- Kernel - mailweb.openeuler.org

[PATCH OLK-6.6] nfs: Clean up /proc/net/rpc/nfs when nfs_fs_proc_net_init() fails.
by Wang Zhaolong 03 Jul '25

03 Jul '25

From: Kuniyuki Iwashima <kuniyu(a)google.com> mainline inclusion from mainline-v6.16-rc3 commit e8d6f3ab59468e230f3253efe5cb63efa35289f7 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/ICJTYD Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- syzbot reported a warning below [1] following a fault injection in nfs_fs_proc_net_init(). [0] When nfs_fs_proc_net_init() fails, /proc/net/rpc/nfs is not removed. Later, rpc_proc_exit() tries to remove /proc/net/rpc, and the warning is logged as the directory is not empty. Let's handle the error of nfs_fs_proc_net_init() properly. [0]: FAULT_INJECTION: forcing a failure. name failslab, interval 1, probability 0, space 0, times 0 CPU: 1 UID: 0 PID: 6120 Comm: syz.2.27 Not tainted 6.16.0-rc1-syzkaller-00010-g2c4a1f3fe03e #0 PREEMPT(full) Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/07/2025 Call Trace: <TASK> dump_stack_lvl (lib/dump_stack.c:123) should_fail_ex (lib/fault-inject.c:73 lib/fault-inject.c:174) should_failslab (mm/failslab.c:46) kmem_cache_alloc_noprof (mm/slub.c:4178 mm/slub.c:4204) __proc_create (fs/proc/generic.c:427) proc_create_reg (fs/proc/generic.c:554) proc_create_net_data (fs/proc/proc_net.c:120) nfs_fs_proc_net_init (fs/nfs/client.c:1409) nfs_net_init (fs/nfs/inode.c:2600) ops_init (net/core/net_namespace.c:138) setup_net (net/core/net_namespace.c:443) copy_net_ns (net/core/net_namespace.c:576) create_new_namespaces (kernel/nsproxy.c:110) unshare_nsproxy_namespaces (kernel/nsproxy.c:218 (discriminator 4)) ksys_unshare (kernel/fork.c:3123) __x64_sys_unshare (kernel/fork.c:3190) do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) </TASK> [1]: remove_proc_entry: removing non-empty directory 'net/rpc', leaking at least 'nfs' WARNING: CPU: 1 PID: 6120 at fs/proc/generic.c:727 remove_proc_entry+0x45e/0x530 fs/proc/generic.c:727 Modules linked in: CPU: 1 UID: 0 PID: 6120 Comm: syz.2.27 Not tainted 6.16.0-rc1-syzkaller-00010-g2c4a1f3fe03e #0 PREEMPT(full) Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/07/2025 RIP: 0010:remove_proc_entry+0x45e/0x530 fs/proc/generic.c:727 Code: 3c 02 00 0f 85 85 00 00 00 48 8b 93 d8 00 00 00 4d 89 f0 4c 89 e9 48 c7 c6 40 ba a2 8b 48 c7 c7 60 b9 a2 8b e8 33 81 1d ff 90 <0f> 0b 90 90 e9 5f fe ff ff e8 04 69 5e ff 90 48 b8 00 00 00 00 00 RSP: 0018:ffffc90003637b08 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff88805f534140 RCX: ffffffff817a92c8 RDX: ffff88807da99e00 RSI: ffffffff817a92d5 RDI: 0000000000000001 RBP: ffff888033431ac0 R08: 0000000000000001 R09: 0000000000000000 R10: 0000000000000001 R11: 0000000000000001 R12: ffff888033431a00 R13: ffff888033431ae4 R14: ffff888033184724 R15: dffffc0000000000 FS: 0000555580328500(0000) GS:ffff888124a62000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f71733743e0 CR3: 000000007f618000 CR4: 00000000003526f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> sunrpc_exit_net+0x46/0x90 net/sunrpc/sunrpc_syms.c:76 ops_exit_list net/core/net_namespace.c:200 [inline] ops_undo_list+0x2eb/0xab0 net/core/net_namespace.c:253 setup_net+0x2e1/0x510 net/core/net_namespace.c:457 copy_net_ns+0x2a6/0x5f0 net/core/net_namespace.c:574 create_new_namespaces+0x3ea/0xa90 kernel/nsproxy.c:110 unshare_nsproxy_namespaces+0xc0/0x1f0 kernel/nsproxy.c:218 ksys_unshare+0x45b/0xa40 kernel/fork.c:3121 __do_sys_unshare kernel/fork.c:3192 [inline] __se_sys_unshare kernel/fork.c:3190 [inline] __x64_sys_unshare+0x31/0x40 kernel/fork.c:3190 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0xcd/0x490 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7fa1a6b8e929 Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fff3a090368 EFLAGS: 00000246 ORIG_RAX: 0000000000000110 RAX: ffffffffffffffda RBX: 00007fa1a6db5fa0 RCX: 00007fa1a6b8e929 RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000040000080 RBP: 00007fa1a6c10b39 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fa1a6db5fa0 R14: 00007fa1a6db5fa0 R15: 0000000000000001 </TASK> Fixes: d47151b79e32 ("nfs: expose /proc/net/sunrpc/nfs in net namespaces") Reported-by: syzbot+a4cc4ac22daa4a71b87c(a)syzkaller.appspotmail.com Closes: https://syzkaller.appspot.com/bug?extid=a4cc4ac22daa4a71b87c Tested-by: syzbot+a4cc4ac22daa4a71b87c(a)syzkaller.appspotmail.com Signed-off-by: Kuniyuki Iwashima <kuniyu(a)google.com> Signed-off-by: Anna Schumaker <anna.schumaker(a)oracle.com> Signed-off-by: Wang Zhaolong <wangzhaolong(a)huaweicloud.com> --- fs/nfs/inode.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index db917dd2a6a7..01d26beb3418 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -2442,19 +2442,30 @@ unsigned int nfs_net_id; EXPORT_SYMBOL_GPL(nfs_net_id); static int nfs_net_init(struct net *net) { struct nfs_net *nn = net_generic(net, nfs_net_id); + int err; nfs_clients_init(net); if (!rpc_proc_register(net, &nn->rpcstats)) { - nfs_clients_exit(net); - return -ENOMEM; + err = -ENOMEM; + goto err_proc_rpc; } - return nfs_fs_proc_net_init(net); + err = nfs_fs_proc_net_init(net); + if (err) + goto err_proc_nfs; + + return 0; + +err_proc_nfs: + rpc_proc_unregister(net, "nfs"); +err_proc_rpc: + nfs_clients_exit(net); + return err; } static void nfs_net_exit(struct net *net) { rpc_proc_unregister(net, "nfs"); -- 2.34.3

2 1

[PATCH OLK-6.6 v2 0/2] support enable pci sriov concurrently
by Xiongfeng Wang 03 Jul '25

03 Jul '25

Jialin Zhang (2): PCI/IOV: Add pci_sriov_numvfs_lock to support enable pci sriov concurrently PCI/IOV: Improve performance of creating VFs concurrently drivers/pci/iov.c | 40 +++++++++++++++++++++++++++++++++++----- include/linux/pci.h | 8 ++++++++ 2 files changed, 43 insertions(+), 5 deletions(-) -- 2.20.1

2 3

[PATCH openEuler-1.0-LTS] PM: hibernate: defer device probing when resuming from hibernation
by Zeng Heng 03 Jul '25

03 Jul '25

From: Tetsuo Handa <penguin-kernel(a)I-love.SAKURA.ne.jp> stable inclusion from stable-v4.19.256 commit 5a283b59bce72c05c60e9f0fa92a28b5b850d8bb category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/ICG9OR CVE: CVE-2022-50202 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------------------------------- syzbot is reporting hung task at misc_open() [1], for there is a race window of AB-BA deadlock which involves probe_count variable. Currently wait_for_device_probe() from snapshot_open() from misc_open() can sleep forever with misc_mtx held if probe_count cannot become 0. When a device is probed by hub_event() work function, probe_count is incremented before the probe function starts, and probe_count is decremented after the probe function completed. There are three cases that can prevent probe_count from dropping to 0. (a) A device being probed stopped responding (i.e. broken/malicious hardware). (b) A process emulating a USB device using /dev/raw-gadget interface stopped responding for some reason. (c) New device probe requests keeps coming in before existing device probe requests complete. The phenomenon syzbot is reporting is (b). A process which is holding system_transition_mutex and misc_mtx is waiting for probe_count to become 0 inside wait_for_device_probe(), but the probe function which is called from hub_event() work function is waiting for the processes which are blocked at mutex_lock(&misc_mtx) to respond via /dev/raw-gadget interface. This patch mitigates (b) by deferring wait_for_device_probe() from snapshot_open() to snapshot_write() and snapshot_ioctl(). Please note that the possibility of (b) remains as long as any thread which is emulating a USB device via /dev/raw-gadget interface can be blocked by uninterruptible blocking operations (e.g. mutex_lock()). Please also note that (a) and (c) are not addressed. Regarding (c), we should change the code to wait for only one device which contains the image for resuming from hibernation. I don't know how to address (a), for use of timeout for wait_for_device_probe() might result in loss of user data in the image. Maybe we should require the userland to wait for the image device before opening /dev/snapshot interface. Link: https://syzkaller.appspot.com/bug?extid=358c9ab4c93da7b7238c [1] Reported-by: syzbot <syzbot+358c9ab4c93da7b7238c(a)syzkaller.appspotmail.com> Signed-off-by: Tetsuo Handa <penguin-kernel(a)I-love.SAKURA.ne.jp> Tested-by: syzbot <syzbot+358c9ab4c93da7b7238c(a)syzkaller.appspotmail.com> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> Conflicts: kernel/power/user.c [Fix context conflicts.] Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- kernel/power/user.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/kernel/power/user.c b/kernel/power/user.c index 2d8b60a3c86b..6a11154b3d52 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -29,6 +29,7 @@ #include "power.h" +static bool need_wait; #define SNAPSHOT_MINOR 231 @@ -82,7 +83,7 @@ static int snapshot_open(struct inode *inode, struct file *filp) * Resuming. We may need to wait for the image device to * appear. */ - wait_for_device_probe(); + need_wait = true; data->swap = -1; data->mode = O_WRONLY; @@ -174,6 +175,11 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf, ssize_t res; loff_t pg_offp = *offp & ~PAGE_MASK; + if (need_wait) { + wait_for_device_probe(); + need_wait = false; + } + lock_system_sleep(); data = filp->private_data; @@ -209,6 +215,11 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, loff_t size; sector_t offset; + if (need_wait) { + wait_for_device_probe(); + need_wait = false; + } + if (_IOC_TYPE(cmd) != SNAPSHOT_IOC_MAGIC) return -ENOTTY; if (_IOC_NR(cmd) > SNAPSHOT_IOC_MAXNR) -- 2.25.1

2 1

[openeuler:openEuler-1.0-LTS 1605/1605] kernel/cgroup/cgroup.c:2240: warning: Excess function parameter 'lock_threadgroup' description in 'cgroup_attach_lock'
by kernel test robot 03 Jul '25

03 Jul '25

tree: https://gitee.com/openeuler/kernel.git openEuler-1.0-LTS head: 26d81348fb134a6bffb49fd1b55d8842cbf6424d commit: 4924308a1ca9cc2f791398836a8744c22078ffbd [1605/1605] cgroup: Fix threadgroup_rwsem <-> cpus_read_lock() deadlock config: x86_64-buildonly-randconfig-2004-20250501 (https://download.01.org/0day-ci/archive/20250703/202507031346.HRMtINKf-lkp@…) compiler: clang version 20.1.2 (https://github.com/llvm/llvm-project 58df0ef89dd64126512e4ee27b4ac3fd8ddf6247) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250703/202507031346.HRMtINKf-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/202507031346.HRMtINKf-lkp@intel.com/ All warnings (new ones prefixed by >>): >> kernel/cgroup/cgroup.c:2240: warning: Excess function parameter 'lock_threadgroup' description in 'cgroup_attach_lock' >> kernel/cgroup/cgroup.c:2250: warning: Excess function parameter 'lock_threadgroup' description in 'cgroup_attach_unlock' vim +2240 kernel/cgroup/cgroup.c 2215 2216 /** 2217 * cgroup_attach_lock - Lock for ->attach() 2218 * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem 2219 * 2220 * cgroup migration sometimes needs to stabilize threadgroups against forks and 2221 * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach() 2222 * implementations (e.g. cpuset), also need to disable CPU hotplug. 2223 * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can 2224 * lead to deadlocks. 2225 * 2226 * Bringing up a CPU may involve creating and destroying tasks which requires 2227 * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside 2228 * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while 2229 * write-locking threadgroup_rwsem, the locking order is reversed and we end up 2230 * waiting for an on-going CPU hotplug operation which in turn is waiting for 2231 * the threadgroup_rwsem to be released to create new tasks. For more details: 2232 * 2233 * http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu 2234 * 2235 * Resolve the situation by always acquiring cpus_read_lock() before optionally 2236 * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that 2237 * CPU hotplug is disabled on entry. 2238 */ 2239 static void cgroup_attach_lock(void) > 2240 { 2241 cpus_read_lock(); 2242 percpu_down_write(&cgroup_threadgroup_rwsem); 2243 } 2244 2245 /** 2246 * cgroup_attach_unlock - Undo cgroup_attach_lock() 2247 * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem 2248 */ 2249 static void cgroup_attach_unlock(void) > 2250 { 2251 percpu_up_write(&cgroup_threadgroup_rwsem); 2252 cpus_read_unlock(); 2253 } 2254 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH OLK-6.6 v2] irqchip/gic-v3: Fix xint sleeping function called from invalid context
by Jinjie Ruan 03 Jul '25

03 Jul '25

hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/ICEDX1 ------------------ disable_irq() and debugfs_create_symlink() might sleep, local_irq_disable() will mask IRQS on current PE. Because sleep is not allowed when interrupts are disabled, the following bug occurs. So move them out of local_irq_disable/enable() to fix it. BUG: sleeping function called from invalid context at kernel/irq/manage.c:737 in_atomic(): 0, irqs_disabled(): 1, non_block: 0, pid: 1033, name: bash preempt_count: 0, expected: 0 CPU: 1 PID: 1033 Comm: bash Not tainted 6.6.0+ #1 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0xf8/0x290 show_stack+0x3c/0x70 dump_stack_lvl+0x1a8/0x2e8 dump_stack+0x34/0x50 __might_resched+0x31c/0x5f8 __might_sleep+0xc8/0x1d8 disable_irq+0x48/0xb8 xint_proc_write+0x1b0/0x3f8 proc_reg_write+0x218/0x348 vfs_write+0x244/0xfd0 ksys_write+0x11c/0x290 __arm64_sys_write+0x8c/0xd8 invoke_syscall+0xb4/0x300 el0_svc_common.constprop.0+0x1f8/0x310 do_el0_svc+0x5c/0x88 el0_svc+0x44/0x200 el0t_64_sync_handler+0xc0/0xc8 el0t_64_sync+0x3b8/0x3c0 BUG: sleeping function called from invalid context at mm/slab.h:494 in_atomic(): 0, irqs_disabled(): 128, non_block: 0, pid: 414, name: bash CPU: 0 PID: 414 Comm: bash Tainted: G W 5.10.0-00033-gee505d161ada #4 Hardware name: linux,dummy-virt (DT) Call trace: dump_backtrace+0x0/0x430 show_stack+0x34/0x4c dump_stack+0x1d0/0x248 ___might_sleep+0x15c/0x1bc __might_sleep+0x7c/0x114 __kmalloc_track_caller+0x198/0x87c kstrdup+0x134/0x1d0 debugfs_create_symlink+0x3c/0x250 xint_add_debugfs_entry+0xd4/0x140 xint_transform+0x1f4/0x210 xint_proc_write+0x26c/0x344 proc_reg_write+0x184/0x210 vfs_write+0x17c/0x634 ksys_write+0x104/0x230 __arm64_sys_write+0x54/0x80 invoke_syscall+0x84/0x230 el0_xcall_common.constprop.0+0x1ec/0x204 do_el0_xcall+0x98/0x18c el0_xcall_handler+0x24/0x3c el0_sync+0x17c/0x194 Fixes: 63f9ef213a47 ("arm64: Add debugfs dir for xint") Fixes: 3053668e6b21 ("arm64: Introduce Xint software solution") Signed-off-by: Jinjie Ruan <ruanjinjie(a)huawei.com> --- drivers/irqchip/irq-gic-v3.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index 5686ca0b960c..b91ff6a8b8e9 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -1030,11 +1030,9 @@ static bool xint_transform(int irqno, enum xint_op op) switch (op) { case IRQ_TO_XINT: set_bit(hwirq, irqnr_xint_map); - xint_add_debugfs_entry(irqno); return true; case XINT_TO_IRQ: clear_bit(hwirq, irqnr_xint_map); - xint_remove_debugfs_entry(irqno); return false; case XINT_SET_CHECK: return test_bit(hwirq, irqnr_xint_map); @@ -1049,6 +1047,7 @@ static ssize_t xint_proc_write(struct file *file, const char __user *buffer, size_t count, loff_t *pos) { int irq = (int)(long)pde_data(file_inode(file)); + enum xint_op switch_type; bool xint_state = false; unsigned long val; char *buf = NULL; @@ -1071,13 +1070,21 @@ static ssize_t xint_proc_write(struct file *file, return -EBUSY; } - local_irq_disable(); + if (xint_state) { + switch_type = XINT_TO_IRQ; + xint_remove_debugfs_entry(irq); + } else { + switch_type = IRQ_TO_XINT; + xint_add_debugfs_entry(irq); + } + disable_irq(irq); + local_irq_disable(); - xint_transform(irq, xint_state ? XINT_TO_IRQ : IRQ_TO_XINT); + xint_transform(irq, switch_type); - enable_irq(irq); local_irq_enable(); + enable_irq(irq); kfree(buf); -- 2.34.1

2 1

[PATCH OLK-6.6 0/2] support enable pci sriov concurrently
by Xiongfeng Wang 03 Jul '25

03 Jul '25

Jialin Zhang (2): PCI/IOV: Add pci_sriov_numvfs_lock to support enable pci sriov concurrently PCI/IOV: Improve performance of creating VFs concurrently drivers/pci/iov.c | 40 +++++++++++++++++++++++++++++++++++----- include/linux/pci.h | 8 ++++++++ 2 files changed, 43 insertions(+), 5 deletions(-) -- 2.20.1

2 3

[openeuler:openEuler-1.0-LTS 1605/1605] mm/hugetlb.c:1370:6: warning: no previous prototype for function 'free_huge_page_to_dhugetlb_pool'
by kernel test robot 03 Jul '25

03 Jul '25

tree: https://gitee.com/openeuler/kernel.git openEuler-1.0-LTS head: fc7fe8d28044724c4f29058aeb93f2e492585380 commit: 0bc0d0d57edacd59ebe38d05ad9c4b2bc185aa51 [1605/1605] dhugetlb: backport dynamic hugetlb feature config: x86_64-buildonly-randconfig-2004-20250501 (https://download.01.org/0day-ci/archive/20250703/202507031140.U5GKFBc9-lkp@…) compiler: clang version 20.1.2 (https://github.com/llvm/llvm-project 58df0ef89dd64126512e4ee27b4ac3fd8ddf6247) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250703/202507031140.U5GKFBc9-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/202507031140.U5GKFBc9-lkp@intel.com/ All warnings (new ones prefixed by >>): >> mm/hugetlb.c:1370:6: warning: no previous prototype for function 'free_huge_page_to_dhugetlb_pool' [-Wmissing-prototypes] 1370 | void free_huge_page_to_dhugetlb_pool(struct page *page, bool restore_reserve) | ^ mm/hugetlb.c:1370:1: note: declare 'static' if the function is not intended to be used outside of this translation unit 1370 | void free_huge_page_to_dhugetlb_pool(struct page *page, bool restore_reserve) | ^ | static In file included from mm/hugetlb.c:14: include/linux/mempolicy.h:329:13: warning: unused function '__do_mbind' [-Wunused-function] 329 | static long __do_mbind(unsigned long start, unsigned long len, | ^~~~~~~~~~ 2 warnings generated. vim +/free_huge_page_to_dhugetlb_pool +1370 mm/hugetlb.c 1324 1325 #ifdef CONFIG_DYNAMIC_HUGETLB 1326 static void free_huge_page_to_dhugetlb_pool(struct page *page, 1327 bool restore_reserve) 1328 { 1329 struct hstate *h = page_hstate(page); 1330 struct dhugetlb_pool *hpool; 1331 1332 hpool = get_dhugetlb_pool_from_dhugetlb_pagelist(page); 1333 if (unlikely(!hpool)) { 1334 pr_err("dhugetlb: free error: get hpool failed\n"); 1335 return; 1336 } 1337 1338 spin_lock(&hpool->lock); 1339 ClearPagePool(page); 1340 set_compound_page_dtor(page, NULL_COMPOUND_DTOR); 1341 if (!hstate_is_gigantic(h)) { 1342 list_add(&page->lru, &hpool->dhugetlb_2M_freelists); 1343 hpool->free_reserved_2M++; 1344 hpool->used_2M--; 1345 if (restore_reserve) { 1346 hpool->mmap_reserved_2M++; 1347 trace_dhugetlb_acct_memory(hpool, 1348 hpool->mmap_reserved_2M, 1349 DHUGETLB_RESV_2M); 1350 } 1351 trace_dhugetlb_alloc_free(hpool, page, hpool->free_reserved_2M, 1352 DHUGETLB_FREE_2M); 1353 } else { 1354 list_add(&page->lru, &hpool->dhugetlb_1G_freelists); 1355 hpool->free_reserved_1G++; 1356 hpool->used_1G--; 1357 if (restore_reserve) { 1358 hpool->mmap_reserved_1G++; 1359 trace_dhugetlb_acct_memory(hpool, 1360 hpool->mmap_reserved_1G, 1361 DHUGETLB_RESV_1G); 1362 } 1363 trace_dhugetlb_alloc_free(hpool, page, hpool->free_reserved_1G, 1364 DHUGETLB_FREE_1G); 1365 } 1366 spin_unlock(&hpool->lock); 1367 dhugetlb_pool_put(hpool); 1368 } 1369 #else > 1370 void free_huge_page_to_dhugetlb_pool(struct page *page, bool restore_reserve) 1371 { 1372 } 1373 #endif 1374 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH openEuler-1.0-LTS] net: tunnels: annotate lockless accesses to dev->needed_headroom
by Wang Liang 03 Jul '25

03 Jul '25

From: Eric Dumazet <edumazet(a)google.com> stable inclusion from stable-v4.19.279 commit 51f3bd3765bc5ca4583af07a00833da00d2ace1d category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IC5DCE CVE: CVE-2023-53109 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 4b397c06cb987935b1b097336532aa6b4210e091 ] IP tunnels can apparently update dev->needed_headroom in their xmit path. This patch takes care of three tunnels xmit, and also the core LL_RESERVED_SPACE() and LL_RESERVED_SPACE_EXTRA() helpers. More changes might be needed for completeness. BUG: KCSAN: data-race in ip_tunnel_xmit / ip_tunnel_xmit read to 0xffff88815b9da0ec of 2 bytes by task 888 on cpu 1: ip_tunnel_xmit+0x1270/0x1730 net/ipv4/ip_tunnel.c:803 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 write to 0xffff88815b9da0ec of 2 bytes by task 2379 on cpu 0: ip_tunnel_xmit+0x1294/0x1730 net/ipv4/ip_tunnel.c:804 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip6_finish_output2+0x9bc/0xc50 net/ipv6/ip6_output.c:134 __ip6_finish_output net/ipv6/ip6_output.c:195 [inline] ip6_finish_output+0x39a/0x4e0 net/ipv6/ip6_output.c:206 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip6_output+0xeb/0x220 net/ipv6/ip6_output.c:227 dst_output include/net/dst.h:444 [inline] NF_HOOK include/linux/netfilter.h:302 [inline] mld_sendpack+0x438/0x6a0 net/ipv6/mcast.c:1820 mld_send_cr net/ipv6/mcast.c:2121 [inline] mld_ifc_work+0x519/0x7b0 net/ipv6/mcast.c:2653 process_one_work+0x3e6/0x750 kernel/workqueue.c:2390 worker_thread+0x5f2/0xa10 kernel/workqueue.c:2537 kthread+0x1ac/0x1e0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 value changed: 0x0dd4 -> 0x0e14 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 2379 Comm: kworker/0:0 Not tainted 6.3.0-rc1-syzkaller-00002-g8ca09d5fa354-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/02/2023 Workqueue: mld mld_ifc_work Fixes: 8eb30be0352d ("ipv6: Create ip6_tnl_xmit") Reported-by: syzbot <syzkaller(a)googlegroups.com> Signed-off-by: Eric Dumazet <edumazet(a)google.com> Link: https://lore.kernel.org/r/20230310191109.2384387-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Conflicts: net/ipv4/ip_tunnel.c [conflicts due to merged mainline 5ae1e9922bbd ("net: ip_tunnel: prevent perpetual headroom growth")] Signed-off-by: Wang Liang <wangliang74(a)huawei.com> --- include/linux/netdevice.h | 6 ++++-- net/ipv6/ip6_tunnel.c | 4 ++-- 2 files changed, 6 insertions(+), 4 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dfddf928a16b..a5089c3fe9e6 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -294,9 +294,11 @@ struct hh_cache { * relationship HH alignment <= LL alignment. */ #define LL_RESERVED_SPACE(dev) \ - ((((dev)->hard_header_len+(dev)->needed_headroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) + ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom)) \ + & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) #define LL_RESERVED_SPACE_EXTRA(dev,extra) \ - ((((dev)->hard_header_len+(dev)->needed_headroom+(extra))&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) + ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom) + (extra)) \ + & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) struct header_ops { int (*create) (struct sk_buff *skb, struct net_device *dev, diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 69792012da3d..cd32d859e4da 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1221,8 +1221,8 @@ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, */ max_headroom = LL_RESERVED_SPACE(dst->dev) + sizeof(struct ipv6hdr) + dst->header_len + t->hlen; - if (max_headroom > dev->needed_headroom) - dev->needed_headroom = max_headroom; + if (max_headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, max_headroom); err = ip6_tnl_encap(skb, t, &proto, fl6); if (err) -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] net: atlantic: fix aq_vec index out of range error
by Wang Liang 03 Jul '25

03 Jul '25

From: "Chia-Lin Kao (AceLan)" <acelan.kao(a)canonical.com> mainline inclusion from mainline-v6.0-rc1 commit 2ba5e47fb75fbb8fab45f5c1bc8d5c33d8834bd3 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/ICGA4Q CVE: CVE-2022-50066 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- The final update statement of the for loop exceeds the array range, the dereference of self->aq_vec[i] is not checked and then leads to the index out of range error. Also fixed this kind of coding style in other for loop. [ 97.937604] UBSAN: array-index-out-of-bounds in drivers/net/ethernet/aquantia/atlantic/aq_nic.c:1404:48 [ 97.937607] index 8 is out of range for type 'aq_vec_s *[8]' [ 97.937608] CPU: 38 PID: 3767 Comm: kworker/u256:18 Not tainted 5.19.0+ #2 [ 97.937610] Hardware name: Dell Inc. Precision 7865 Tower/, BIOS 1.0.0 06/12/2022 [ 97.937611] Workqueue: events_unbound async_run_entry_fn [ 97.937616] Call Trace: [ 97.937617] <TASK> [ 97.937619] dump_stack_lvl+0x49/0x63 [ 97.937624] dump_stack+0x10/0x16 [ 97.937626] ubsan_epilogue+0x9/0x3f [ 97.937627] __ubsan_handle_out_of_bounds.cold+0x44/0x49 [ 97.937629] ? __scm_send+0x348/0x440 [ 97.937632] ? aq_vec_stop+0x72/0x80 [atlantic] [ 97.937639] aq_nic_stop+0x1b6/0x1c0 [atlantic] [ 97.937644] aq_suspend_common+0x88/0x90 [atlantic] [ 97.937648] aq_pm_suspend_poweroff+0xe/0x20 [atlantic] [ 97.937653] pci_pm_suspend+0x7e/0x1a0 [ 97.937655] ? pci_pm_suspend_noirq+0x2b0/0x2b0 [ 97.937657] dpm_run_callback+0x54/0x190 [ 97.937660] __device_suspend+0x14c/0x4d0 [ 97.937661] async_suspend+0x23/0x70 [ 97.937663] async_run_entry_fn+0x33/0x120 [ 97.937664] process_one_work+0x21f/0x3f0 [ 97.937666] worker_thread+0x4a/0x3c0 [ 97.937668] ? process_one_work+0x3f0/0x3f0 [ 97.937669] kthread+0xf0/0x120 [ 97.937671] ? kthread_complete_and_exit+0x20/0x20 [ 97.937672] ret_from_fork+0x22/0x30 [ 97.937676] </TASK> v2. fixed "warning: variable 'aq_vec' set but not used" v3. simplified a for loop Fixes: 97bde5c4f909 ("net: ethernet: aquantia: Support for NIC-specific code") Signed-off-by: Chia-Lin Kao (AceLan) <acelan.kao(a)canonical.com> Acked-by: Sudarsana Reddy Kalluru <skalluru(a)marvell.com> Link: https://lore.kernel.org/r/20220808081845.42005-1-acelan.kao@canonical.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: drivers/net/ethernet/aquantia/atlantic/aq_nic.c [conflicts due to not merge 04a1839950d9 ("net: aquantia: implement data PTP datapath"), conflicts due to not merge 4272ba8b11f8 ("net: atlantic: per-TC queue statistics")] Signed-off-by: Wang Liang <wangliang74(a)huawei.com> --- .../net/ethernet/aquantia/atlantic/aq_nic.c | 22 ++++++++----------- 1 file changed, 9 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 8cc34b0bedc3..a29a4f804448 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -181,12 +181,10 @@ static void aq_nic_service_timer_cb(struct timer_list *t) static void aq_nic_polling_timer_cb(struct timer_list *t) { struct aq_nic_s *self = from_timer(self, t, polling_timer); - struct aq_vec_s *aq_vec = NULL; unsigned int i = 0U; - for (i = 0U, aq_vec = self->aq_vec[0]; - self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) - aq_vec_isr(i, (void *)aq_vec); + for (i = 0U; self->aq_vecs > i; ++i) + aq_vec_isr(i, (void *)self->aq_vec[i]); mod_timer(&self->polling_timer, jiffies + AQ_CFG_POLLING_TIMER_INTERVAL); @@ -643,7 +641,6 @@ void aq_nic_get_stats(struct aq_nic_s *self, u64 *data) { unsigned int i = 0U; unsigned int count = 0U; - struct aq_vec_s *aq_vec = NULL; struct aq_stats_s *stats = self->aq_hw_ops->hw_get_hw_stats(self->aq_hw); if (!stats) @@ -676,10 +673,11 @@ void aq_nic_get_stats(struct aq_nic_s *self, u64 *data) data += i; - for (i = 0U, aq_vec = self->aq_vec[0]; - aq_vec && self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) { + for (i = 0U; self->aq_vecs > i; ++i) { + if (!self->aq_vec[i]) + break; data += count; - aq_vec_get_sw_stats(aq_vec, data, &count); + aq_vec_get_sw_stats(self->aq_vec[i], data, &count); } err_exit:; @@ -855,7 +853,6 @@ u32 aq_nic_get_fw_version(struct aq_nic_s *self) int aq_nic_stop(struct aq_nic_s *self) { - struct aq_vec_s *aq_vec = NULL; unsigned int i = 0U; netif_tx_disable(self->ndev); @@ -870,9 +867,8 @@ int aq_nic_stop(struct aq_nic_s *self) else aq_pci_func_free_irqs(self); - for (i = 0U, aq_vec = self->aq_vec[0]; - self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) - aq_vec_stop(aq_vec); + for (i = 0U; self->aq_vecs > i; ++i) + aq_vec_stop(self->aq_vec[i]); return self->aq_hw_ops->hw_stop(self->aq_hw); } @@ -974,4 +970,4 @@ void aq_nic_shutdown(struct aq_nic_s *self) err_exit: rtnl_unlock(); -} \ No newline at end of file +} -- 2.34.1

2 1

[PATCH OLK-6.6 0/5] Backport mainline patches
by Wang Liang 03 Jul '25

03 Jul '25

Florian Westphal (4): xfrm: pass struct net to xfrm_decode_session wrappers xfrm: move mark and oif flowi decode into common code xfrm: policy: replace session decode with flow dissector xfrm: policy: fix layer 4 flowi decoding Guillaume Nault (1): xfrm: Clear low order bits of ->flowi4_tos in decode_session4(). include/net/xfrm.h | 12 +- net/ipv4/icmp.c | 2 +- net/ipv4/ip_vti.c | 4 +- net/ipv4/netfilter.c | 2 +- net/ipv6/icmp.c | 2 +- net/ipv6/ip6_vti.c | 4 +- net/ipv6/netfilter.c | 2 +- net/netfilter/nf_nat_proto.c | 2 +- net/xfrm/xfrm_interface_core.c | 4 +- net/xfrm/xfrm_policy.c | 299 ++++++++++++++------------------- 10 files changed, 142 insertions(+), 191 deletions(-) -- 2.34.1

2 6