroy_workqueue Need to call destroy_workqueue() before ath10k_core_destroy(), free the work queue buffer first and then free pointer of work queue by ath10k_core_destroy(). This order matches the error path order in ath10k_sdio_probe(). No work will be queued on sdio workqueue between it is destroyed and ath10k_core_destroy() is called. Based on the call_stack above, the reason is: Only ath10k_sdio_sleep_timer_handler(), ath10k_sdio_hif_tx_sg() and ath10k_sdio_irq_disable() will queue work on sdio workqueue. Sleep timer will be deleted before ath10k_core_destroy() in ath10k_hif_power_down(). ath10k_sdio_irq_disable() only be called in ath10k_hif_stop(). ath10k_core_unregister() will call ath10k_hif_power_down() to stop hif bus, so ath10k_sdio_hif_tx_sg() won't be called anymore. Tested-on: QCA6174 hw3.2 SDIO WLAN.RMH.4.4.1-00189 Signed-off-by: Kang Yang <quic_kangyang(a)quicinc.com> Tested-by: David Ruth <druth(a)chromium.org> Reviewed-by: David Ruth <druth(a)chromium.org> Link: https://patch.msgid.link/20241008022246.1010-1-quic_kangyang@quicinc.com Signed-off-by: Jeff Johnson <quic_jjohnson(a)quicinc.com> Conflicts: drivers/net/wireless/ath/ath10k/sdio.c Signed-off-by: Liu Mingrui <liumingrui(a)huawei.com> --- drivers/net/wireless/ath/ath10k/sdio.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c index 56fbcfb80bf8..850d999615a2 100644 --- a/drivers/net/wireless/ath/ath10k/sdio.c +++ b/drivers/net/wireless/ath/ath10k/sdio.c @@ -3,6 +3,7 @@ * Copyright (c) 2004-2011 Atheros Communications Inc. * Copyright (c) 2011-2012,2017 Qualcomm Atheros, Inc. * Copyright (c) 2016-2017 Erik Stromdahl <erik.stromdahl(a)gmail.com> + * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved. */ #include <linux/module.h> @@ -2647,9 +2648,9 @@ static void ath10k_sdio_remove(struct sdio_func *func) netif_napi_del(&ar->napi); - ath10k_core_destroy(ar); - destroy_workqueue(ar_sdio->workqueue); + + ath10k_core_destroy(ar); } static const struct sdio_device_id ath10k_sdio_devices[] = { -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1 0/1] backport mainline bugfix patch
by Lin Yujun 06 Jan '25

06 Jan '25

Jinjie Ruan (1): [Backport] genirq/msi: Fix off-by-one error in msi_domain_alloc() kernel/irq/msi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) -- 2.34.1

2 2

[PATCH OLK-5.10] usb: gadget: u_serial: Fix the issue that gs_start_io crashed due to accessing null pointer
by Liu Mingrui 06 Jan '25

06 Jan '25

From: Lianqin Hu <hulianqin(a)vivo.com> stable inclusion from stable-v5.10.232 commit 28b3c03a6790de1f6f2683919ad657840f0f0f58 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAO8 CVE: CVE-2024-56670 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 4cfbca86f6a8b801f3254e0e3c8f2b1d2d64be2b upstream. Considering that in some extreme cases, when u_serial driver is accessed by multiple threads, Thread A is executing the open operation and calling the gs_open, Thread B is executing the disconnect operation and calling the gserial_disconnect function,The port->port_usb pointer will be set to NULL. E.g. Thread A Thread B gs_open() gadget_unbind_driver() gs_start_io() composite_disconnect() gs_start_rx() gserial_disconnect() ... ... spin_unlock(&port->port_lock) status = usb_ep_queue() spin_lock(&port->port_lock) spin_lock(&port->port_lock) port->port_usb = NULL gs_free_requests(port->port_usb->in) spin_unlock(&port->port_lock) Crash This causes thread A to access a null pointer (port->port_usb is null) when calling the gs_free_requests function, causing a crash. If port_usb is NULL, the release request will be skipped as it will be done by gserial_disconnect. So add a null pointer check to gs_start_io before attempting to access the value of the pointer port->port_usb. Call trace: gs_start_io+0x164/0x25c gs_open+0x108/0x13c tty_open+0x314/0x638 chrdev_open+0x1b8/0x258 do_dentry_open+0x2c4/0x700 vfs_open+0x2c/0x3c path_openat+0xa64/0xc60 do_filp_open+0xb8/0x164 do_sys_openat2+0x84/0xf0 __arm64_sys_openat+0x70/0x9c invoke_syscall+0x58/0x114 el0_svc_common+0x80/0xe0 do_el0_svc+0x1c/0x28 el0_svc+0x38/0x68 Fixes: c1dca562be8a ("usb gadget: split out serial core") Cc: stable(a)vger.kernel.org Suggested-by: Prashanth K <quic_prashk(a)quicinc.com> Signed-off-by: Lianqin Hu <hulianqin(a)vivo.com> Acked-by: Prashanth K <quic_prashk(a)quicinc.com> Link: https://lore.kernel.org/r/TYUPR06MB62178DC3473F9E1A537DCD02D2362@TYUPR06MB6… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Liu Mingrui <liumingrui(a)huawei.com> --- drivers/usb/gadget/function/u_serial.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c index 2caccbb6e014..b3cb3bef06d2 100644 --- a/drivers/usb/gadget/function/u_serial.c +++ b/drivers/usb/gadget/function/u_serial.c @@ -569,9 +569,12 @@ static int gs_start_io(struct gs_port *port) * we didn't in gs_start_tx() */ tty_wakeup(port->port.tty); } else { - gs_free_requests(ep, head, &port->read_allocated); - gs_free_requests(port->port_usb->in, &port->write_pool, - &port->write_allocated); + /* Free reqs only if we are still connected */ + if (port->port_usb) { + gs_free_requests(ep, head, &port->read_allocated); + gs_free_requests(port->port_usb->in, &port->write_pool, + &port->write_allocated); + } status = -EIO; } -- 2.25.1

2 1

[PATCH OLK-5.10 0/1] backport mainline bugfix patch
by Lin Yujun 06 Jan '25

06 Jan '25

Jinjie Ruan (1): [Backport] genirq/msi: Fix off-by-one error in msi_domain_alloc() kernel/irq/msi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) -- 2.34.1

2 2

[PATCH OLK-6.6] RDMA/mlx5: Move events notifier registration to be after device registration
by Tengda Wu 06 Jan '25

06 Jan '25

From: Patrisious Haddad <phaddad(a)nvidia.com> stable inclusion from stable-v6.6.64 commit 921fcf2971a1e8d3b904ba2c2905b96f4ec3d4ad category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEADY CVE: CVE-2024-53224 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit ede132a5cf559f3ab35a4c28bac4f4a6c20334d8 ] Move pkey change work initialization and cleanup from device resources stage to notifier stage, since this is the stage which handles this work events. Fix a race between the device deregistration and pkey change work by moving MLX5_IB_STAGE_DEVICE_NOTIFIER to be after MLX5_IB_STAGE_IB_REG in order to ensure that the notifier is deregistered before the device during cleanup. Which ensures there are no works that are being executed after the device has already unregistered which can cause the panic below. BUG: kernel NULL pointer dereference, address: 0000000000000000 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 1 PID: 630071 Comm: kworker/1:2 Kdump: loaded Tainted: G W OE --------- --- 5.14.0-162.6.1.el9_1.x86_64 #1 Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090008 02/27/2023 Workqueue: events pkey_change_handler [mlx5_ib] RIP: 0010:setup_qp+0x38/0x1f0 [mlx5_ib] Code: ee 41 54 45 31 e4 55 89 f5 53 48 89 fb 48 83 ec 20 8b 77 08 65 48 8b 04 25 28 00 00 00 48 89 44 24 18 48 8b 07 48 8d 4c 24 16 <4c> 8b 38 49 8b 87 80 0b 00 00 4c 89 ff 48 8b 80 08 05 00 00 8b 40 RSP: 0018:ffffbcc54068be20 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff954054494128 RCX: ffffbcc54068be36 RDX: ffff954004934000 RSI: 0000000000000001 RDI: ffff954054494128 RBP: 0000000000000023 R08: ffff954001be2c20 R09: 0000000000000001 R10: ffff954001be2c20 R11: ffff9540260133c0 R12: 0000000000000000 R13: 0000000000000023 R14: 0000000000000000 R15: ffff9540ffcb0905 FS: 0000000000000000(0000) GS:ffff9540ffc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000010625c001 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: mlx5_ib_gsi_pkey_change+0x20/0x40 [mlx5_ib] process_one_work+0x1e8/0x3c0 worker_thread+0x50/0x3b0 ? rescuer_thread+0x380/0x380 kthread+0x149/0x170 ? set_kthread_struct+0x50/0x50 ret_from_fork+0x22/0x30 Modules linked in: rdma_ucm(OE) rdma_cm(OE) iw_cm(OE) ib_ipoib(OE) ib_cm(OE) ib_umad(OE) mlx5_ib(OE) mlx5_fwctl(OE) fwctl(OE) ib_uverbs(OE) mlx5_core(OE) mlxdevm(OE) ib_core(OE) mlx_compat(OE) psample mlxfw(OE) tls knem(OE) netconsole nfsv3 nfs_acl nfs lockd grace fscache netfs qrtr rfkill sunrpc intel_rapl_msr intel_rapl_common rapl hv_balloon hv_utils i2c_piix4 pcspkr joydev fuse ext4 mbcache jbd2 sr_mod sd_mod cdrom t10_pi sg ata_generic pci_hyperv pci_hyperv_intf hyperv_drm drm_shmem_helper drm_kms_helper hv_storvsc syscopyarea hv_netvsc sysfillrect sysimgblt hid_hyperv fb_sys_fops scsi_transport_fc hyperv_keyboard drm ata_piix crct10dif_pclmul crc32_pclmul crc32c_intel libata ghash_clmulni_intel hv_vmbus serio_raw [last unloaded: ib_core] CR2: 0000000000000000 ---[ end trace f6f8be4eae12f7bc ]--- Fixes: 7722f47e71e5 ("IB/mlx5: Create GSI transmission QPs when P_Key table is changed") Signed-off-by: Patrisious Haddad <phaddad(a)nvidia.com> Reviewed-by: Michael Guralnik <michaelgur(a)nvidia.com> Link: https://patch.msgid.link/d271ceeff0c08431b3cbbbb3e2d416f09b6d1621.173149694… Signed-off-by: Leon Romanovsky <leon(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Pu Lehui <pulehui(a)huawei.com> --- drivers/infiniband/hw/mlx5/main.c | 40 +++++++++++++--------------- drivers/infiniband/hw/mlx5/mlx5_ib.h | 2 +- 2 files changed, 20 insertions(+), 22 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index bc38af6cda6e..c510484e024b 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -2899,7 +2899,6 @@ int mlx5_ib_dev_res_srq_init(struct mlx5_ib_dev *dev) static int mlx5_ib_dev_res_init(struct mlx5_ib_dev *dev) { struct mlx5_ib_resources *devr = &dev->devr; - int port; int ret; if (!MLX5_CAP_GEN(dev->mdev, xrc)) @@ -2915,10 +2914,6 @@ static int mlx5_ib_dev_res_init(struct mlx5_ib_dev *dev) return ret; } - for (port = 0; port < ARRAY_SIZE(devr->ports); ++port) - INIT_WORK(&devr->ports[port].pkey_change_work, - pkey_change_handler); - mutex_init(&devr->cq_lock); mutex_init(&devr->srq_lock); @@ -2928,16 +2923,6 @@ static int mlx5_ib_dev_res_init(struct mlx5_ib_dev *dev) static void mlx5_ib_dev_res_cleanup(struct mlx5_ib_dev *dev) { struct mlx5_ib_resources *devr = &dev->devr; - int port; - - /* - * Make sure no change P_Key work items are still executing. - * - * At this stage, the mlx5_ib_event should be unregistered - * and it ensures that no new works are added. - */ - for (port = 0; port < ARRAY_SIZE(devr->ports); ++port) - cancel_work_sync(&devr->ports[port].pkey_change_work); /* After s0/s1 init, they are not unset during the device lifetime. */ if (devr->s1) { @@ -4201,6 +4186,13 @@ static void mlx5_ib_stage_delay_drop_cleanup(struct mlx5_ib_dev *dev) static int mlx5_ib_stage_dev_notifier_init(struct mlx5_ib_dev *dev) { + struct mlx5_ib_resources *devr = &dev->devr; + int port; + + for (port = 0; port < ARRAY_SIZE(devr->ports); ++port) + INIT_WORK(&devr->ports[port].pkey_change_work, + pkey_change_handler); + dev->mdev_events.notifier_call = mlx5_ib_event; mlx5_notifier_register(dev->mdev, &dev->mdev_events); @@ -4211,8 +4203,14 @@ static int mlx5_ib_stage_dev_notifier_init(struct mlx5_ib_dev *dev) static void mlx5_ib_stage_dev_notifier_cleanup(struct mlx5_ib_dev *dev) { + struct mlx5_ib_resources *devr = &dev->devr; + int port; + mlx5r_macsec_event_unregister(dev); mlx5_notifier_unregister(dev->mdev, &dev->mdev_events); + + for (port = 0; port < ARRAY_SIZE(devr->ports); ++port) + cancel_work_sync(&devr->ports[port].pkey_change_work); } void __mlx5_ib_remove(struct mlx5_ib_dev *dev, @@ -4286,9 +4284,6 @@ static const struct mlx5_ib_profile pf_profile = { STAGE_CREATE(MLX5_IB_STAGE_DEVICE_RESOURCES, mlx5_ib_dev_res_init, mlx5_ib_dev_res_cleanup), - STAGE_CREATE(MLX5_IB_STAGE_DEVICE_NOTIFIER, - mlx5_ib_stage_dev_notifier_init, - mlx5_ib_stage_dev_notifier_cleanup), STAGE_CREATE(MLX5_IB_STAGE_ODP, mlx5_ib_odp_init_one, mlx5_ib_odp_cleanup_one), @@ -4313,6 +4308,9 @@ static const struct mlx5_ib_profile pf_profile = { STAGE_CREATE(MLX5_IB_STAGE_IB_REG, mlx5_ib_stage_ib_reg_init, mlx5_ib_stage_ib_reg_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_DEVICE_NOTIFIER, + mlx5_ib_stage_dev_notifier_init, + mlx5_ib_stage_dev_notifier_cleanup), STAGE_CREATE(MLX5_IB_STAGE_POST_IB_REG_UMR, mlx5_ib_stage_post_ib_reg_umr_init, NULL), @@ -4349,9 +4347,6 @@ const struct mlx5_ib_profile raw_eth_profile = { STAGE_CREATE(MLX5_IB_STAGE_DEVICE_RESOURCES, mlx5_ib_dev_res_init, mlx5_ib_dev_res_cleanup), - STAGE_CREATE(MLX5_IB_STAGE_DEVICE_NOTIFIER, - mlx5_ib_stage_dev_notifier_init, - mlx5_ib_stage_dev_notifier_cleanup), STAGE_CREATE(MLX5_IB_STAGE_COUNTERS, mlx5_ib_counters_init, mlx5_ib_counters_cleanup), @@ -4373,6 +4368,9 @@ const struct mlx5_ib_profile raw_eth_profile = { STAGE_CREATE(MLX5_IB_STAGE_IB_REG, mlx5_ib_stage_ib_reg_init, mlx5_ib_stage_ib_reg_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_DEVICE_NOTIFIER, + mlx5_ib_stage_dev_notifier_init, + mlx5_ib_stage_dev_notifier_cleanup), STAGE_CREATE(MLX5_IB_STAGE_POST_IB_REG_UMR, mlx5_ib_stage_post_ib_reg_umr_init, NULL), diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 1c83d132197f..94678e5c59dd 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -954,7 +954,6 @@ enum mlx5_ib_stages { MLX5_IB_STAGE_QP, MLX5_IB_STAGE_SRQ, MLX5_IB_STAGE_DEVICE_RESOURCES, - MLX5_IB_STAGE_DEVICE_NOTIFIER, MLX5_IB_STAGE_ODP, MLX5_IB_STAGE_COUNTERS, MLX5_IB_STAGE_CONG_DEBUGFS, @@ -963,6 +962,7 @@ enum mlx5_ib_stages { MLX5_IB_STAGE_PRE_IB_REG_UMR, MLX5_IB_STAGE_WHITELIST_UID, MLX5_IB_STAGE_IB_REG, + MLX5_IB_STAGE_DEVICE_NOTIFIER, MLX5_IB_STAGE_POST_IB_REG_UMR, MLX5_IB_STAGE_DELAY_DROP, MLX5_IB_STAGE_RESTRACK, -- 2.34.1

2 1

[PATCH OLK-5.10] memcg: fix soft lockup in the OOM process
by Chen Ridong 06 Jan '25

06 Jan '25

maillist inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBE42N Reference: https://lore.kernel.org/linux-kernel/8cf29751-7c71-52ff-5492-0019ca7b0e02@g… ---------------------------------------- A soft lockup issue was found in the product with about 56,000 tasks were in the OOM cgroup, it was traversing them when the soft lockup was triggered. watchdog: BUG: soft lockup - CPU#2 stuck for 23s! [VM Thread:1503066] CPU: 2 PID: 1503066 Comm: VM Thread Kdump: loaded Tainted: G Hardware name: Huawei Cloud OpenStack Nova, BIOS RIP: 0010:console_unlock+0x343/0x540 RSP: 0000:ffffb751447db9a0 EFLAGS: 00000247 ORIG_RAX: ffffffffffffff13 RAX: 0000000000000001 RBX: 0000000000000000 RCX: 00000000ffffffff RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000247 RBP: ffffffffafc71f90 R08: 0000000000000000 R09: 0000000000000040 R10: 0000000000000080 R11: 0000000000000000 R12: ffffffffafc74bd0 R13: ffffffffaf60a220 R14: 0000000000000247 R15: 0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f2fe6ad91f0 CR3: 00000004b2076003 CR4: 0000000000360ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: vprintk_emit+0x193/0x280 printk+0x52/0x6e dump_task+0x114/0x130 mem_cgroup_scan_tasks+0x76/0x100 dump_header+0x1fe/0x210 oom_kill_process+0xd1/0x100 out_of_memory+0x125/0x570 mem_cgroup_out_of_memory+0xb5/0xd0 try_charge+0x720/0x770 mem_cgroup_try_charge+0x86/0x180 mem_cgroup_try_charge_delay+0x1c/0x40 do_anonymous_page+0xb5/0x390 handle_mm_fault+0xc4/0x1f0 This is because thousands of processes are in the OOM cgroup, it takes a long time to traverse all of them. As a result, this lead to soft lockup in the OOM process. To fix this issue, call 'cond_resched' in the 'mem_cgroup_scan_tasks' function per 1000 iterations. For global OOM, call 'touch_softlockup_watchdog' per 1000 iterations to avoid this issue. Fixes: 9cbb78bb3143 ("mm, memcg: introduce own oom handler to iterate only over its own threads") Signed-off-by: Chen Ridong <chenridong(a)huawei.com> --- mm/memcontrol.c | 7 ++++++- mm/oom_kill.c | 8 +++++++- 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3e928581ab47..f5b1322ac77e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1202,6 +1202,7 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, { struct mem_cgroup *iter; int ret = 0; + int i = 0; BUG_ON(memcg == root_mem_cgroup); @@ -1210,8 +1211,12 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, struct task_struct *task; css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it); - while (!ret && (task = css_task_iter_next(&it))) + while (!ret && (task = css_task_iter_next(&it))) { + /* Avoid potential softlockup warning */ + if ((++i & 1023) == 0) + cond_resched(); ret = fn(task, arg); + } css_task_iter_end(&it); if (ret) { mem_cgroup_iter_break(memcg, iter); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 9d595265bbf5..fe5f4f20c5c8 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -43,6 +43,7 @@ #include <linux/kthread.h> #include <linux/init.h> #include <linux/mmu_notifier.h> +#include <linux/nmi.h> #include <asm/tlb.h> #include "internal.h" @@ -479,10 +480,15 @@ static void dump_tasks(struct oom_control *oc) memcg_print_bad_task(oc); } else { struct task_struct *p; + int i = 0; rcu_read_lock(); - for_each_process(p) + for_each_process(p) { + /* Avoid potential softlockup warning */ + if ((++i & 1023) == 0) + touch_softlockup_watchdog(); dump_task(p, oc); + } rcu_read_unlock(); } } -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] memcg: fix soft lockup in the OOM process
by Chen Ridong 06 Jan '25

06 Jan '25

maillist inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBE42N Reference: https://lore.kernel.org/linux-kernel/8cf29751-7c71-52ff-5492-0019ca7b0e02@g… ---------------------------------------- A soft lockup issue was found in the product with about 56,000 tasks were in the OOM cgroup, it was traversing them when the soft lockup was triggered. watchdog: BUG: soft lockup - CPU#2 stuck for 23s! [VM Thread:1503066] CPU: 2 PID: 1503066 Comm: VM Thread Kdump: loaded Tainted: G Hardware name: Huawei Cloud OpenStack Nova, BIOS RIP: 0010:console_unlock+0x343/0x540 RSP: 0000:ffffb751447db9a0 EFLAGS: 00000247 ORIG_RAX: ffffffffffffff13 RAX: 0000000000000001 RBX: 0000000000000000 RCX: 00000000ffffffff RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000247 RBP: ffffffffafc71f90 R08: 0000000000000000 R09: 0000000000000040 R10: 0000000000000080 R11: 0000000000000000 R12: ffffffffafc74bd0 R13: ffffffffaf60a220 R14: 0000000000000247 R15: 0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f2fe6ad91f0 CR3: 00000004b2076003 CR4: 0000000000360ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: vprintk_emit+0x193/0x280 printk+0x52/0x6e dump_task+0x114/0x130 mem_cgroup_scan_tasks+0x76/0x100 dump_header+0x1fe/0x210 oom_kill_process+0xd1/0x100 out_of_memory+0x125/0x570 mem_cgroup_out_of_memory+0xb5/0xd0 try_charge+0x720/0x770 mem_cgroup_try_charge+0x86/0x180 mem_cgroup_try_charge_delay+0x1c/0x40 do_anonymous_page+0xb5/0x390 handle_mm_fault+0xc4/0x1f0 This is because thousands of processes are in the OOM cgroup, it takes a long time to traverse all of them. As a result, this lead to soft lockup in the OOM process. To fix this issue, call 'cond_resched' in the 'mem_cgroup_scan_tasks' function per 1000 iterations. For global OOM, call 'touch_softlockup_watchdog' per 1000 iterations to avoid this issue. Fixes: 9cbb78bb3143 ("mm, memcg: introduce own oom handler to iterate only over its own threads") Signed-off-by: Chen Ridong <chenridong(a)huawei.com> --- mm/memcontrol.c | 7 ++++++- mm/oom_kill.c | 8 +++++++- 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 3e928581ab47..f5b1322ac77e 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1202,6 +1202,7 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, { struct mem_cgroup *iter; int ret = 0; + int i = 0; BUG_ON(memcg == root_mem_cgroup); @@ -1210,8 +1211,12 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, struct task_struct *task; css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it); - while (!ret && (task = css_task_iter_next(&it))) + while (!ret && (task = css_task_iter_next(&it))) { + /* Avoid potential softlockup warning */ + if ((++i & 1023) == 0) + cond_resched(); ret = fn(task, arg); + } css_task_iter_end(&it); if (ret) { mem_cgroup_iter_break(memcg, iter); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 9d595265bbf5..fe5f4f20c5c8 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -43,6 +43,7 @@ #include <linux/kthread.h> #include <linux/init.h> #include <linux/mmu_notifier.h> +#include <linux/nmi.h> #include <asm/tlb.h> #include "internal.h" @@ -479,10 +480,15 @@ static void dump_tasks(struct oom_control *oc) memcg_print_bad_task(oc); } else { struct task_struct *p; + int i = 0; rcu_read_lock(); - for_each_process(p) + for_each_process(p) { + /* Avoid potential softlockup warning */ + if ((++i & 1023) == 0) + touch_softlockup_watchdog(); dump_task(p, oc); + } rcu_read_unlock(); } } -- 2.34.1

2 1

[PATCH OLK-6.6] memcg: fix soft lockup in the OOM process
by Chen Ridong 06 Jan '25

06 Jan '25

maillist inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBE42N Reference: https://lore.kernel.org/linux-kernel/8cf29751-7c71-52ff-5492-0019ca7b0e02@g… ---------------------------------------- A soft lockup issue was found in the product with about 56,000 tasks were in the OOM cgroup, it was traversing them when the soft lockup was triggered. watchdog: BUG: soft lockup - CPU#2 stuck for 23s! [VM Thread:1503066] CPU: 2 PID: 1503066 Comm: VM Thread Kdump: loaded Tainted: G Hardware name: Huawei Cloud OpenStack Nova, BIOS RIP: 0010:console_unlock+0x343/0x540 RSP: 0000:ffffb751447db9a0 EFLAGS: 00000247 ORIG_RAX: ffffffffffffff13 RAX: 0000000000000001 RBX: 0000000000000000 RCX: 00000000ffffffff RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000247 RBP: ffffffffafc71f90 R08: 0000000000000000 R09: 0000000000000040 R10: 0000000000000080 R11: 0000000000000000 R12: ffffffffafc74bd0 R13: ffffffffaf60a220 R14: 0000000000000247 R15: 0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f2fe6ad91f0 CR3: 00000004b2076003 CR4: 0000000000360ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: vprintk_emit+0x193/0x280 printk+0x52/0x6e dump_task+0x114/0x130 mem_cgroup_scan_tasks+0x76/0x100 dump_header+0x1fe/0x210 oom_kill_process+0xd1/0x100 out_of_memory+0x125/0x570 mem_cgroup_out_of_memory+0xb5/0xd0 try_charge+0x720/0x770 mem_cgroup_try_charge+0x86/0x180 mem_cgroup_try_charge_delay+0x1c/0x40 do_anonymous_page+0xb5/0x390 handle_mm_fault+0xc4/0x1f0 This is because thousands of processes are in the OOM cgroup, it takes a long time to traverse all of them. As a result, this lead to soft lockup in the OOM process. To fix this issue, call 'cond_resched' in the 'mem_cgroup_scan_tasks' function per 1000 iterations. For global OOM, call 'touch_softlockup_watchdog' per 1000 iterations to avoid this issue. Fixes: 9cbb78bb3143 ("mm, memcg: introduce own oom handler to iterate only over its own threads") Signed-off-by: Chen Ridong <chenridong(a)huawei.com> --- mm/memcontrol.c | 7 ++++++- mm/oom_kill.c | 8 +++++++- 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9bc0819629344..606a481afe2e2 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1322,6 +1322,7 @@ void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, { struct mem_cgroup *iter; int ret = 0; + int i = 0; BUG_ON(mem_cgroup_is_root(memcg)); @@ -1330,8 +1331,12 @@ void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, struct task_struct *task; css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it); - while (!ret && (task = css_task_iter_next(&it))) + while (!ret && (task = css_task_iter_next(&it))) { + /* Avoid potential softlockup warning */ + if ((++i & 1023) == 0) + cond_resched(); ret = fn(task, arg); + } css_task_iter_end(&it); if (ret) { mem_cgroup_iter_break(memcg, iter); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index dc932c5837479..f8a45a224ca2a 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -44,6 +44,7 @@ #include <linux/kthread.h> #include <linux/init.h> #include <linux/mmu_notifier.h> +#include <linux/nmi.h> #include <asm/tlb.h> #include "internal.h" @@ -482,10 +483,15 @@ static void dump_tasks(struct oom_control *oc) memcg_print_bad_task(oc); } else { struct task_struct *p; + int i = 0; rcu_read_lock(); - for_each_process(p) + for_each_process(p) { + /* Avoid potential softlockup warning */ + if ((++i & 1023) == 0) + touch_softlockup_watchdog(); dump_task(p, oc); + } rcu_read_unlock(); } } -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] memcg: fix soft lockup in the OOM process
by Chen Ridong 06 Jan '25

06 Jan '25

maillist inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IBE42N CVE: NA Reference: https://lore.kernel.org/linux-kernel/8cf29751-7c71-52ff-5492-0019ca7b0e02@g… ---------------------------------------- A soft lockup issue was found in the product with about 56,000 tasks were in the OOM cgroup, it was traversing them when the soft lockup was triggered. watchdog: BUG: soft lockup - CPU#2 stuck for 23s! [VM Thread:1503066] CPU: 2 PID: 1503066 Comm: VM Thread Kdump: loaded Tainted: G Hardware name: Huawei Cloud OpenStack Nova, BIOS RIP: 0010:console_unlock+0x343/0x540 RSP: 0000:ffffb751447db9a0 EFLAGS: 00000247 ORIG_RAX: ffffffffffffff13 RAX: 0000000000000001 RBX: 0000000000000000 RCX: 00000000ffffffff RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000247 RBP: ffffffffafc71f90 R08: 0000000000000000 R09: 0000000000000040 R10: 0000000000000080 R11: 0000000000000000 R12: ffffffffafc74bd0 R13: ffffffffaf60a220 R14: 0000000000000247 R15: 0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f2fe6ad91f0 CR3: 00000004b2076003 CR4: 0000000000360ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: vprintk_emit+0x193/0x280 printk+0x52/0x6e dump_task+0x114/0x130 mem_cgroup_scan_tasks+0x76/0x100 dump_header+0x1fe/0x210 oom_kill_process+0xd1/0x100 out_of_memory+0x125/0x570 mem_cgroup_out_of_memory+0xb5/0xd0 try_charge+0x720/0x770 mem_cgroup_try_charge+0x86/0x180 mem_cgroup_try_charge_delay+0x1c/0x40 do_anonymous_page+0xb5/0x390 handle_mm_fault+0xc4/0x1f0 This is because thousands of processes are in the OOM cgroup, it takes a long time to traverse all of them. As a result, this lead to soft lockup in the OOM process. To fix this issue, call 'cond_resched' in the 'mem_cgroup_scan_tasks' function per 1000 iterations. For global OOM, call 'touch_softlockup_watchdog' per 1000 iterations to avoid this issue. Fixes: 9cbb78bb3143 ("mm, memcg: introduce own oom handler to iterate only over its own threads") Signed-off-by: Chen Ridong <chenridong(a)huawei.com> --- mm/memcontrol.c | 7 ++++++- mm/oom_kill.c | 8 +++++++- 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6d062b0022be..a35b94cacada 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1230,6 +1230,7 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, { struct mem_cgroup *iter; int ret = 0; + int i = 0; BUG_ON(memcg == root_mem_cgroup); @@ -1238,8 +1239,12 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, struct task_struct *task; css_task_iter_start(&iter->css, CSS_TASK_ITER_PROCS, &it); - while (!ret && (task = css_task_iter_next(&it))) + while (!ret && (task = css_task_iter_next(&it))) { + /* Avoid potential softlockup warning */ + if ((++i & 1023) == 0) + cond_resched(); ret = fn(task, arg); + } css_task_iter_end(&it); if (ret) { mem_cgroup_iter_break(memcg, iter); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index d917e1e47f7d..3ab166322986 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -42,6 +42,7 @@ #include <linux/init.h> #include <linux/mmu_notifier.h> #include <linux/share_pool.h> +#include <linux/nmi.h> #include <asm/tlb.h> #include "internal.h" @@ -518,10 +519,15 @@ static void dump_tasks(struct oom_control *oc) memcg_print_bad_task(oc); } else { struct task_struct *p; + int i = 0; rcu_read_lock(); - for_each_process(p) + for_each_process(p) { + /* Avoid potential softlockup warning */ + if ((++i & 1023) == 0) + touch_softlockup_watchdog(); dump_task(p, oc); + } rcu_read_unlock(); } } -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] media: s5p_cec: limit msg.len to CEC_MAX_MSG_SIZE
by Cai Xinchen 06 Jan '25

06 Jan '25

From: Hans Verkuil <hverkuil-cisco(a)xs4all.nl> stable inclusion from stable-v4.19.265 commit a2728bf9b6c65e46468c763e3dab7e04839d4e11 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBFBZR CVE: CVE-2022-49035 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 93f65ce036863893c164ca410938e0968964b26c ] I expect that the hardware will have limited this to 16, but just in case it hasn't, check for this corner case. Signed-off-by: Hans Verkuil <hverkuil-cisco(a)xs4all.nl> Signed-off-by: Mauro Carvalho Chehab <mchehab(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Cai Xinchen <caixinchen1(a)huawei.com> --- drivers/media/platform/s5p-cec/s5p_cec.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/media/platform/s5p-cec/s5p_cec.c b/drivers/media/platform/s5p-cec/s5p_cec.c index 8837e2678bde..b8f125e45e38 100644 --- a/drivers/media/platform/s5p-cec/s5p_cec.c +++ b/drivers/media/platform/s5p-cec/s5p_cec.c @@ -116,6 +116,8 @@ static irqreturn_t s5p_cec_irq_handler(int irq, void *priv) dev_dbg(cec->dev, "Buffer overrun (worker did not process previous message)\n"); cec->rx = STATE_BUSY; cec->msg.len = status >> 24; + if (cec->msg.len > CEC_MAX_MSG_SIZE) + cec->msg.len = CEC_MAX_MSG_SIZE; cec->msg.rx_status = CEC_RX_STATUS_OK; s5p_cec_get_rx_buf(cec, cec->msg.len, cec->msg.msg); -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] f2fs: fix to do sanity check on node blkaddr in truncate_node()
by Yifan Qiao 06 Jan '25

06 Jan '25

From: Chao Yu <chao(a)kernel.org> mainline inclusion from mainline-v6.13-rc1 commit 6babe00ccd34fc65b78ef8b99754e32b4385f23d category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEDP8 CVE: CVE-2024-56692 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- syzbot reports a f2fs bug as below: ------------[ cut here ]------------ kernel BUG at fs/f2fs/segment.c:2534! RIP: 0010:f2fs_invalidate_blocks+0x35f/0x370 fs/f2fs/segment.c:2534 Call Trace: truncate_node+0x1ae/0x8c0 fs/f2fs/node.c:909 f2fs_remove_inode_page+0x5c2/0x870 fs/f2fs/node.c:1288 f2fs_evict_inode+0x879/0x15c0 fs/f2fs/inode.c:856 evict+0x4e8/0x9b0 fs/inode.c:723 f2fs_handle_failed_inode+0x271/0x2e0 fs/f2fs/inode.c:986 f2fs_create+0x357/0x530 fs/f2fs/namei.c:394 lookup_open fs/namei.c:3595 [inline] open_last_lookups fs/namei.c:3694 [inline] path_openat+0x1c03/0x3590 fs/namei.c:3930 do_filp_open+0x235/0x490 fs/namei.c:3960 do_sys_openat2+0x13e/0x1d0 fs/open.c:1415 do_sys_open fs/open.c:1430 [inline] __do_sys_openat fs/open.c:1446 [inline] __se_sys_openat fs/open.c:1441 [inline] __x64_sys_openat+0x247/0x2a0 fs/open.c:1441 do_syscall_x64 arch/x86/entry/common.c:52 [inline] do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0010:f2fs_invalidate_blocks+0x35f/0x370 fs/f2fs/segment.c:2534 The root cause is: on a fuzzed image, blkaddr in nat entry may be corrupted, then it will cause system panic when using it in f2fs_invalidate_blocks(), to avoid this, let's add sanity check on nat blkaddr in truncate_node(). Reported-by: syzbot+33379ce4ac76acf7d0c7(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-f2fs-devel/0000000000009a6cd706224ca720@googl… Cc: stable(a)vger.kernel.org Signed-off-by: Chao Yu <chao(a)kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> Signed-off-by: Yifan Qiao <qiaoyifan4(a)huawei.com> --- fs/f2fs/node.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index c63274d4b74b..97c5e521acae 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -838,6 +838,15 @@ static int truncate_node(struct dnode_of_data *dn) if (err) return err; + if (ni.blk_addr != NEW_ADDR && + !f2fs_is_valid_blkaddr(sbi, ni.blk_addr, DATA_GENERIC_ENHANCE)) { + f2fs_err(sbi, + "nat entry is corrupted, run fsck to fix it, ino:%u, " + "nid:%u, blkaddr:%u", ni.ino, ni.nid, ni.blk_addr); + set_sbi_flag(sbi, SBI_NEED_FSCK); + return -EFSCORRUPTED; + } + /* Deallocate node address */ f2fs_invalidate_blocks(sbi, ni.blk_addr); dec_valid_node_count(sbi, dn->inode, dn->nid == dn->inode->i_ino); -- 2.39.2

2 1

[PATCH OLK-6.6] KVM: arm64: Don't retire aborted MMIO instruction
by Zhang Kunbo 06 Jan '25

06 Jan '25

From: Oliver Upton <oliver.upton(a)linux.dev> from stable-v6.6.66 commit ea6b5d98fea4ee8cb443ea98fda520909e90d30e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAG3 CVE: CVE-2024-53196 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit e735a5da64420a86be370b216c269b5dd8e830e2 ] Returning an abort to the guest for an unsupported MMIO access is a documented feature of the KVM UAPI. Nevertheless, it's clear that this plumbing has seen limited testing, since userspace can trivially cause a WARN in the MMIO return: WARNING: CPU: 0 PID: 30558 at arch/arm64/include/asm/kvm_emulate.h:536 kvm_handle_mmio_return+0x46c/0x5c4 arch/arm64/include/asm/kvm_emulate.h:536 Call trace: kvm_handle_mmio_return+0x46c/0x5c4 arch/arm64/include/asm/kvm_emulate.h:536 kvm_arch_vcpu_ioctl_run+0x98/0x15b4 arch/arm64/kvm/arm.c:1133 kvm_vcpu_ioctl+0x75c/0xa78 virt/kvm/kvm_main.c:4487 __do_sys_ioctl fs/ioctl.c:51 [inline] __se_sys_ioctl fs/ioctl.c:893 [inline] __arm64_sys_ioctl+0x14c/0x1c8 fs/ioctl.c:893 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:49 el0_svc_common+0x1e0/0x23c arch/arm64/kernel/syscall.c:132 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:151 el0_svc+0x38/0x68 arch/arm64/kernel/entry-common.c:712 el0t_64_sync_handler+0x90/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 The splat is complaining that KVM is advancing PC while an exception is pending, i.e. that KVM is retiring the MMIO instruction despite a pending synchronous external abort. Womp womp. Fix the glaring UAPI bug by skipping over all the MMIO emulation in case there is a pending synchronous exception. Note that while userspace is capable of pending an asynchronous exception (SError, IRQ, or FIQ), it is still safe to retire the MMIO instruction in this case as (1) they are by definition asynchronous, and (2) KVM relies on hardware support for pending/delivering these exceptions instead of the software state machine for advancing PC. Cc: stable(a)vger.kernel.org Fixes: da345174ceca ("KVM: arm/arm64: Allow user injection of external data aborts") Reported-by: Alexander Potapenko <glider(a)google.com> Reviewed-by: Marc Zyngier <maz(a)kernel.org> Link: https://lore.kernel.org/r/20241025203106.3529261-2-oliver.upton@linux.dev Signed-off-by: Oliver Upton <oliver.upton(a)linux.dev> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: arch/arm64/kvm/mmio.c [ different return polarity introduced by this commit not merged: cc81b6dfc3bc8 ("KVM: arm64: Change kvm_handle_mmio_return() return polarity") ] Signed-off-by: Zhang Kunbo <zhangkunbo(a)huawei.com> --- arch/arm64/kvm/mmio.c | 32 ++++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kvm/mmio.c b/arch/arm64/kvm/mmio.c index 40d6d056e261..bf5de05cb7a8 100644 --- a/arch/arm64/kvm/mmio.c +++ b/arch/arm64/kvm/mmio.c @@ -73,6 +73,31 @@ unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len) return data; } +static bool kvm_pending_sync_exception(struct kvm_vcpu *vcpu) +{ + if (!vcpu_get_flag(vcpu, PENDING_EXCEPTION)) + return false; + + if (vcpu_el1_is_32bit(vcpu)) { + switch (vcpu_get_flag(vcpu, EXCEPT_MASK)) { + case unpack_vcpu_flag(EXCEPT_AA32_UND): + case unpack_vcpu_flag(EXCEPT_AA32_IABT): + case unpack_vcpu_flag(EXCEPT_AA32_DABT): + return true; + default: + return false; + } + } else { + switch (vcpu_get_flag(vcpu, EXCEPT_MASK)) { + case unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC): + case unpack_vcpu_flag(EXCEPT_AA64_EL2_SYNC): + return true; + default: + return false; + } + } +} + /** * kvm_handle_mmio_return -- Handle MMIO loads after user space emulation * or in-kernel IO emulation @@ -85,8 +110,11 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu) unsigned int len; int mask; - /* Detect an already handled MMIO return */ - if (unlikely(!vcpu->mmio_needed)) + /* + * Detect if the MMIO return was already handled or if userspace aborted + * the MMIO access. + */ + if (unlikely(!vcpu->mmio_needed || kvm_pending_sync_exception(vcpu))) return 0; vcpu->mmio_needed = 0; -- 2.34.1

2 1

[PATCH OLK-5.10] KVM: arm64: Don't retire aborted MMIO instruction
by Zhang Kunbo 06 Jan '25

06 Jan '25

From: Oliver Upton <oliver.upton(a)linux.dev> stable inclusion from stable-v6.6.66 commit ea6b5d98fea4ee8cb443ea98fda520909e90d30e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAG3 CVE: CVE-2024-53196 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit e735a5da64420a86be370b216c269b5dd8e830e2 ] Returning an abort to the guest for an unsupported MMIO access is a documented feature of the KVM UAPI. Nevertheless, it's clear that this plumbing has seen limited testing, since userspace can trivially cause a WARN in the MMIO return: WARNING: CPU: 0 PID: 30558 at arch/arm64/include/asm/kvm_emulate.h:536 kvm_handle_mmio_return+0x46c/0x5c4 arch/arm64/include/asm/kvm_emulate.h:536 Call trace: kvm_handle_mmio_return+0x46c/0x5c4 arch/arm64/include/asm/kvm_emulate.h:536 kvm_arch_vcpu_ioctl_run+0x98/0x15b4 arch/arm64/kvm/arm.c:1133 kvm_vcpu_ioctl+0x75c/0xa78 virt/kvm/kvm_main.c:4487 __do_sys_ioctl fs/ioctl.c:51 [inline] __se_sys_ioctl fs/ioctl.c:893 [inline] __arm64_sys_ioctl+0x14c/0x1c8 fs/ioctl.c:893 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:49 el0_svc_common+0x1e0/0x23c arch/arm64/kernel/syscall.c:132 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:151 el0_svc+0x38/0x68 arch/arm64/kernel/entry-common.c:712 el0t_64_sync_handler+0x90/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 The splat is complaining that KVM is advancing PC while an exception is pending, i.e. that KVM is retiring the MMIO instruction despite a pending synchronous external abort. Womp womp. Fix the glaring UAPI bug by skipping over all the MMIO emulation in case there is a pending synchronous exception. Note that while userspace is capable of pending an asynchronous exception (SError, IRQ, or FIQ), it is still safe to retire the MMIO instruction in this case as (1) they are by definition asynchronous, and (2) KVM relies on hardware support for pending/delivering these exceptions instead of the software state machine for advancing PC. Cc: stable(a)vger.kernel.org Fixes: da345174ceca ("KVM: arm/arm64: Allow user injection of external data aborts") Reported-by: Alexander Potapenko <glider(a)google.com> Reviewed-by: Marc Zyngier <maz(a)kernel.org> Link: https://lore.kernel.org/r/20241025203106.3529261-2-oliver.upton@linux.dev Signed-off-by: Oliver Upton <oliver.upton(a)linux.dev> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: arch/arm64/kvm/mmio.c [ different return polarity introduced by this commit not merged: cc81b6dfc3bc8 ("KVM: arm64: Change kvm_handle_mmio_return() return polarity") ] Signed-off-by: Zhang Kunbo <zhangkunbo(a)huawei.com> --- arch/arm64/kvm/mmio.c | 32 ++++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kvm/mmio.c b/arch/arm64/kvm/mmio.c index 6bda06ad3196..b0f4f3dfaf67 100644 --- a/arch/arm64/kvm/mmio.c +++ b/arch/arm64/kvm/mmio.c @@ -76,6 +76,31 @@ unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len) return data; } +static bool kvm_pending_sync_exception(struct kvm_vcpu *vcpu) +{ + if (!vcpu_get_flag(vcpu, PENDING_EXCEPTION)) + return false; + + if (vcpu_el1_is_32bit(vcpu)) { + switch (vcpu_get_flag(vcpu, EXCEPT_MASK)) { + case unpack_vcpu_flag(EXCEPT_AA32_UND): + case unpack_vcpu_flag(EXCEPT_AA32_IABT): + case unpack_vcpu_flag(EXCEPT_AA32_DABT): + return true; + default: + return false; + } + } else { + switch (vcpu_get_flag(vcpu, EXCEPT_MASK)) { + case unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC): + case unpack_vcpu_flag(EXCEPT_AA64_EL2_SYNC): + return true; + default: + return false; + } + } +} + /** * kvm_handle_mmio_return -- Handle MMIO loads after user space emulation * or in-kernel IO emulation @@ -88,8 +113,11 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu) unsigned int len; int mask; - /* Detect an already handled MMIO return */ - if (unlikely(!vcpu->mmio_needed)) + /* + * Detect if the MMIO return was already handled or if userspace aborted + * the MMIO access. + */ + if (unlikely(!vcpu->mmio_needed || kvm_pending_sync_exception(vcpu))) return 0; vcpu->mmio_needed = 0; -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] KVM: arm64: Don't retire aborted MMIO instruction
by Zhang Kunbo 06 Jan '25

06 Jan '25

From: Oliver Upton <oliver.upton(a)linux.dev> stable inclusion from stable-v6.6.66 commit ea6b5d98fea4ee8cb443ea98fda520909e90d30e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAG3 CVE: CVE-2024-53196 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit e735a5da64420a86be370b216c269b5dd8e830e2 ] Returning an abort to the guest for an unsupported MMIO access is a documented feature of the KVM UAPI. Nevertheless, it's clear that this plumbing has seen limited testing, since userspace can trivially cause a WARN in the MMIO return: WARNING: CPU: 0 PID: 30558 at arch/arm64/include/asm/kvm_emulate.h:536 kvm_handle_mmio_return+0x46c/0x5c4 arch/arm64/include/asm/kvm_emulate.h:536 Call trace: kvm_handle_mmio_return+0x46c/0x5c4 arch/arm64/include/asm/kvm_emulate.h:536 kvm_arch_vcpu_ioctl_run+0x98/0x15b4 arch/arm64/kvm/arm.c:1133 kvm_vcpu_ioctl+0x75c/0xa78 virt/kvm/kvm_main.c:4487 __do_sys_ioctl fs/ioctl.c:51 [inline] __se_sys_ioctl fs/ioctl.c:893 [inline] __arm64_sys_ioctl+0x14c/0x1c8 fs/ioctl.c:893 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:49 el0_svc_common+0x1e0/0x23c arch/arm64/kernel/syscall.c:132 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:151 el0_svc+0x38/0x68 arch/arm64/kernel/entry-common.c:712 el0t_64_sync_handler+0x90/0xfc arch/arm64/kernel/entry-common.c:730 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598 The splat is complaining that KVM is advancing PC while an exception is pending, i.e. that KVM is retiring the MMIO instruction despite a pending synchronous external abort. Womp womp. Fix the glaring UAPI bug by skipping over all the MMIO emulation in case there is a pending synchronous exception. Note that while userspace is capable of pending an asynchronous exception (SError, IRQ, or FIQ), it is still safe to retire the MMIO instruction in this case as (1) they are by definition asynchronous, and (2) KVM relies on hardware support for pending/delivering these exceptions instead of the software state machine for advancing PC. Cc: stable(a)vger.kernel.org Fixes: da345174ceca ("KVM: arm/arm64: Allow user injection of external data aborts") Reported-by: Alexander Potapenko <glider(a)google.com> Reviewed-by: Marc Zyngier <maz(a)kernel.org> Link: https://lore.kernel.org/r/20241025203106.3529261-2-oliver.upton@linux.dev Signed-off-by: Oliver Upton <oliver.upton(a)linux.dev> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: arch/arm64/kvm/mmio.c [ different return polarity introduced by this commit not merged: cc81b6dfc3bc8 ("KVM: arm64: Change kvm_handle_mmio_return() return polarity") ] Signed-off-by: Zhang Kunbo <zhangkunbo(a)huawei.com> --- arch/arm64/kvm/mmio.c | 32 ++++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kvm/mmio.c b/arch/arm64/kvm/mmio.c index 6a2826f1bf5e..3b68e2b3a933 100644 --- a/arch/arm64/kvm/mmio.c +++ b/arch/arm64/kvm/mmio.c @@ -72,6 +72,31 @@ unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len) return data; } +static bool kvm_pending_sync_exception(struct kvm_vcpu *vcpu) +{ + if (!vcpu_get_flag(vcpu, PENDING_EXCEPTION)) + return false; + + if (vcpu_el1_is_32bit(vcpu)) { + switch (vcpu_get_flag(vcpu, EXCEPT_MASK)) { + case unpack_vcpu_flag(EXCEPT_AA32_UND): + case unpack_vcpu_flag(EXCEPT_AA32_IABT): + case unpack_vcpu_flag(EXCEPT_AA32_DABT): + return true; + default: + return false; + } + } else { + switch (vcpu_get_flag(vcpu, EXCEPT_MASK)) { + case unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC): + case unpack_vcpu_flag(EXCEPT_AA64_EL2_SYNC): + return true; + default: + return false; + } + } +} + /** * kvm_handle_mmio_return -- Handle MMIO loads after user space emulation * or in-kernel IO emulation @@ -84,8 +109,11 @@ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu) unsigned int len; int mask; - /* Detect an already handled MMIO return */ - if (unlikely(!vcpu->mmio_needed)) + /* + * Detect if the MMIO return was already handled or if userspace aborted + * the MMIO access. + */ + if (unlikely(!vcpu->mmio_needed || kvm_pending_sync_exception(vcpu))) return 0; vcpu->mmio_needed = 0; -- 2.34.1

2 1

[openeuler:openEuler-1.0-LTS 1367/1367] drivers/media/platform/qcom/camss/camss.o: warning: objtool: missing symbol for section .init.text
by kernel test robot 05 Jan '25

05 Jan '25

tree: https://gitee.com/openeuler/kernel.git openEuler-1.0-LTS head: 21eb7b92f86861232fed9eff3c46634d7535ef8a commit: ec6859b23f2212275fbd476df14d7a94839c2a35 [1367/1367] media: Rename CAMSS driver path config: x86_64-buildonly-randconfig-005-20250103 (https://download.01.org/0day-ci/archive/20250105/202501051713.LBoKPNXw-lkp@…) compiler: clang version 19.1.3 (https://github.com/llvm/llvm-project ab51eccf88f5321e7c60591c5546b254b6afab99) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250105/202501051713.LBoKPNXw-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202501051713.LBoKPNXw-lkp@intel.com/ All warnings (new ones prefixed by >>): >> drivers/media/platform/qcom/camss/camss.o: warning: objtool: missing symbol for section .init.text -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH openEuler-1.0-LTS 0/2] net: Fix CVE-2024-47684
by Dong Chenchen 04 Jan '25

04 Jan '25

Fix CVE-2024-47684. Eric Dumazet (1): tcp: introduce tcp_skb_timestamp_us() helper Josh Hunt (1): tcp: check skb is non-NULL in tcp_rto_delta_us() include/net/tcp.h | 27 +++++++++++++++++++++++++-- net/ipv4/tcp_input.c | 11 ++++++----- net/ipv4/tcp_ipv4.c | 2 +- net/ipv4/tcp_output.c | 2 +- net/ipv4/tcp_rate.c | 15 ++++++++------- net/ipv4/tcp_recovery.c | 5 +++-- 6 files changed, 44 insertions(+), 18 deletions(-) -- 2.25.1

2 3

[PATCH openEuler-1.0-LTS] xfrm: validate new SA's prefixlen using SA family when sel.family is unset
by Dong Chenchen 04 Jan '25

04 Jan '25

From: Sabrina Dubroca <sd(a)queasysnail.net> stable inclusion from stable-v4.19.323 commit f31398570acf0f0804c644006f7bfa9067106b0a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IB2SWP CVE: CVE-2024-50142 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 3f0ab59e6537c6a8f9e1b355b48f9c05a76e8563 ] This expands the validation introduced in commit 07bf7908950a ("xfrm: Validate address prefix lengths in the xfrm selector.") syzbot created an SA with usersa.sel.family = AF_UNSPEC usersa.sel.prefixlen_s = 128 usersa.family = AF_INET Because of the AF_UNSPEC selector, verify_newsa_info doesn't put limits on prefixlen_{s,d}. But then copy_from_user_state sets x->sel.family to usersa.family (AF_INET). Do the same conversion in verify_newsa_info before validating prefixlen_{s,d}, since that's how prefixlen is going to be used later on. Reported-by: syzbot+cc39f136925517aed571(a)syzkaller.appspotmail.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Sabrina Dubroca <sd(a)queasysnail.net> Signed-off-by: Steffen Klassert <steffen.klassert(a)secunet.com> Signed-off-by: Antony Antony <antony.antony(a)secunet.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/xfrm/xfrm_user.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 4fe9651c6331..ff1e14019ff7 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -148,6 +148,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, struct nlattr **attrs) { int err; + u16 family = p->sel.family; err = -EINVAL; switch (p->family) { @@ -166,7 +167,10 @@ static int verify_newsa_info(struct xfrm_usersa_info *p, goto out; } - switch (p->sel.family) { + if (!family && !(p->flags & XFRM_STATE_AF_UNSPEC)) + family = p->family; + + switch (family) { case AF_UNSPEC: break; -- 2.25.1

2 1

[PATCH OLK-5.10] i40e: fix race condition by adding filter's intermediate sync state
by Zhang Changzhong 04 Jan '25

04 Jan '25

From: Aleksandr Loktionov <aleksandr.loktionov(a)intel.com> mainline inclusion from mainline-v6.12-rc7 commit f30490e9695ef7da3d0899c6a0293cc7cd373567 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IB5KRJ CVE: CVE-2024-53088 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Fix a race condition in the i40e driver that leads to MAC/VLAN filters becoming corrupted and leaking. Address the issue that occurs under heavy load when multiple threads are concurrently modifying MAC/VLAN filters by setting mac and port VLAN. 1. Thread T0 allocates a filter in i40e_add_filter() within i40e_ndo_set_vf_port_vlan(). 2. Thread T1 concurrently frees the filter in __i40e_del_filter() within i40e_ndo_set_vf_mac(). 3. Subsequently, i40e_service_task() calls i40e_sync_vsi_filters(), which refers to the already freed filter memory, causing corruption. Reproduction steps: 1. Spawn multiple VFs. 2. Apply a concurrent heavy load by running parallel operations to change MAC addresses on the VFs and change port VLANs on the host. 3. Observe errors in dmesg: "Error I40E_AQ_RC_ENOSPC adding RX filters on VF XX, please set promiscuous on manually for VF XX". Exact code for stable reproduction Intel can't open-source now. The fix involves implementing a new intermediate filter state, I40E_FILTER_NEW_SYNC, for the time when a filter is on a tmp_add_list. These filters cannot be deleted from the hash list directly but must be removed using the full process. Fixes: 278e7d0b9d68 ("i40e: store MAC/VLAN filters in a hash with the MAC Address as key") Signed-off-by: Aleksandr Loktionov <aleksandr.loktionov(a)intel.com> Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha(a)intel.com> (A Contingent worker at Intel) Reviewed-by: Michal Schmidt <mschmidt(a)redhat.com> Tested-by: Michal Schmidt <mschmidt(a)redhat.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen(a)intel.com> Conflicts: drivers/net/ethernet/intel/i40e/i40e_main.c [c87c938f62d8 ("i40e: Add VF VLAN pruning") and 5180ff1364bc ("i40e: use int for i40e_status") not merged] Signed-off-by: Zhang Changzhong <zhangchangzhong(a)huawei.com> --- drivers/net/ethernet/intel/i40e/i40e.h | 1 + drivers/net/ethernet/intel/i40e/i40e_debugfs.c | 1 + drivers/net/ethernet/intel/i40e/i40e_main.c | 10 ++++++++-- 3 files changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index dd630b6..1641145 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -681,6 +681,7 @@ enum i40e_filter_state { I40E_FILTER_ACTIVE, /* Added to switch by FW */ I40E_FILTER_FAILED, /* Rejected by FW */ I40E_FILTER_REMOVE, /* To be removed */ + I40E_FILTER_NEW_SYNC, /* New, not sent yet, is in i40e_sync_vsi_filters() */ /* There is no 'removed' state; the filter struct is freed */ }; struct i40e_mac_filter { diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 8bcf590..66eacbf 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -105,6 +105,7 @@ static char *i40e_filter_state_string[] = { "ACTIVE", "FAILED", "REMOVE", + "NEW_SYNC", }; /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 35a903f..00b6028 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1232,6 +1232,7 @@ int i40e_count_filters(struct i40e_vsi *vsi) hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { if (f->state == I40E_FILTER_NEW || + f->state == I40E_FILTER_NEW_SYNC || f->state == I40E_FILTER_ACTIVE) ++cnt; } @@ -1418,6 +1419,8 @@ static int i40e_correct_mac_vlan_filters(struct i40e_vsi *vsi, new->f = add_head; new->state = add_head->state; + if (add_head->state == I40E_FILTER_NEW) + add_head->state = I40E_FILTER_NEW_SYNC; /* Add the new filter to the tmp list */ hlist_add_head(&new->hlist, tmp_add_list); @@ -2307,7 +2310,8 @@ static i40e_status i40e_aqc_broadcast_filter(struct i40e_vsi *vsi, const char *vsi_name, struct i40e_mac_filter *f) { - bool enable = f->state == I40E_FILTER_NEW; + bool enable = f->state == I40E_FILTER_NEW || + f->state == I40E_FILTER_NEW_SYNC; struct i40e_hw *hw = &vsi->back->hw; i40e_status aq_ret; @@ -2481,6 +2485,7 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) /* Add it to the hash list */ hlist_add_head(&new->hlist, &tmp_add_list); + f->state = I40E_FILTER_NEW_SYNC; } /* Count the number of active (current and new) VLAN @@ -2628,7 +2633,8 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) spin_lock_bh(&vsi->mac_filter_hash_lock); hlist_for_each_entry_safe(new, h, &tmp_add_list, hlist) { /* Only update the state if we're still NEW */ - if (new->f->state == I40E_FILTER_NEW) + if (new->f->state == I40E_FILTER_NEW || + new->f->state == I40E_FILTER_NEW_SYNC) new->f->state = new->state; hlist_del(&new->hlist); netdev_hw_addr_refcnt(new->f, vsi->netdev, -1); -- 2.9.5

2 1

[PATCH openEuler-22.03-LTS-SP1 0/2] CVE-2024-56604_openEuler-22.03-LTS-SP1
by dinglongwei 04 Jan '25

04 Jan '25

CVE-2024-56604_openEuler-22.03-LTS-SP1 Ignat Korchagin (1): Bluetooth: RFCOMM: avoid leaving dangling sk pointer in rfcomm_sock_alloc() Luiz Augusto von Dentz (1): Bluetooth: Consolidate code around sk_alloc into a helper function include/net/bluetooth/bluetooth.h | 2 ++ net/bluetooth/af_bluetooth.c | 21 +++++++++++++++++++++ net/bluetooth/bnep/sock.c | 10 +--------- net/bluetooth/hci_sock.c | 10 ++-------- net/bluetooth/l2cap_sock.c | 10 +--------- net/bluetooth/rfcomm/sock.c | 21 +++++++-------------- net/bluetooth/sco.c | 10 +--------- 7 files changed, 35 insertions(+), 49 deletions(-) -- 2.22.0

2 3

[PATCH OLK-5.10 0/2] CVE-2024-56604_OLK-5.10
by dinglongwei 04 Jan '25

04 Jan '25

CVE-2024-56604_OLK-5.10 Ignat Korchagin (1): Bluetooth: RFCOMM: avoid leaving dangling sk pointer in rfcomm_sock_alloc() Luiz Augusto von Dentz (1): Bluetooth: Consolidate code around sk_alloc into a helper function include/net/bluetooth/bluetooth.h | 2 ++ net/bluetooth/af_bluetooth.c | 21 +++++++++++++++++++++ net/bluetooth/bnep/sock.c | 10 +--------- net/bluetooth/hci_sock.c | 10 ++-------- net/bluetooth/l2cap_sock.c | 10 +--------- net/bluetooth/rfcomm/sock.c | 21 +++++++-------------- net/bluetooth/sco.c | 10 +--------- 7 files changed, 35 insertions(+), 49 deletions(-) -- 2.22.0

2 3

[PATCH OLK-6.6] Bluetooth: RFCOMM: avoid leaving dangling sk pointer in rfcomm_sock_alloc()
by dinglongwei 04 Jan '25

04 Jan '25

From: Ignat Korchagin <ignat(a)cloudflare.com> stable inclusion from stable-v6.6.66 commit 6021ccc2471b7b95e29b7cfc7938e042bf56e281 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEANI CVE: CVE-2024-56604 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 3945c799f12b8d1f49a3b48369ca494d981ac465 ] bt_sock_alloc() attaches allocated sk object to the provided sock object. If rfcomm_dlc_alloc() fails, we release the sk object, but leave the dangling pointer in the sock object, which may cause use-after-free. Fix this by swapping calls to bt_sock_alloc() and rfcomm_dlc_alloc(). Signed-off-by: Ignat Korchagin <ignat(a)cloudflare.com> Reviewed-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Reviewed-by: Eric Dumazet <edumazet(a)google.com> Link: https://patch.msgid.link/20241014153808.51894-4-ignat@cloudflare.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: dinglongwei <dinglongwei1(a)huawei.com> --- net/bluetooth/rfcomm/sock.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index cbff37b32734..c32a2374638b 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -274,13 +274,13 @@ static struct sock *rfcomm_sock_alloc(struct net *net, struct socket *sock, struct rfcomm_dlc *d; struct sock *sk; - sk = bt_sock_alloc(net, sock, &rfcomm_proto, proto, prio, kern); - if (!sk) + d = rfcomm_dlc_alloc(prio); + if (!d) return NULL; - d = rfcomm_dlc_alloc(prio); - if (!d) { - sk_free(sk); + sk = bt_sock_alloc(net, sock, &rfcomm_proto, proto, prio, kern); + if (!sk) { + rfcomm_dlc_free(d); return NULL; } -- 2.22.0

2 1

[openeuler:openEuler-1.0-LTS 1367/1367] sound/soc/rockchip/rockchip_pcm.o: warning: objtool: missing symbol for section .text
by kernel test robot 04 Jan '25

04 Jan '25

Hi Mark, FYI, the error/warning still remains. tree: https://gitee.com/openeuler/kernel.git openEuler-1.0-LTS head: 21eb7b92f86861232fed9eff3c46634d7535ef8a commit: 4aa5db22d35588e1a5d2ee88472348ea73d9fb23 [1367/1367] Merge branch 'asoc-4.19' into asoc-next config: x86_64-buildonly-randconfig-005-20250103 (https://download.01.org/0day-ci/archive/20250104/202501041833.o4WHox7g-lkp@…) compiler: clang version 19.1.3 (https://github.com/llvm/llvm-project ab51eccf88f5321e7c60591c5546b254b6afab99) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250104/202501041833.o4WHox7g-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202501041833.o4WHox7g-lkp@intel.com/ All warnings (new ones prefixed by >>): >> sound/soc/rockchip/rockchip_pcm.o: warning: objtool: missing symbol for section .text -- >> sound/soc/meson/axg-tdmin.o: warning: objtool: missing symbol for section .init.text -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH OLK-6.6] RDMA/mlx5: Move events notifier registration to be after device registration
by Pu Lehui 04 Jan '25

04 Jan '25

From: Patrisious Haddad <phaddad(a)nvidia.com> stable inclusion from stable-v6.6.64 commit 921fcf2971a1e8d3b904ba2c2905b96f4ec3d4ad category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEADY CVE: CVE-2024-53224 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit ede132a5cf559f3ab35a4c28bac4f4a6c20334d8 ] Move pkey change work initialization and cleanup from device resources stage to notifier stage, since this is the stage which handles this work events. Fix a race between the device deregistration and pkey change work by moving MLX5_IB_STAGE_DEVICE_NOTIFIER to be after MLX5_IB_STAGE_IB_REG in order to ensure that the notifier is deregistered before the device during cleanup. Which ensures there are no works that are being executed after the device has already unregistered which can cause the panic below. BUG: kernel NULL pointer dereference, address: 0000000000000000 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 1 PID: 630071 Comm: kworker/1:2 Kdump: loaded Tainted: G W OE --------- --- 5.14.0-162.6.1.el9_1.x86_64 #1 Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090008 02/27/2023 Workqueue: events pkey_change_handler [mlx5_ib] RIP: 0010:setup_qp+0x38/0x1f0 [mlx5_ib] Code: ee 41 54 45 31 e4 55 89 f5 53 48 89 fb 48 83 ec 20 8b 77 08 65 48 8b 04 25 28 00 00 00 48 89 44 24 18 48 8b 07 48 8d 4c 24 16 <4c> 8b 38 49 8b 87 80 0b 00 00 4c 89 ff 48 8b 80 08 05 00 00 8b 40 RSP: 0018:ffffbcc54068be20 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff954054494128 RCX: ffffbcc54068be36 RDX: ffff954004934000 RSI: 0000000000000001 RDI: ffff954054494128 RBP: 0000000000000023 R08: ffff954001be2c20 R09: 0000000000000001 R10: ffff954001be2c20 R11: ffff9540260133c0 R12: 0000000000000000 R13: 0000000000000023 R14: 0000000000000000 R15: ffff9540ffcb0905 FS: 0000000000000000(0000) GS:ffff9540ffc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000010625c001 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: mlx5_ib_gsi_pkey_change+0x20/0x40 [mlx5_ib] process_one_work+0x1e8/0x3c0 worker_thread+0x50/0x3b0 ? rescuer_thread+0x380/0x380 kthread+0x149/0x170 ? set_kthread_struct+0x50/0x50 ret_from_fork+0x22/0x30 Modules linked in: rdma_ucm(OE) rdma_cm(OE) iw_cm(OE) ib_ipoib(OE) ib_cm(OE) ib_umad(OE) mlx5_ib(OE) mlx5_fwctl(OE) fwctl(OE) ib_uverbs(OE) mlx5_core(OE) mlxdevm(OE) ib_core(OE) mlx_compat(OE) psample mlxfw(OE) tls knem(OE) netconsole nfsv3 nfs_acl nfs lockd grace fscache netfs qrtr rfkill sunrpc intel_rapl_msr intel_rapl_common rapl hv_balloon hv_utils i2c_piix4 pcspkr joydev fuse ext4 mbcache jbd2 sr_mod sd_mod cdrom t10_pi sg ata_generic pci_hyperv pci_hyperv_intf hyperv_drm drm_shmem_helper drm_kms_helper hv_storvsc syscopyarea hv_netvsc sysfillrect sysimgblt hid_hyperv fb_sys_fops scsi_transport_fc hyperv_keyboard drm ata_piix crct10dif_pclmul crc32_pclmul crc32c_intel libata ghash_clmulni_intel hv_vmbus serio_raw [last unloaded: ib_core] CR2: 0000000000000000 ---[ end trace f6f8be4eae12f7bc ]--- Fixes: 7722f47e71e5 ("IB/mlx5: Create GSI transmission QPs when P_Key table is changed") Signed-off-by: Patrisious Haddad <phaddad(a)nvidia.com> Reviewed-by: Michael Guralnik <michaelgur(a)nvidia.com> Link: https://patch.msgid.link/d271ceeff0c08431b3cbbbb3e2d416f09b6d1621.173149694… Signed-off-by: Leon Romanovsky <leon(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Pu Lehui <pulehui(a)huawei.com> --- drivers/infiniband/hw/mlx5/main.c | 40 +++++++++++++--------------- drivers/infiniband/hw/mlx5/mlx5_ib.h | 2 +- 2 files changed, 20 insertions(+), 22 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index bc38af6cda6e..c510484e024b 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -2899,7 +2899,6 @@ int mlx5_ib_dev_res_srq_init(struct mlx5_ib_dev *dev) static int mlx5_ib_dev_res_init(struct mlx5_ib_dev *dev) { struct mlx5_ib_resources *devr = &dev->devr; - int port; int ret; if (!MLX5_CAP_GEN(dev->mdev, xrc)) @@ -2915,10 +2914,6 @@ static int mlx5_ib_dev_res_init(struct mlx5_ib_dev *dev) return ret; } - for (port = 0; port < ARRAY_SIZE(devr->ports); ++port) - INIT_WORK(&devr->ports[port].pkey_change_work, - pkey_change_handler); - mutex_init(&devr->cq_lock); mutex_init(&devr->srq_lock); @@ -2928,16 +2923,6 @@ static int mlx5_ib_dev_res_init(struct mlx5_ib_dev *dev) static void mlx5_ib_dev_res_cleanup(struct mlx5_ib_dev *dev) { struct mlx5_ib_resources *devr = &dev->devr; - int port; - - /* - * Make sure no change P_Key work items are still executing. - * - * At this stage, the mlx5_ib_event should be unregistered - * and it ensures that no new works are added. - */ - for (port = 0; port < ARRAY_SIZE(devr->ports); ++port) - cancel_work_sync(&devr->ports[port].pkey_change_work); /* After s0/s1 init, they are not unset during the device lifetime. */ if (devr->s1) { @@ -4201,6 +4186,13 @@ static void mlx5_ib_stage_delay_drop_cleanup(struct mlx5_ib_dev *dev) static int mlx5_ib_stage_dev_notifier_init(struct mlx5_ib_dev *dev) { + struct mlx5_ib_resources *devr = &dev->devr; + int port; + + for (port = 0; port < ARRAY_SIZE(devr->ports); ++port) + INIT_WORK(&devr->ports[port].pkey_change_work, + pkey_change_handler); + dev->mdev_events.notifier_call = mlx5_ib_event; mlx5_notifier_register(dev->mdev, &dev->mdev_events); @@ -4211,8 +4203,14 @@ static int mlx5_ib_stage_dev_notifier_init(struct mlx5_ib_dev *dev) static void mlx5_ib_stage_dev_notifier_cleanup(struct mlx5_ib_dev *dev) { + struct mlx5_ib_resources *devr = &dev->devr; + int port; + mlx5r_macsec_event_unregister(dev); mlx5_notifier_unregister(dev->mdev, &dev->mdev_events); + + for (port = 0; port < ARRAY_SIZE(devr->ports); ++port) + cancel_work_sync(&devr->ports[port].pkey_change_work); } void __mlx5_ib_remove(struct mlx5_ib_dev *dev, @@ -4286,9 +4284,6 @@ static const struct mlx5_ib_profile pf_profile = { STAGE_CREATE(MLX5_IB_STAGE_DEVICE_RESOURCES, mlx5_ib_dev_res_init, mlx5_ib_dev_res_cleanup), - STAGE_CREATE(MLX5_IB_STAGE_DEVICE_NOTIFIER, - mlx5_ib_stage_dev_notifier_init, - mlx5_ib_stage_dev_notifier_cleanup), STAGE_CREATE(MLX5_IB_STAGE_ODP, mlx5_ib_odp_init_one, mlx5_ib_odp_cleanup_one), @@ -4313,6 +4308,9 @@ static const struct mlx5_ib_profile pf_profile = { STAGE_CREATE(MLX5_IB_STAGE_IB_REG, mlx5_ib_stage_ib_reg_init, mlx5_ib_stage_ib_reg_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_DEVICE_NOTIFIER, + mlx5_ib_stage_dev_notifier_init, + mlx5_ib_stage_dev_notifier_cleanup), STAGE_CREATE(MLX5_IB_STAGE_POST_IB_REG_UMR, mlx5_ib_stage_post_ib_reg_umr_init, NULL), @@ -4349,9 +4347,6 @@ const struct mlx5_ib_profile raw_eth_profile = { STAGE_CREATE(MLX5_IB_STAGE_DEVICE_RESOURCES, mlx5_ib_dev_res_init, mlx5_ib_dev_res_cleanup), - STAGE_CREATE(MLX5_IB_STAGE_DEVICE_NOTIFIER, - mlx5_ib_stage_dev_notifier_init, - mlx5_ib_stage_dev_notifier_cleanup), STAGE_CREATE(MLX5_IB_STAGE_COUNTERS, mlx5_ib_counters_init, mlx5_ib_counters_cleanup), @@ -4373,6 +4368,9 @@ const struct mlx5_ib_profile raw_eth_profile = { STAGE_CREATE(MLX5_IB_STAGE_IB_REG, mlx5_ib_stage_ib_reg_init, mlx5_ib_stage_ib_reg_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_DEVICE_NOTIFIER, + mlx5_ib_stage_dev_notifier_init, + mlx5_ib_stage_dev_notifier_cleanup), STAGE_CREATE(MLX5_IB_STAGE_POST_IB_REG_UMR, mlx5_ib_stage_post_ib_reg_umr_init, NULL), diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 1c83d132197f..94678e5c59dd 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -954,7 +954,6 @@ enum mlx5_ib_stages { MLX5_IB_STAGE_QP, MLX5_IB_STAGE_SRQ, MLX5_IB_STAGE_DEVICE_RESOURCES, - MLX5_IB_STAGE_DEVICE_NOTIFIER, MLX5_IB_STAGE_ODP, MLX5_IB_STAGE_COUNTERS, MLX5_IB_STAGE_CONG_DEBUGFS, @@ -963,6 +962,7 @@ enum mlx5_ib_stages { MLX5_IB_STAGE_PRE_IB_REG_UMR, MLX5_IB_STAGE_WHITELIST_UID, MLX5_IB_STAGE_IB_REG, + MLX5_IB_STAGE_DEVICE_NOTIFIER, MLX5_IB_STAGE_POST_IB_REG_UMR, MLX5_IB_STAGE_DELAY_DROP, MLX5_IB_STAGE_RESTRACK, -- 2.34.1

2 1

[PATCH OLK-6.6 0/1] backport mainline bugfix patch
by Lin Yujun 04 Jan '25

04 Jan '25

Jinjie Ruan (1): [Backport] genirq/msi: Fix off-by-one error in msi_domain_alloc() kernel/irq/msi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) -- 2.34.1

2 2

[PATCH openEuler-1.0-LTS 0/1] backport mainline bugfix patch
by Lin Yujun 04 Jan '25

04 Jan '25

Jinjie Ruan (1): [Backport] genirq/msi: Fix off-by-one error in msi_domain_alloc() kernel/irq/msi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) -- 2.34.1

2 2

[PATCH openEuler-22.03-LTS-SP1] wifi: brcmfmac: Fix oops due to NULL pointer dereference in brcmf_sdiod_sglist_rw()
by Wang Hai 04 Jan '25

04 Jan '25

From: Norbert van Bolhuis <nvbolhuis(a)gmail.com> stable inclusion from stable-v5.10.231 commit 7522d7d745d13fbeff3350fe6aa56c8dae263571 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAO3 CVE: CVE-2024-56593 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 857282b819cbaa0675aaab1e7542e2c0579f52d7 ] This patch fixes a NULL pointer dereference bug in brcmfmac that occurs when a high 'sd_sgentry_align' value applies (e.g. 512) and a lot of queued SKBs are sent from the pkt queue. The problem is the number of entries in the pre-allocated sgtable, it is nents = max(rxglom_size, txglom_size) + max(rxglom_size, txglom_size) >> 4 + 1. Given the default [rt]xglom_size=32 it's actually 35 which is too small. Worst case, the pkt queue can end up with 64 SKBs. This occurs when a new SKB is added for each original SKB if tailroom isn't enough to hold tail_pad. At least one sg entry is needed for each SKB. So, eventually the "skb_queue_walk loop" in brcmf_sdiod_sglist_rw may run out of sg entries. This makes sg_next return NULL and this causes the oops. The patch sets nents to max(rxglom_size, txglom_size) * 2 to be able handle the worst-case. Btw. this requires only 64-35=29 * 16 (or 20 if CONFIG_NEED_SG_DMA_LENGTH) = 464 additional bytes of memory. Signed-off-by: Norbert van Bolhuis <nvbolhuis(a)gmail.com> Signed-off-by: Kalle Valo <kvalo(a)kernel.org> Link: https://patch.msgid.link/20241107132903.13513-1-nvbolhuis@gmail.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Hai <wanghai38(a)huawei.com> --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c index b6d0bc73923f..75dc7904a4bd 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c @@ -769,7 +769,7 @@ void brcmf_sdiod_sgtable_alloc(struct brcmf_sdio_dev *sdiodev) nents = max_t(uint, BRCMF_DEFAULT_RXGLOM_SIZE, sdiodev->settings->bus.sdio.txglomsz); - nents += (nents >> 4) + 1; + nents *= 2; WARN_ON(nents > sdiodev->max_segment_count); -- 2.17.1

2 1

[PATCH OLK-5.10] wifi: brcmfmac: Fix oops due to NULL pointer dereference in brcmf_sdiod_sglist_rw()
by Wang Hai 04 Jan '25

04 Jan '25

From: Norbert van Bolhuis <nvbolhuis(a)gmail.com> stable inclusion from stable-v5.10.231 commit 7522d7d745d13fbeff3350fe6aa56c8dae263571 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAO3 CVE: CVE-2024-56593 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 857282b819cbaa0675aaab1e7542e2c0579f52d7 ] This patch fixes a NULL pointer dereference bug in brcmfmac that occurs when a high 'sd_sgentry_align' value applies (e.g. 512) and a lot of queued SKBs are sent from the pkt queue. The problem is the number of entries in the pre-allocated sgtable, it is nents = max(rxglom_size, txglom_size) + max(rxglom_size, txglom_size) >> 4 + 1. Given the default [rt]xglom_size=32 it's actually 35 which is too small. Worst case, the pkt queue can end up with 64 SKBs. This occurs when a new SKB is added for each original SKB if tailroom isn't enough to hold tail_pad. At least one sg entry is needed for each SKB. So, eventually the "skb_queue_walk loop" in brcmf_sdiod_sglist_rw may run out of sg entries. This makes sg_next return NULL and this causes the oops. The patch sets nents to max(rxglom_size, txglom_size) * 2 to be able handle the worst-case. Btw. this requires only 64-35=29 * 16 (or 20 if CONFIG_NEED_SG_DMA_LENGTH) = 464 additional bytes of memory. Signed-off-by: Norbert van Bolhuis <nvbolhuis(a)gmail.com> Signed-off-by: Kalle Valo <kvalo(a)kernel.org> Link: https://patch.msgid.link/20241107132903.13513-1-nvbolhuis@gmail.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Hai <wanghai38(a)huawei.com> --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c index b6d0bc73923f..75dc7904a4bd 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c @@ -769,7 +769,7 @@ void brcmf_sdiod_sgtable_alloc(struct brcmf_sdio_dev *sdiodev) nents = max_t(uint, BRCMF_DEFAULT_RXGLOM_SIZE, sdiodev->settings->bus.sdio.txglomsz); - nents += (nents >> 4) + 1; + nents *= 2; WARN_ON(nents > sdiodev->max_segment_count); -- 2.17.1

2 1

[PATCH OLK-6.6] wifi: brcmfmac: Fix oops due to NULL pointer dereference in brcmf_sdiod_sglist_rw()
by Wang Hai 04 Jan '25

04 Jan '25

From: Norbert van Bolhuis <nvbolhuis(a)gmail.com> stable inclusion from stable-v6.6.66 commit 07c020c6d14d29e5a3ea4e4576b8ecf956a80834 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAO3 CVE: CVE-2024-56593 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 857282b819cbaa0675aaab1e7542e2c0579f52d7 ] This patch fixes a NULL pointer dereference bug in brcmfmac that occurs when a high 'sd_sgentry_align' value applies (e.g. 512) and a lot of queued SKBs are sent from the pkt queue. The problem is the number of entries in the pre-allocated sgtable, it is nents = max(rxglom_size, txglom_size) + max(rxglom_size, txglom_size) >> 4 + 1. Given the default [rt]xglom_size=32 it's actually 35 which is too small. Worst case, the pkt queue can end up with 64 SKBs. This occurs when a new SKB is added for each original SKB if tailroom isn't enough to hold tail_pad. At least one sg entry is needed for each SKB. So, eventually the "skb_queue_walk loop" in brcmf_sdiod_sglist_rw may run out of sg entries. This makes sg_next return NULL and this causes the oops. The patch sets nents to max(rxglom_size, txglom_size) * 2 to be able handle the worst-case. Btw. this requires only 64-35=29 * 16 (or 20 if CONFIG_NEED_SG_DMA_LENGTH) = 464 additional bytes of memory. Signed-off-by: Norbert van Bolhuis <nvbolhuis(a)gmail.com> Signed-off-by: Kalle Valo <kvalo(a)kernel.org> Link: https://patch.msgid.link/20241107132903.13513-1-nvbolhuis@gmail.com Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Hai <wanghai38(a)huawei.com> --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c index 00679a990e3d..7710367c319e 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c @@ -770,7 +770,7 @@ void brcmf_sdiod_sgtable_alloc(struct brcmf_sdio_dev *sdiodev) nents = max_t(uint, BRCMF_DEFAULT_RXGLOM_SIZE, sdiodev->settings->bus.sdio.txglomsz); - nents += (nents >> 4) + 1; + nents *= 2; WARN_ON(nents > sdiodev->max_segment_count); -- 2.17.1

2 1

[PATCH OLK-5.10] net/mlx5: Fix error path in multi-packet WQE transmit
by Guo Mengqi 04 Jan '25

04 Jan '25

From: Gerd Bayer <gbayer(a)linux.ibm.com> stable inclusion from stable-v5.10.227 commit ca36d6c1a49b6965c86dd528a73f38bc62d9c625 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAYRD9 CVE: CVE-2024-50001 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 2bcae12c795f32ddfbf8c80d1b5f1d3286341c32 ] Remove the erroneous unmap in case no DMA mapping was established The multi-packet WQE transmit code attempts to obtain a DMA mapping for the skb. This could fail, e.g. under memory pressure, when the IOMMU driver just can't allocate more memory for page tables. While the code tries to handle this in the path below the err_unmap label it erroneously unmaps one entry from the sq's FIFO list of active mappings. Since the current map attempt failed this unmap is removing some random DMA mapping that might still be required. If the PCI function now presents that IOVA, the IOMMU may assumes a rogue DMA access and e.g. on s390 puts the PCI function in error state. The erroneous behavior was seen in a stress-test environment that created memory pressure. Fixes: 5af75c747e2a ("net/mlx5e: Enhanced TX MPWQE for SKBs") Signed-off-by: Gerd Bayer <gbayer(a)linux.ibm.com> Reviewed-by: Zhu Yanjun <yanjun.zhu(a)linux.dev> Acked-by: Maxim Mikityanskiy <maxtram95(a)gmail.com> Signed-off-by: Saeed Mahameed <saeedm(a)nvidia.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> --- drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 373668068071..9b1e43ff8ae1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -601,7 +601,6 @@ mlx5e_sq_xmit_mpwqe(struct mlx5e_txqsq *sq, struct sk_buff *skb, return; err_unmap: - mlx5e_dma_unmap_wqe_err(sq, 1); sq->stats->dropped++; dev_kfree_skb_any(skb); } -- 2.22.0

2 1

[PATCH openEuler-22.03-LTS-SP1] net/mlx5: Fix error path in multi-packet WQE transmit
by Guo Mengqi 04 Jan '25

04 Jan '25

From: Gerd Bayer <gbayer(a)linux.ibm.com> stable inclusion from stable-v5.10.227 commit ca36d6c1a49b6965c86dd528a73f38bc62d9c625 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAYRD9 CVE: CVE-2024-50001 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 2bcae12c795f32ddfbf8c80d1b5f1d3286341c32 ] Remove the erroneous unmap in case no DMA mapping was established The multi-packet WQE transmit code attempts to obtain a DMA mapping for the skb. This could fail, e.g. under memory pressure, when the IOMMU driver just can't allocate more memory for page tables. While the code tries to handle this in the path below the err_unmap label it erroneously unmaps one entry from the sq's FIFO list of active mappings. Since the current map attempt failed this unmap is removing some random DMA mapping that might still be required. If the PCI function now presents that IOVA, the IOMMU may assumes a rogue DMA access and e.g. on s390 puts the PCI function in error state. The erroneous behavior was seen in a stress-test environment that created memory pressure. Fixes: 5af75c747e2a ("net/mlx5e: Enhanced TX MPWQE for SKBs") Signed-off-by: Gerd Bayer <gbayer(a)linux.ibm.com> Reviewed-by: Zhu Yanjun <yanjun.zhu(a)linux.dev> Acked-by: Maxim Mikityanskiy <maxtram95(a)gmail.com> Signed-off-by: Saeed Mahameed <saeedm(a)nvidia.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> --- drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 373668068071..9b1e43ff8ae1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -601,7 +601,6 @@ mlx5e_sq_xmit_mpwqe(struct mlx5e_txqsq *sq, struct sk_buff *skb, return; err_unmap: - mlx5e_dma_unmap_wqe_err(sq, 1); sq->stats->dropped++; dev_kfree_skb_any(skb); } -- 2.22.0

2 1

[PATCH OLK-5.10] crypto: hisilicon/qm - inject error before stopping queue
by Guo Mengqi 04 Jan '25

04 Jan '25

From: Weili Qian <qianweili(a)huawei.com> stable inclusion from stable-v6.1.113 commit 98d3be34c9153eceadb56de50d9f9347e88d86e4 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAYQSI CVE: CVE-2024-47730 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit b04f06fc0243600665b3b50253869533b7938468 ] The master ooo cannot be completely closed when the accelerator core reports memory error. Therefore, the driver needs to inject the qm error to close the master ooo. Currently, the qm error is injected after stopping queue, memory may be released immediately after stopping queue, causing the device to access the released memory. Therefore, error is injected to close master ooo before stopping queue to ensure that the device does not access the released memory. Fixes: 6c6dd5802c2d ("crypto: hisilicon/qm - add controller reset interface") Signed-off-by: Weili Qian <qianweili(a)huawei.com> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: drivers/crypto/hisilicon/qm.c [context conflict] Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> --- drivers/crypto/hisilicon/qm.c | 48 +++++++++++++++++------------------ 1 file changed, 24 insertions(+), 24 deletions(-) diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index fe043487ae58..23f74b630e5c 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -4196,6 +4196,28 @@ static int qm_set_vf_mse(struct hisi_qm *qm, bool set) return -ETIMEDOUT; } +static void qm_dev_ecc_mbit_handle(struct hisi_qm *qm) +{ + u32 nfe_enb = 0; + + /* Kunpeng930 hardware automatically close master ooo when NFE occurs */ + if (qm->ver >= QM_HW_V3) + return; + + if (!qm->err_status.is_dev_ecc_mbit && + qm->err_status.is_qm_ecc_mbit && + qm->err_ini->close_axi_master_ooo) { + qm->err_ini->close_axi_master_ooo(qm); + } else if (qm->err_status.is_dev_ecc_mbit && + !qm->err_status.is_qm_ecc_mbit && + !qm->err_ini->close_axi_master_ooo) { + nfe_enb = readl(qm->io_base + QM_RAS_NFE_ENABLE); + writel(nfe_enb & QM_RAS_NFE_MBIT_DISABLE, + qm->io_base + QM_RAS_NFE_ENABLE); + writel(QM_ECC_MBIT, qm->io_base + QM_ABNORMAL_INT_SET); + } +} + static int qm_vf_reset_prepare(struct hisi_qm *qm, enum qm_stop_reason stop_reason) { @@ -4260,6 +4282,8 @@ static int qm_controller_reset_prepare(struct hisi_qm *qm) return ret; } + qm_dev_ecc_mbit_handle(qm); + /* PF obtains the information of VF by querying the register. */ qm_cmd_uninit(qm); @@ -4288,28 +4312,6 @@ static int qm_controller_reset_prepare(struct hisi_qm *qm) return 0; } -static void qm_dev_ecc_mbit_handle(struct hisi_qm *qm) -{ - u32 nfe_enb = 0; - - /* Kunpeng930 hardware automatically close master ooo when NFE occurs */ - if (qm->ver >= QM_HW_V3) - return; - - if (!qm->err_status.is_dev_ecc_mbit && - qm->err_status.is_qm_ecc_mbit && - qm->err_ini->close_axi_master_ooo) { - qm->err_ini->close_axi_master_ooo(qm); - } else if (qm->err_status.is_dev_ecc_mbit && - !qm->err_status.is_qm_ecc_mbit && - !qm->err_ini->close_axi_master_ooo) { - nfe_enb = readl(qm->io_base + QM_RAS_NFE_ENABLE); - writel(nfe_enb & QM_RAS_NFE_MBIT_DISABLE, - qm->io_base + QM_RAS_NFE_ENABLE); - writel(QM_ECC_MBIT, qm->io_base + QM_ABNORMAL_INT_SET); - } -} - static int qm_soft_reset_prepare(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; @@ -4335,8 +4337,6 @@ static int qm_soft_reset_prepare(struct hisi_qm *qm) return ret; } - qm_dev_ecc_mbit_handle(qm); - /* OOO register set and check */ writel(ACC_MASTER_GLOBAL_CTRL_SHUTDOWN, qm->io_base + ACC_MASTER_GLOBAL_CTRL); -- 2.22.0

2 1

[PATCH OLK-5.10] drm/amd/display: Check null pointers before using dc->clk_mgr
by Guo Mengqi 04 Jan '25

04 Jan '25

From: Alex Hung <alex.hung(a)amd.com> stable inclusion from stable-v5.10.227 commit 8d54001f8dccd56146973f23f3ab2ba037a21251 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAZVX4 CVE: CVE-2024-49907 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 95d9e0803e51d5a24276b7643b244c7477daf463 ] [WHY & HOW] dc->clk_mgr is null checked previously in the same function, indicating it might be null. Passing "dc" to "dc->hwss.apply_idle_power_optimizations", which dereferences null "dc->clk_mgr". (The function pointer resolves to "dcn35_apply_idle_power_optimizations".) This fixes 1 FORWARD_NULL issue reported by Coverity. Reviewed-by: Rodrigo Siqueira <rodrigo.siqueira(a)amd.com> Signed-off-by: Alex Hung <alex.hung(a)amd.com> Signed-off-by: Tom Chung <chiahsuan.chung(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> --- drivers/gpu/drm/amd/display/dc/core/dc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 287a5b15cec9..3ecc4561a43e 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -3077,7 +3077,8 @@ void dc_allow_idle_optimizations(struct dc *dc, bool allow) if (allow == dc->idle_optimizations_allowed) return; - if (dc->hwss.apply_idle_power_optimizations && dc->hwss.apply_idle_power_optimizations(dc, allow)) + if (dc->hwss.apply_idle_power_optimizations && dc->clk_mgr != NULL && + dc->hwss.apply_idle_power_optimizations(dc, allow)) dc->idle_optimizations_allowed = allow; } -- 2.22.0

2 1

[PATCH openEuler-22.03-LTS-SP1] iommu/vt-d: Fix PCI device refcount leak in dmar_dev_scope_init()
by Guo Mengqi 04 Jan '25

04 Jan '25

From: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> stable inclusion from stable-v5.10.158 commit a5c65cd56aed027f8a97fda8b691caaeb66d115e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAYRE3 CVE: CVE-2022-49002 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 4bedbbd782ebbe7287231fea862c158d4f08a9e3 ] for_each_pci_dev() is implemented by pci_get_device(). The comment of pci_get_device() says that it will increase the reference count for the returned pci_dev and also decrease the reference count for the input pci_dev @from if it is not NULL. If we break for_each_pci_dev() loop with pdev not NULL, we need to call pci_dev_put() to decrease the reference count. Add the missing pci_dev_put() for the error path to avoid reference count leak. Fixes: 2e4552893038 ("iommu/vt-d: Unify the way to process DMAR device scope array") Signed-off-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Link: https://lore.kernel.org/r/20221121113649.190393-3-wangxiongfeng2@huawei.com Signed-off-by: Lu Baolu <baolu.lu(a)linux.intel.com> Signed-off-by: Joerg Roedel <jroedel(a)suse.de> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Hai <wanghai38(a)huawei.com> Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> --- drivers/iommu/intel/dmar.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index c2af96eb633f..fde7eb3d8103 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -827,6 +827,7 @@ int __init dmar_dev_scope_init(void) info = dmar_alloc_pci_notify_info(dev, BUS_NOTIFY_ADD_DEVICE); if (!info) { + pci_dev_put(dev); return dmar_dev_scope_status; } else { dmar_pci_bus_add_dev(info); -- 2.22.0

2 1

[PATCH openEuler-22.03-LTS-SP1] drm/amd/display: Check null pointers before using dc->clk_mgr
by Guo Mengqi 04 Jan '25

04 Jan '25

From: Alex Hung <alex.hung(a)amd.com> stable inclusion from stable-v5.10.227 commit 8d54001f8dccd56146973f23f3ab2ba037a21251 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAZVX4 CVE: CVE-2024-49907 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 95d9e0803e51d5a24276b7643b244c7477daf463 ] [WHY & HOW] dc->clk_mgr is null checked previously in the same function, indicating it might be null. Passing "dc" to "dc->hwss.apply_idle_power_optimizations", which dereferences null "dc->clk_mgr". (The function pointer resolves to "dcn35_apply_idle_power_optimizations".) This fixes 1 FORWARD_NULL issue reported by Coverity. Reviewed-by: Rodrigo Siqueira <rodrigo.siqueira(a)amd.com> Signed-off-by: Alex Hung <alex.hung(a)amd.com> Signed-off-by: Tom Chung <chiahsuan.chung(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> --- drivers/gpu/drm/amd/display/dc/core/dc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index f1d84092f057..1a183eb0568b 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -3075,7 +3075,8 @@ void dc_allow_idle_optimizations(struct dc *dc, bool allow) if (allow == dc->idle_optimizations_allowed) return; - if (dc->hwss.apply_idle_power_optimizations && dc->hwss.apply_idle_power_optimizations(dc, allow)) + if (dc->hwss.apply_idle_power_optimizations && dc->clk_mgr != NULL && + dc->hwss.apply_idle_power_optimizations(dc, allow)) dc->idle_optimizations_allowed = allow; } -- 2.22.0

2 1

[PATCH OLK-5.10] staging: iio: frequency: ad9832: fix division by zero in ad9832_calc_freqreg()
by Guo Mengqi 04 Jan '25

04 Jan '25

From: Zicheng Qu <quzicheng(a)huawei.com> stable inclusion from stable-v5.10.229 commit 442f786c5bff8cfd756ebdeaa4aadbf05c22aa5a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IB67SG CVE: CVE-2024-50233 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 6bd301819f8f69331a55ae2336c8b111fc933f3d upstream. In the ad9832_write_frequency() function, clk_get_rate() might return 0. This can lead to a division by zero when calling ad9832_calc_freqreg(). The check if (fout > (clk_get_rate(st->mclk) / 2)) does not protect against the case when fout is 0. The ad9832_write_frequency() function is called from ad9832_write(), and fout is derived from a text buffer, which can contain any value. Link: https://lore.kernel.org/all/2024100904-CVE-2024-47663-9bdc@gregkh/ Fixes: ea707584bac1 ("Staging: IIO: DDS: AD9832 / AD9835 driver") Cc: stable(a)vger.kernel.org Signed-off-by: Zicheng Qu <quzicheng(a)huawei.com> Reviewed-by: Nuno Sa <nuno.sa(a)analog.com> Reviewed-by: Dan Carpenter <dan.carpenter(a)linaro.org> Link: https://patch.msgid.link/20241022134354.574614-1-quzicheng@huawei.com Signed-off-by: Jonathan Cameron <Jonathan.Cameron(a)huawei.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> --- drivers/staging/iio/frequency/ad9832.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/staging/iio/frequency/ad9832.c b/drivers/staging/iio/frequency/ad9832.c index 447937e04ebd..61c5f33ac271 100644 --- a/drivers/staging/iio/frequency/ad9832.c +++ b/drivers/staging/iio/frequency/ad9832.c @@ -129,12 +129,15 @@ static unsigned long ad9832_calc_freqreg(unsigned long mclk, unsigned long fout) static int ad9832_write_frequency(struct ad9832_state *st, unsigned int addr, unsigned long fout) { + unsigned long clk_freq; unsigned long regval; - if (fout > (clk_get_rate(st->mclk) / 2)) + clk_freq = clk_get_rate(st->mclk); + + if (!clk_freq || fout > (clk_freq / 2)) return -EINVAL; - regval = ad9832_calc_freqreg(clk_get_rate(st->mclk), fout); + regval = ad9832_calc_freqreg(clk_freq, fout); st->freq_data[0] = cpu_to_be16((AD9832_CMD_FRE8BITSW << CMD_SHIFT) | (addr << ADD_SHIFT) | -- 2.22.0

2 1

[PATCH openEuler-22.03-LTS-SP1] staging: iio: frequency: ad9832: fix division by zero in ad9832_calc_freqreg()
by Guo Mengqi 04 Jan '25

04 Jan '25

From: Zicheng Qu <quzicheng(a)huawei.com> stable inclusion from stable-v5.10.229 commit 442f786c5bff8cfd756ebdeaa4aadbf05c22aa5a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IB67SG CVE: CVE-2024-50233 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 6bd301819f8f69331a55ae2336c8b111fc933f3d upstream. In the ad9832_write_frequency() function, clk_get_rate() might return 0. This can lead to a division by zero when calling ad9832_calc_freqreg(). The check if (fout > (clk_get_rate(st->mclk) / 2)) does not protect against the case when fout is 0. The ad9832_write_frequency() function is called from ad9832_write(), and fout is derived from a text buffer, which can contain any value. Link: https://lore.kernel.org/all/2024100904-CVE-2024-47663-9bdc@gregkh/ Fixes: ea707584bac1 ("Staging: IIO: DDS: AD9832 / AD9835 driver") Cc: stable(a)vger.kernel.org Signed-off-by: Zicheng Qu <quzicheng(a)huawei.com> Reviewed-by: Nuno Sa <nuno.sa(a)analog.com> Reviewed-by: Dan Carpenter <dan.carpenter(a)linaro.org> Link: https://patch.msgid.link/20241022134354.574614-1-quzicheng@huawei.com Signed-off-by: Jonathan Cameron <Jonathan.Cameron(a)huawei.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> --- drivers/staging/iio/frequency/ad9832.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/staging/iio/frequency/ad9832.c b/drivers/staging/iio/frequency/ad9832.c index 447937e04ebd..61c5f33ac271 100644 --- a/drivers/staging/iio/frequency/ad9832.c +++ b/drivers/staging/iio/frequency/ad9832.c @@ -129,12 +129,15 @@ static unsigned long ad9832_calc_freqreg(unsigned long mclk, unsigned long fout) static int ad9832_write_frequency(struct ad9832_state *st, unsigned int addr, unsigned long fout) { + unsigned long clk_freq; unsigned long regval; - if (fout > (clk_get_rate(st->mclk) / 2)) + clk_freq = clk_get_rate(st->mclk); + + if (!clk_freq || fout > (clk_freq / 2)) return -EINVAL; - regval = ad9832_calc_freqreg(clk_get_rate(st->mclk), fout); + regval = ad9832_calc_freqreg(clk_freq, fout); st->freq_data[0] = cpu_to_be16((AD9832_CMD_FRE8BITSW << CMD_SHIFT) | (addr << ADD_SHIFT) | -- 2.22.0

2 1

[PATCH OLK-6.6] brd: defer automatic disk creation until module initialization succeeds
by Zheng Qixing 04 Jan '25

04 Jan '25

From: Yang Erkun <yangerkun(a)huawei.com> stable inclusion from stable-v6.6.64 commit 410896624db639500f24f46478b4bfa05c76bf56 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEDPI CVE: CVE-2024-56693 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 826cc42adf44930a633d11a5993676d85ddb0842 ] My colleague Wupeng found the following problems during fault injection: BUG: unable to handle page fault for address: fffffbfff809d073 PGD 6e648067 P4D 123ec8067 PUD 123ec4067 PMD 100e38067 PTE 0 Oops: Oops: 0000 [#1] PREEMPT SMP KASAN NOPTI CPU: 5 UID: 0 PID: 755 Comm: modprobe Not tainted 6.12.0-rc3+ #17 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.1-2.fc37 04/01/2014 RIP: 0010:__asan_load8+0x4c/0xa0 ... Call Trace: <TASK> blkdev_put_whole+0x41/0x70 bdev_release+0x1a3/0x250 blkdev_release+0x11/0x20 __fput+0x1d7/0x4a0 task_work_run+0xfc/0x180 syscall_exit_to_user_mode+0x1de/0x1f0 do_syscall_64+0x6b/0x170 entry_SYSCALL_64_after_hwframe+0x76/0x7e loop_init() is calling loop_add() after __register_blkdev() succeeds and is ignoring disk_add() failure from loop_add(), for loop_add() failure is not fatal and successfully created disks are already visible to bdev_open(). brd_init() is currently calling brd_alloc() before __register_blkdev() succeeds and is releasing successfully created disks when brd_init() returns an error. This can cause UAF for the latter two case: case 1: T1: modprobe brd brd_init brd_alloc(0) // success add_disk disk_scan_partitions bdev_file_open_by_dev // alloc file fput // won't free until back to userspace brd_alloc(1) // failed since mem alloc error inject // error path for modprobe will release code segment // back to userspace __fput blkdev_release bdev_release blkdev_put_whole bdev->bd_disk->fops->release // fops is freed now, UAF! case 2: T1: T2: modprobe brd brd_init brd_alloc(0) // success open(/dev/ram0) brd_alloc(1) // fail // error path for modprobe close(/dev/ram0) ... /* UAF! */ bdev->bd_disk->fops->release Fix this problem by following what loop_init() does. Besides, reintroduce brd_devices_mutex to help serialize modifications to brd_list. Fixes: 7f9b348cb5e9 ("brd: convert to blk_alloc_disk/blk_cleanup_disk") Reported-by: Wupeng Ma <mawupeng1(a)huawei.com> Signed-off-by: Yang Erkun <yangerkun(a)huawei.com> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Link: https://lore.kernel.org/r/20241030034914.907829-1-yangerkun@huaweicloud.com Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> --- drivers/block/brd.c | 66 ++++++++++++++++++++++++++++++--------------- 1 file changed, 44 insertions(+), 22 deletions(-) diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 970bd6ff38c4..d816d1512531 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -310,8 +310,40 @@ __setup("ramdisk_size=", ramdisk_size); * (should share code eventually). */ static LIST_HEAD(brd_devices); +static DEFINE_MUTEX(brd_devices_mutex); static struct dentry *brd_debugfs_dir; +static struct brd_device *brd_find_or_alloc_device(int i) +{ + struct brd_device *brd; + + mutex_lock(&brd_devices_mutex); + list_for_each_entry(brd, &brd_devices, brd_list) { + if (brd->brd_number == i) { + mutex_unlock(&brd_devices_mutex); + return ERR_PTR(-EEXIST); + } + } + + brd = kzalloc(sizeof(*brd), GFP_KERNEL); + if (!brd) { + mutex_unlock(&brd_devices_mutex); + return ERR_PTR(-ENOMEM); + } + brd->brd_number = i; + list_add_tail(&brd->brd_list, &brd_devices); + mutex_unlock(&brd_devices_mutex); + return brd; +} + +static void brd_free_device(struct brd_device *brd) +{ + mutex_lock(&brd_devices_mutex); + list_del(&brd->brd_list); + mutex_unlock(&brd_devices_mutex); + kfree(brd); +} + static int brd_alloc(int i) { struct brd_device *brd; @@ -319,14 +351,9 @@ static int brd_alloc(int i) char buf[DISK_NAME_LEN]; int err = -ENOMEM; - list_for_each_entry(brd, &brd_devices, brd_list) - if (brd->brd_number == i) - return -EEXIST; - brd = kzalloc(sizeof(*brd), GFP_KERNEL); - if (!brd) - return -ENOMEM; - brd->brd_number = i; - list_add_tail(&brd->brd_list, &brd_devices); + brd = brd_find_or_alloc_device(i); + if (IS_ERR(brd)) + return PTR_ERR(brd); xa_init(&brd->brd_pages); @@ -369,8 +396,7 @@ static int brd_alloc(int i) out_cleanup_disk: put_disk(disk); out_free_dev: - list_del(&brd->brd_list); - kfree(brd); + brd_free_device(brd); return err; } @@ -389,8 +415,7 @@ static void brd_cleanup(void) del_gendisk(brd->brd_disk); put_disk(brd->brd_disk); brd_free_pages(brd); - list_del(&brd->brd_list); - kfree(brd); + brd_free_device(brd); } } @@ -417,16 +442,6 @@ static int __init brd_init(void) { int err, i; - brd_check_and_reset_par(); - - brd_debugfs_dir = debugfs_create_dir("ramdisk_pages", NULL); - - for (i = 0; i < rd_nr; i++) { - err = brd_alloc(i); - if (err) - goto out_free; - } - /* * brd module now has a feature to instantiate underlying device * structure on-demand, provided that there is an access dev node. @@ -442,11 +457,18 @@ static int __init brd_init(void) * dynamically. */ + brd_check_and_reset_par(); + + brd_debugfs_dir = debugfs_create_dir("ramdisk_pages", NULL); + if (__register_blkdev(RAMDISK_MAJOR, "ramdisk", brd_probe)) { err = -EIO; goto out_free; } + for (i = 0; i < rd_nr; i++) + brd_alloc(i); + pr_info("brd: module loaded\n"); return 0; -- 2.39.2

2 1

[PATCH OLK-5.10] drm: zynqmp_kms: Unplug DRM device before removal
by Zheng Qixing 04 Jan '25

04 Jan '25

From: Sean Anderson <sean.anderson(a)linux.dev> mainline inclusion from mainline-v6.13-rc1 commit 2e07c88914fc5289c21820b1aa94f058feb38197 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAE5 CVE: CVE-2024-56538 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Prevent userspace accesses to the DRM device from causing use-after-frees by unplugging the device before we remove it. This causes any further userspace accesses to result in an error without further calls into this driver's internals. Fixes: d76271d22694 ("drm: xlnx: DRM/KMS driver for Xilinx ZynqMP DisplayPort Subsystem") Closes: https://lore.kernel.org/dri-devel/4d8f4c9b-2efb-4774-9a37-2f257f79b2c9@linu… Signed-off-by: Sean Anderson <sean.anderson(a)linux.dev> Signed-off-by: Tomi Valkeinen <tomi.valkeinen(a)ideasonboard.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240809193600.3360015-2-sean… Conflicts: drivers/gpu/drm/xlnx/zynqmp_kms.c [The conflict is due to the commit 074ef0ce9f83 ("drm: xlnx: zynqmp_dpsub: Move all DRM init and cleanup to zynqmp_kms.c") not being merged.] Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> --- drivers/gpu/drm/xlnx/zynqmp_dpsub.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xlnx/zynqmp_dpsub.c b/drivers/gpu/drm/xlnx/zynqmp_dpsub.c index 5f6eea81f3cc..2f69e2671e79 100644 --- a/drivers/gpu/drm/xlnx/zynqmp_dpsub.c +++ b/drivers/gpu/drm/xlnx/zynqmp_dpsub.c @@ -264,7 +264,7 @@ static int zynqmp_dpsub_remove(struct platform_device *pdev) struct zynqmp_dpsub *dpsub = platform_get_drvdata(pdev); struct drm_device *drm = &dpsub->drm; - drm_dev_unregister(drm); + drm_dev_unplug(drm); drm_atomic_helper_shutdown(drm); drm_kms_helper_poll_fini(drm); -- 2.39.2

2 1

[PATCH openEuler-22.03-LTS-SP1] drm: zynqmp_kms: Unplug DRM device before removal
by Zheng Qixing 04 Jan '25

04 Jan '25

From: Sean Anderson <sean.anderson(a)linux.dev> mainline inclusion from mainline-v6.13-rc1 commit 2e07c88914fc5289c21820b1aa94f058feb38197 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAE5 CVE: CVE-2024-56538 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Prevent userspace accesses to the DRM device from causing use-after-frees by unplugging the device before we remove it. This causes any further userspace accesses to result in an error without further calls into this driver's internals. Fixes: d76271d22694 ("drm: xlnx: DRM/KMS driver for Xilinx ZynqMP DisplayPort Subsystem") Closes: https://lore.kernel.org/dri-devel/4d8f4c9b-2efb-4774-9a37-2f257f79b2c9@linu… Signed-off-by: Sean Anderson <sean.anderson(a)linux.dev> Signed-off-by: Tomi Valkeinen <tomi.valkeinen(a)ideasonboard.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240809193600.3360015-2-sean… Conflicts: drivers/gpu/drm/xlnx/zynqmp_kms.c [The conflict is due to the commit 074ef0ce9f83 ("drm: xlnx: zynqmp_dpsub: Move all DRM init and cleanup to zynqmp_kms.c") not being merged.] Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> --- drivers/gpu/drm/xlnx/zynqmp_dpsub.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xlnx/zynqmp_dpsub.c b/drivers/gpu/drm/xlnx/zynqmp_dpsub.c index 5f6eea81f3cc..2f69e2671e79 100644 --- a/drivers/gpu/drm/xlnx/zynqmp_dpsub.c +++ b/drivers/gpu/drm/xlnx/zynqmp_dpsub.c @@ -264,7 +264,7 @@ static int zynqmp_dpsub_remove(struct platform_device *pdev) struct zynqmp_dpsub *dpsub = platform_get_drvdata(pdev); struct drm_device *drm = &dpsub->drm; - drm_dev_unregister(drm); + drm_dev_unplug(drm); drm_atomic_helper_shutdown(drm); drm_kms_helper_poll_fini(drm); -- 2.39.2

2 1

[PATCH OLK-6.6] drm: zynqmp_kms: Unplug DRM device before removal
by Zheng Qixing 04 Jan '25

04 Jan '25

From: Sean Anderson <sean.anderson(a)linux.dev> stable inclusion from stable-v6.6.64 commit a17b9afe58c474657449cf87e238b1788200576b category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAE5 CVE: CVE-2024-56538 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 2e07c88914fc5289c21820b1aa94f058feb38197 ] Prevent userspace accesses to the DRM device from causing use-after-frees by unplugging the device before we remove it. This causes any further userspace accesses to result in an error without further calls into this driver's internals. Fixes: d76271d22694 ("drm: xlnx: DRM/KMS driver for Xilinx ZynqMP DisplayPort Subsystem") Closes: https://lore.kernel.org/dri-devel/4d8f4c9b-2efb-4774-9a37-2f257f79b2c9@linu… Signed-off-by: Sean Anderson <sean.anderson(a)linux.dev> Signed-off-by: Tomi Valkeinen <tomi.valkeinen(a)ideasonboard.com> Link: https://patchwork.freedesktop.org/patch/msgid/20240809193600.3360015-2-sean… Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> --- drivers/gpu/drm/xlnx/zynqmp_kms.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xlnx/zynqmp_kms.c b/drivers/gpu/drm/xlnx/zynqmp_kms.c index 44d4a510ad7d..ccb6e065dc6d 100644 --- a/drivers/gpu/drm/xlnx/zynqmp_kms.c +++ b/drivers/gpu/drm/xlnx/zynqmp_kms.c @@ -533,7 +533,7 @@ void zynqmp_dpsub_drm_cleanup(struct zynqmp_dpsub *dpsub) { struct drm_device *drm = &dpsub->drm->dev; - drm_dev_unregister(drm); + drm_dev_unplug(drm); drm_atomic_helper_shutdown(drm); drm_encoder_cleanup(&dpsub->drm->encoder); drm_kms_helper_poll_fini(drm); -- 2.39.2

2 1

[PATCH OLK-6.6] block: fix uaf for flush rq while iterating tags
by Zheng Qixing 04 Jan '25

04 Jan '25

From: Yu Kuai <yukuai3(a)huawei.com> mainline inclusion from mainline-v6.13-rc1 commit 3802f73bd80766d70f319658f334754164075bc3 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAF4 CVE: CVE-2024-53170 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------- blk_mq_clear_flush_rq_mapping() is not called during scsi probe, by checking blk_queue_init_done(). However, QUEUE_FLAG_INIT_DONE is cleared in del_gendisk by commit aec89dc5d421 ("block: keep q_usage_counter in atomic mode after del_gendisk"), hence for disk like scsi, following blk_mq_destroy_queue() will not clear flush rq from tags->rqs[] as well, cause following uaf that is found by our syzkaller for v6.6: ================================================================== BUG: KASAN: slab-use-after-free in blk_mq_find_and_get_req+0x16e/0x1a0 block/blk-mq-tag.c:261 Read of size 4 at addr ffff88811c969c20 by task kworker/1:2H/224909 CPU: 1 PID: 224909 Comm: kworker/1:2H Not tainted 6.6.0-ga836a5060850 #32 Workqueue: kblockd blk_mq_timeout_work Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x91/0xf0 lib/dump_stack.c:106 print_address_description.constprop.0+0x66/0x300 mm/kasan/report.c:364 print_report+0x3e/0x70 mm/kasan/report.c:475 kasan_report+0xb8/0xf0 mm/kasan/report.c:588 blk_mq_find_and_get_req+0x16e/0x1a0 block/blk-mq-tag.c:261 bt_iter block/blk-mq-tag.c:288 [inline] __sbitmap_for_each_set include/linux/sbitmap.h:295 [inline] sbitmap_for_each_set include/linux/sbitmap.h:316 [inline] bt_for_each+0x455/0x790 block/blk-mq-tag.c:325 blk_mq_queue_tag_busy_iter+0x320/0x740 block/blk-mq-tag.c:534 blk_mq_timeout_work+0x1a3/0x7b0 block/blk-mq.c:1673 process_one_work+0x7c4/0x1450 kernel/workqueue.c:2631 process_scheduled_works kernel/workqueue.c:2704 [inline] worker_thread+0x804/0xe40 kernel/workqueue.c:2785 kthread+0x346/0x450 kernel/kthread.c:388 ret_from_fork+0x4d/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1b/0x30 arch/x86/entry/entry_64.S:293 Allocated by task 942: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 ____kasan_kmalloc mm/kasan/common.c:374 [inline] __kasan_kmalloc mm/kasan/common.c:383 [inline] __kasan_kmalloc+0xaa/0xb0 mm/kasan/common.c:380 kasan_kmalloc include/linux/kasan.h:198 [inline] __do_kmalloc_node mm/slab_common.c:1007 [inline] __kmalloc_node+0x69/0x170 mm/slab_common.c:1014 kmalloc_node include/linux/slab.h:620 [inline] kzalloc_node include/linux/slab.h:732 [inline] blk_alloc_flush_queue+0x144/0x2f0 block/blk-flush.c:499 blk_mq_alloc_hctx+0x601/0x940 block/blk-mq.c:3788 blk_mq_alloc_and_init_hctx+0x27f/0x330 block/blk-mq.c:4261 blk_mq_realloc_hw_ctxs+0x488/0x5e0 block/blk-mq.c:4294 blk_mq_init_allocated_queue+0x188/0x860 block/blk-mq.c:4350 blk_mq_init_queue_data block/blk-mq.c:4166 [inline] blk_mq_init_queue+0x8d/0x100 block/blk-mq.c:4176 scsi_alloc_sdev+0x843/0xd50 drivers/scsi/scsi_scan.c:335 scsi_probe_and_add_lun+0x77c/0xde0 drivers/scsi/scsi_scan.c:1189 __scsi_scan_target+0x1fc/0x5a0 drivers/scsi/scsi_scan.c:1727 scsi_scan_channel drivers/scsi/scsi_scan.c:1815 [inline] scsi_scan_channel+0x14b/0x1e0 drivers/scsi/scsi_scan.c:1791 scsi_scan_host_selected+0x2fe/0x400 drivers/scsi/scsi_scan.c:1844 scsi_scan+0x3a0/0x3f0 drivers/scsi/scsi_sysfs.c:151 store_scan+0x2a/0x60 drivers/scsi/scsi_sysfs.c:191 dev_attr_store+0x5c/0x90 drivers/base/core.c:2388 sysfs_kf_write+0x11c/0x170 fs/sysfs/file.c:136 kernfs_fop_write_iter+0x3fc/0x610 fs/kernfs/file.c:338 call_write_iter include/linux/fs.h:2083 [inline] new_sync_write+0x1b4/0x2d0 fs/read_write.c:493 vfs_write+0x76c/0xb00 fs/read_write.c:586 ksys_write+0x127/0x250 fs/read_write.c:639 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x70/0x120 arch/x86/entry/common.c:81 entry_SYSCALL_64_after_hwframe+0x78/0xe2 Freed by task 244687: kasan_save_stack+0x22/0x50 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 kasan_save_free_info+0x2b/0x50 mm/kasan/generic.c:522 ____kasan_slab_free mm/kasan/common.c:236 [inline] __kasan_slab_free+0x12a/0x1b0 mm/kasan/common.c:244 kasan_slab_free include/linux/kasan.h:164 [inline] slab_free_hook mm/slub.c:1815 [inline] slab_free_freelist_hook mm/slub.c:1841 [inline] slab_free mm/slub.c:3807 [inline] __kmem_cache_free+0xe4/0x520 mm/slub.c:3820 blk_free_flush_queue+0x40/0x60 block/blk-flush.c:520 blk_mq_hw_sysfs_release+0x4a/0x170 block/blk-mq-sysfs.c:37 kobject_cleanup+0x136/0x410 lib/kobject.c:689 kobject_release lib/kobject.c:720 [inline] kref_put include/linux/kref.h:65 [inline] kobject_put+0x119/0x140 lib/kobject.c:737 blk_mq_release+0x24f/0x3f0 block/blk-mq.c:4144 blk_free_queue block/blk-core.c:298 [inline] blk_put_queue+0xe2/0x180 block/blk-core.c:314 blkg_free_workfn+0x376/0x6e0 block/blk-cgroup.c:144 process_one_work+0x7c4/0x1450 kernel/workqueue.c:2631 process_scheduled_works kernel/workqueue.c:2704 [inline] worker_thread+0x804/0xe40 kernel/workqueue.c:2785 kthread+0x346/0x450 kernel/kthread.c:388 ret_from_fork+0x4d/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x1b/0x30 arch/x86/entry/entry_64.S:293 Other than blk_mq_clear_flush_rq_mapping(), the flag is only used in blk_register_queue() from initialization path, hence it's safe not to clear the flag in del_gendisk. And since QUEUE_FLAG_REGISTERED already make sure that queue should only be registered once, there is no need to test the flag as well. Fixes: 6cfeadbff3f8 ("blk-mq: don't clear flush_rq from tags->rqs[]") Depends-on: commit aec89dc5d421 ("block: keep q_usage_counter in atomic mode after del_gendisk") Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Ming Lei <ming.lei(a)redhat.com> Link: https://lore.kernel.org/r/20241104110005.1412161-1-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Conflicts: block/genhd.c [Context conflict.] Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> --- block/blk-sysfs.c | 6 ++---- block/genhd.c | 9 +++------ 2 files changed, 5 insertions(+), 10 deletions(-) diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 7a38a1d5dceb..2de6c14dfecf 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -894,10 +894,8 @@ int blk_register_queue(struct gendisk *disk) * faster to shut down and is made fully functional here as * request_queues for non-existent devices never get registered. */ - if (!blk_queue_init_done(q)) { - blk_queue_flag_set(QUEUE_FLAG_INIT_DONE, q); - percpu_ref_switch_to_percpu(&q->q_usage_counter); - } + blk_queue_flag_set(QUEUE_FLAG_INIT_DONE, q); + percpu_ref_switch_to_percpu(&q->q_usage_counter); return ret; diff --git a/block/genhd.c b/block/genhd.c index de21c79cbda6..28fb6476ee7f 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -710,13 +710,10 @@ void del_gendisk(struct gendisk *disk) * If the disk does not own the queue, allow using passthrough requests * again. Else leave the queue frozen to fail all I/O. */ - if (!test_bit(GD_OWNS_QUEUE, &disk->state)) { - blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q); + if (!test_bit(GD_OWNS_QUEUE, &disk->state)) __blk_mq_unfreeze_queue(q, true); - } else { - if (queue_is_mq(q)) - blk_mq_exit_queue(q); - } + else if (queue_is_mq(q)) + blk_mq_exit_queue(q); } EXPORT_SYMBOL(del_gendisk); -- 2.39.2

2 1

[PATCH OLK-5.10] scsi: sg: Fix slab-use-after-free read in sg_release()
by Zheng Qixing 04 Jan '25

04 Jan '25

From: Suraj Sonawane <surajsonawane0215(a)gmail.com> mainline inclusion from mainline-v6.13-rc2 commit f10593ad9bc36921f623361c9e3dd96bd52d85ee category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAN7 CVE: CVE-2024-56631 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Fix a use-after-free bug in sg_release(), detected by syzbot with KASAN: BUG: KASAN: slab-use-after-free in lock_release+0x151/0xa30 kernel/locking/lockdep.c:5838 __mutex_unlock_slowpath+0xe2/0x750 kernel/locking/mutex.c:912 sg_release+0x1f4/0x2e0 drivers/scsi/sg.c:407 In sg_release(), the function kref_put(&sfp->f_ref, sg_remove_sfp) is called before releasing the open_rel_lock mutex. The kref_put() call may decrement the reference count of sfp to zero, triggering its cleanup through sg_remove_sfp(). This cleanup includes scheduling deferred work via sg_remove_sfp_usercontext(), which ultimately frees sfp. After kref_put(), sg_release() continues to unlock open_rel_lock and may reference sfp or sdp. If sfp has already been freed, this results in a slab-use-after-free error. Move the kref_put(&sfp->f_ref, sg_remove_sfp) call after unlocking the open_rel_lock mutex. This ensures: - No references to sfp or sdp occur after the reference count is decremented. - Cleanup functions such as sg_remove_sfp() and sg_remove_sfp_usercontext() can safely execute without impacting the mutex handling in sg_release(). The fix has been tested and validated by syzbot. This patch closes the bug reported at the following syzkaller link and ensures proper sequencing of resource cleanup and mutex operations, eliminating the risk of use-after-free errors in sg_release(). Reported-by: syzbot+7efb5850a17ba6ce098b(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=7efb5850a17ba6ce098b Tested-by: syzbot+7efb5850a17ba6ce098b(a)syzkaller.appspotmail.com Fixes: cc833acbee9d ("sg: O_EXCL and other lock handling") Signed-off-by: Suraj Sonawane <surajsonawane0215(a)gmail.com> Link: https://lore.kernel.org/r/20241120125944.88095-1-surajsonawane0215@gmail.com Reviewed-by: Bart Van Assche <bvanassche(a)acm.org> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Conflicts: drivers/scsi/sg.c [Context conflicts.] Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> --- drivers/scsi/sg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index e1c086ac8a60..91cbf45cf880 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -390,7 +390,6 @@ sg_release(struct inode *inode, struct file *filp) mutex_lock(&sdp->open_rel_lock); scsi_autopm_put_device(sdp->device); - kref_put(&sfp->f_ref, sg_remove_sfp); sdp->open_cnt--; /* possibly many open()s waiting on exlude clearing, start many; @@ -402,6 +401,7 @@ sg_release(struct inode *inode, struct file *filp) wake_up_interruptible(&sdp->open_wait); } mutex_unlock(&sdp->open_rel_lock); + kref_put(&sfp->f_ref, sg_remove_sfp); return 0; } -- 2.39.2

2 1

[PATCH openEuler-22.03-LTS-SP1] scsi: sg: Fix slab-use-after-free read in sg_release()
by Zheng Qixing 04 Jan '25

04 Jan '25

From: Suraj Sonawane <surajsonawane0215(a)gmail.com> mainline inclusion from mainline-v6.13-rc2 commit f10593ad9bc36921f623361c9e3dd96bd52d85ee category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAN7 CVE: CVE-2024-56631 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Fix a use-after-free bug in sg_release(), detected by syzbot with KASAN: BUG: KASAN: slab-use-after-free in lock_release+0x151/0xa30 kernel/locking/lockdep.c:5838 __mutex_unlock_slowpath+0xe2/0x750 kernel/locking/mutex.c:912 sg_release+0x1f4/0x2e0 drivers/scsi/sg.c:407 In sg_release(), the function kref_put(&sfp->f_ref, sg_remove_sfp) is called before releasing the open_rel_lock mutex. The kref_put() call may decrement the reference count of sfp to zero, triggering its cleanup through sg_remove_sfp(). This cleanup includes scheduling deferred work via sg_remove_sfp_usercontext(), which ultimately frees sfp. After kref_put(), sg_release() continues to unlock open_rel_lock and may reference sfp or sdp. If sfp has already been freed, this results in a slab-use-after-free error. Move the kref_put(&sfp->f_ref, sg_remove_sfp) call after unlocking the open_rel_lock mutex. This ensures: - No references to sfp or sdp occur after the reference count is decremented. - Cleanup functions such as sg_remove_sfp() and sg_remove_sfp_usercontext() can safely execute without impacting the mutex handling in sg_release(). The fix has been tested and validated by syzbot. This patch closes the bug reported at the following syzkaller link and ensures proper sequencing of resource cleanup and mutex operations, eliminating the risk of use-after-free errors in sg_release(). Reported-by: syzbot+7efb5850a17ba6ce098b(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=7efb5850a17ba6ce098b Tested-by: syzbot+7efb5850a17ba6ce098b(a)syzkaller.appspotmail.com Fixes: cc833acbee9d ("sg: O_EXCL and other lock handling") Signed-off-by: Suraj Sonawane <surajsonawane0215(a)gmail.com> Link: https://lore.kernel.org/r/20241120125944.88095-1-surajsonawane0215@gmail.com Reviewed-by: Bart Van Assche <bvanassche(a)acm.org> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Conflicts: drivers/scsi/sg.c [Context conflicts.] Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> --- drivers/scsi/sg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index e1c086ac8a60..91cbf45cf880 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -390,7 +390,6 @@ sg_release(struct inode *inode, struct file *filp) mutex_lock(&sdp->open_rel_lock); scsi_autopm_put_device(sdp->device); - kref_put(&sfp->f_ref, sg_remove_sfp); sdp->open_cnt--; /* possibly many open()s waiting on exlude clearing, start many; @@ -402,6 +401,7 @@ sg_release(struct inode *inode, struct file *filp) wake_up_interruptible(&sdp->open_wait); } mutex_unlock(&sdp->open_rel_lock); + kref_put(&sfp->f_ref, sg_remove_sfp); return 0; } -- 2.39.2

2 1

[PATCH OLK-6.6] scsi: sg: Fix slab-use-after-free read in sg_release()
by Zheng Qixing 04 Jan '25

04 Jan '25

From: Suraj Sonawane <surajsonawane0215(a)gmail.com> stable inclusion from stable-v6.6.66 commit 59b30afa578637169e2819536bb66459fdddc39d category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAN7 CVE: CVE-2024-56631 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit f10593ad9bc36921f623361c9e3dd96bd52d85ee ] Fix a use-after-free bug in sg_release(), detected by syzbot with KASAN: BUG: KASAN: slab-use-after-free in lock_release+0x151/0xa30 kernel/locking/lockdep.c:5838 __mutex_unlock_slowpath+0xe2/0x750 kernel/locking/mutex.c:912 sg_release+0x1f4/0x2e0 drivers/scsi/sg.c:407 In sg_release(), the function kref_put(&sfp->f_ref, sg_remove_sfp) is called before releasing the open_rel_lock mutex. The kref_put() call may decrement the reference count of sfp to zero, triggering its cleanup through sg_remove_sfp(). This cleanup includes scheduling deferred work via sg_remove_sfp_usercontext(), which ultimately frees sfp. After kref_put(), sg_release() continues to unlock open_rel_lock and may reference sfp or sdp. If sfp has already been freed, this results in a slab-use-after-free error. Move the kref_put(&sfp->f_ref, sg_remove_sfp) call after unlocking the open_rel_lock mutex. This ensures: - No references to sfp or sdp occur after the reference count is decremented. - Cleanup functions such as sg_remove_sfp() and sg_remove_sfp_usercontext() can safely execute without impacting the mutex handling in sg_release(). The fix has been tested and validated by syzbot. This patch closes the bug reported at the following syzkaller link and ensures proper sequencing of resource cleanup and mutex operations, eliminating the risk of use-after-free errors in sg_release(). Reported-by: syzbot+7efb5850a17ba6ce098b(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=7efb5850a17ba6ce098b Tested-by: syzbot+7efb5850a17ba6ce098b(a)syzkaller.appspotmail.com Fixes: cc833acbee9d ("sg: O_EXCL and other lock handling") Signed-off-by: Suraj Sonawane <surajsonawane0215(a)gmail.com> Link: https://lore.kernel.org/r/20241120125944.88095-1-surajsonawane0215@gmail.com Reviewed-by: Bart Van Assche <bvanassche(a)acm.org> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: drivers/scsi/sg.c [Context conflicts.] Signed-off-by: Zheng Qixing <zhengqixing(a)huawei.com> --- drivers/scsi/sg.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index e6d8beb87776..59de84387def 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -393,7 +393,6 @@ sg_release(struct inode *inode, struct file *filp) mutex_lock(&sdp->open_rel_lock); scsi_autopm_put_device(sdp->device); - kref_put(&sfp->f_ref, sg_remove_sfp); sdp->open_cnt--; /* possibly many open()s waiting on exlude clearing, start many; @@ -405,6 +404,7 @@ sg_release(struct inode *inode, struct file *filp) wake_up_interruptible(&sdp->open_wait); } mutex_unlock(&sdp->open_rel_lock); + kref_put(&sfp->f_ref, sg_remove_sfp); return 0; } -- 2.39.2

2 1

[PATCH openEuler-22.03-LTS-SP1 0/1] CVE-2024-56724
by Liao Chen 04 Jan '25

04 Jan '25

fix CVE-2024-56724 Andy Shevchenko (1): mfd: intel_soc_pmic_bxtwc: Use IRQ domain for TMU device drivers/mfd/intel_soc_pmic_bxtwc.c | 33 +++++++++++++------------- drivers/platform/x86/intel_bxtwc_tmu.c | 22 +++++------------ 2 files changed, 23 insertions(+), 32 deletions(-) -- 2.34.1

2 2

[PATCH OLK-5.10 0/1] CVE-2024-56724
by Liao Chen 04 Jan '25

04 Jan '25

fix CVE-2024-56724 Andy Shevchenko (1): mfd: intel_soc_pmic_bxtwc: Use IRQ domain for TMU device drivers/mfd/intel_soc_pmic_bxtwc.c | 33 +++++++++++++------------- drivers/platform/x86/intel_bxtwc_tmu.c | 22 +++++------------ 2 files changed, 23 insertions(+), 32 deletions(-) -- 2.34.1

2 2

[openeuler:OLK-5.10 2626/2626] ld.lld: error: undefined symbol: latency_fsnotify
by kernel test robot 04 Jan '25

04 Jan '25

Hi Daniel, FYI, the error/warning still remains. tree: https://gitee.com/openeuler/kernel.git OLK-5.10 head: d51fb86ce6a3a3e59d7cba58738b63903b8cb37c commit: d11dbe8b4e8ad4c5bd90147912352ef6f13a2bb6 [2626/2626] trace: Add osnoise tracer config: x86_64-randconfig-104-20250103 (https://download.01.org/0day-ci/archive/20250104/202501041734.WciMoLAr-lkp@…) compiler: clang version 19.1.3 (https://github.com/llvm/llvm-project ab51eccf88f5321e7c60591c5546b254b6afab99) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250104/202501041734.WciMoLAr-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202501041734.WciMoLAr-lkp@intel.com/ All errors (new ones prefixed by >>): >> ld.lld: error: undefined symbol: latency_fsnotify >>> referenced by trace_osnoise.c:933 (kernel/trace/trace_osnoise.c:933) >>> trace/trace_osnoise.o:(run_osnoise) in archive kernel/built-in.a -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH OLK-6.6] RDMA/mlx5: Move events notifier registration to be after device registration
by Pu Lehui 04 Jan '25

04 Jan '25

From: Patrisious Haddad <phaddad(a)nvidia.com> stable inclusion from stable-v6.6.64 commit 921fcf2971a1e8d3b904ba2c2905b96f4ec3d4ad category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEADY CVE: CVE-2024-53224 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit ede132a5cf559f3ab35a4c28bac4f4a6c20334d8 ] Move pkey change work initialization and cleanup from device resources stage to notifier stage, since this is the stage which handles this work events. Fix a race between the device deregistration and pkey change work by moving MLX5_IB_STAGE_DEVICE_NOTIFIER to be after MLX5_IB_STAGE_IB_REG in order to ensure that the notifier is deregistered before the device during cleanup. Which ensures there are no works that are being executed after the device has already unregistered which can cause the panic below. BUG: kernel NULL pointer dereference, address: 0000000000000000 PGD 0 P4D 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 1 PID: 630071 Comm: kworker/1:2 Kdump: loaded Tainted: G W OE --------- --- 5.14.0-162.6.1.el9_1.x86_64 #1 Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS 090008 02/27/2023 Workqueue: events pkey_change_handler [mlx5_ib] RIP: 0010:setup_qp+0x38/0x1f0 [mlx5_ib] Code: ee 41 54 45 31 e4 55 89 f5 53 48 89 fb 48 83 ec 20 8b 77 08 65 48 8b 04 25 28 00 00 00 48 89 44 24 18 48 8b 07 48 8d 4c 24 16 <4c> 8b 38 49 8b 87 80 0b 00 00 4c 89 ff 48 8b 80 08 05 00 00 8b 40 RSP: 0018:ffffbcc54068be20 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff954054494128 RCX: ffffbcc54068be36 RDX: ffff954004934000 RSI: 0000000000000001 RDI: ffff954054494128 RBP: 0000000000000023 R08: ffff954001be2c20 R09: 0000000000000001 R10: ffff954001be2c20 R11: ffff9540260133c0 R12: 0000000000000000 R13: 0000000000000023 R14: 0000000000000000 R15: ffff9540ffcb0905 FS: 0000000000000000(0000) GS:ffff9540ffc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000010625c001 CR4: 00000000003706e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: mlx5_ib_gsi_pkey_change+0x20/0x40 [mlx5_ib] process_one_work+0x1e8/0x3c0 worker_thread+0x50/0x3b0 ? rescuer_thread+0x380/0x380 kthread+0x149/0x170 ? set_kthread_struct+0x50/0x50 ret_from_fork+0x22/0x30 Modules linked in: rdma_ucm(OE) rdma_cm(OE) iw_cm(OE) ib_ipoib(OE) ib_cm(OE) ib_umad(OE) mlx5_ib(OE) mlx5_fwctl(OE) fwctl(OE) ib_uverbs(OE) mlx5_core(OE) mlxdevm(OE) ib_core(OE) mlx_compat(OE) psample mlxfw(OE) tls knem(OE) netconsole nfsv3 nfs_acl nfs lockd grace fscache netfs qrtr rfkill sunrpc intel_rapl_msr intel_rapl_common rapl hv_balloon hv_utils i2c_piix4 pcspkr joydev fuse ext4 mbcache jbd2 sr_mod sd_mod cdrom t10_pi sg ata_generic pci_hyperv pci_hyperv_intf hyperv_drm drm_shmem_helper drm_kms_helper hv_storvsc syscopyarea hv_netvsc sysfillrect sysimgblt hid_hyperv fb_sys_fops scsi_transport_fc hyperv_keyboard drm ata_piix crct10dif_pclmul crc32_pclmul crc32c_intel libata ghash_clmulni_intel hv_vmbus serio_raw [last unloaded: ib_core] CR2: 0000000000000000 ---[ end trace f6f8be4eae12f7bc ]--- Fixes: 7722f47e71e5 ("IB/mlx5: Create GSI transmission QPs when P_Key table is changed") Signed-off-by: Patrisious Haddad <phaddad(a)nvidia.com> Reviewed-by: Michael Guralnik <michaelgur(a)nvidia.com> Link: https://patch.msgid.link/d271ceeff0c08431b3cbbbb3e2d416f09b6d1621.173149694… Signed-off-by: Leon Romanovsky <leon(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Pu Lehui <pulehui(a)huawei.com> --- drivers/infiniband/hw/mlx5/main.c | 40 +++++++++++++--------------- drivers/infiniband/hw/mlx5/mlx5_ib.h | 2 +- 2 files changed, 20 insertions(+), 22 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index bc38af6cda6e..c510484e024b 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -2899,7 +2899,6 @@ int mlx5_ib_dev_res_srq_init(struct mlx5_ib_dev *dev) static int mlx5_ib_dev_res_init(struct mlx5_ib_dev *dev) { struct mlx5_ib_resources *devr = &dev->devr; - int port; int ret; if (!MLX5_CAP_GEN(dev->mdev, xrc)) @@ -2915,10 +2914,6 @@ static int mlx5_ib_dev_res_init(struct mlx5_ib_dev *dev) return ret; } - for (port = 0; port < ARRAY_SIZE(devr->ports); ++port) - INIT_WORK(&devr->ports[port].pkey_change_work, - pkey_change_handler); - mutex_init(&devr->cq_lock); mutex_init(&devr->srq_lock); @@ -2928,16 +2923,6 @@ static int mlx5_ib_dev_res_init(struct mlx5_ib_dev *dev) static void mlx5_ib_dev_res_cleanup(struct mlx5_ib_dev *dev) { struct mlx5_ib_resources *devr = &dev->devr; - int port; - - /* - * Make sure no change P_Key work items are still executing. - * - * At this stage, the mlx5_ib_event should be unregistered - * and it ensures that no new works are added. - */ - for (port = 0; port < ARRAY_SIZE(devr->ports); ++port) - cancel_work_sync(&devr->ports[port].pkey_change_work); /* After s0/s1 init, they are not unset during the device lifetime. */ if (devr->s1) { @@ -4201,6 +4186,13 @@ static void mlx5_ib_stage_delay_drop_cleanup(struct mlx5_ib_dev *dev) static int mlx5_ib_stage_dev_notifier_init(struct mlx5_ib_dev *dev) { + struct mlx5_ib_resources *devr = &dev->devr; + int port; + + for (port = 0; port < ARRAY_SIZE(devr->ports); ++port) + INIT_WORK(&devr->ports[port].pkey_change_work, + pkey_change_handler); + dev->mdev_events.notifier_call = mlx5_ib_event; mlx5_notifier_register(dev->mdev, &dev->mdev_events); @@ -4211,8 +4203,14 @@ static int mlx5_ib_stage_dev_notifier_init(struct mlx5_ib_dev *dev) static void mlx5_ib_stage_dev_notifier_cleanup(struct mlx5_ib_dev *dev) { + struct mlx5_ib_resources *devr = &dev->devr; + int port; + mlx5r_macsec_event_unregister(dev); mlx5_notifier_unregister(dev->mdev, &dev->mdev_events); + + for (port = 0; port < ARRAY_SIZE(devr->ports); ++port) + cancel_work_sync(&devr->ports[port].pkey_change_work); } void __mlx5_ib_remove(struct mlx5_ib_dev *dev, @@ -4286,9 +4284,6 @@ static const struct mlx5_ib_profile pf_profile = { STAGE_CREATE(MLX5_IB_STAGE_DEVICE_RESOURCES, mlx5_ib_dev_res_init, mlx5_ib_dev_res_cleanup), - STAGE_CREATE(MLX5_IB_STAGE_DEVICE_NOTIFIER, - mlx5_ib_stage_dev_notifier_init, - mlx5_ib_stage_dev_notifier_cleanup), STAGE_CREATE(MLX5_IB_STAGE_ODP, mlx5_ib_odp_init_one, mlx5_ib_odp_cleanup_one), @@ -4313,6 +4308,9 @@ static const struct mlx5_ib_profile pf_profile = { STAGE_CREATE(MLX5_IB_STAGE_IB_REG, mlx5_ib_stage_ib_reg_init, mlx5_ib_stage_ib_reg_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_DEVICE_NOTIFIER, + mlx5_ib_stage_dev_notifier_init, + mlx5_ib_stage_dev_notifier_cleanup), STAGE_CREATE(MLX5_IB_STAGE_POST_IB_REG_UMR, mlx5_ib_stage_post_ib_reg_umr_init, NULL), @@ -4349,9 +4347,6 @@ const struct mlx5_ib_profile raw_eth_profile = { STAGE_CREATE(MLX5_IB_STAGE_DEVICE_RESOURCES, mlx5_ib_dev_res_init, mlx5_ib_dev_res_cleanup), - STAGE_CREATE(MLX5_IB_STAGE_DEVICE_NOTIFIER, - mlx5_ib_stage_dev_notifier_init, - mlx5_ib_stage_dev_notifier_cleanup), STAGE_CREATE(MLX5_IB_STAGE_COUNTERS, mlx5_ib_counters_init, mlx5_ib_counters_cleanup), @@ -4373,6 +4368,9 @@ const struct mlx5_ib_profile raw_eth_profile = { STAGE_CREATE(MLX5_IB_STAGE_IB_REG, mlx5_ib_stage_ib_reg_init, mlx5_ib_stage_ib_reg_cleanup), + STAGE_CREATE(MLX5_IB_STAGE_DEVICE_NOTIFIER, + mlx5_ib_stage_dev_notifier_init, + mlx5_ib_stage_dev_notifier_cleanup), STAGE_CREATE(MLX5_IB_STAGE_POST_IB_REG_UMR, mlx5_ib_stage_post_ib_reg_umr_init, NULL), diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index 1c83d132197f..94678e5c59dd 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -954,7 +954,6 @@ enum mlx5_ib_stages { MLX5_IB_STAGE_QP, MLX5_IB_STAGE_SRQ, MLX5_IB_STAGE_DEVICE_RESOURCES, - MLX5_IB_STAGE_DEVICE_NOTIFIER, MLX5_IB_STAGE_ODP, MLX5_IB_STAGE_COUNTERS, MLX5_IB_STAGE_CONG_DEBUGFS, @@ -963,6 +962,7 @@ enum mlx5_ib_stages { MLX5_IB_STAGE_PRE_IB_REG_UMR, MLX5_IB_STAGE_WHITELIST_UID, MLX5_IB_STAGE_IB_REG, + MLX5_IB_STAGE_DEVICE_NOTIFIER, MLX5_IB_STAGE_POST_IB_REG_UMR, MLX5_IB_STAGE_DELAY_DROP, MLX5_IB_STAGE_RESTRACK, -- 2.34.1

2 1

[PATCH OLK-6.6 0/6] merge mainline patches into OLK-6.6
by Kaixiong Yu 04 Jan '25

04 Jan '25

merge mainline patches into OLK-6.6 Jeongjun Park (1): mm: migrate: annotate data-race in migrate_folio_unmap() Kefeng Wang (1): tmpfs: don't enable large folios if not supported Pei Li (1): mm: ignore data-race in __swap_writepage Sergey Senozhatsky (1): mm: Kconfig: fixup zsmalloc configuration Wei Xu (1): mm/mglru: reset page lru tier bits when activating Zeng Jingxiang (1): mm/vmscan: wake up flushers conditionally to avoid cgroup OOM include/linux/mm_inline.h | 15 ++++++++++++++- include/linux/mmzone.h | 2 ++ mm/Kconfig | 2 +- mm/migrate.c | 2 +- mm/page_io.c | 7 ++++++- mm/shmem.c | 5 ++++- mm/vmscan.c | 33 ++++++++++++++++++++++++++------- 7 files changed, 54 insertions(+), 12 deletions(-) -- 2.34.1

2 7

[PATCH OLK-6.6 0/1] CVE-2024-56724
by Liao Chen 04 Jan '25

04 Jan '25

fix CVE-2024-56724 Andy Shevchenko (1): mfd: intel_soc_pmic_bxtwc: Use IRQ domain for TMU device drivers/mfd/intel_soc_pmic_bxtwc.c | 31 ++++++++++++++------------ drivers/platform/x86/intel/bxtwc_tmu.c | 22 +++++------------- 2 files changed, 23 insertions(+), 30 deletions(-) -- 2.34.1

2 2

[PATCH OLK-6.6 0/1] CVE-2024-56724
by Liao Chen 04 Jan '25

04 Jan '25

fix CVE-2024-56724 Andy Shevchenko (1): mfd: intel_soc_pmic_bxtwc: Use IRQ domain for TMU device drivers/mfd/intel_soc_pmic_bxtwc.c | 31 ++++++++++++++------------ drivers/platform/x86/intel/bxtwc_tmu.c | 22 +++++------------- 2 files changed, 23 insertions(+), 30 deletions(-) -- 2.34.1

2 4

[PATCH OLK-6.6] scsi: qla2xxx: Fix use after free on unload
by Yu Kuai 04 Jan '25

04 Jan '25

From: Quinn Tran <qutran(a)marvell.com> stable inclusion from stable-v6.6.66 commit 15369e774f27ec790f207de87c0b541e3f90b22d category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAOL CVE: CVE-2024-56623 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 07c903db0a2ff84b68efa1a74a4de353ea591eb0 upstream. System crash is observed with stack trace warning of use after free. There are 2 signals to tell dpc_thread to terminate (UNLOADING flag and kthread_stop). On setting the UNLOADING flag when dpc_thread happens to run at the time and sees the flag, this causes dpc_thread to exit and clean up itself. When kthread_stop is called for final cleanup, this causes use after free. Remove UNLOADING signal to terminate dpc_thread. Use the kthread_stop as the main signal to exit dpc_thread. [596663.812935] kernel BUG at mm/slub.c:294! [596663.812950] invalid opcode: 0000 [#1] SMP PTI [596663.812957] CPU: 13 PID: 1475935 Comm: rmmod Kdump: loaded Tainted: G IOE --------- - - 4.18.0-240.el8.x86_64 #1 [596663.812960] Hardware name: HP ProLiant DL380p Gen8, BIOS P70 08/20/2012 [596663.812974] RIP: 0010:__slab_free+0x17d/0x360 ... [596663.813008] Call Trace: [596663.813022] ? __dentry_kill+0x121/0x170 [596663.813030] ? _cond_resched+0x15/0x30 [596663.813034] ? _cond_resched+0x15/0x30 [596663.813039] ? wait_for_completion+0x35/0x190 [596663.813048] ? try_to_wake_up+0x63/0x540 [596663.813055] free_task+0x5a/0x60 [596663.813061] kthread_stop+0xf3/0x100 [596663.813103] qla2x00_remove_one+0x284/0x440 [qla2xxx] Cc: stable(a)vger.kernel.org Signed-off-by: Quinn Tran <qutran(a)marvell.com> Signed-off-by: Nilesh Javali <njavali(a)marvell.com> Link: https://lore.kernel.org/r/20241115130313.46826-3-njavali@marvell.com Reviewed-by: Himanshu Madhani <himanshu.madhani(a)oracle.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> --- drivers/scsi/qla2xxx/qla_os.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index da8331dbb01c..91d12198cc6c 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -6899,12 +6899,15 @@ qla2x00_do_dpc(void *data) set_user_nice(current, MIN_NICE); set_current_state(TASK_INTERRUPTIBLE); - while (!kthread_should_stop()) { + while (1) { ql_dbg(ql_dbg_dpc, base_vha, 0x4000, "DPC handler sleeping.\n"); schedule(); + if (kthread_should_stop()) + break; + if (test_and_clear_bit(DO_EEH_RECOVERY, &base_vha->dpc_flags)) qla_pci_set_eeh_busy(base_vha); @@ -6917,15 +6920,16 @@ qla2x00_do_dpc(void *data) goto end_loop; } + if (test_bit(UNLOADING, &base_vha->dpc_flags)) + /* don't do any work. Wait to be terminated by kthread_stop */ + goto end_loop; + ha->dpc_active = 1; ql_dbg(ql_dbg_dpc + ql_dbg_verbose, base_vha, 0x4001, "DPC handler waking up, dpc_flags=0x%lx.\n", base_vha->dpc_flags); - if (test_bit(UNLOADING, &base_vha->dpc_flags)) - break; - if (IS_P3P_TYPE(ha)) { if (IS_QLA8044(ha)) { if (test_and_clear_bit(ISP_UNRECOVERABLE, @@ -7238,9 +7242,6 @@ qla2x00_do_dpc(void *data) */ ha->dpc_active = 0; - /* Cleanup any residual CTX SRBs. */ - qla2x00_abort_all_cmds(base_vha, DID_NO_CONNECT << 16); - return 0; } -- 2.39.2

2 1

[PATCH openEuler-22.03-LTS-SP1 0/1] CVE-2024-56701
by Liao Chen 04 Jan '25

04 Jan '25

fix CVE-2024-56701 Michael Ellerman (1): powerpc/pseries: Fix dtl_access_lock to be a rw_semaphore arch/powerpc/include/asm/dtl.h | 4 ++-- arch/powerpc/platforms/pseries/dtl.c | 8 ++++---- arch/powerpc/platforms/pseries/lpar.c | 8 ++++---- 3 files changed, 10 insertions(+), 10 deletions(-) -- 2.34.1

2 2

[PATCH OLK-5.10] scsi: qla2xxx: Fix use after free on unload
by Yu Kuai 04 Jan '25

04 Jan '25

From: Quinn Tran <qutran(a)marvell.com> stable inclusion from stable-v5.10.231 commit 12f04fc8580eafb0510f805749553eb6213f323e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAOL CVE: CVE-2024-56623 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 07c903db0a2ff84b68efa1a74a4de353ea591eb0 upstream. System crash is observed with stack trace warning of use after free. There are 2 signals to tell dpc_thread to terminate (UNLOADING flag and kthread_stop). On setting the UNLOADING flag when dpc_thread happens to run at the time and sees the flag, this causes dpc_thread to exit and clean up itself. When kthread_stop is called for final cleanup, this causes use after free. Remove UNLOADING signal to terminate dpc_thread. Use the kthread_stop as the main signal to exit dpc_thread. [596663.812935] kernel BUG at mm/slub.c:294! [596663.812950] invalid opcode: 0000 [#1] SMP PTI [596663.812957] CPU: 13 PID: 1475935 Comm: rmmod Kdump: loaded Tainted: G IOE --------- - - 4.18.0-240.el8.x86_64 #1 [596663.812960] Hardware name: HP ProLiant DL380p Gen8, BIOS P70 08/20/2012 [596663.812974] RIP: 0010:__slab_free+0x17d/0x360 ... [596663.813008] Call Trace: [596663.813022] ? __dentry_kill+0x121/0x170 [596663.813030] ? _cond_resched+0x15/0x30 [596663.813034] ? _cond_resched+0x15/0x30 [596663.813039] ? wait_for_completion+0x35/0x190 [596663.813048] ? try_to_wake_up+0x63/0x540 [596663.813055] free_task+0x5a/0x60 [596663.813061] kthread_stop+0xf3/0x100 [596663.813103] qla2x00_remove_one+0x284/0x440 [qla2xxx] Cc: stable(a)vger.kernel.org Signed-off-by: Quinn Tran <qutran(a)marvell.com> Signed-off-by: Nilesh Javali <njavali(a)marvell.com> Link: https://lore.kernel.org/r/20241115130313.46826-3-njavali@marvell.com Reviewed-by: Himanshu Madhani <himanshu.madhani(a)oracle.com> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> --- drivers/scsi/qla2xxx/qla_os.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 00b971d1c419..a6ecb4bb7456 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -6655,12 +6655,15 @@ qla2x00_do_dpc(void *data) set_user_nice(current, MIN_NICE); set_current_state(TASK_INTERRUPTIBLE); - while (!kthread_should_stop()) { + while (1) { ql_dbg(ql_dbg_dpc, base_vha, 0x4000, "DPC handler sleeping.\n"); schedule(); + if (kthread_should_stop()) + break; + if (test_and_clear_bit(DO_EEH_RECOVERY, &base_vha->dpc_flags)) qla_pci_set_eeh_busy(base_vha); @@ -6673,15 +6676,16 @@ qla2x00_do_dpc(void *data) goto end_loop; } + if (test_bit(UNLOADING, &base_vha->dpc_flags)) + /* don't do any work. Wait to be terminated by kthread_stop */ + goto end_loop; + ha->dpc_active = 1; ql_dbg(ql_dbg_dpc + ql_dbg_verbose, base_vha, 0x4001, "DPC handler waking up, dpc_flags=0x%lx.\n", base_vha->dpc_flags); - if (test_bit(UNLOADING, &base_vha->dpc_flags)) - break; - if (IS_P3P_TYPE(ha)) { if (IS_QLA8044(ha)) { if (test_and_clear_bit(ISP_UNRECOVERABLE, @@ -6999,9 +7003,6 @@ qla2x00_do_dpc(void *data) */ ha->dpc_active = 0; - /* Cleanup any residual CTX SRBs. */ - qla2x00_abort_all_cmds(base_vha, DID_NO_CONNECT << 16); - return 0; } -- 2.39.2

2 1

[PATCH OLK-6.6] scsi: qedi: Fix a possible memory leak in qedi_alloc_and_init_sb()
by Yu Kuai 04 Jan '25

04 Jan '25

From: Zhen Lei <thunder.leizhen(a)huawei.com> stable inclusion from stable-v6.6.64 commit 10a6fc486ac40a410f0fb84cc15161238eccd20a category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEGGL CVE: CVE-2024-56747 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 95bbdca4999bc59a72ebab01663d421d6ce5775d ] Hook "qedi_ops->common->sb_init = qed_sb_init" does not release the DMA memory sb_virt when it fails. Add dma_free_coherent() to free it. This is the same way as qedr_alloc_mem_sb() and qede_alloc_mem_sb(). Fixes: ace7f46ba5fd ("scsi: qedi: Add QLogic FastLinQ offload iSCSI driver framework.") Signed-off-by: Zhen Lei <thunder.leizhen(a)huawei.com> Link: https://lore.kernel.org/r/20241026125711.484-3-thunder.leizhen@huawei.com Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> --- drivers/scsi/qedi/qedi_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index cd0180b1f5b9..ede8d1f6ae23 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -369,6 +369,7 @@ static int qedi_alloc_and_init_sb(struct qedi_ctx *qedi, ret = qedi_ops->common->sb_init(qedi->cdev, sb_info, sb_virt, sb_phys, sb_id, QED_SB_TYPE_STORAGE); if (ret) { + dma_free_coherent(&qedi->pdev->dev, sizeof(*sb_virt), sb_virt, sb_phys); QEDI_ERR(&qedi->dbg_ctx, "Status block initialization failed for id = %d.\n", sb_id); -- 2.39.2

2 1

[PATCH OLK-5.10] scsi: qedi: Fix a possible memory leak in qedi_alloc_and_init_sb()
by Yu Kuai 04 Jan '25

04 Jan '25

From: Zhen Lei <thunder.leizhen(a)huawei.com> stable inclusion from stable-v5.10.231 commit a4d2011cbe039b25024831427b60ab91ee247066 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEGGL CVE: CVE-2024-56747 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 95bbdca4999bc59a72ebab01663d421d6ce5775d ] Hook "qedi_ops->common->sb_init = qed_sb_init" does not release the DMA memory sb_virt when it fails. Add dma_free_coherent() to free it. This is the same way as qedr_alloc_mem_sb() and qede_alloc_mem_sb(). Fixes: ace7f46ba5fd ("scsi: qedi: Add QLogic FastLinQ offload iSCSI driver framework.") Signed-off-by: Zhen Lei <thunder.leizhen(a)huawei.com> Link: https://lore.kernel.org/r/20241026125711.484-3-thunder.leizhen@huawei.com Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> --- drivers/scsi/qedi/qedi_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index 96e470746767..3bf75d466b2c 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -371,6 +371,7 @@ static int qedi_alloc_and_init_sb(struct qedi_ctx *qedi, ret = qedi_ops->common->sb_init(qedi->cdev, sb_info, sb_virt, sb_phys, sb_id, QED_SB_TYPE_STORAGE); if (ret) { + dma_free_coherent(&qedi->pdev->dev, sizeof(*sb_virt), sb_virt, sb_phys); QEDI_ERR(&qedi->dbg_ctx, "Status block initialization failed for id = %d.\n", sb_id); -- 2.39.2

2 1

[PATCH openEuler-1.0-LTS] scsi: qedi: Fix a possible memory leak in qedi_alloc_and_init_sb()
by Yu Kuai 04 Jan '25

04 Jan '25

From: Zhen Lei <thunder.leizhen(a)huawei.com> stable inclusion from stable-v4.19.325 commit 4e48e5b26b3edc0e1dd329201ffc924a7a1f9337 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEGGL CVE: CVE-2024-56747 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 95bbdca4999bc59a72ebab01663d421d6ce5775d ] Hook "qedi_ops->common->sb_init = qed_sb_init" does not release the DMA memory sb_virt when it fails. Add dma_free_coherent() to free it. This is the same way as qedr_alloc_mem_sb() and qede_alloc_mem_sb(). Fixes: ace7f46ba5fd ("scsi: qedi: Add QLogic FastLinQ offload iSCSI driver framework.") Signed-off-by: Zhen Lei <thunder.leizhen(a)huawei.com> Link: https://lore.kernel.org/r/20241026125711.484-3-thunder.leizhen@huawei.com Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> --- drivers/scsi/qedi/qedi_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index 756e0ccc37fb..04aa7953c0c4 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -357,6 +357,7 @@ static int qedi_alloc_and_init_sb(struct qedi_ctx *qedi, ret = qedi_ops->common->sb_init(qedi->cdev, sb_info, sb_virt, sb_phys, sb_id, QED_SB_TYPE_STORAGE); if (ret) { + dma_free_coherent(&qedi->pdev->dev, sizeof(*sb_virt), sb_virt, sb_phys); QEDI_ERR(&qedi->dbg_ctx, "Status block initialization failed for id = %d.\n", sb_id); -- 2.39.2

2 1

[PATCH OLK-6.6] blk-cgroup: Fix UAF in blkcg_unpin_online()
by Yu Kuai 04 Jan '25

04 Jan '25

From: Tejun Heo <tj(a)kernel.org> stable inclusion from stable-v6.6.67 commit 5baa28569c924d9a90d036c2aaab79f791fedaf8 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAKO CVE: CVE-2024-56672 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 86e6ca55b83c575ab0f2e105cf08f98e58d3d7af upstream. blkcg_unpin_online() walks up the blkcg hierarchy putting the online pin. To walk up, it uses blkcg_parent(blkcg) but it was calling that after blkcg_destroy_blkgs(blkcg) which could free the blkcg, leading to the following UAF: ================================================================== BUG: KASAN: slab-use-after-free in blkcg_unpin_online+0x15a/0x270 Read of size 8 at addr ffff8881057678c0 by task kworker/9:1/117 CPU: 9 UID: 0 PID: 117 Comm: kworker/9:1 Not tainted 6.13.0-rc1-work-00182-gb8f52214c61a-dirty #48 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS unknown 02/02/2022 Workqueue: cgwb_release cgwb_release_workfn Call Trace: <TASK> dump_stack_lvl+0x27/0x80 print_report+0x151/0x710 kasan_report+0xc0/0x100 blkcg_unpin_online+0x15a/0x270 cgwb_release_workfn+0x194/0x480 process_scheduled_works+0x71b/0xe20 worker_thread+0x82a/0xbd0 kthread+0x242/0x2c0 ret_from_fork+0x33/0x70 ret_from_fork_asm+0x1a/0x30 </TASK> ... Freed by task 1944: kasan_save_track+0x2b/0x70 kasan_save_free_info+0x3c/0x50 __kasan_slab_free+0x33/0x50 kfree+0x10c/0x330 css_free_rwork_fn+0xe6/0xb30 process_scheduled_works+0x71b/0xe20 worker_thread+0x82a/0xbd0 kthread+0x242/0x2c0 ret_from_fork+0x33/0x70 ret_from_fork_asm+0x1a/0x30 Note that the UAF is not easy to trigger as the free path is indirected behind a couple RCU grace periods and a work item execution. I could only trigger it with artifical msleep() injected in blkcg_unpin_online(). Fix it by reading the parent pointer before destroying the blkcg's blkg's. Signed-off-by: Tejun Heo <tj(a)kernel.org> Reported-by: Abagail ren <renzezhongucas(a)gmail.com> Suggested-by: Linus Torvalds <torvalds(a)linuxfoundation.org> Fixes: 4308a434e5e0 ("blkcg: don't offline parent blkcg first") Cc: stable(a)vger.kernel.org # v5.7+ Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Yang Erkun <yangerkun(a)huawei.com> --- block/blk-cgroup.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index cd3e8ac50fd0..7809546cd418 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1325,10 +1325,14 @@ void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css) struct blkcg *blkcg = css_to_blkcg(blkcg_css); do { + struct blkcg *parent; + if (!refcount_dec_and_test(&blkcg->online_pin)) break; + + parent = blkcg_parent(blkcg); blkcg_destroy_blkgs(blkcg); - blkcg = blkcg_parent(blkcg); + blkcg = parent; } while (blkcg); } -- 2.39.2

2 1

[PATCH OLK-5.10] nvme-pci: fix freeing of the HMB descriptor table
by Yu Kuai 04 Jan '25

04 Jan '25

From: Christoph Hellwig <hch(a)lst.de> stable inclusion from stable-v5.10.231 commit 452f9ddd12bebc04cef741e8ba3806bf0e1fd015 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEGGM CVE: CVE-2024-56756 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 3c2fb1ca8086eb139b2a551358137525ae8e0d7a ] The HMB descriptor table is sized to the maximum number of descriptors that could be used for a given device, but __nvme_alloc_host_mem could break out of the loop earlier on memory allocation failure and end up using less descriptors than planned for, which leads to an incorrect size passed to dma_free_coherent. In practice this was not showing up because the number of descriptors tends to be low and the dma coherent allocator always allocates and frees at least a page. Fixes: 87ad72a59a38 ("nvme-pci: implement host memory buffer support") Signed-off-by: Christoph Hellwig <hch(a)lst.de> Signed-off-by: Keith Busch <kbusch(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> --- drivers/nvme/host/pci.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index da624c4f2a5f..b397370ba36a 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -147,6 +147,7 @@ struct nvme_dev { /* host memory buffer support: */ u64 host_mem_size; u32 nr_host_mem_descs; + u32 host_mem_descs_size; dma_addr_t host_mem_descs_dma; struct nvme_host_mem_buf_desc *host_mem_descs; void **host_mem_desc_bufs; @@ -1926,10 +1927,10 @@ static void nvme_free_host_mem(struct nvme_dev *dev) kfree(dev->host_mem_desc_bufs); dev->host_mem_desc_bufs = NULL; - dma_free_coherent(dev->dev, - dev->nr_host_mem_descs * sizeof(*dev->host_mem_descs), + dma_free_coherent(dev->dev, dev->host_mem_descs_size, dev->host_mem_descs, dev->host_mem_descs_dma); dev->host_mem_descs = NULL; + dev->host_mem_descs_size = 0; dev->nr_host_mem_descs = 0; } @@ -1937,7 +1938,7 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred, u32 chunk_size) { struct nvme_host_mem_buf_desc *descs; - u32 max_entries, len; + u32 max_entries, len, descs_size; dma_addr_t descs_dma; int i = 0; void **bufs; @@ -1950,8 +1951,9 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred, if (dev->ctrl.hmmaxd && dev->ctrl.hmmaxd < max_entries) max_entries = dev->ctrl.hmmaxd; - descs = dma_alloc_coherent(dev->dev, max_entries * sizeof(*descs), - &descs_dma, GFP_KERNEL); + descs_size = max_entries * sizeof(*descs); + descs = dma_alloc_coherent(dev->dev, descs_size, &descs_dma, + GFP_KERNEL); if (!descs) goto out; @@ -1980,6 +1982,7 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred, dev->host_mem_size = size; dev->host_mem_descs = descs; dev->host_mem_descs_dma = descs_dma; + dev->host_mem_descs_size = descs_size; dev->host_mem_desc_bufs = bufs; return 0; @@ -1994,8 +1997,7 @@ static int __nvme_alloc_host_mem(struct nvme_dev *dev, u64 preferred, kfree(bufs); out_free_descs: - dma_free_coherent(dev->dev, max_entries * sizeof(*descs), descs, - descs_dma); + dma_free_coherent(dev->dev, descs_size, descs, descs_dma); out: dev->host_mem_descs = NULL; return -ENOMEM; -- 2.39.2

2 1

[PATCH OLK-6.6] blk-cgroup: Fix UAF in blkcg_unpin_online()
by Yu Kuai 04 Jan '25

04 Jan '25

From: Tejun Heo <tj(a)kernel.org> stable inclusion from stable-v6.6.67 commit 5baa28569c924d9a90d036c2aaab79f791fedaf8 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBEAKO CVE: CVE-2024-56672 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 86e6ca55b83c575ab0f2e105cf08f98e58d3d7af upstream. blkcg_unpin_online() walks up the blkcg hierarchy putting the online pin. To walk up, it uses blkcg_parent(blkcg) but it was calling that after blkcg_destroy_blkgs(blkcg) which could free the blkcg, leading to the following UAF: ================================================================== BUG: KASAN: slab-use-after-free in blkcg_unpin_online+0x15a/0x270 Read of size 8 at addr ffff8881057678c0 by task kworker/9:1/117 CPU: 9 UID: 0 PID: 117 Comm: kworker/9:1 Not tainted 6.13.0-rc1-work-00182-gb8f52214c61a-dirty #48 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS unknown 02/02/2022 Workqueue: cgwb_release cgwb_release_workfn Call Trace: <TASK> dump_stack_lvl+0x27/0x80 print_report+0x151/0x710 kasan_report+0xc0/0x100 blkcg_unpin_online+0x15a/0x270 cgwb_release_workfn+0x194/0x480 process_scheduled_works+0x71b/0xe20 worker_thread+0x82a/0xbd0 kthread+0x242/0x2c0 ret_from_fork+0x33/0x70 ret_from_fork_asm+0x1a/0x30 </TASK> ... Freed by task 1944: kasan_save_track+0x2b/0x70 kasan_save_free_info+0x3c/0x50 __kasan_slab_free+0x33/0x50 kfree+0x10c/0x330 css_free_rwork_fn+0xe6/0xb30 process_scheduled_works+0x71b/0xe20 worker_thread+0x82a/0xbd0 kthread+0x242/0x2c0 ret_from_fork+0x33/0x70 ret_from_fork_asm+0x1a/0x30 Note that the UAF is not easy to trigger as the free path is indirected behind a couple RCU grace periods and a work item execution. I could only trigger it with artifical msleep() injected in blkcg_unpin_online(). Fix it by reading the parent pointer before destroying the blkcg's blkg's. Signed-off-by: Tejun Heo <tj(a)kernel.org> Reported-by: Abagail ren <renzezhongucas(a)gmail.com> Suggested-by: Linus Torvalds <torvalds(a)linuxfoundation.org> Fixes: 4308a434e5e0 ("blkcg: don't offline parent blkcg first") Cc: stable(a)vger.kernel.org # v5.7+ Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Yang Erkun <yangerkun(a)huawei.com> --- block/blk-cgroup.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index cd3e8ac50fd0..7809546cd418 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1325,10 +1325,14 @@ void blkcg_unpin_online(struct cgroup_subsys_state *blkcg_css) struct blkcg *blkcg = css_to_blkcg(blkcg_css); do { + struct blkcg *parent; + if (!refcount_dec_and_test(&blkcg->online_pin)) break; + + parent = blkcg_parent(blkcg); blkcg_destroy_blkgs(blkcg); - blkcg = blkcg_parent(blkcg); + blkcg = parent; } while (blkcg); } -- 2.39.2

2 1

[PATCH OLK-5.10 0/1] CVE-2024-56701
by Liao Chen 04 Jan '25

04 Jan '25

fix CVE-2024-56701 Michael Ellerman (1): powerpc/pseries: Fix dtl_access_lock to be a rw_semaphore arch/powerpc/include/asm/dtl.h | 4 ++-- arch/powerpc/platforms/pseries/dtl.c | 8 ++++---- arch/powerpc/platforms/pseries/lpar.c | 8 ++++---- 3 files changed, 10 insertions(+), 10 deletions(-) -- 2.34.1

2 2