- Kernel - mailweb.openeuler.org

[PATCH OLK-5.10] smb: client: Fix use-after-free of network namespace.
by Long Li 03 Dec '24

03 Dec '24

From: Kuniyuki Iwashima <kuniyu(a)amazon.com> mainline inclusion from mainline-v6.10-rc2 commit ef7134c7fc48e1441b398e55a862232868a6f0a7 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IB67YB CVE: CVE-2024-53095 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Recently, we got a customer report that CIFS triggers oops while reconnecting to a server. [0] The workload runs on Kubernetes, and some pods mount CIFS servers in non-root network namespaces. The problem rarely happened, but it was always while the pod was dying. The root cause is wrong reference counting for network namespace. CIFS uses kernel sockets, which do not hold refcnt of the netns that the socket belongs to. That means CIFS must ensure the socket is always freed before its netns; otherwise, use-after-free happens. The repro steps are roughly: 1. mount CIFS in a non-root netns 2. drop packets from the netns 3. destroy the netns 4. unmount CIFS We can reproduce the issue quickly with the script [1] below and see the splat [2] if CONFIG_NET_NS_REFCNT_TRACKER is enabled. When the socket is TCP, it is hard to guarantee the netns lifetime without holding refcnt due to async timers. Let's hold netns refcnt for each socket as done for SMC in commit 9744d2bf1976 ("smc: Fix use-after-free in tcp_write_timer_handler()."). Note that we need to move put_net() from cifs_put_tcp_session() to clean_demultiplex_info(); otherwise, __sock_create() still could touch a freed netns while cifsd tries to reconnect from cifs_demultiplex_thread(). Also, maybe_get_net() cannot be put just before __sock_create() because the code is not under RCU and there is a small chance that the same address happened to be reallocated to another netns. [0]: CIFS: VFS: \\XXXXXXXXXXX has not responded in 15 seconds. Reconnecting... CIFS: Serverclose failed 4 times, giving up Unable to handle kernel paging request at virtual address 14de99e461f84a07 Mem abort info: ESR = 0x0000000096000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x04: level 0 translation fault Data abort info: ISV = 0, ISS = 0x00000004 CM = 0, WnR = 0 [14de99e461f84a07] address between user and kernel address ranges Internal error: Oops: 0000000096000004 [#1] SMP Modules linked in: cls_bpf sch_ingress nls_utf8 cifs cifs_arc4 cifs_md4 dns_resolver tcp_diag inet_diag veth xt_state xt_connmark nf_conntrack_netlink xt_nat xt_statistic xt_MASQUERADE xt_mark xt_addrtype ipt_REJECT nf_reject_ipv4 nft_chain_nat nf_nat xt_conntrack nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 xt_comment nft_compat nf_tables nfnetlink overlay nls_ascii nls_cp437 sunrpc vfat fat aes_ce_blk aes_ce_cipher ghash_ce sm4_ce_cipher sm4 sm3_ce sm3 sha3_ce sha512_ce sha512_arm64 sha1_ce ena button sch_fq_codel loop fuse configfs dmi_sysfs sha2_ce sha256_arm64 dm_mirror dm_region_hash dm_log dm_mod dax efivarfs CPU: 5 PID: 2690970 Comm: cifsd Not tainted 6.1.103-109.184.amzn2023.aarch64 #1 Hardware name: Amazon EC2 r7g.4xlarge/, BIOS 1.0 11/1/2018 pstate: 00400005 (nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : fib_rules_lookup+0x44/0x238 lr : __fib_lookup+0x64/0xbc sp : ffff8000265db790 x29: ffff8000265db790 x28: 0000000000000000 x27: 000000000000bd01 x26: 0000000000000000 x25: ffff000b4baf8000 x24: ffff00047b5e4580 x23: ffff8000265db7e0 x22: 0000000000000000 x21: ffff00047b5e4500 x20: ffff0010e3f694f8 x19: 14de99e461f849f7 x18: 0000000000000000 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: 0000000000000000 x13: 0000000000000000 x12: 3f92800abd010002 x11: 0000000000000001 x10: ffff0010e3f69420 x9 : ffff800008a6f294 x8 : 0000000000000000 x7 : 0000000000000006 x6 : 0000000000000000 x5 : 0000000000000001 x4 : ffff001924354280 x3 : ffff8000265db7e0 x2 : 0000000000000000 x1 : ffff0010e3f694f8 x0 : ffff00047b5e4500 Call trace: fib_rules_lookup+0x44/0x238 __fib_lookup+0x64/0xbc ip_route_output_key_hash_rcu+0x2c4/0x398 ip_route_output_key_hash+0x60/0x8c tcp_v4_connect+0x290/0x488 __inet_stream_connect+0x108/0x3d0 inet_stream_connect+0x50/0x78 kernel_connect+0x6c/0xac generic_ip_connect+0x10c/0x6c8 [cifs] __reconnect_target_unlocked+0xa0/0x214 [cifs] reconnect_dfs_server+0x144/0x460 [cifs] cifs_reconnect+0x88/0x148 [cifs] cifs_readv_from_socket+0x230/0x430 [cifs] cifs_read_from_socket+0x74/0xa8 [cifs] cifs_demultiplex_thread+0xf8/0x704 [cifs] kthread+0xd0/0xd4 Code: aa0003f8 f8480f13 eb18027f 540006c0 (b9401264) [1]: CIFS_CRED="/root/cred.cifs" CIFS_USER="Administrator" CIFS_PASS="Password" CIFS_IP="X.X.X.X" CIFS_PATH="//${CIFS_IP}/Users/Administrator/Desktop/CIFS_TEST" CIFS_MNT="/mnt/smb" DEV="enp0s3" cat <<EOF > ${CIFS_CRED} username=${CIFS_USER} password=${CIFS_PASS} domain=EXAMPLE.COM EOF unshare -n bash -c " mkdir -p ${CIFS_MNT} ip netns attach root 1 ip link add eth0 type veth peer veth0 netns root ip link set eth0 up ip -n root link set veth0 up ip addr add 192.168.0.2/24 dev eth0 ip -n root addr add 192.168.0.1/24 dev veth0 ip route add default via 192.168.0.1 dev eth0 ip netns exec root sysctl net.ipv4.ip_forward=1 ip netns exec root iptables -t nat -A POSTROUTING -s 192.168.0.2 -o ${DEV} -j MASQUERADE mount -t cifs ${CIFS_PATH} ${CIFS_MNT} -o vers=3.0,sec=ntlmssp,credentials=${CIFS_CRED},rsize=65536,wsize=65536,cache=none,echo_interval=1 touch ${CIFS_MNT}/a.txt ip netns exec root iptables -t nat -D POSTROUTING -s 192.168.0.2 -o ${DEV} -j MASQUERADE " umount ${CIFS_MNT} [2]: ref_tracker: net notrefcnt@000000004bbc008d has 1/1 users at sk_alloc (./include/net/net_namespace.h:339 net/core/sock.c:2227) inet_create (net/ipv4/af_inet.c:326 net/ipv4/af_inet.c:252) __sock_create (net/socket.c:1576) generic_ip_connect (fs/smb/client/connect.c:3075) cifs_get_tcp_session.part.0 (fs/smb/client/connect.c:3160 fs/smb/client/connect.c:1798) cifs_mount_get_session (fs/smb/client/trace.h:959 fs/smb/client/connect.c:3366) dfs_mount_share (fs/smb/client/dfs.c:63 fs/smb/client/dfs.c:285) cifs_mount (fs/smb/client/connect.c:3622) cifs_smb3_do_mount (fs/smb/client/cifsfs.c:949) smb3_get_tree (fs/smb/client/fs_context.c:784 fs/smb/client/fs_context.c:802 fs/smb/client/fs_context.c:794) vfs_get_tree (fs/super.c:1800) path_mount (fs/namespace.c:3508 fs/namespace.c:3834) __x64_sys_mount (fs/namespace.c:3848 fs/namespace.c:4057 fs/namespace.c:4034 fs/namespace.c:4034) do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Fixes: 26abe14379f8 ("net: Modify sk_alloc to not reference count the netns of kernel sockets.") Signed-off-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Acked-by: Tom Talpey <tom(a)talpey.com> Signed-off-by: Steve French <stfrench(a)microsoft.com> Conflicts: fs/cifs/connect.c fs/smb/client/connect.c [conflicts due to cifs rename to smb/client] Signed-off-by: Long Li <leo.lilong(a)huawei.com> --- fs/cifs/connect.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 5a688129b5ca..d64e4a2b1a9b 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -966,6 +966,7 @@ static void clean_demultiplex_info(struct TCP_Server_Info *server) */ } + put_net(cifs_net_ns(server)); kfree(server->hostname); kfree(server); @@ -2530,8 +2531,6 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect) return; } - put_net(cifs_net_ns(server)); - list_del_init(&server->tcp_ses_list); spin_unlock(&cifs_tcp_ses_lock); @@ -3743,7 +3742,10 @@ generic_ip_connect(struct TCP_Server_Info *server) } if (socket == NULL) { - rc = __sock_create(cifs_net_ns(server), sfamily, SOCK_STREAM, + struct net *net = cifs_net_ns(server); + struct sock *sk; + + rc = __sock_create(net, sfamily, SOCK_STREAM, IPPROTO_TCP, &socket, 1); if (rc < 0) { cifs_server_dbg(VFS, "Error %d creating socket\n", rc); @@ -3751,6 +3753,13 @@ generic_ip_connect(struct TCP_Server_Info *server) return rc; } + sk = socket->sk; + sk->sk_net_refcnt = 1; + get_net(net); +#ifdef CONFIG_PROC_FS + this_cpu_add(*net->core.sock_inuse, 1); +#endif + /* BB other socket options to set KEEPALIVE, NODELAY? */ cifs_dbg(FYI, "Socket created\n"); server->ssocket = socket; -- 2.39.2

2 1

[PATCH OLK-5.10 0/1] etmem : fix page_ref count leak and head missing useing problem
by chenrenhui 03 Dec '24

03 Dec '24

etmem : fix page_ref count leak and head missing useing problem chenrenhui (1): etmem : fix page_ref count leak and head missing useing problem fs/proc/etmem_swap.c | 2 ++ mm/vmscan.c | 17 ++++++----------- 2 files changed, 8 insertions(+), 11 deletions(-) -- 2.33.0

2 2

[PATCH OLK-5.10 000/133] erofs: add ondemand mode support
by Baokun Li 03 Dec '24

03 Dec '24

Al Viro (1): erofs: fix handling kern_mount() failure Baokun Li (29): openeuler_defconfig: enable erofs ondemand for x86 and arm64 fscache: fix reference count leakage during abort init fscache: fix assertion failure in fscache_put_object() erofs: fix lockdep false positives on initializing erofs_pseudo_mnt erofs: remove erofs_fscache_netfs fscache: rename new_location to new_version cachefiles: use mainline xattr in ondemand mode cachefiles: remove err_put_fd tag in cachefiles_ondemand_daemon_read() cachefiles: fix slab-use-after-free in cachefiles_ondemand_get_fd() cachefiles: fix slab-use-after-free in cachefiles_ondemand_daemon_read() cachefiles: add output string to cachefiles_obj_[get|put]_ondemand_fd cachefiles: add consistency check for copen/cread cachefiles: stop sending new request when dropping object cachefiles: flush all requests for the object that is being dropped fscache: limit fscache_object_max_active to avoid blocking cachefiles: add spin_lock for cachefiles_ondemand_info cachefiles: never get a new anon fd if ondemand_id is valid cachefiles: make on-demand read killable fscache: set the default value of object_max_active to 256 cachefiles: flush all requests after setting CACHEFILES_DEAD cachefiles: call cachefiles_ondemand_init_object() out of dir inode lock cachefiles: defer exposing anon_fd until after copy_to_user() succeeds cachefiles: disallow to complete open requests with uninitialised ondemand_id cachefiles: clear FSCACHE_COOKIE_NO_DATA_YET for the new ondemand object erofs: correct the blknr/blkoff calculation in erofs_read_raw_page() fscache: fix op leak due to abort init after parent ready cachefiles: cyclic allocation of msg_id to avoid reuse fscache: fix assertion failure in cachefiles_put_object() cachefiles: prefault in user pages to aovid ABBA deadlock David Howells (1): cachefiles, erofs: Fix NULL deref in when cachefiles is not doing ondemand-mode Dawei Li (1): erofs: protect s_inodes with s_inode_list_lock for fscache Gao Xiang (26): erofs: clean up file headers & footers erofs: introduce chunk-based file on-disk format erofs: support reading chunk-based uncompressed files erofs: fix double free of 'copied' erofs: introduce erofs_sb_has_xxx() helpers erofs: decouple basic mount options from fs_context erofs: add multiple device support erofs: clean up erofs_map_blocks tracepoints erofs: introduce meta buffer operations erofs: use meta buffers for inode operations erofs: use meta buffers for super operations erofs: use meta buffers for xattr operations erofs: use meta buffers for zmap operations erofs: fix misbehavior of unsupported chunk format check erofs: add fscache mode check helper erofs: register fscache volume erofs: add fscache context helper functions erofs: add anonymous inode caching metadata for data blobs erofs: register fscache context for primary data blob erofs: register fscache context for extra data blobs erofs: implement fscache-based metadata read erofs: implement fscache-based data read for non-inline layout erofs: implement fscache-based data read for inline layout erofs: add 'fsid' mount option erofs: scan devices from device table erofs: fix order >= MAX_ORDER warning due to crafted negative i_size Hou Tao (2): erofs: check the uniqueness of fsid in shared domain in advance cachefiles: flush ondemand_object_worker during clean object Jeffle Xu (9): erofs: use meta buffers for erofs_read_superblock() cachefiles: notify the user daemon when looking up cookie cachefiles: unbind cachefiles gracefully in on-demand mode cachefiles: notify the user daemon when withdrawing cookie cachefiles: implement on-demand read cachefiles: enable on-demand read mode anolis: cachefiles: skip check for n_children in on-demand mode erofs: make erofs_map_blocks() generally available erofs: leave compressed inodes unsupported in fscache mode for now Jia Zhu (12): cachefiles: narrow the scope of flushed requests when releasing fd erofs: use kill_anon_super() to kill super in fscache mode erofs: code clean up for fscache erofs: introduce fscache-based domain erofs: introduce a pseudo mnt to manage shared cookies erofs: Support sharing cookies in the same domain erofs: introduce 'domain_id' mount option anolis: cachefiles: introduce object ondemand state anolis: cachefiles: extract ondemand info field from cachefiles_object anolis: cachefiles: resend an open request if the read request's object is closed anolis: cachefiles: narrow the scope of triggering EPOLLIN events in ondemand mode anolis: cachefiles: add restore command to recover inflight ondemand read requests Jingbo Xu (18): anolis: cachefiles: replace BUG_ON() with WARN_ON() anolis: cachefiles: fix volume key setup for cachefiles_open anolis: cachefiles: refactor cachefiles_ondemand_daemon_read() anolis: erofs: fix the name of erofs_fscache_super_index_def anolis: cachefiles: maintain a file descriptor to the backing file anolis: fscache,cachefiles: add fscache_prepare_read() helper anolis: erofs: implement fscache-based data readahead erofs: fix use-after-free of fsid and domain_id string erofs: remove unused EROFS_GET_BLOCKS_RAW flag anolis: cachefiles: optimize on-demand IO path with buffer IO anolis: fscache: export fscache_object_wq anolis: cachefiles: reset object->private to NULL when it's freed anolis: cachefiles: add missing lock protection when polling anolis: cachefiles: fix potential NULL in error path erofs: relinquish volume with mutex held erofs: maintain cookies of share domain in self-contained list erofs: remove unused device mapping in meta routine erofs: unify anonymous inodes for blob Mikulas Patocka (1): wait_on_bit: add an acquire memory barrier Sun Ke (1): cachefiles: fix error return code in cachefiles_ondemand_copen() Xin Yin (1): cachefiles: make on-demand request distribution fairer Yu Kuai (10): fscache: add new helper to determine cachefile location fscache: generate new key_hash for new location cachefiles: factor out helper to generate acc from cachefiles_cook_key() cachefiles: factor out helper to generate csum from cachefiles_cook_key() cachefiles: use volume key directly in cachefiles_cook_key() for new location cachefiles: skip acc in cachefiles_cook_key() for new location cachefiles: skip volum csum cachefiles_cook_key() for new location cachefiles: use key_hash as csum for new location cachefiles: handle the unprintable case for new location in cachefiles_cook_key() erofs: switch to use new location Yue Hu (1): erofs: don't use erofs_map_blocks() any more Zizhi Wo (20): erofs: fix page unlock advance during readahead erofs: add erofs switch to better control it erofs: add erofs_ondemand switch fscache: fix kernel BUG at __fscache_read_or_alloc_page fscache: add a waiting mechanism when duplicate cookies are detected fscache: Fix trace UAF in fscache_cookie_put() cachefiles: Fix NULL pointer dereference in object->file cachefiles: Restrict monitor calls to read_page cachefiles: Fix cookie reference count leakage error fscache: Add the unhash_cookie mechanism to fscache_drop_object() cachefiles: Add restrictions to cachefiles_daemon_cull() cachefiles: Change the mark inactive sequence in erofs ondemand mode cachefiles: Set object to close if ondemand_id < 0 in copen s390: provide arch_test_bit_acquire() for architecture s390 wait_on_bit: Add wait_on_bit_acquire() to provide memory barrier fscache: add a memory barrier for FSCACHE_COOKIE_LOOKING_UP fscache/cachefiles: add a memory barrier for waking and waiting fscache/cachefiles: add a memory barrier for page_write fscache: modify fscache_hash_cookie() to enhance security cachefiles: modify inappropriate error return value in cachefiles_daemon_secctx Documentation/atomic_bitops.txt | 10 +- Documentation/filesystems/erofs.rst | 28 +- arch/arm64/configs/openeuler_defconfig | 9 +- arch/s390/include/asm/bitops.h | 7 + arch/x86/configs/openeuler_defconfig | 9 +- arch/x86/include/asm/bitops.h | 21 + fs/Makefile | 2 + fs/cachefiles/Kconfig | 12 + fs/cachefiles/Makefile | 1 + fs/cachefiles/bind.c | 28 +- fs/cachefiles/daemon.c | 134 +++- fs/cachefiles/interface.c | 34 +- fs/cachefiles/internal.h | 132 ++- fs/cachefiles/key.c | 167 +++- fs/cachefiles/namei.c | 45 +- fs/cachefiles/ondemand.c | 752 ++++++++++++++++++ fs/cachefiles/rdwr.c | 201 ++++- fs/cachefiles/xattr.c | 179 ++++- fs/erofs/Kconfig | 35 +- fs/erofs/Makefile | 2 +- fs/erofs/compress.h | 2 - fs/erofs/data.c | 259 ++++-- fs/erofs/decompressor.c | 5 +- fs/erofs/dir.c | 2 - fs/erofs/erofs_fs.h | 68 +- fs/erofs/fscache.c | 568 +++++++++++++ fs/erofs/inode.c | 98 ++- fs/erofs/internal.h | 161 +++- fs/erofs/namei.c | 2 - fs/erofs/super.c | 353 ++++++-- fs/erofs/tagptr.h | 3 - fs/erofs/utils.c | 2 - fs/erofs/xattr.c | 141 +--- fs/erofs/xattr.h | 2 - fs/erofs/zdata.c | 35 +- fs/erofs/zdata.h | 1 - fs/erofs/zmap.c | 48 +- fs/erofs/zpvec.h | 2 - fs/fs_ctl.c | 43 + fs/fscache/cookie.c | 149 ++-- fs/fscache/internal.h | 1 + fs/fscache/main.c | 17 +- fs/fscache/object.c | 39 +- fs/fscache/page.c | 90 ++- .../bitops/instrumented-non-atomic.h | 12 + include/asm-generic/bitops/non-atomic.h | 14 + include/linux/fs.h | 17 + include/linux/fscache-cache.h | 8 + include/linux/fscache.h | 60 +- include/linux/wait_bit.h | 25 + include/trace/events/cachefiles.h | 10 +- include/trace/events/erofs.h | 7 +- include/uapi/linux/cachefiles.h | 69 ++ kernel/sched/wait_bit.c | 40 + lib/radix-tree.c | 1 + 55 files changed, 3614 insertions(+), 548 deletions(-) create mode 100644 fs/cachefiles/ondemand.c create mode 100644 fs/erofs/fscache.c create mode 100644 fs/fs_ctl.c create mode 100644 include/uapi/linux/cachefiles.h -- 2.46.1

2 134

[PATCH v2 OLK-5.10 0/8] CVE-2024-40927
by Yongqiang Liu 03 Dec '24

03 Dec '24

Hector Martin (1): xhci: Handle TD clearing for multiple streams case Mathias Nyman (6): xhci: use xhci_td_cleanup() helper when giving back cancelled URBs xhci: split handling halted endpoints into two steps xhci: fix giving back URB with incorrect status regression in 5.12 xhci: Fix 5.12 regression of missing xHC cache clearing command after a Stall xhci: introduce a new move_dequeue_past_td() function to replace old code. xhci: Fix failure to give back some cached cancelled URBs. Michal Pecio (1): usb: xhci: Fix TD invalidation under pending Set TR Dequeue drivers/usb/host/xhci-ring.c | 385 ++++++++++++++++++++++++++--------- drivers/usb/host/xhci.c | 94 +-------- drivers/usb/host/xhci.h | 9 + 3 files changed, 299 insertions(+), 189 deletions(-) -- 2.25.1

2 9

[PATCH OLK-5.10 1/1] etmem : fix page_ref count leak and head missing useing problem
by chenrenhui 03 Dec '24

03 Dec '24

euleros inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IAXJCE CVE: NA ---------------------------------------------------- In the etmem swap process, use get_page_from_vaddr to obtain the page and add the page reference counting. If a page does not meet the recycling criteria, release the reference counting of the page. In the add_page_for_swap process, if the input page is the middle page of a compound page, head and page cannot be used together. Instead, head must be used as the input parameter. Fixes: 715de52cae8d ("etmem : fix page_ref count leak and head missing useing problem") Signed-off-by: chenrenhui <chenrenhui1(a)huawei.com> --- fs/proc/etmem_swap.c | 2 ++ mm/vmscan.c | 17 ++++++----------- 2 files changed, 8 insertions(+), 11 deletions(-) diff --git a/fs/proc/etmem_swap.c b/fs/proc/etmem_swap.c index 86f5cf8c90a1..becc7f7c2fa8 100644 --- a/fs/proc/etmem_swap.c +++ b/fs/proc/etmem_swap.c @@ -70,6 +70,8 @@ static ssize_t swap_pages_write(struct file *file, const char __user *buf, continue; add_page_for_swap(page, &pagelist); + /* release the ref count we get from the get_page_from_vaddr interface */ + put_page(page); } if (!list_empty(&pagelist)) diff --git a/mm/vmscan.c b/mm/vmscan.c index 7cb214d44417..08213f1c18ee 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -4623,7 +4623,6 @@ EXPORT_SYMBOL_GPL(check_move_unevictable_pages); #ifdef CONFIG_ETMEM int add_page_for_swap(struct page *page, struct list_head *pagelist) { - int err = -EBUSY; struct page *head; /* If the page is mapped by more than one process, do not swap it */ @@ -4634,19 +4633,15 @@ int add_page_for_swap(struct page *page, struct list_head *pagelist) return -EACCES; head = compound_head(page); - err = isolate_lru_page(head); - if (err) { - put_page(page); - return err; - } - put_page(page); - if (PageUnevictable(page)) - putback_lru_page(page); + if (isolate_lru_page(head)) + return -EBUSY; + + if (PageUnevictable(head)) + putback_lru_page(head); else list_add_tail(&head->lru, pagelist); - err = 0; - return err; + return 0; } EXPORT_SYMBOL_GPL(add_page_for_swap); -- 2.33.0

2 1

[openeuler:OLK-5.10 2516/2516] drivers/gpu/drm/ast/ast_mm.c:91:39: sparse: sparse: incorrect type in assignment (different address spaces)
by kernel test robot 03 Dec '24

03 Dec '24

tree: https://gitee.com/openeuler/kernel.git OLK-5.10 head: f030ffc8e0c6dac3503bebddbf49cc339003fcdb commit: 968ee436e4d0ce09994f74015dc163ef280ccc1e [2516/2516] drm/ast: Fixed display error for ps23xx when using ast bmc card config: x86_64-randconfig-121-20241203 (https://download.01.org/0day-ci/archive/20241203/202412032029.eVzOP3UR-lkp@…) compiler: gcc-12 (Debian 12.2.0-14) 12.2.0 reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20241203/202412032029.eVzOP3UR-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/202412032029.eVzOP3UR-lkp@intel.com/ sparse warnings: (new ones prefixed by >>) >> drivers/gpu/drm/ast/ast_mm.c:91:39: sparse: sparse: incorrect type in assignment (different address spaces) @@ expected void *addr @@ got void [noderef] __iomem * @@ drivers/gpu/drm/ast/ast_mm.c:91:39: sparse: expected void *addr drivers/gpu/drm/ast/ast_mm.c:91:39: sparse: got void [noderef] __iomem * vim +91 drivers/gpu/drm/ast/ast_mm.c 76 77 static int ast_driver_io_mem_reserve(struct ttm_bo_device *bdev, 78 struct ttm_resource *mem) 79 { 80 struct drm_vram_mm *vmm = drm_vram_mm_of_bdev(bdev); 81 size_t bus_size = (size_t)mem->num_pages << PAGE_SHIFT; 82 83 switch (mem->mem_type) { 84 case TTM_PL_SYSTEM: /* nothing to do */ 85 break; 86 case TTM_PL_VRAM: 87 mem->bus.offset = (mem->start << PAGE_SHIFT) + vmm->vram_base; 88 mem->bus.is_iomem = true; 89 90 mem->placement = TTM_PL_FLAG_UNCACHED; > 91 mem->bus.addr = ioremap(mem->bus.offset, bus_size); 92 93 if (!mem->bus.addr) 94 return -ENOMEM; 95 96 break; 97 default: 98 return -EINVAL; 99 } 100 101 return 0; 102 } 103 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH OLK-5.10] hwpoison, memory_hotplug: lock page before unmap for hwpoisoned page
by Wupeng Ma 03 Dec '24

03 Dec '24

From: Ma Wupeng <mawupeng1(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IB8TSF -------------------------------- Commit b15c87263a69 ("hwpoison, memory_hotplug: allow hwpoisoned pages to be offlined) add page poison checks in do_migrate_range in order to make offline hwpoisoned page possible by introducing isolate_lru_page and try_to_unmap for hwpoisoned page. However page lock must be held before calling try_to_unmap. Add it to fix this problem. Without page lock, kernel will BUG_ON with the following log: ------------[ cut here ]------------ kernel BUG at include/linux/swapops.h:326! Internal error: Oops - BUG: 00000000f2000800 [#1] SMP CPU: 55 PID: 59981 Comm: sh Kdump: loaded Tainted: G W OE 5.10.0 #1 pstate: 60400009 (nZCv daif +PAN -UAO -TCO BTYPE=--) pc : try_to_unmap_one+0xdfc/0x1380 lr : try_to_unmap_one+0x4f4/0x1380 Call trace: try_to_unmap_one+0xdfc/0x1380 rmap_walk_anon+0x150/0x45c rmap_walk+0x50/0xfc try_to_unmap+0x108/0x1b0 do_migrate_range+0x3bc/0x6d0 offline_pages+0x450/0x5b0 memory_subsys_offline+0x4c/0x9c device_offline+0xfc/0x14c state_store+0x98/0x110 dev_attr_store+0x1c/0x40 sysfs_kf_write+0x48/0x70 kernfs_fop_write_iter+0x128/0x1d0 new_sync_write+0xec/0x1a0 vfs_write+0x208/0x2b0 ksys_write+0x70/0x110 __arm64_sys_write+0x20/0x40 invoke_syscall+0x4c/0x124 el0_svc_common.constprop.0+0x140/0x15c do_el0_svc+0x30/0xd0 el0_svc+0x1c/0x2c el0_sync_handler+0xb0/0xb4 el0_sync+0x168/0x180 Code: 17ffffde d1000400 f9400000 3707a240 (d4210000) SMP: stopping secondary CPUs Fixes: b15c87263a69 ("hwpoison, memory_hotplug: allow hwpoisoned pages to be offlined") Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> --- mm/memory_hotplug.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index e49bc4753eca..465100749d2d 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1160,8 +1160,11 @@ int do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) if (PageHWPoison(page)) { if (WARN_ON(PageLRU(page))) isolate_lru_page(page); - if (page_mapped(page)) + if (page_mapped(page)) { + lock_page(page); try_to_unmap(page, TTU_IGNORE_MLOCK); + unlock_page(page); + } continue; } -- 2.25.1

2 1

[openeuler:openEuler-1.0-LTS 1297/1297] kernel/locking/.tmp_percpu-rwsem.o: warning: objtool: missing symbol for section .text
by kernel test robot 03 Dec '24

03 Dec '24

tree: https://gitee.com/openeuler/kernel.git openEuler-1.0-LTS head: 312efa97a54edf7e64f108312c4d8c6961a1abaf commit: 96d4baaa81cce700eb801a0a9bf28b7fbbba3162 [1297/1297] tasks, sched/core: With a grace period after finish_task_switch(), remove unnecessary code config: x86_64-buildonly-randconfig-002-20241117 (https://download.01.org/0day-ci/archive/20241203/202412032008.TV1mkLUs-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/20241203/202412032008.TV1mkLUs-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/202412032008.TV1mkLUs-lkp@intel.com/ All warnings (new ones prefixed by >>): >> kernel/locking/.tmp_percpu-rwsem.o: warning: objtool: missing symbol for section .text -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH OLK-5.10] drivers/perf: hisi: Enable HiSilicon Erratum 162400501 quirk
by Yushan Wang 03 Dec '24

03 Dec '24

From: Junhao He <hejunhao3(a)huawei.com> driver inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/IB7OM0 CVE: NA ---------------------------------------------------------------------- On HiSilicon HIP10C platform, the DDRC PMU interrupt registers offset is modified, causing the interrupt handler to fail to properly handle counter overflows. This patch tries to fix this by correcting the HIP10C platform DDRC PMU interrupt registers offset (including mask/status/clear registers). Signed-off-by: Junhao He <hejunhao3(a)huawei.com> Signed-off-by: Qizhi Zhang <zhangqizhi3(a)h-partners.com> Signed-off-by: Yushan Wang <wangyushan12(a)huawei.com> --- drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c | 70 +++++++++++++++++-- drivers/perf/hisilicon/hisi_uncore_pmu.h | 1 + 2 files changed, 65 insertions(+), 6 deletions(-) diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c index ee020669d134..816770ace86f 100644 --- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c @@ -43,6 +43,16 @@ #define DDRC_V2_EVENT_TYPE 0xe74 #define DDRC_V2_PERF_CTRL 0xeA0 +/* + * HIP10C platform v2 PMU DDRC interrupt registers definition + * On HIP10C platform, the DDRC PMU interrupt register offset is + * modified, causing the interrupt handler to fail to properly + * handle counter overflows. + */ +#define DDRC_V2_HIP10C_INT_MASK 0x534 +#define DDRC_V2_HIP10C_INT_STATUS 0x538 +#define DDRC_V2_HIP10C_INT_CLEAR 0x53C + /* DDRC has 8-counters */ #define DDRC_NR_COUNTERS 0x8 #define DDRC_V1_PERF_CTRL_EN 0x2 @@ -58,11 +68,39 @@ */ #define GET_DDRC_EVENTID(hwc) (hwc->config_base & 0x7) +#define HISI_DDRC_PMU_NORMAL_PMU 0x0 /* HiSilicon normal PMU */ +#define HISI_DDRC_PMU_INCORRECT_INT_REGS BIT(0) /* HiSilicon HIP10C PMU */ + static const u32 ddrc_reg_off[] = { DDRC_FLUX_WR, DDRC_FLUX_RD, DDRC_FLUX_WCMD, DDRC_FLUX_RCMD, DDRC_PRE_CMD, DDRC_ACT_CMD, DDRC_RNK_CHG, DDRC_RW_CHG }; +static struct acpi_platform_list hisi_uncore_plat_info[] = { + /* HiSilicon Hip10C Platform */ + {"HISI ", "HIP10C ", 0, ACPI_SIG_DSDT, greater_than_or_equal, + "Erratum #162400501", HISI_DDRC_PMU_INCORRECT_INT_REGS}, + { } +}; + +static void hisi_ddrc_pmu_check_errata(struct platform_device *pdev, struct hisi_pmu *ddrc_pmu) +{ + int idx; + + idx = acpi_match_platform_list(hisi_uncore_plat_info); + if (idx >= 0) + ddrc_pmu->errata = hisi_uncore_plat_info[idx].data; + else + ddrc_pmu->errata = HISI_DDRC_PMU_NORMAL_PMU; + + dev_dbg(ddrc_pmu->dev, "errata mask %#x\n", ddrc_pmu->errata); +} + +static bool hisi_ddrc_pmu_has_erratum(struct hisi_pmu *ddrc_pmu, u32 erratum) +{ + return !!(ddrc_pmu->errata & erratum); +} + /* * Select the counter register offset using the counter index. * In PMU v1, there are no programmable counter, the count @@ -248,21 +286,29 @@ static void hisi_ddrc_pmu_v1_disable_counter_int(struct hisi_pmu *ddrc_pmu, static void hisi_ddrc_pmu_v2_enable_counter_int(struct hisi_pmu *ddrc_pmu, struct hw_perf_event *hwc) { + u32 int_mask = DDRC_V2_INT_MASK; u32 val; - val = readl(ddrc_pmu->base + DDRC_V2_INT_MASK); + if (hisi_ddrc_pmu_has_erratum(ddrc_pmu, HISI_DDRC_PMU_INCORRECT_INT_REGS)) + int_mask = DDRC_V2_HIP10C_INT_MASK; + + val = readl(ddrc_pmu->base + int_mask); val &= ~(1 << hwc->idx); - writel(val, ddrc_pmu->base + DDRC_V2_INT_MASK); + writel(val, ddrc_pmu->base + int_mask); } static void hisi_ddrc_pmu_v2_disable_counter_int(struct hisi_pmu *ddrc_pmu, struct hw_perf_event *hwc) { + u32 int_mask = DDRC_V2_INT_MASK; u32 val; - val = readl(ddrc_pmu->base + DDRC_V2_INT_MASK); + if (hisi_ddrc_pmu_has_erratum(ddrc_pmu, HISI_DDRC_PMU_INCORRECT_INT_REGS)) + int_mask = DDRC_V2_HIP10C_INT_MASK; + + val = readl(ddrc_pmu->base + int_mask); val |= 1 << hwc->idx; - writel(val, ddrc_pmu->base + DDRC_V2_INT_MASK); + writel(val, ddrc_pmu->base + int_mask); } static u32 hisi_ddrc_pmu_v1_get_int_status(struct hisi_pmu *ddrc_pmu) @@ -278,13 +324,23 @@ static void hisi_ddrc_pmu_v1_clear_int_status(struct hisi_pmu *ddrc_pmu, static u32 hisi_ddrc_pmu_v2_get_int_status(struct hisi_pmu *ddrc_pmu) { - return readl(ddrc_pmu->base + DDRC_V2_INT_STATUS); + u32 int_status = DDRC_V2_INT_STATUS; + + if (hisi_ddrc_pmu_has_erratum(ddrc_pmu, HISI_DDRC_PMU_INCORRECT_INT_REGS)) + int_status = DDRC_V2_HIP10C_INT_STATUS; + + return readl(ddrc_pmu->base + int_status); } static void hisi_ddrc_pmu_v2_clear_int_status(struct hisi_pmu *ddrc_pmu, int idx) { - writel(1 << idx, ddrc_pmu->base + DDRC_V2_INT_CLEAR); + u32 int_clear = DDRC_V2_INT_CLEAR; + + if (hisi_ddrc_pmu_has_erratum(ddrc_pmu, HISI_DDRC_PMU_INCORRECT_INT_REGS)) + int_clear = DDRC_V2_HIP10C_INT_CLEAR; + + writel(1 << idx, ddrc_pmu->base + int_clear); } static const struct acpi_device_id hisi_ddrc_pmu_acpi_match[] = { @@ -464,6 +520,8 @@ static int hisi_ddrc_pmu_dev_probe(struct platform_device *pdev, if (ret) return ret; + hisi_ddrc_pmu_check_errata(pdev, ddrc_pmu); + if (ddrc_pmu->identifier >= HISI_PMU_V2) { ddrc_pmu->counter_bits = 48; ddrc_pmu->check_event = DDRC_V2_NR_EVENTS; diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.h b/drivers/perf/hisilicon/hisi_uncore_pmu.h index 9cf06c80acf4..eeacf2e89568 100644 --- a/drivers/perf/hisilicon/hisi_uncore_pmu.h +++ b/drivers/perf/hisilicon/hisi_uncore_pmu.h @@ -107,6 +107,7 @@ struct hisi_pmu { /* check event code range */ int check_event; u32 identifier; + u32 errata; }; int hisi_uncore_pmu_get_event_idx(struct perf_event *event); -- 2.33.0

2 1

[PATCH OLK-6.6] drivers/perf: hisi: Enable HiSilicon Erratum 162400501 quirk
by Yushan Wang 03 Dec '24

03 Dec '24

From: Junhao He <hejunhao3(a)huawei.com> driver inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/IB7ONX CVE: NA ---------------------------------------------------------------------- On HiSilicon HIP10C platform, the DDRC PMU interrupt registers offset is modified, causing the interrupt handler to fail to properly handle counter overflows. This patch tries to fix this by correcting the HIP10C platform DDRC PMU interrupt registers offset (including mask/status/clear registers). Signed-off-by: Junhao He <hejunhao3(a)huawei.com> Signed-off-by: Qizhi Zhang <zhangqizhi3(a)h-partners.com> Signed-off-by: Yushan Wang <wangyushan12(a)huawei.com> --- drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c | 70 +++++++++++++++++-- drivers/perf/hisilicon/hisi_uncore_pmu.h | 1 + 2 files changed, 65 insertions(+), 6 deletions(-) diff --git a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c index ee020669d134..816770ace86f 100644 --- a/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c +++ b/drivers/perf/hisilicon/hisi_uncore_ddrc_pmu.c @@ -43,6 +43,16 @@ #define DDRC_V2_EVENT_TYPE 0xe74 #define DDRC_V2_PERF_CTRL 0xeA0 +/* + * HIP10C platform v2 PMU DDRC interrupt registers definition + * On HIP10C platform, the DDRC PMU interrupt register offset is + * modified, causing the interrupt handler to fail to properly + * handle counter overflows. + */ +#define DDRC_V2_HIP10C_INT_MASK 0x534 +#define DDRC_V2_HIP10C_INT_STATUS 0x538 +#define DDRC_V2_HIP10C_INT_CLEAR 0x53C + /* DDRC has 8-counters */ #define DDRC_NR_COUNTERS 0x8 #define DDRC_V1_PERF_CTRL_EN 0x2 @@ -58,11 +68,39 @@ */ #define GET_DDRC_EVENTID(hwc) (hwc->config_base & 0x7) +#define HISI_DDRC_PMU_NORMAL_PMU 0x0 /* HiSilicon normal PMU */ +#define HISI_DDRC_PMU_INCORRECT_INT_REGS BIT(0) /* HiSilicon HIP10C PMU */ + static const u32 ddrc_reg_off[] = { DDRC_FLUX_WR, DDRC_FLUX_RD, DDRC_FLUX_WCMD, DDRC_FLUX_RCMD, DDRC_PRE_CMD, DDRC_ACT_CMD, DDRC_RNK_CHG, DDRC_RW_CHG }; +static struct acpi_platform_list hisi_uncore_plat_info[] = { + /* HiSilicon Hip10C Platform */ + {"HISI ", "HIP10C ", 0, ACPI_SIG_DSDT, greater_than_or_equal, + "Erratum #162400501", HISI_DDRC_PMU_INCORRECT_INT_REGS}, + { } +}; + +static void hisi_ddrc_pmu_check_errata(struct platform_device *pdev, struct hisi_pmu *ddrc_pmu) +{ + int idx; + + idx = acpi_match_platform_list(hisi_uncore_plat_info); + if (idx >= 0) + ddrc_pmu->errata = hisi_uncore_plat_info[idx].data; + else + ddrc_pmu->errata = HISI_DDRC_PMU_NORMAL_PMU; + + dev_dbg(ddrc_pmu->dev, "errata mask %#x\n", ddrc_pmu->errata); +} + +static bool hisi_ddrc_pmu_has_erratum(struct hisi_pmu *ddrc_pmu, u32 erratum) +{ + return !!(ddrc_pmu->errata & erratum); +} + /* * Select the counter register offset using the counter index. * In PMU v1, there are no programmable counter, the count @@ -248,21 +286,29 @@ static void hisi_ddrc_pmu_v1_disable_counter_int(struct hisi_pmu *ddrc_pmu, static void hisi_ddrc_pmu_v2_enable_counter_int(struct hisi_pmu *ddrc_pmu, struct hw_perf_event *hwc) { + u32 int_mask = DDRC_V2_INT_MASK; u32 val; - val = readl(ddrc_pmu->base + DDRC_V2_INT_MASK); + if (hisi_ddrc_pmu_has_erratum(ddrc_pmu, HISI_DDRC_PMU_INCORRECT_INT_REGS)) + int_mask = DDRC_V2_HIP10C_INT_MASK; + + val = readl(ddrc_pmu->base + int_mask); val &= ~(1 << hwc->idx); - writel(val, ddrc_pmu->base + DDRC_V2_INT_MASK); + writel(val, ddrc_pmu->base + int_mask); } static void hisi_ddrc_pmu_v2_disable_counter_int(struct hisi_pmu *ddrc_pmu, struct hw_perf_event *hwc) { + u32 int_mask = DDRC_V2_INT_MASK; u32 val; - val = readl(ddrc_pmu->base + DDRC_V2_INT_MASK); + if (hisi_ddrc_pmu_has_erratum(ddrc_pmu, HISI_DDRC_PMU_INCORRECT_INT_REGS)) + int_mask = DDRC_V2_HIP10C_INT_MASK; + + val = readl(ddrc_pmu->base + int_mask); val |= 1 << hwc->idx; - writel(val, ddrc_pmu->base + DDRC_V2_INT_MASK); + writel(val, ddrc_pmu->base + int_mask); } static u32 hisi_ddrc_pmu_v1_get_int_status(struct hisi_pmu *ddrc_pmu) @@ -278,13 +324,23 @@ static void hisi_ddrc_pmu_v1_clear_int_status(struct hisi_pmu *ddrc_pmu, static u32 hisi_ddrc_pmu_v2_get_int_status(struct hisi_pmu *ddrc_pmu) { - return readl(ddrc_pmu->base + DDRC_V2_INT_STATUS); + u32 int_status = DDRC_V2_INT_STATUS; + + if (hisi_ddrc_pmu_has_erratum(ddrc_pmu, HISI_DDRC_PMU_INCORRECT_INT_REGS)) + int_status = DDRC_V2_HIP10C_INT_STATUS; + + return readl(ddrc_pmu->base + int_status); } static void hisi_ddrc_pmu_v2_clear_int_status(struct hisi_pmu *ddrc_pmu, int idx) { - writel(1 << idx, ddrc_pmu->base + DDRC_V2_INT_CLEAR); + u32 int_clear = DDRC_V2_INT_CLEAR; + + if (hisi_ddrc_pmu_has_erratum(ddrc_pmu, HISI_DDRC_PMU_INCORRECT_INT_REGS)) + int_clear = DDRC_V2_HIP10C_INT_CLEAR; + + writel(1 << idx, ddrc_pmu->base + int_clear); } static const struct acpi_device_id hisi_ddrc_pmu_acpi_match[] = { @@ -464,6 +520,8 @@ static int hisi_ddrc_pmu_dev_probe(struct platform_device *pdev, if (ret) return ret; + hisi_ddrc_pmu_check_errata(pdev, ddrc_pmu); + if (ddrc_pmu->identifier >= HISI_PMU_V2) { ddrc_pmu->counter_bits = 48; ddrc_pmu->check_event = DDRC_V2_NR_EVENTS; diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.h b/drivers/perf/hisilicon/hisi_uncore_pmu.h index 9cf06c80acf4..eeacf2e89568 100644 --- a/drivers/perf/hisilicon/hisi_uncore_pmu.h +++ b/drivers/perf/hisilicon/hisi_uncore_pmu.h @@ -107,6 +107,7 @@ struct hisi_pmu { /* check event code range */ int check_event; u32 identifier; + u32 errata; }; int hisi_uncore_pmu_get_event_idx(struct perf_event *event); -- 2.33.0

2 1