- Kernel - mailweb.openeuler.org

[PATCH OLK-6.6] perf: Fix event leak upon exec and file release
by Li Huafei 23 Aug '24

23 Aug '24

From: Frederic Weisbecker <frederic(a)kernel.org> stable inclusion from stable-v6.6.44 commit 104e258a004037bc7dba9f6085c71dad6af57ad4 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALEPL CVE: CVE-2024-43869 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 3a5465418f5fd970e86a86c7f4075be262682840 upstream. The perf pending task work is never waited upon the matching event release. In the case of a child event, released via free_event() directly, this can potentially result in a leaked event, such as in the following scenario that doesn't even require a weak IRQ work implementation to trigger: schedule() prepare_task_switch() =======> <NMI> perf_event_overflow() event->pending_sigtrap = ... irq_work_queue(&event->pending_irq) <======= </NMI> perf_event_task_sched_out() event_sched_out() event->pending_sigtrap = 0; atomic_long_inc_not_zero(&event->refcount) task_work_add(&event->pending_task) finish_lock_switch() =======> <IRQ> perf_pending_irq() //do nothing, rely on pending task work <======= </IRQ> begin_new_exec() perf_event_exit_task() perf_event_exit_event() // If is child event free_event() WARN(atomic_long_cmpxchg(&event->refcount, 1, 0) != 1) // event is leaked Similar scenarios can also happen with perf_event_remove_on_exec() or simply against concurrent perf_event_release(). Fix this with synchonizing against the possibly remaining pending task work while freeing the event, just like is done with remaining pending IRQ work. This means that the pending task callback neither need nor should hold a reference to the event, preventing it from ever beeing freed. Fixes: 517e6a301f34 ("perf: Fix perf_pending_task() UaF") Signed-off-by: Frederic Weisbecker <frederic(a)kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/20240621091601.18227-5-frederic@kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Li Huafei <lihuafei1(a)huawei.com> --- include/linux/perf_event.h | 1 + kernel/events/core.c | 38 ++++++++++++++++++++++++++++++++++---- 2 files changed, 35 insertions(+), 4 deletions(-) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 1601aa405669..618a729c9f9c 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -797,6 +797,7 @@ struct perf_event { struct irq_work pending_irq; struct callback_head pending_task; unsigned int pending_work; + struct rcuwait pending_work_wait; atomic_t event_limit; diff --git a/kernel/events/core.c b/kernel/events/core.c index e373f901ac20..b7c4b49411be 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2288,7 +2288,6 @@ event_sched_out(struct perf_event *event, struct perf_event_context *ctx) if (state != PERF_EVENT_STATE_OFF && !event->pending_work && !task_work_add(current, &event->pending_task, TWA_RESUME)) { - WARN_ON_ONCE(!atomic_long_inc_not_zero(&event->refcount)); event->pending_work = 1; } else { local_dec(&event->ctx->nr_pending); @@ -5172,9 +5171,35 @@ static bool exclusive_event_installable(struct perf_event *event, static void perf_addr_filters_splice(struct perf_event *event, struct list_head *head); +static void perf_pending_task_sync(struct perf_event *event) +{ + struct callback_head *head = &event->pending_task; + + if (!event->pending_work) + return; + /* + * If the task is queued to the current task's queue, we + * obviously can't wait for it to complete. Simply cancel it. + */ + if (task_work_cancel(current, head)) { + event->pending_work = 0; + local_dec(&event->ctx->nr_pending); + return; + } + + /* + * All accesses related to the event are within the same + * non-preemptible section in perf_pending_task(). The RCU + * grace period before the event is freed will make sure all + * those accesses are complete by then. + */ + rcuwait_wait_event(&event->pending_work_wait, !event->pending_work, TASK_UNINTERRUPTIBLE); +} + static void _free_event(struct perf_event *event) { irq_work_sync(&event->pending_irq); + perf_pending_task_sync(event); unaccount_event(event); @@ -6807,24 +6832,28 @@ static void perf_pending_task(struct callback_head *head) struct perf_event *event = container_of(head, struct perf_event, pending_task); int rctx; + /* + * All accesses to the event must belong to the same implicit RCU read-side + * critical section as the ->pending_work reset. See comment in + * perf_pending_task_sync(). + */ + preempt_disable_notrace(); /* * If we 'fail' here, that's OK, it means recursion is already disabled * and we won't recurse 'further'. */ - preempt_disable_notrace(); rctx = perf_swevent_get_recursion_context(); if (event->pending_work) { event->pending_work = 0; perf_sigtrap(event); local_dec(&event->ctx->nr_pending); + rcuwait_wake_up(&event->pending_work_wait); } if (rctx >= 0) perf_swevent_put_recursion_context(rctx); preempt_enable_notrace(); - - put_event(event); } #ifdef CONFIG_GUEST_PERF_EVENTS @@ -11934,6 +11963,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, init_waitqueue_head(&event->waitq); init_irq_work(&event->pending_irq, perf_pending_irq); init_task_work(&event->pending_task, perf_pending_task); + rcuwait_init(&event->pending_work_wait); mutex_init(&event->mmap_mutex); raw_spin_lock_init(&event->addr_filters.lock); -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] wifi: mac80211: sdata can be NULL during AMPDU start
by Yue Haibing 23 Aug '24

23 Aug '24

From: Alexander Wetzel <alexander(a)wetzel-home.de> stable inclusion from stable-v5.10.165 commit 187523fa7c2d4c780f775cb869216865c4a909ef category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6IXN2 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 69403bad97aa0162e3d7911b27e25abe774093df upstream. ieee80211_tx_ba_session_handle_start() may get NULL for sdata when a deauthentication is ongoing. Here a trace triggering the race with the hostapd test multi_ap_fronthaul_on_ap: (gdb) list *drv_ampdu_action+0x46 0x8b16 is in drv_ampdu_action (net/mac80211/driver-ops.c:396). 391 int ret = -EOPNOTSUPP; 392 393 might_sleep(); 394 395 sdata = get_bss_sdata(sdata); 396 if (!check_sdata_in_driver(sdata)) 397 return -EIO; 398 399 trace_drv_ampdu_action(local, sdata, params); 400 wlan0: moving STA 02:00:00:00:03:00 to state 3 wlan0: associated wlan0: deauthenticating from 02:00:00:00:03:00 by local choice (Reason: 3=DEAUTH_LEAVING) wlan3.sta1: Open BA session requested for 02:00:00:00:00:00 tid 0 wlan3.sta1: dropped frame to 02:00:00:00:00:00 (unauthorized port) wlan0: moving STA 02:00:00:00:03:00 to state 2 wlan0: moving STA 02:00:00:00:03:00 to state 1 wlan0: Removed STA 02:00:00:00:03:00 wlan0: Destroyed STA 02:00:00:00:03:00 BUG: unable to handle page fault for address: fffffffffffffb48 PGD 11814067 P4D 11814067 PUD 11816067 PMD 0 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 2 PID: 133397 Comm: kworker/u16:1 Tainted: G W 6.1.0-rc8-wt+ #59 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.0-20220807_005459-localhost 04/01/2014 Workqueue: phy3 ieee80211_ba_session_work [mac80211] RIP: 0010:drv_ampdu_action+0x46/0x280 [mac80211] Code: 53 48 89 f3 be 89 01 00 00 e8 d6 43 bf ef e8 21 46 81 f0 83 bb a0 1b 00 00 04 75 0e 48 8b 9b 28 0d 00 00 48 81 eb 10 0e 00 00 <8b> 93 58 09 00 00 f6 c2 20 0f 84 3b 01 00 00 8b 05 dd 1c 0f 00 85 RSP: 0018:ffffc900025ebd20 EFLAGS: 00010287 RAX: 0000000000000000 RBX: fffffffffffff1f0 RCX: ffff888102228240 RDX: 0000000080000000 RSI: ffffffff918c5de0 RDI: ffff888102228b40 RBP: ffffc900025ebd40 R08: 0000000000000001 R09: 0000000000000001 R10: 0000000000000001 R11: 0000000000000000 R12: ffff888118c18ec0 R13: 0000000000000000 R14: ffffc900025ebd60 R15: ffff888018b7efb8 FS: 0000000000000000(0000) GS:ffff88817a600000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffffffffffb48 CR3: 0000000105228006 CR4: 0000000000170ee0 Call Trace: <TASK> ieee80211_tx_ba_session_handle_start+0xd0/0x190 [mac80211] ieee80211_ba_session_work+0xff/0x2e0 [mac80211] process_one_work+0x29f/0x620 worker_thread+0x4d/0x3d0 ? process_one_work+0x620/0x620 kthread+0xfb/0x120 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x22/0x30 </TASK> Signed-off-by: Alexander Wetzel <alexander(a)wetzel-home.de> Link: https://lore.kernel.org/r/20221230121850.218810-2-alexander@wetzel-home.de Cc: stable(a)vger.kernel.org Signed-off-by: Johannes Berg <johannes.berg(a)intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Wang Hai <wanghai38(a)huawei.com> --- net/mac80211/agg-tx.c | 6 +++++- net/mac80211/driver-ops.c | 3 +++ 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 4b4ab1961068..92e5812daf89 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -491,7 +491,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) { struct tid_ampdu_tx *tid_tx; struct ieee80211_local *local = sta->local; - struct ieee80211_sub_if_data *sdata = sta->sdata; + struct ieee80211_sub_if_data *sdata; struct ieee80211_ampdu_params params = { .sta = &sta->sta, .action = IEEE80211_AMPDU_TX_START, @@ -521,6 +521,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) */ synchronize_net(); + sdata = sta->sdata; params.ssn = sta->tid_seq[tid] >> 4; ret = drv_ampdu_action(local, sdata, &params); tid_tx->ssn = params.ssn; @@ -534,6 +535,9 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) */ set_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state); } else if (ret) { + if (!sdata) + return; + ht_dbg(sdata, "BA request denied - HW unavailable for %pM tid %d\n", sta->sta.addr, tid); diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index 48322e45e7dd..120bd9cdf7df 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -331,6 +331,9 @@ int drv_ampdu_action(struct ieee80211_local *local, might_sleep(); + if (!sdata) + return -EIO; + sdata = get_bss_sdata(sdata); if (!check_sdata_in_driver(sdata)) return -EIO; -- 2.34.1

2 1

[PATCH OLK-6.6] exec: Fix ToCToU between perm check and set-uid/gid usage
by Zizhi Wo 23 Aug '24

23 Aug '24

From: Kees Cook <kees(a)kernel.org> stable inclusion from stable-v6.6.47 commit d2a2a4714d80d09b0f8eb6438ab4224690b7121e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALED4 CVE: CVE-2024-43882 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- commit f50733b45d865f91db90919f8311e2127ce5a0cb upstream. When opening a file for exec via do_filp_open(), permission checking is done against the file's metadata at that moment, and on success, a file pointer is passed back. Much later in the execve() code path, the file metadata (specifically mode, uid, and gid) is used to determine if/how to set the uid and gid. However, those values may have changed since the permissions check, meaning the execution may gain unintended privileges. For example, if a file could change permissions from executable and not set-id: ---------x 1 root root 16048 Aug 7 13:16 target to set-id and non-executable: ---S------ 1 root root 16048 Aug 7 13:16 target it is possible to gain root privileges when execution should have been disallowed. While this race condition is rare in real-world scenarios, it has been observed (and proven exploitable) when package managers are updating the setuid bits of installed programs. Such files start with being world-executable but then are adjusted to be group-exec with a set-uid bit. For example, "chmod o-x,u+s target" makes "target" executable only by uid "root" and gid "cdrom", while also becoming setuid-root: -rwxr-xr-x 1 root cdrom 16048 Aug 7 13:16 target becomes: -rwsr-xr-- 1 root cdrom 16048 Aug 7 13:16 target But racing the chmod means users without group "cdrom" membership can get the permission to execute "target" just before the chmod, and when the chmod finishes, the exec reaches brpm_fill_uid(), and performs the setuid to root, violating the expressed authorization of "only cdrom group members can setuid to root". Re-check that we still have execute permissions in case the metadata has changed. It would be better to keep a copy from the perm-check time, but until we can do that refactoring, the least-bad option is to do a full inode_permission() call (under inode lock). It is understood that this is safe against dead-locks, but hardly optimal. Reported-by: Marco Vanotti <mvanotti(a)google.com> Tested-by: Marco Vanotti <mvanotti(a)google.com> Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: stable(a)vger.kernel.org Cc: Eric Biederman <ebiederm(a)xmission.com> Cc: Alexander Viro <viro(a)zeniv.linux.org.uk> Cc: Christian Brauner <brauner(a)kernel.org> Signed-off-by: Kees Cook <kees(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- fs/exec.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/exec.c b/fs/exec.c index 04fb89656cc3..a4725461a443 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1589,6 +1589,7 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) unsigned int mode; vfsuid_t vfsuid; vfsgid_t vfsgid; + int err; if (!mnt_may_suid(file->f_path.mnt)) return; @@ -1605,12 +1606,17 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) /* Be careful if suid/sgid is set */ inode_lock(inode); - /* reload atomically mode/uid/gid now that lock held */ + /* Atomically reload and check mode/uid/gid now that lock held. */ mode = inode->i_mode; vfsuid = i_uid_into_vfsuid(idmap, inode); vfsgid = i_gid_into_vfsgid(idmap, inode); + err = inode_permission(idmap, inode, MAY_EXEC); inode_unlock(inode); + /* Did the exec bit vanish out from under us? Give up. */ + if (err) + return; + /* We ignore suid/sgid if there are no mappings for them in the ns */ if (!vfsuid_has_mapping(bprm->cred->user_ns, vfsuid) || !vfsgid_has_mapping(bprm->cred->user_ns, vfsgid)) -- 2.39.2

2 1

[PATCH OLK-5.10] exec: Fix ToCToU between perm check and set-uid/gid usage
by Zizhi Wo 23 Aug '24

23 Aug '24

From: Kees Cook <kees(a)kernel.org> stable inclusion from stable-v5.10.224 commit 15469d46ba34559bfe7e3de6659115778c624759 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALED4 CVE: CVE-2024-43882 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- commit f50733b45d865f91db90919f8311e2127ce5a0cb upstream. When opening a file for exec via do_filp_open(), permission checking is done against the file's metadata at that moment, and on success, a file pointer is passed back. Much later in the execve() code path, the file metadata (specifically mode, uid, and gid) is used to determine if/how to set the uid and gid. However, those values may have changed since the permissions check, meaning the execution may gain unintended privileges. For example, if a file could change permissions from executable and not set-id: ---------x 1 root root 16048 Aug 7 13:16 target to set-id and non-executable: ---S------ 1 root root 16048 Aug 7 13:16 target it is possible to gain root privileges when execution should have been disallowed. While this race condition is rare in real-world scenarios, it has been observed (and proven exploitable) when package managers are updating the setuid bits of installed programs. Such files start with being world-executable but then are adjusted to be group-exec with a set-uid bit. For example, "chmod o-x,u+s target" makes "target" executable only by uid "root" and gid "cdrom", while also becoming setuid-root: -rwxr-xr-x 1 root cdrom 16048 Aug 7 13:16 target becomes: -rwsr-xr-- 1 root cdrom 16048 Aug 7 13:16 target But racing the chmod means users without group "cdrom" membership can get the permission to execute "target" just before the chmod, and when the chmod finishes, the exec reaches brpm_fill_uid(), and performs the setuid to root, violating the expressed authorization of "only cdrom group members can setuid to root". Re-check that we still have execute permissions in case the metadata has changed. It would be better to keep a copy from the perm-check time, but until we can do that refactoring, the least-bad option is to do a full inode_permission() call (under inode lock). It is understood that this is safe against dead-locks, but hardly optimal. Reported-by: Marco Vanotti <mvanotti(a)google.com> Tested-by: Marco Vanotti <mvanotti(a)google.com> Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: stable(a)vger.kernel.org Cc: Eric Biederman <ebiederm(a)xmission.com> Cc: Alexander Viro <viro(a)zeniv.linux.org.uk> Cc: Christian Brauner <brauner(a)kernel.org> Signed-off-by: Kees Cook <kees(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- fs/exec.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/exec.c b/fs/exec.c index c8c5818ece9e..802566d81db7 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1584,6 +1584,7 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) unsigned int mode; kuid_t uid; kgid_t gid; + int err; if (!mnt_may_suid(file->f_path.mnt)) return; @@ -1599,12 +1600,17 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) /* Be careful if suid/sgid is set */ inode_lock(inode); - /* reload atomically mode/uid/gid now that lock held */ + /* Atomically reload and check mode/uid/gid now that lock held. */ mode = inode->i_mode; uid = inode->i_uid; gid = inode->i_gid; + err = inode_permission(inode, MAY_EXEC); inode_unlock(inode); + /* Did the exec bit vanish out from under us? Give up. */ + if (err) + return; + /* We ignore suid/sgid if there are no mappings for them in the ns */ if (!kuid_has_mapping(bprm->cred->user_ns, uid) || !kgid_has_mapping(bprm->cred->user_ns, gid)) -- 2.39.2

2 1

[PATCH openEuler-22.03-LTS-SP1] exec: Fix ToCToU between perm check and set-uid/gid usage
by Zizhi Wo 23 Aug '24

23 Aug '24

From: Kees Cook <kees(a)kernel.org> stable inclusion from stable-v5.10.224 commit 15469d46ba34559bfe7e3de6659115778c624759 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALED4 CVE: CVE-2024-43882 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- commit f50733b45d865f91db90919f8311e2127ce5a0cb upstream. When opening a file for exec via do_filp_open(), permission checking is done against the file's metadata at that moment, and on success, a file pointer is passed back. Much later in the execve() code path, the file metadata (specifically mode, uid, and gid) is used to determine if/how to set the uid and gid. However, those values may have changed since the permissions check, meaning the execution may gain unintended privileges. For example, if a file could change permissions from executable and not set-id: ---------x 1 root root 16048 Aug 7 13:16 target to set-id and non-executable: ---S------ 1 root root 16048 Aug 7 13:16 target it is possible to gain root privileges when execution should have been disallowed. While this race condition is rare in real-world scenarios, it has been observed (and proven exploitable) when package managers are updating the setuid bits of installed programs. Such files start with being world-executable but then are adjusted to be group-exec with a set-uid bit. For example, "chmod o-x,u+s target" makes "target" executable only by uid "root" and gid "cdrom", while also becoming setuid-root: -rwxr-xr-x 1 root cdrom 16048 Aug 7 13:16 target becomes: -rwsr-xr-- 1 root cdrom 16048 Aug 7 13:16 target But racing the chmod means users without group "cdrom" membership can get the permission to execute "target" just before the chmod, and when the chmod finishes, the exec reaches brpm_fill_uid(), and performs the setuid to root, violating the expressed authorization of "only cdrom group members can setuid to root". Re-check that we still have execute permissions in case the metadata has changed. It would be better to keep a copy from the perm-check time, but until we can do that refactoring, the least-bad option is to do a full inode_permission() call (under inode lock). It is understood that this is safe against dead-locks, but hardly optimal. Reported-by: Marco Vanotti <mvanotti(a)google.com> Tested-by: Marco Vanotti <mvanotti(a)google.com> Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: stable(a)vger.kernel.org Cc: Eric Biederman <ebiederm(a)xmission.com> Cc: Alexander Viro <viro(a)zeniv.linux.org.uk> Cc: Christian Brauner <brauner(a)kernel.org> Signed-off-by: Kees Cook <kees(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- fs/exec.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/exec.c b/fs/exec.c index add4a298a49a..81f8df151d6a 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1567,6 +1567,7 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) unsigned int mode; kuid_t uid; kgid_t gid; + int err; if (!mnt_may_suid(file->f_path.mnt)) return; @@ -1582,12 +1583,17 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) /* Be careful if suid/sgid is set */ inode_lock(inode); - /* reload atomically mode/uid/gid now that lock held */ + /* Atomically reload and check mode/uid/gid now that lock held. */ mode = inode->i_mode; uid = inode->i_uid; gid = inode->i_gid; + err = inode_permission(inode, MAY_EXEC); inode_unlock(inode); + /* Did the exec bit vanish out from under us? Give up. */ + if (err) + return; + /* We ignore suid/sgid if there are no mappings for them in the ns */ if (!kuid_has_mapping(bprm->cred->user_ns, uid) || !kgid_has_mapping(bprm->cred->user_ns, gid)) -- 2.39.2

2 1

[PATCH openEuler-22.03-LTS-SP1] io_uring: lock overflowing for IOPOLL
by Zizhi Wo 23 Aug '24

23 Aug '24

From: Pavel Begunkov <asml.silence(a)gmail.com> stable inclusion from stable-v5.10.165 commit de77faee280163ff03b7ab64af6c9d779a43d4c4 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALIEY CVE: CVE-2023-52903 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- commit 544d163d659d45a206d8929370d5a2984e546cb7 upstream. syzbot reports an issue with overflow filling for IOPOLL: WARNING: CPU: 0 PID: 28 at io_uring/io_uring.c:734 io_cqring_event_overflow+0x1c0/0x230 io_uring/io_uring.c:734 CPU: 0 PID: 28 Comm: kworker/u4:1 Not tainted 6.2.0-rc3-syzkaller-16369-g358a161a6a9e #0 Workqueue: events_unbound io_ring_exit_work Call trace: io_cqring_event_overflow+0x1c0/0x230 io_uring/io_uring.c:734 io_req_cqe_overflow+0x5c/0x70 io_uring/io_uring.c:773 io_fill_cqe_req io_uring/io_uring.h:168 [inline] io_do_iopoll+0x474/0x62c io_uring/rw.c:1065 io_iopoll_try_reap_events+0x6c/0x108 io_uring/io_uring.c:1513 io_uring_try_cancel_requests+0x13c/0x258 io_uring/io_uring.c:3056 io_ring_exit_work+0xec/0x390 io_uring/io_uring.c:2869 process_one_work+0x2d8/0x504 kernel/workqueue.c:2289 worker_thread+0x340/0x610 kernel/workqueue.c:2436 kthread+0x12c/0x158 kernel/kthread.c:376 ret_from_fork+0x10/0x20 arch/arm64/kernel/entry.S:863 There is no real problem for normal IOPOLL as flush is also called with uring_lock taken, but it's getting more complicated for IOPOLL|SQPOLL, for which __io_cqring_overflow_flush() happens from the CQ waiting path. Reported-and-tested-by: syzbot+6805087452d72929404e(a)syzkaller.appspotmail.com Cc: stable(a)vger.kernel.org # 5.10+ Signed-off-by: Pavel Begunkov <asml.silence(a)gmail.com> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- io_uring/io_uring.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index f33926715f57..b3ba5adc3ca7 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2472,12 +2472,26 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, io_init_req_batch(&rb); while (!list_empty(done)) { + struct io_uring_cqe *cqe; + unsigned cflags; + req = list_first_entry(done, struct io_kiocb, inflight_entry); list_del(&req->inflight_entry); - - io_fill_cqe_req(req, req->result, io_put_rw_kbuf(req)); + cflags = io_put_rw_kbuf(req); (*nr_events)++; + cqe = io_get_cqe(ctx); + if (cqe) { + WRITE_ONCE(cqe->user_data, req->user_data); + WRITE_ONCE(cqe->res, req->result); + WRITE_ONCE(cqe->flags, cflags); + } else { + spin_lock(&ctx->completion_lock); + io_cqring_event_overflow(ctx, req->user_data, + req->result, cflags); + spin_unlock(&ctx->completion_lock); + } + if (req_ref_put_and_test(req)) io_req_free_batch(&rb, req, &ctx->submit_state); } -- 2.39.2

2 1

[PATCH openEuler-22.03-LTS-SP1 0/1] usb: xhci: Check endpoint is valid before dereferencing it
by Liao Chen 23 Aug '24

23 Aug '24

usb: xhci: Check endpoint is valid before dereferencing it Jimmy Hu (1): usb: xhci: Check endpoint is valid before dereferencing it drivers/usb/host/xhci-ring.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) -- 2.34.1

2 2

[PATCH openEuler-1.0-LTS] exec: Fix ToCToU between perm check and set-uid/gid usage
by Zizhi Wo 23 Aug '24

23 Aug '24

From: Kees Cook <kees(a)kernel.org> stable inclusion from stable-v4.19.320 commit d5c3c7e26275a2d83b894d30f7582a42853a958f category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALED4 CVE: CVE-2024-43882 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- commit f50733b45d865f91db90919f8311e2127ce5a0cb upstream. When opening a file for exec via do_filp_open(), permission checking is done against the file's metadata at that moment, and on success, a file pointer is passed back. Much later in the execve() code path, the file metadata (specifically mode, uid, and gid) is used to determine if/how to set the uid and gid. However, those values may have changed since the permissions check, meaning the execution may gain unintended privileges. For example, if a file could change permissions from executable and not set-id: ---------x 1 root root 16048 Aug 7 13:16 target to set-id and non-executable: ---S------ 1 root root 16048 Aug 7 13:16 target it is possible to gain root privileges when execution should have been disallowed. While this race condition is rare in real-world scenarios, it has been observed (and proven exploitable) when package managers are updating the setuid bits of installed programs. Such files start with being world-executable but then are adjusted to be group-exec with a set-uid bit. For example, "chmod o-x,u+s target" makes "target" executable only by uid "root" and gid "cdrom", while also becoming setuid-root: -rwxr-xr-x 1 root cdrom 16048 Aug 7 13:16 target becomes: -rwsr-xr-- 1 root cdrom 16048 Aug 7 13:16 target But racing the chmod means users without group "cdrom" membership can get the permission to execute "target" just before the chmod, and when the chmod finishes, the exec reaches brpm_fill_uid(), and performs the setuid to root, violating the expressed authorization of "only cdrom group members can setuid to root". Re-check that we still have execute permissions in case the metadata has changed. It would be better to keep a copy from the perm-check time, but until we can do that refactoring, the least-bad option is to do a full inode_permission() call (under inode lock). It is understood that this is safe against dead-locks, but hardly optimal. Reported-by: Marco Vanotti <mvanotti(a)google.com> Tested-by: Marco Vanotti <mvanotti(a)google.com> Suggested-by: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: stable(a)vger.kernel.org Cc: Eric Biederman <ebiederm(a)xmission.com> Cc: Alexander Viro <viro(a)zeniv.linux.org.uk> Cc: Christian Brauner <brauner(a)kernel.org> Signed-off-by: Kees Cook <kees(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- fs/exec.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/fs/exec.c b/fs/exec.c index da6cca9bd1ba..1d66dd0c759e 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1529,6 +1529,7 @@ static void bprm_fill_uid(struct linux_binprm *bprm) unsigned int mode; kuid_t uid; kgid_t gid; + int err; /* * Since this can be called multiple times (via prepare_binprm), @@ -1553,12 +1554,17 @@ static void bprm_fill_uid(struct linux_binprm *bprm) /* Be careful if suid/sgid is set */ inode_lock(inode); - /* reload atomically mode/uid/gid now that lock held */ + /* Atomically reload and check mode/uid/gid now that lock held. */ mode = inode->i_mode; uid = inode->i_uid; gid = inode->i_gid; + err = inode_permission(inode, MAY_EXEC); inode_unlock(inode); + /* Did the exec bit vanish out from under us? Give up. */ + if (err) + return; + /* We ignore suid/sgid if there are no mappings for them in the ns */ if (!kuid_has_mapping(bprm->cred->user_ns, uid) || !kgid_has_mapping(bprm->cred->user_ns, gid)) -- 2.39.2

2 1

[PATCH openEuler-1.0-LTS-SP1 0/1] usb: xhci: Check endpoint is valid before dereferencing it
by Liao Chen 23 Aug '24

23 Aug '24

usb: xhci: Check endpoint is valid before dereferencing it Jimmy Hu (1): usb: xhci: Check endpoint is valid before dereferencing it drivers/usb/host/xhci-ring.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) -- 2.34.1

1 1

[PATCH openEuler-1.0-LTS-SP1 0/1] usb: xhci: Check endpoint is valid before dereferencing it
by Liao Chen 23 Aug '24

23 Aug '24

usb: xhci: Check endpoint is valid before dereferencing it Jimmy Hu (1): usb: xhci: Check endpoint is valid before dereferencing it drivers/usb/host/xhci-ring.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) -- 2.34.1

2 3

[PATCH openEuler-1.0-LTS-SP1 0/1] usb: xhci: Check endpoint is valid before dereferencing it
by Liao Chen 23 Aug '24

23 Aug '24

usb: xhci: Check endpoint is valid before dereferencing it Jimmy Hu (1): usb: xhci: Check endpoint is valid before dereferencing it drivers/usb/host/xhci-ring.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) -- 2.34.1

1 0

[openeuler:OLK-6.6 7228/13476] ld.lld: error: undefined symbol: msi_domain_first_desc
by kernel test robot 23 Aug '24

23 Aug '24

tree: https://gitee.com/openeuler/kernel.git OLK-6.6 head: eccf28eefc9db7799534bd84bb958f3ecf978e2d commit: 165b3cc224374728856b5584455d7ae7f054fbe5 [7228/13476] SCSI: SSSRAID: Support 3SNIC 3S5XX serial RAID/HBA controllers config: x86_64-randconfig-001-20240823 (https://download.01.org/0day-ci/archive/20240823/202408231150.d9tyFM1M-lkp@…) compiler: clang version 18.1.5 (https://github.com/llvm/llvm-project 617a15a9eac96088ae5e9134248d8236e34b91b1) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240823/202408231150.d9tyFM1M-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/202408231150.d9tyFM1M-lkp@intel.com/ All errors (new ones prefixed by >>): >> ld.lld: error: undefined symbol: msi_domain_first_desc >>> referenced by sssraid_os.c:1553 (drivers/scsi/sssraid/sssraid_os.c:1553) >>> vmlinux.o:(sssraid_map_queues) -- >> ld.lld: error: undefined symbol: msi_next_desc >>> referenced by sssraid_os.c:1553 (drivers/scsi/sssraid/sssraid_os.c:1553) >>> vmlinux.o:(sssraid_map_queues) -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH OLK-6.6 v4 00/19] Backport bugfix of folio from v6.11
by Liu Shixin 23 Aug '24

23 Aug '24

v3->v4: Fix the fixtag of ("ext4: Fix WARNON in generic write begin path for iomap mode") v2->v3: Add new bugfix ("ext4: Fix WARNON in generic write begin path for iomap mode") v1->v2: Move patch ("shmem: set a_ops earlier in shmem_symlink") into patch series "mm/shmem: mTHP support for anon shmem" Baolin Wang (1): mm: page_alloc: allowing mTHP compaction to capture the freed page directly Gao Xiang (1): mm/migrate: fix deadlock in migrate_pages_batch() on large folios Gavin Shan (2): mm/huge_memory: avoid PMD-size page cache if needed mm/readahead: limit page cache size in page_cache_ra_order() Hugh Dickins (2): mm: fix crashes from deferred split racing folio migration mm: simplify folio_migrate_mapping() Kefeng Wang (1): mm: refactor folio_undo_large_rmappable() Liu Shixin (1): mm/huge_memory: fix comment errors of thp_mapping_align Matthew Wilcox (Oracle) (1): filemap: Convert generic_perform_write() to support large folios Pankaj Raghav (1): readahead: use ilog2 instead of a while loop in page_cache_ra_order() Peter Xu (1): mm/migrate: putback split folios when numa hint migration fails Ran Xiaokai (1): mm/huge_memory: mark racy access onhuge_anon_orders_always Ryan Roberts (1): mm: fix khugepaged activation policy Yajun Deng (1): mm/mmap: simplify vma link and unlink Zhihao Cheng (1): ext4: Fix WARNON in generic write begin path for iomap mode Zi Yan (1): mm/migrate: make migrate_pages_batch() stats consistent linke li (3): mm/swapfile: mark racy access on si->highest_bit mm/slub: mark racy access on slab->freelist mm/slub: mark racy accesses on slab->slabs Documentation/admin-guide/mm/transhuge.rst | 15 ++++---- fs/ext4/inode.c | 9 +++-- include/linux/huge_mm.h | 24 +++++------- mm/filemap.c | 40 ++++++++++++-------- mm/huge_memory.c | 32 +++++++++------- mm/internal.h | 17 ++++++++- mm/khugepaged.c | 33 ++++++++++++---- mm/memcontrol.c | 11 ------ mm/migrate.c | 42 +++++++++++++++------ mm/mmap.c | 44 ++++++++++------------ mm/page_alloc.c | 9 +++-- mm/readahead.c | 10 ++--- mm/slub.c | 8 ++-- mm/swap.c | 8 +--- mm/swapfile.c | 2 +- mm/vmscan.c | 8 +--- 16 files changed, 173 insertions(+), 139 deletions(-) -- 2.25.1

2 20

[PATCH openEuler-22.03-LTS-SP1] mISDN: Fix a use after free in hfcmulti_tx()
by Zhang Changzhong 23 Aug '24

23 Aug '24

From: Dan Carpenter <dan.carpenter(a)linaro.org> stable inclusion from stable-v5.10.224 commit 9460ac3dd1ae033bc2b021a458fb535a0c36ddb2 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAKPV2 CVE: CVE-2024-42280 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 61ab751451f5ebd0b98e02276a44e23a10110402 ] Don't dereference *sp after calling dev_kfree_skb(*sp). Fixes: af69fb3a8ffa ("Add mISDN HFC multiport driver") Signed-off-by: Dan Carpenter <dan.carpenter(a)linaro.org> Reviewed-by: Simon Horman <horms(a)kernel.org> Link: https://patch.msgid.link/8be65f5a-c2dd-4ba0-8a10-bfe5980b8cfb@stanley.mount… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zhang Changzhong <zhangchangzhong(a)huawei.com> --- drivers/isdn/hardware/mISDN/hfcmulti.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c index 7013a3f..545d381 100644 --- a/drivers/isdn/hardware/mISDN/hfcmulti.c +++ b/drivers/isdn/hardware/mISDN/hfcmulti.c @@ -1931,7 +1931,7 @@ hfcmulti_dtmf(struct hfc_multi *hc) static void hfcmulti_tx(struct hfc_multi *hc, int ch) { - int i, ii, temp, len = 0; + int i, ii, temp, tmp_len, len = 0; int Zspace, z1, z2; /* must be int for calculation */ int Fspace, f1, f2; u_char *d; @@ -2152,14 +2152,15 @@ hfcmulti_tx(struct hfc_multi *hc, int ch) HFC_wait_nodebug(hc); } + tmp_len = (*sp)->len; dev_kfree_skb(*sp); /* check for next frame */ if (bch && get_next_bframe(bch)) { - len = (*sp)->len; + len = tmp_len; goto next_frame; } if (dch && get_next_dframe(dch)) { - len = (*sp)->len; + len = tmp_len; goto next_frame; } -- 2.9.5

2 1

[PATCH OLK-5.10] mISDN: Fix a use after free in hfcmulti_tx()
by Zhang Changzhong 23 Aug '24

23 Aug '24

From: Dan Carpenter <dan.carpenter(a)linaro.org> stable inclusion from stable-v5.10.224 commit 9460ac3dd1ae033bc2b021a458fb535a0c36ddb2 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAKPV2 CVE: CVE-2024-42280 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 61ab751451f5ebd0b98e02276a44e23a10110402 ] Don't dereference *sp after calling dev_kfree_skb(*sp). Fixes: af69fb3a8ffa ("Add mISDN HFC multiport driver") Signed-off-by: Dan Carpenter <dan.carpenter(a)linaro.org> Reviewed-by: Simon Horman <horms(a)kernel.org> Link: https://patch.msgid.link/8be65f5a-c2dd-4ba0-8a10-bfe5980b8cfb@stanley.mount… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zhang Changzhong <zhangchangzhong(a)huawei.com> --- drivers/isdn/hardware/mISDN/hfcmulti.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c index 4c5b677..a0697d6 100644 --- a/drivers/isdn/hardware/mISDN/hfcmulti.c +++ b/drivers/isdn/hardware/mISDN/hfcmulti.c @@ -1931,7 +1931,7 @@ hfcmulti_dtmf(struct hfc_multi *hc) static void hfcmulti_tx(struct hfc_multi *hc, int ch) { - int i, ii, temp, len = 0; + int i, ii, temp, tmp_len, len = 0; int Zspace, z1, z2; /* must be int for calculation */ int Fspace, f1, f2; u_char *d; @@ -2152,14 +2152,15 @@ hfcmulti_tx(struct hfc_multi *hc, int ch) HFC_wait_nodebug(hc); } + tmp_len = (*sp)->len; dev_kfree_skb(*sp); /* check for next frame */ if (bch && get_next_bframe(bch)) { - len = (*sp)->len; + len = tmp_len; goto next_frame; } if (dch && get_next_dframe(dch)) { - len = (*sp)->len; + len = tmp_len; goto next_frame; } -- 2.9.5

2 1

[PATCH OLK-5.10] net/mlx5: Always drain health in shutdown callback
by Zhengchao Shao 23 Aug '24

23 Aug '24

From: Shay Drory <shayd(a)nvidia.com> mainline inclusion from mainline-v6.11-rc2 commit 1b75da22ed1e6171e261bc9265370162553d5393 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALCRV CVE: CVE-2024-43866 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------------- There is no point in recovery during device shutdown. if health work started need to wait for it to avoid races and NULL pointer access. Hence, drain health WQ on shutdown callback. Fixes: 1958fc2f0712 ("net/mlx5: SF, Add auxiliary device driver") Fixes: d2aa060d40fa ("net/mlx5: Cancel health poll before sending panic teardown command") Signed-off-by: Shay Drory <shayd(a)nvidia.com> Reviewed-by: Moshe Shemesh <moshe(a)nvidia.com> Signed-off-by: Tariq Toukan <tariqt(a)nvidia.com> Reviewed-by: Wojciech Drewek <wojciech.drewek(a)intel.com> Link: https://patch.msgid.link/20240730061638.1831002-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: drivers/net/ethernet/mellanox/mlx5/core/main.c drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c [The conflict occurs because the commit 8324a02c342a("net/mlx5: Add exit route when waiting for FW") and 1958fc2f0712("net/mlx5: SF, Add auxiliary device driver") are not merged] Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 35e11cb883c9..d4712fbc7856 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1524,7 +1524,6 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) /* Panic tear down fw command will stop the PCI bus communication * with the HCA, so the health polll is no longer needed. */ - mlx5_drain_health_wq(dev); mlx5_stop_health_poll(dev, false); ret = mlx5_cmd_fast_teardown_hca(dev); @@ -1558,6 +1557,7 @@ static void shutdown(struct pci_dev *pdev) int err; mlx5_core_info(dev, "Shutdown was called\n"); + mlx5_drain_health_wq(dev); err = mlx5_try_fast_unload(dev); if (err) mlx5_unload_one(dev, false); -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] net/mlx5: Always drain health in shutdown callback
by Zhengchao Shao 23 Aug '24

23 Aug '24

From: Shay Drory <shayd(a)nvidia.com> mainline inclusion from mainline-v6.11-rc2 commit 1b75da22ed1e6171e261bc9265370162553d5393 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALCRV CVE: CVE-2024-43866 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------------- There is no point in recovery during device shutdown. if health work started need to wait for it to avoid races and NULL pointer access. Hence, drain health WQ on shutdown callback. Fixes: 1958fc2f0712 ("net/mlx5: SF, Add auxiliary device driver") Fixes: d2aa060d40fa ("net/mlx5: Cancel health poll before sending panic teardown command") Signed-off-by: Shay Drory <shayd(a)nvidia.com> Reviewed-by: Moshe Shemesh <moshe(a)nvidia.com> Signed-off-by: Tariq Toukan <tariqt(a)nvidia.com> Reviewed-by: Wojciech Drewek <wojciech.drewek(a)intel.com> Link: https://patch.msgid.link/20240730061638.1831002-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: drivers/net/ethernet/mellanox/mlx5/core/main.c drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c [The conflict occurs because the commit 8324a02c342a("net/mlx5: Add exit route when waiting for FW") and 1958fc2f0712("net/mlx5: SF, Add auxiliary device driver") are not merged] Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 8246b6285d5a..e0a605c1130f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1523,7 +1523,6 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) /* Panic tear down fw command will stop the PCI bus communication * with the HCA, so the health polll is no longer needed. */ - mlx5_drain_health_wq(dev); mlx5_stop_health_poll(dev, false); ret = mlx5_cmd_fast_teardown_hca(dev); @@ -1557,6 +1556,7 @@ static void shutdown(struct pci_dev *pdev) int err; mlx5_core_info(dev, "Shutdown was called\n"); + mlx5_drain_health_wq(dev); err = mlx5_try_fast_unload(dev); if (err) mlx5_unload_one(dev, false); -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] f2fs: fix to don't dirty inode for readonly filesystem
by Zizhi Wo 23 Aug '24

23 Aug '24

From: Chao Yu <chao(a)kernel.org> stable inclusion from stable-v6.1.103 commit 9ce8135accf103f7333af472709125878704fdd4 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAKQ0F CVE: CVE-2024-42297 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- commit 192b8fb8d1c8ca3c87366ebbef599fa80bb626b8 upstream. syzbot reports f2fs bug as below: kernel BUG at fs/f2fs/inode.c:933! RIP: 0010:f2fs_evict_inode+0x1576/0x1590 fs/f2fs/inode.c:933 Call Trace: evict+0x2a4/0x620 fs/inode.c:664 dispose_list fs/inode.c:697 [inline] evict_inodes+0x5f8/0x690 fs/inode.c:747 generic_shutdown_super+0x9d/0x2c0 fs/super.c:675 kill_block_super+0x44/0x90 fs/super.c:1667 kill_f2fs_super+0x303/0x3b0 fs/f2fs/super.c:4894 deactivate_locked_super+0xc1/0x130 fs/super.c:484 cleanup_mnt+0x426/0x4c0 fs/namespace.c:1256 task_work_run+0x24a/0x300 kernel/task_work.c:180 ptrace_notify+0x2cd/0x380 kernel/signal.c:2399 ptrace_report_syscall include/linux/ptrace.h:411 [inline] ptrace_report_syscall_exit include/linux/ptrace.h:473 [inline] syscall_exit_work kernel/entry/common.c:251 [inline] syscall_exit_to_user_mode_prepare kernel/entry/common.c:278 [inline] __syscall_exit_to_user_mode_work kernel/entry/common.c:283 [inline] syscall_exit_to_user_mode+0x15c/0x280 kernel/entry/common.c:296 do_syscall_64+0x50/0x110 arch/x86/entry/common.c:88 entry_SYSCALL_64_after_hwframe+0x63/0x6b The root cause is: - do_sys_open - f2fs_lookup - __f2fs_find_entry - f2fs_i_depth_write - f2fs_mark_inode_dirty_sync - f2fs_dirty_inode - set_inode_flag(inode, FI_DIRTY_INODE) - umount - kill_f2fs_super - kill_block_super - generic_shutdown_super - sync_filesystem : sb is readonly, skip sync_filesystem() - evict_inodes - iput - f2fs_evict_inode - f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE)) : trigger kernel panic When we try to repair i_current_depth in readonly filesystem, let's skip dirty inode to avoid panic in later f2fs_evict_inode(). Cc: stable(a)vger.kernel.org Reported-by: syzbot+31e4659a3fe953aec2f4(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-f2fs-devel/000000000000e890bc0609a55cff@googl… Signed-off-by: Chao Yu <chao(a)kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- fs/f2fs/inode.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index a01be7d8db86..a716150ae14e 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -25,6 +25,9 @@ void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync) if (is_inode_flag_set(inode, FI_NEW_INODE)) return; + if (f2fs_readonly(F2FS_I_SB(inode)->sb)) + return; + if (f2fs_inode_dirtied(inode, sync)) return; -- 2.39.2

2 1

[PATCH openEuler-22.03-LTS-SP1] net/mlx5: Always drain health in shutdown callback
by Zhengchao Shao 23 Aug '24

23 Aug '24

From: Shay Drory <shayd(a)nvidia.com> mainline inclusion from mainline-v6.11-rc2 commit 1b75da22ed1e6171e261bc9265370162553d5393 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALCRV CVE: CVE-2024-43866 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------------- There is no point in recovery during device shutdown. if health work started need to wait for it to avoid races and NULL pointer access. Hence, drain health WQ on shutdown callback. Fixes: 1958fc2f0712 ("net/mlx5: SF, Add auxiliary device driver") Fixes: d2aa060d40fa ("net/mlx5: Cancel health poll before sending panic teardown command") Signed-off-by: Shay Drory <shayd(a)nvidia.com> Reviewed-by: Moshe Shemesh <moshe(a)nvidia.com> Signed-off-by: Tariq Toukan <tariqt(a)nvidia.com> Reviewed-by: Wojciech Drewek <wojciech.drewek(a)intel.com> Link: https://patch.msgid.link/20240730061638.1831002-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: drivers/net/ethernet/mellanox/mlx5/core/main.c [The conflict occurs because the commit 8324a02c342a("net/mlx5: Add exit route when waiting for FW") and 1958fc2f0712("net/mlx5: SF, Add auxiliary device driver") are not merged] Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 8246b6285d5a..e0a605c1130f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1523,7 +1523,6 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) /* Panic tear down fw command will stop the PCI bus communication * with the HCA, so the health polll is no longer needed. */ - mlx5_drain_health_wq(dev); mlx5_stop_health_poll(dev, false); ret = mlx5_cmd_fast_teardown_hca(dev); @@ -1557,6 +1556,7 @@ static void shutdown(struct pci_dev *pdev) int err; mlx5_core_info(dev, "Shutdown was called\n"); + mlx5_drain_health_wq(dev); err = mlx5_try_fast_unload(dev); if (err) mlx5_unload_one(dev, false); -- 2.34.1

2 1

[PATCH OLK-5.10] net/mlx5: Always drain health in shutdown callback
by Zhengchao Shao 23 Aug '24

23 Aug '24

From: Shay Drory <shayd(a)nvidia.com> mainline inclusion from mainline-v6.11-rc2 commit 1b75da22ed1e6171e261bc9265370162553d5393 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALCRV CVE: CVE-2024-43866 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ------------------------------------------- There is no point in recovery during device shutdown. if health work started need to wait for it to avoid races and NULL pointer access. Hence, drain health WQ on shutdown callback. Fixes: 1958fc2f0712 ("net/mlx5: SF, Add auxiliary device driver") Fixes: d2aa060d40fa ("net/mlx5: Cancel health poll before sending panic teardown command") Signed-off-by: Shay Drory <shayd(a)nvidia.com> Reviewed-by: Moshe Shemesh <moshe(a)nvidia.com> Signed-off-by: Tariq Toukan <tariqt(a)nvidia.com> Reviewed-by: Wojciech Drewek <wojciech.drewek(a)intel.com> Link: https://patch.msgid.link/20240730061638.1831002-2-tariqt@nvidia.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: drivers/net/ethernet/mellanox/mlx5/core/main.c [The conflict occurs because the commit 8324a02c342a("net/mlx5: Add exit route when waiting for FW") and 1958fc2f0712("net/mlx5: SF, Add auxiliary device driver") are not merged] Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 35e11cb883c9..d4712fbc7856 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1524,7 +1524,6 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) /* Panic tear down fw command will stop the PCI bus communication * with the HCA, so the health polll is no longer needed. */ - mlx5_drain_health_wq(dev); mlx5_stop_health_poll(dev, false); ret = mlx5_cmd_fast_teardown_hca(dev); @@ -1558,6 +1557,7 @@ static void shutdown(struct pci_dev *pdev) int err; mlx5_core_info(dev, "Shutdown was called\n"); + mlx5_drain_health_wq(dev); err = mlx5_try_fast_unload(dev); if (err) mlx5_unload_one(dev, false); -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] thermal: int340x: fix memory leak in int3400_notify()
by Liu Chuang 23 Aug '24

23 Aug '24

From: Chuansheng Liu <chuansheng.liu(a)intel.com> stable inclusion from stable-v4.19.237 commit c3fa6d1937a8d0828131a04ae2cd2c30d0668693 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALOJQ Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… --------------------------- commit 3abea10e6a8f0e7804ed4c124bea2d15aca977c8 upstream. It is easy to hit the below memory leaks in my TigerLake platform: unreferenced object 0xffff927c8b91dbc0 (size 32): comm "kworker/0:2", pid 112, jiffies 4294893323 (age 83.604s) hex dump (first 32 bytes): 4e 41 4d 45 3d 49 4e 54 33 34 30 30 20 54 68 65 NAME=INT3400 The 72 6d 61 6c 00 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b a5 rmal.kkkkkkkkkk. backtrace: [<ffffffff9c502c3e>] __kmalloc_track_caller+0x2fe/0x4a0 [<ffffffff9c7b7c15>] kvasprintf+0x65/0xd0 [<ffffffff9c7b7d6e>] kasprintf+0x4e/0x70 [<ffffffffc04cb662>] int3400_notify+0x82/0x120 [int3400_thermal] [<ffffffff9c8b7358>] acpi_ev_notify_dispatch+0x54/0x71 [<ffffffff9c88f1a7>] acpi_os_execute_deferred+0x17/0x30 [<ffffffff9c2c2c0a>] process_one_work+0x21a/0x3f0 [<ffffffff9c2c2e2a>] worker_thread+0x4a/0x3b0 [<ffffffff9c2cb4dd>] kthread+0xfd/0x130 [<ffffffff9c201c1f>] ret_from_fork+0x1f/0x30 Fix it by calling kfree() accordingly. Fixes: 38e44da59130 ("thermal: int3400_thermal: process "thermal table changed" event") Signed-off-by: Chuansheng Liu <chuansheng.liu(a)intel.com> Cc: 4.14+ <stable(a)vger.kernel.org> # 4.14+ Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki(a)intel.com> [sudip: change in old path] Signed-off-by: Sudip Mukherjee <sudipm.mukherjee(a)gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Liu Chuang <liuchuang40(a)huawei.com> --- drivers/thermal/int340x_thermal/int3400_thermal.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/thermal/int340x_thermal/int3400_thermal.c b/drivers/thermal/int340x_thermal/int3400_thermal.c index e9d58de8b5da..77967da5d406 100644 --- a/drivers/thermal/int340x_thermal/int3400_thermal.c +++ b/drivers/thermal/int340x_thermal/int3400_thermal.c @@ -223,6 +223,10 @@ static void int3400_notify(acpi_handle handle, thermal_prop[4] = NULL; kobject_uevent_env(&priv->thermal->device.kobj, KOBJ_CHANGE, thermal_prop); + kfree(thermal_prop[0]); + kfree(thermal_prop[1]); + kfree(thermal_prop[2]); + kfree(thermal_prop[3]); break; default: /* Ignore unknown notification codes sent to INT3400 device */ -- 2.34.1

2 1

[PATCH OLK-5.10] f2fs: fix to don't dirty inode for readonly filesystem
by Zizhi Wo 23 Aug '24

23 Aug '24

From: Chao Yu <chao(a)kernel.org> stable inclusion from stable-v6.1.103 commit 9ce8135accf103f7333af472709125878704fdd4 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAKQ0F CVE: CVE-2024-42297 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- commit 192b8fb8d1c8ca3c87366ebbef599fa80bb626b8 upstream. syzbot reports f2fs bug as below: kernel BUG at fs/f2fs/inode.c:933! RIP: 0010:f2fs_evict_inode+0x1576/0x1590 fs/f2fs/inode.c:933 Call Trace: evict+0x2a4/0x620 fs/inode.c:664 dispose_list fs/inode.c:697 [inline] evict_inodes+0x5f8/0x690 fs/inode.c:747 generic_shutdown_super+0x9d/0x2c0 fs/super.c:675 kill_block_super+0x44/0x90 fs/super.c:1667 kill_f2fs_super+0x303/0x3b0 fs/f2fs/super.c:4894 deactivate_locked_super+0xc1/0x130 fs/super.c:484 cleanup_mnt+0x426/0x4c0 fs/namespace.c:1256 task_work_run+0x24a/0x300 kernel/task_work.c:180 ptrace_notify+0x2cd/0x380 kernel/signal.c:2399 ptrace_report_syscall include/linux/ptrace.h:411 [inline] ptrace_report_syscall_exit include/linux/ptrace.h:473 [inline] syscall_exit_work kernel/entry/common.c:251 [inline] syscall_exit_to_user_mode_prepare kernel/entry/common.c:278 [inline] __syscall_exit_to_user_mode_work kernel/entry/common.c:283 [inline] syscall_exit_to_user_mode+0x15c/0x280 kernel/entry/common.c:296 do_syscall_64+0x50/0x110 arch/x86/entry/common.c:88 entry_SYSCALL_64_after_hwframe+0x63/0x6b The root cause is: - do_sys_open - f2fs_lookup - __f2fs_find_entry - f2fs_i_depth_write - f2fs_mark_inode_dirty_sync - f2fs_dirty_inode - set_inode_flag(inode, FI_DIRTY_INODE) - umount - kill_f2fs_super - kill_block_super - generic_shutdown_super - sync_filesystem : sb is readonly, skip sync_filesystem() - evict_inodes - iput - f2fs_evict_inode - f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE)) : trigger kernel panic When we try to repair i_current_depth in readonly filesystem, let's skip dirty inode to avoid panic in later f2fs_evict_inode(). Cc: stable(a)vger.kernel.org Reported-by: syzbot+31e4659a3fe953aec2f4(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-f2fs-devel/000000000000e890bc0609a55cff@googl… Signed-off-by: Chao Yu <chao(a)kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- fs/f2fs/inode.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index aeafd8b73cbf..8f29eb07c296 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -23,6 +23,9 @@ void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync) if (is_inode_flag_set(inode, FI_NEW_INODE)) return; + if (f2fs_readonly(F2FS_I_SB(inode)->sb)) + return; + if (f2fs_inode_dirtied(inode, sync)) return; -- 2.39.2

2 1

[PATCH openEuler-22.03-LTS-SP1] f2fs: fix to don't dirty inode for readonly filesystem
by Zizhi Wo 23 Aug '24

23 Aug '24

From: Chao Yu <chao(a)kernel.org> stable inclusion from stable-v6.1.103 commit 9ce8135accf103f7333af472709125878704fdd4 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAKQ0F CVE: CVE-2024-42297 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- commit 192b8fb8d1c8ca3c87366ebbef599fa80bb626b8 upstream. syzbot reports f2fs bug as below: kernel BUG at fs/f2fs/inode.c:933! RIP: 0010:f2fs_evict_inode+0x1576/0x1590 fs/f2fs/inode.c:933 Call Trace: evict+0x2a4/0x620 fs/inode.c:664 dispose_list fs/inode.c:697 [inline] evict_inodes+0x5f8/0x690 fs/inode.c:747 generic_shutdown_super+0x9d/0x2c0 fs/super.c:675 kill_block_super+0x44/0x90 fs/super.c:1667 kill_f2fs_super+0x303/0x3b0 fs/f2fs/super.c:4894 deactivate_locked_super+0xc1/0x130 fs/super.c:484 cleanup_mnt+0x426/0x4c0 fs/namespace.c:1256 task_work_run+0x24a/0x300 kernel/task_work.c:180 ptrace_notify+0x2cd/0x380 kernel/signal.c:2399 ptrace_report_syscall include/linux/ptrace.h:411 [inline] ptrace_report_syscall_exit include/linux/ptrace.h:473 [inline] syscall_exit_work kernel/entry/common.c:251 [inline] syscall_exit_to_user_mode_prepare kernel/entry/common.c:278 [inline] __syscall_exit_to_user_mode_work kernel/entry/common.c:283 [inline] syscall_exit_to_user_mode+0x15c/0x280 kernel/entry/common.c:296 do_syscall_64+0x50/0x110 arch/x86/entry/common.c:88 entry_SYSCALL_64_after_hwframe+0x63/0x6b The root cause is: - do_sys_open - f2fs_lookup - __f2fs_find_entry - f2fs_i_depth_write - f2fs_mark_inode_dirty_sync - f2fs_dirty_inode - set_inode_flag(inode, FI_DIRTY_INODE) - umount - kill_f2fs_super - kill_block_super - generic_shutdown_super - sync_filesystem : sb is readonly, skip sync_filesystem() - evict_inodes - iput - f2fs_evict_inode - f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE)) : trigger kernel panic When we try to repair i_current_depth in readonly filesystem, let's skip dirty inode to avoid panic in later f2fs_evict_inode(). Cc: stable(a)vger.kernel.org Reported-by: syzbot+31e4659a3fe953aec2f4(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-f2fs-devel/000000000000e890bc0609a55cff@googl… Signed-off-by: Chao Yu <chao(a)kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- fs/f2fs/inode.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index aeafd8b73cbf..8f29eb07c296 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -23,6 +23,9 @@ void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync) if (is_inode_flag_set(inode, FI_NEW_INODE)) return; + if (f2fs_readonly(F2FS_I_SB(inode)->sb)) + return; + if (f2fs_inode_dirtied(inode, sync)) return; -- 2.39.2

2 1

[PATCH OLK-6.6 v3 00/19] Backport bugfix of folio from v6.11
by Liu Shixin 23 Aug '24

23 Aug '24

v2->v3: Add new bugfix ("ext4: Fix WARNON in generic write begin path for iomap mode") v1->v2: Move patch ("shmem: set a_ops earlier in shmem_symlink") into patch series "mm/shmem: mTHP support for anon shmem" Baolin Wang (1): mm: page_alloc: allowing mTHP compaction to capture the freed page directly Gao Xiang (1): mm/migrate: fix deadlock in migrate_pages_batch() on large folios Gavin Shan (2): mm/huge_memory: avoid PMD-size page cache if needed mm/readahead: limit page cache size in page_cache_ra_order() Hugh Dickins (2): mm: fix crashes from deferred split racing folio migration mm: simplify folio_migrate_mapping() Kefeng Wang (1): mm: refactor folio_undo_large_rmappable() Liu Shixin (1): mm/huge_memory: fix comment errors of thp_mapping_align Matthew Wilcox (Oracle) (1): filemap: Convert generic_perform_write() to support large folios Pankaj Raghav (1): readahead: use ilog2 instead of a while loop in page_cache_ra_order() Peter Xu (1): mm/migrate: putback split folios when numa hint migration fails Ran Xiaokai (1): mm/huge_memory: mark racy access onhuge_anon_orders_always Ryan Roberts (1): mm: fix khugepaged activation policy Yajun Deng (1): mm/mmap: simplify vma link and unlink Zhihao Cheng (1): ext4: Fix WARNON in generic write begin path for iomap mode Zi Yan (1): mm/migrate: make migrate_pages_batch() stats consistent linke li (3): mm/swapfile: mark racy access on si->highest_bit mm/slub: mark racy access on slab->freelist mm/slub: mark racy accesses on slab->slabs Documentation/admin-guide/mm/transhuge.rst | 15 ++++---- fs/ext4/inode.c | 9 +++-- include/linux/huge_mm.h | 24 +++++------- mm/filemap.c | 40 ++++++++++++-------- mm/huge_memory.c | 32 +++++++++------- mm/internal.h | 17 ++++++++- mm/khugepaged.c | 33 ++++++++++++---- mm/memcontrol.c | 11 ------ mm/migrate.c | 42 +++++++++++++++------ mm/mmap.c | 44 ++++++++++------------ mm/page_alloc.c | 9 +++-- mm/readahead.c | 10 ++--- mm/slub.c | 8 ++-- mm/swap.c | 8 +--- mm/swapfile.c | 2 +- mm/vmscan.c | 8 +--- 16 files changed, 173 insertions(+), 139 deletions(-) -- 2.25.1

2 20

[PATCH openEuler-22.03-LTS-SP1] f2fs: fix to don't dirty inode for readonly filesystem
by Zizhi Wo 23 Aug '24

23 Aug '24

From: Chao Yu <chao(a)kernel.org> stable inclusion from stable-v6.1.103 commit 9ce8135accf103f7333af472709125878704fdd4 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAKQ0F CVE: CVE-2024-42297 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- commit 192b8fb8d1c8ca3c87366ebbef599fa80bb626b8 upstream. syzbot reports f2fs bug as below: kernel BUG at fs/f2fs/inode.c:933! RIP: 0010:f2fs_evict_inode+0x1576/0x1590 fs/f2fs/inode.c:933 Call Trace: evict+0x2a4/0x620 fs/inode.c:664 dispose_list fs/inode.c:697 [inline] evict_inodes+0x5f8/0x690 fs/inode.c:747 generic_shutdown_super+0x9d/0x2c0 fs/super.c:675 kill_block_super+0x44/0x90 fs/super.c:1667 kill_f2fs_super+0x303/0x3b0 fs/f2fs/super.c:4894 deactivate_locked_super+0xc1/0x130 fs/super.c:484 cleanup_mnt+0x426/0x4c0 fs/namespace.c:1256 task_work_run+0x24a/0x300 kernel/task_work.c:180 ptrace_notify+0x2cd/0x380 kernel/signal.c:2399 ptrace_report_syscall include/linux/ptrace.h:411 [inline] ptrace_report_syscall_exit include/linux/ptrace.h:473 [inline] syscall_exit_work kernel/entry/common.c:251 [inline] syscall_exit_to_user_mode_prepare kernel/entry/common.c:278 [inline] __syscall_exit_to_user_mode_work kernel/entry/common.c:283 [inline] syscall_exit_to_user_mode+0x15c/0x280 kernel/entry/common.c:296 do_syscall_64+0x50/0x110 arch/x86/entry/common.c:88 entry_SYSCALL_64_after_hwframe+0x63/0x6b The root cause is: - do_sys_open - f2fs_lookup - __f2fs_find_entry - f2fs_i_depth_write - f2fs_mark_inode_dirty_sync - f2fs_dirty_inode - set_inode_flag(inode, FI_DIRTY_INODE) - umount - kill_f2fs_super - kill_block_super - generic_shutdown_super - sync_filesystem : sb is readonly, skip sync_filesystem() - evict_inodes - iput - f2fs_evict_inode - f2fs_bug_on(sbi, is_inode_flag_set(inode, FI_DIRTY_INODE)) : trigger kernel panic When we try to repair i_current_depth in readonly filesystem, let's skip dirty inode to avoid panic in later f2fs_evict_inode(). Cc: stable(a)vger.kernel.org Reported-by: syzbot+31e4659a3fe953aec2f4(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/linux-f2fs-devel/000000000000e890bc0609a55cff@googl… Signed-off-by: Chao Yu <chao(a)kernel.org> Signed-off-by: Jaegeuk Kim <jaegeuk(a)kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zizhi Wo <wozizhi(a)huawei.com> --- fs/f2fs/inode.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index aeafd8b73cbf..8f29eb07c296 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -23,6 +23,9 @@ void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync) if (is_inode_flag_set(inode, FI_NEW_INODE)) return; + if (f2fs_readonly(F2FS_I_SB(inode)->sb)) + return; + if (f2fs_inode_dirtied(inode, sync)) return; -- 2.39.2

2 1

[PATCH OLK-6.6 0/8] Backport LTS conflicting patches
by Peng Zhang 23 Aug '24

23 Aug '24

From: ZhangPeng <zhangpeng362(a)huawei.com> Backport v6.6.34-40 LTS conflicting patches for OLK-6.6. Ajrat Makhmutov (1): ALSA: hda/realtek: Enable headset mic on IdeaPad 330-17IKB 81DM Alex Williamson (2): vfio/pci: Collect hot-reset devices to local buffer vfio/pci: Restore zero affected bus reset devices warning Ilpo Järvinen (1): EDAC/amd64: Convert PCIBIOS_* return codes to errnos Karthikeyan Ramasubramanian (1): platform/chrome: cros_ec: Handle events during suspend after resume completion Takashi Iwai (1): ALSA: hda/realtek: Fix conflicting quirk for PCI SSID 17aa:3820 Yao Xingtao (1): cxl/region: check interleave capability Yi Liu (1): vfio/pci: Init the count variable in collecting hot-reset devices drivers/cxl/core/hdm.c | 13 +++++ drivers/cxl/core/region.c | 82 +++++++++++++++++++++++++++++++ drivers/cxl/cxl.h | 2 + drivers/cxl/cxlmem.h | 10 ++++ drivers/edac/amd64_edac.c | 8 +-- drivers/platform/chrome/cros_ec.c | 16 +++--- drivers/vfio/pci/vfio_pci_core.c | 81 +++++++++++++++++++----------- sound/pci/hda/patch_realtek.c | 21 +++++++- tools/testing/cxl/test/cxl.c | 4 ++ 9 files changed, 196 insertions(+), 41 deletions(-) -- 2.25.1

2 9

[PATCH openEuler-22.03-LTS-SP1] ixgbe: fix pci device refcount leak
by Liu Jian 23 Aug '24

23 Aug '24

From: Yang Yingliang <yangyingliang(a)huawei.com> stable inclusion from stable-v5.10.164 commit 112df4cd2b09acd64bcd18f5ef83ba5d07b34bf0 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALLC8 CVE: CVE-2022-48896 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ------------------------------------------------- commit b93fb4405fcb5112c5739c5349afb52ec7f15c07 upstream. As the comment of pci_get_domain_bus_and_slot() says, it returns a PCI device with refcount incremented, when finish using it, the caller must decrement the reference count by calling pci_dev_put(). In ixgbe_get_first_secondary_devfn() and ixgbe_x550em_a_has_mii(), pci_dev_put() is called to avoid leak. Fixes: 8fa10ef01260 ("ixgbe: register a mdiobus") Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> Tested-by: Gurucharan G <gurucharanx.g(a)intel.com> (A Contingent worker at Intel) Signed-off-by: Tony Nguyen <anthony.l.nguyen(a)intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Liu Jian <liujian56(a)huawei.com> --- drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index fc389eecdd2b..b0413904b798 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -851,9 +851,11 @@ static struct pci_dev *ixgbe_get_first_secondary_devfn(unsigned int devfn) rp_pdev = pci_get_domain_bus_and_slot(0, 0, devfn); if (rp_pdev && rp_pdev->subordinate) { bus = rp_pdev->subordinate->number; + pci_dev_put(rp_pdev); return pci_get_domain_bus_and_slot(0, bus, 0); } + pci_dev_put(rp_pdev); return NULL; } @@ -870,6 +872,7 @@ static bool ixgbe_x550em_a_has_mii(struct ixgbe_hw *hw) struct ixgbe_adapter *adapter = hw->back; struct pci_dev *pdev = adapter->pdev; struct pci_dev *func0_pdev; + bool has_mii = false; /* For the C3000 family of SoCs (x550em_a) the internal ixgbe devices * are always downstream of root ports @ 0000:00:16.0 & 0000:00:17.0 @@ -880,15 +883,16 @@ static bool ixgbe_x550em_a_has_mii(struct ixgbe_hw *hw) func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x16, 0)); if (func0_pdev) { if (func0_pdev == pdev) - return true; - else - return false; + has_mii = true; + goto out; } func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x17, 0)); if (func0_pdev == pdev) - return true; + has_mii = true; - return false; +out: + pci_dev_put(func0_pdev); + return has_mii; } /** -- 2.34.1

2 1

[openeuler:openEuler-1.0-LTS] BUILD SUCCESS 90f4d81f4d19ad3d6d23b8775f4aa07771a1dac5
by kernel test robot 23 Aug '24

23 Aug '24

tree/branch: https://gitee.com/openeuler/kernel.git openEuler-1.0-LTS branch HEAD: 90f4d81f4d19ad3d6d23b8775f4aa07771a1dac5 !11068 Fix CVE-2024-39501 elapsed time: 735m configs tested: 21 configs skipped: 139 The following configs have been built successfully. More configs may be tested in the coming days. tested configs: arm64 allmodconfig gcc-14.1.0 arm64 allnoconfig gcc-14.1.0 arm64 defconfig gcc-14.1.0 arm64 randconfig-001-20240823 gcc-14.1.0 arm64 randconfig-002-20240823 gcc-14.1.0 arm64 randconfig-003-20240823 gcc-14.1.0 arm64 randconfig-004-20240823 gcc-14.1.0 x86_64 allnoconfig clang-18 x86_64 allyesconfig clang-18 x86_64 buildonly-randconfig-001-20240823 gcc-12 x86_64 buildonly-randconfig-002-20240823 gcc-12 x86_64 buildonly-randconfig-003-20240823 gcc-12 x86_64 buildonly-randconfig-004-20240823 clang-18 x86_64 buildonly-randconfig-005-20240823 gcc-12 x86_64 buildonly-randconfig-006-20240823 gcc-12 x86_64 defconfig gcc-11 x86_64 randconfig-001-20240823 clang-18 x86_64 randconfig-002-20240823 clang-18 x86_64 randconfig-003-20240823 clang-18 x86_64 randconfig-004-20240823 clang-18 x86_64 rhel-8.3-rust clang-18 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[openeuler:OLK-6.6 13455/13476] arch/arm64/kernel/virtcca_cvm_tsi.c:57:30: warning: variable 'ver' is uninitialized when used here
by kernel test robot 23 Aug '24

23 Aug '24

tree: https://gitee.com/openeuler/kernel.git OLK-6.6 head: eccf28eefc9db7799534bd84bb958f3ecf978e2d commit: 721f4ea899ff2ab4e3283767cf125dc5952c1d15 [13455/13476] cvm_tsi: add support virtcca attestation config: arm64-allmodconfig (https://download.01.org/0day-ci/archive/20240823/202408230839.S2haccDx-lkp@…) compiler: clang version 20.0.0git (https://github.com/llvm/llvm-project 26670e7fa4f032a019d23d56c6a02926e854e8af) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20240823/202408230839.S2haccDx-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/202408230839.S2haccDx-lkp@intel.com/ All warnings (new ones prefixed by >>): In file included from arch/arm64/kernel/virtcca_cvm_tsi.c:3: In file included from include/linux/memblock.h:12: In file included from include/linux/mm.h:2242: include/linux/vmstat.h:508:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion] 508 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~ ^ 509 | item]; | ~~~~ include/linux/vmstat.h:515:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion] 515 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~ ^ 516 | NR_VM_NUMA_EVENT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~~ include/linux/vmstat.h:522:36: warning: arithmetic between different enumeration types ('enum node_stat_item' and 'enum lru_list') [-Wenum-enum-conversion] 522 | return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_" | ~~~~~~~~~~~ ^ ~~~ include/linux/vmstat.h:527:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion] 527 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~ ^ 528 | NR_VM_NUMA_EVENT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~~ include/linux/vmstat.h:536:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion] 536 | return vmstat_text[NR_VM_ZONE_STAT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~ ^ 537 | NR_VM_NUMA_EVENT_ITEMS + | ~~~~~~~~~~~~~~~~~~~~~~ >> arch/arm64/kernel/virtcca_cvm_tsi.c:57:30: warning: variable 'ver' is uninitialized when used here [-Wuninitialized] 57 | TSI_ABI_VERSION_GET_MAJOR(ver), | ^~~ include/linux/printk.h:508:37: note: expanded from macro 'pr_warn' 508 | printk(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) | ^~~~~~~~~~~ include/linux/printk.h:455:60: note: expanded from macro 'printk' 455 | #define printk(fmt, ...) printk_index_wrap(_printk, fmt, ##__VA_ARGS__) | ^~~~~~~~~~~ include/linux/printk.h:427:19: note: expanded from macro 'printk_index_wrap' 427 | _p_func(_fmt, ##__VA_ARGS__); \ | ^~~~~~~~~~~ arch/arm64/include/asm/virtcca_cvm_smc.h:16:47: note: expanded from macro 'TSI_ABI_VERSION_GET_MAJOR' 16 | #define TSI_ABI_VERSION_GET_MAJOR(_version) ((_version) >> 16) | ^~~~~~~~ arch/arm64/kernel/virtcca_cvm_tsi.c:39:19: note: initialize the variable 'ver' to silence this warning 39 | unsigned long ver; | ^ | = 0 6 warnings generated. vim +/ver +57 arch/arm64/kernel/virtcca_cvm_tsi.c 36 37 static int __init tmm_tsi_init(void) 38 { 39 unsigned long ver; 40 int ret; 41 42 if (!is_virtcca_cvm_world()) 43 return -EIO; 44 45 ret = misc_register(&ioctl_dev); 46 if (ret) { 47 pr_err("tmm_tsi: misc device register failed (%d)!\n", ret); 48 return ret; 49 } 50 51 /* Allocate a large memory */ 52 token.buf = kzalloc(GRANULE_SIZE * MAX_TOKEN_GRANULE_COUNT, GFP_KERNEL); 53 if (!token.buf) 54 return -ENOMEM; 55 56 pr_warn("tmm_tsi: module loaded (version %lu.%lu).\n", > 57 TSI_ABI_VERSION_GET_MAJOR(ver), 58 TSI_ABI_VERSION_GET_MINOR(ver)); 59 60 return 0; 61 } 62 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[openeuler:OLK-6.6] BUILD REGRESSION eccf28eefc9db7799534bd84bb958f3ecf978e2d
by kernel test robot 23 Aug '24

23 Aug '24

tree/branch: https://gitee.com/openeuler/kernel.git OLK-6.6 branch HEAD: eccf28eefc9db7799534bd84bb958f3ecf978e2d !10942 add support for arm virtcca attestation Error/Warning ids grouped by kconfigs: recent_errors |-- arm64-allmodconfig | |-- arch-arm64-kvm-arm.c:warning:variable-r-is-used-uninitialized-whenever-if-condition-is-false | |-- arch-arm64-kvm-tmi.c:warning:no-previous-prototype-for-function-tmi_tmm_inf_test | |-- arch-arm64-kvm-virtcca_cvm.c:warning:no-previous-prototype-for-function-kvm_cvm_create_ttt_levels | |-- arch-arm64-kvm-virtcca_cvm.c:warning:no-previous-prototype-for-function-kvm_cvm_get_num_brps | |-- arch-arm64-kvm-virtcca_cvm.c:warning:no-previous-prototype-for-function-kvm_cvm_get_num_wrps | |-- arch-arm64-kvm-virtcca_cvm.c:warning:no-previous-prototype-for-function-kvm_cvm_ipa_limit | |-- arch-arm64-kvm-virtcca_cvm.c:warning:no-previous-prototype-for-function-kvm_cvm_populate_par_region | |-- arch-arm64-kvm-virtcca_cvm.c:warning:no-previous-prototype-for-function-kvm_cvm_supports_pmu | `-- arch-arm64-kvm-virtcca_cvm.c:warning:no-previous-prototype-for-function-kvm_cvm_supports_sve |-- x86_64-buildonly-randconfig-005-20240823 | `-- kernel-sched-isolation.c:error:setup_max_cpus-undeclared-(first-use-in-this-function) `-- x86_64-buildonly-randconfig-006-20240823 `-- kernel-sched-isolation.c:error:setup_max_cpus-undeclared-(first-use-in-this-function) elapsed time: 732m configs tested: 36 configs skipped: 124 tested configs: arm64 allmodconfig clang-20 arm64 allnoconfig gcc-14.1.0 arm64 randconfig-001-20240823 clang-20 arm64 randconfig-002-20240823 gcc-14.1.0 arm64 randconfig-003-20240823 gcc-14.1.0 arm64 randconfig-004-20240823 clang-20 loongarch allmodconfig gcc-14.1.0 loongarch allnoconfig gcc-14.1.0 loongarch randconfig-001-20240823 gcc-14.1.0 loongarch randconfig-002-20240823 gcc-14.1.0 x86_64 allnoconfig clang-18 x86_64 allyesconfig clang-18 x86_64 buildonly-randconfig-001-20240823 gcc-12 x86_64 buildonly-randconfig-002-20240823 gcc-12 x86_64 buildonly-randconfig-003-20240823 gcc-12 x86_64 buildonly-randconfig-004-20240823 clang-18 x86_64 buildonly-randconfig-005-20240823 gcc-12 x86_64 buildonly-randconfig-006-20240823 gcc-12 x86_64 defconfig gcc-11 x86_64 randconfig-001-20240823 clang-18 x86_64 randconfig-002-20240823 clang-18 x86_64 randconfig-003-20240823 clang-18 x86_64 randconfig-004-20240823 clang-18 x86_64 randconfig-005-20240823 clang-18 x86_64 randconfig-006-20240823 clang-18 x86_64 randconfig-011-20240823 gcc-12 x86_64 randconfig-012-20240823 clang-18 x86_64 randconfig-013-20240823 clang-18 x86_64 randconfig-014-20240823 gcc-11 x86_64 randconfig-015-20240823 clang-18 x86_64 randconfig-016-20240823 gcc-12 x86_64 randconfig-071-20240823 gcc-12 x86_64 randconfig-072-20240823 gcc-12 x86_64 randconfig-073-20240823 gcc-12 x86_64 randconfig-074-20240823 clang-18 x86_64 rhel-8.3-rust clang-18 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[openeuler:OLK-5.10] BUILD SUCCESS e9437292d288968fc2cb9f58fa81e21ab9471f7f
by kernel test robot 23 Aug '24

23 Aug '24

tree/branch: https://gitee.com/openeuler/kernel.git OLK-5.10 branch HEAD: e9437292d288968fc2cb9f58fa81e21ab9471f7f !11045 bpf: Fix a segment issue when downgrading gso_size elapsed time: 746m configs tested: 34 configs skipped: 128 The following configs have been built successfully. More configs may be tested in the coming days. tested configs: arm64 allmodconfig clang-20 arm64 allnoconfig gcc-14.1.0 arm64 randconfig-001-20240823 clang-20 arm64 randconfig-002-20240823 gcc-14.1.0 arm64 randconfig-003-20240823 gcc-14.1.0 arm64 randconfig-004-20240823 clang-20 x86_64 allnoconfig clang-18 x86_64 allyesconfig clang-18 x86_64 buildonly-randconfig-001-20240823 gcc-12 x86_64 buildonly-randconfig-002-20240823 gcc-12 x86_64 buildonly-randconfig-003-20240823 gcc-12 x86_64 buildonly-randconfig-004-20240823 clang-18 x86_64 buildonly-randconfig-005-20240823 gcc-12 x86_64 buildonly-randconfig-006-20240823 gcc-12 x86_64 defconfig gcc-11 x86_64 randconfig-001-20240823 clang-18 x86_64 randconfig-002-20240823 clang-18 x86_64 randconfig-003-20240823 clang-18 x86_64 randconfig-004-20240823 clang-18 x86_64 randconfig-005-20240823 clang-18 x86_64 randconfig-006-20240823 clang-18 x86_64 randconfig-011-20240823 gcc-12 x86_64 randconfig-012-20240823 clang-18 x86_64 randconfig-013-20240823 clang-18 x86_64 randconfig-014-20240823 gcc-11 x86_64 randconfig-015-20240823 clang-18 x86_64 randconfig-016-20240823 gcc-12 x86_64 randconfig-071-20240823 gcc-12 x86_64 randconfig-072-20240823 gcc-12 x86_64 randconfig-073-20240823 gcc-12 x86_64 randconfig-074-20240823 clang-18 x86_64 randconfig-075-20240823 gcc-12 x86_64 randconfig-076-20240823 gcc-12 x86_64 rhel-8.3-rust clang-18 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH openEuler-1.0-LTS] nilfs2: fix general protection fault in nilfs_btree_insert()
by Yang Yingliang 22 Aug '24

22 Aug '24

From: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> stable inclusion from stable-v4.19.271 commit d9fde9eab1766170ff2ade67d09178d2cfd78749 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALLDY CVE: CVE-2023-52900 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… --------------------------- commit 7633355e5c7f29c049a9048e461427d1d8ed3051 upstream. If nilfs2 reads a corrupted disk image and tries to reads a b-tree node block by calling __nilfs_btree_get_block() against an invalid virtual block address, it returns -ENOENT because conversion of the virtual block address to a disk block address fails. However, this return value is the same as the internal code that b-tree lookup routines return to indicate that the block being searched does not exist, so functions that operate on that b-tree may misbehave. When nilfs_btree_insert() receives this spurious 'not found' code from nilfs_btree_do_lookup(), it misunderstands that the 'not found' check was successful and continues the insert operation using incomplete lookup path data, causing the following crash: general protection fault, probably for non-canonical address 0xdffffc0000000005: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000028-0x000000000000002f] ... RIP: 0010:nilfs_btree_get_nonroot_node fs/nilfs2/btree.c:418 [inline] RIP: 0010:nilfs_btree_prepare_insert fs/nilfs2/btree.c:1077 [inline] RIP: 0010:nilfs_btree_insert+0x6d3/0x1c10 fs/nilfs2/btree.c:1238 Code: bc 24 80 00 00 00 4c 89 f8 48 c1 e8 03 42 80 3c 28 00 74 08 4c 89 ff e8 4b 02 92 fe 4d 8b 3f 49 83 c7 28 4c 89 f8 48 c1 e8 03 <42> 80 3c 28 00 74 08 4c 89 ff e8 2e 02 92 fe 4d 8b 3f 49 83 c7 02 ... Call Trace: <TASK> nilfs_bmap_do_insert fs/nilfs2/bmap.c:121 [inline] nilfs_bmap_insert+0x20d/0x360 fs/nilfs2/bmap.c:147 nilfs_get_block+0x414/0x8d0 fs/nilfs2/inode.c:101 __block_write_begin_int+0x54c/0x1a80 fs/buffer.c:1991 __block_write_begin fs/buffer.c:2041 [inline] block_write_begin+0x93/0x1e0 fs/buffer.c:2102 nilfs_write_begin+0x9c/0x110 fs/nilfs2/inode.c:261 generic_perform_write+0x2e4/0x5e0 mm/filemap.c:3772 __generic_file_write_iter+0x176/0x400 mm/filemap.c:3900 generic_file_write_iter+0xab/0x310 mm/filemap.c:3932 call_write_iter include/linux/fs.h:2186 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x7dc/0xc50 fs/read_write.c:584 ksys_write+0x177/0x2a0 fs/read_write.c:637 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd ... </TASK> This patch fixes the root cause of this problem by replacing the error code that __nilfs_btree_get_block() returns on block address conversion failure from -ENOENT to another internal code -EINVAL which means that the b-tree metadata is corrupted. By returning -EINVAL, it propagates without glitches, and for all relevant b-tree operations, functions in the upper bmap layer output an error message indicating corrupted b-tree metadata via nilfs_bmap_convert_error(), and code -EIO will be eventually returned as it should be. Link: https://lkml.kernel.org/r/000000000000bd89e205f0e38355@google.com Link: https://lkml.kernel.org/r/20230105055356.8811-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Reported-by: syzbot+ede796cecd5296353515(a)syzkaller.appspotmail.com Tested-by: Ryusuke Konishi <konishi.ryusuke(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yang Yingliang <yangyingliang(a)huawei.com> --- fs/nilfs2/btree.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index e94b18eb5385..7959d3c34d20 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -478,9 +478,18 @@ static int __nilfs_btree_get_block(const struct nilfs_bmap *btree, __u64 ptr, ret = nilfs_btnode_submit_block(btnc, ptr, 0, REQ_OP_READ, 0, &bh, &submit_ptr); if (ret) { - if (ret != -EEXIST) - return ret; - goto out_check; + if (likely(ret == -EEXIST)) + goto out_check; + if (ret == -ENOENT) { + /* + * Block address translation failed due to invalid + * value of 'ptr'. In this case, return internal code + * -EINVAL (broken bmap) to notify bmap layer of fatal + * metadata corruption. + */ + ret = -EINVAL; + } + return ret; } if (ra) { -- 2.25.1

2 1

[PATCH openEuler-22.03-LTS-SP1] wifi: cfg80211: handle 2x996 RU allocation in cfg80211_calculate_bitrate_he()
by Liu Jian 22 Aug '24

22 Aug '24

From: Baochen Qiang <quic_bqiang(a)quicinc.com> stable inclusion from stable-v5.10.224 commit 2e201b3d162c6c49417c438ffb30b58c9f85769f category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALEA1 CVE: CVE-2024-43879 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ------------------------------------------------- [ Upstream commit bcbd771cd5d68c0c52567556097d75f9fc4e7cd6 ] Currently NL80211_RATE_INFO_HE_RU_ALLOC_2x996 is not handled in cfg80211_calculate_bitrate_he(), leading to below warning: kernel: invalid HE MCS: bw:6, ru:6 kernel: WARNING: CPU: 0 PID: 2312 at net/wireless/util.c:1501 cfg80211_calculate_bitrate_he+0x22b/0x270 [cfg80211] Fix it by handling 2x996 RU allocation in the same way as 160 MHz bandwidth. Fixes: c4cbaf7973a7 ("cfg80211: Add support for HE") Signed-off-by: Baochen Qiang <quic_bqiang(a)quicinc.com> Link: https://msgid.link/20240606020653.33205-3-quic_bqiang@quicinc.com Signed-off-by: Johannes Berg <johannes.berg(a)intel.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Liu Jian <liujian56(a)huawei.com> --- net/wireless/util.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/wireless/util.c b/net/wireless/util.c index 5177fd63b1b8..15773db362a1 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1357,7 +1357,9 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) if (WARN_ON_ONCE(rate->nss < 1 || rate->nss > 8)) return 0; - if (rate->bw == RATE_INFO_BW_160) + if (rate->bw == RATE_INFO_BW_160 || + (rate->bw == RATE_INFO_BW_HE_RU && + rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_2x996)) result = rates_160M[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_80 || (rate->bw == RATE_INFO_BW_HE_RU && -- 2.34.1

2 1

[PATCH OLK-5.10] wifi: cfg80211: handle 2x996 RU allocation in cfg80211_calculate_bitrate_he()
by Liu Jian 22 Aug '24

22 Aug '24

From: Baochen Qiang <quic_bqiang(a)quicinc.com> stable inclusion from stable-v5.10.224 commit 2e201b3d162c6c49417c438ffb30b58c9f85769f category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALEA1 CVE: CVE-2024-43879 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ------------------------------------------------- [ Upstream commit bcbd771cd5d68c0c52567556097d75f9fc4e7cd6 ] Currently NL80211_RATE_INFO_HE_RU_ALLOC_2x996 is not handled in cfg80211_calculate_bitrate_he(), leading to below warning: kernel: invalid HE MCS: bw:6, ru:6 kernel: WARNING: CPU: 0 PID: 2312 at net/wireless/util.c:1501 cfg80211_calculate_bitrate_he+0x22b/0x270 [cfg80211] Fix it by handling 2x996 RU allocation in the same way as 160 MHz bandwidth. Fixes: c4cbaf7973a7 ("cfg80211: Add support for HE") Signed-off-by: Baochen Qiang <quic_bqiang(a)quicinc.com> Link: https://msgid.link/20240606020653.33205-3-quic_bqiang@quicinc.com Signed-off-by: Johannes Berg <johannes.berg(a)intel.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Liu Jian <liujian56(a)huawei.com> --- net/wireless/util.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/wireless/util.c b/net/wireless/util.c index 5177fd63b1b8..15773db362a1 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1357,7 +1357,9 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) if (WARN_ON_ONCE(rate->nss < 1 || rate->nss > 8)) return 0; - if (rate->bw == RATE_INFO_BW_160) + if (rate->bw == RATE_INFO_BW_160 || + (rate->bw == RATE_INFO_BW_HE_RU && + rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_2x996)) result = rates_160M[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_80 || (rate->bw == RATE_INFO_BW_HE_RU && -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] wifi: cfg80211: handle 2x996 RU allocation in cfg80211_calculate_bitrate_he()
by Liu Jian 22 Aug '24

22 Aug '24

From: Baochen Qiang <quic_bqiang(a)quicinc.com> stable inclusion from stable-v4.19.320 commit 45d20a1c54be4f3173862c7b950d4468447814c9 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALEA1 CVE: CVE-2024-43879 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ------------------------------------------------- [ Upstream commit bcbd771cd5d68c0c52567556097d75f9fc4e7cd6 ] Currently NL80211_RATE_INFO_HE_RU_ALLOC_2x996 is not handled in cfg80211_calculate_bitrate_he(), leading to below warning: kernel: invalid HE MCS: bw:6, ru:6 kernel: WARNING: CPU: 0 PID: 2312 at net/wireless/util.c:1501 cfg80211_calculate_bitrate_he+0x22b/0x270 [cfg80211] Fix it by handling 2x996 RU allocation in the same way as 160 MHz bandwidth. Fixes: c4cbaf7973a7 ("cfg80211: Add support for HE") Signed-off-by: Baochen Qiang <quic_bqiang(a)quicinc.com> Link: https://msgid.link/20240606020653.33205-3-quic_bqiang@quicinc.com Signed-off-by: Johannes Berg <johannes.berg(a)intel.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Liu Jian <liujian56(a)huawei.com> --- net/wireless/util.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/wireless/util.c b/net/wireless/util.c index b39ee17dbead..4e81210e5b24 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -1189,7 +1189,9 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) if (WARN_ON_ONCE(rate->nss < 1 || rate->nss > 8)) return 0; - if (rate->bw == RATE_INFO_BW_160) + if (rate->bw == RATE_INFO_BW_160 || + (rate->bw == RATE_INFO_BW_HE_RU && + rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_2x996)) result = rates_160M[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_80 || (rate->bw == RATE_INFO_BW_HE_RU && -- 2.34.1

2 1

[PATCH openEuler-22.03-LTS-SP1] drm/virtio: Fix GEM handle creation UAF
by Zeng Heng 22 Aug '24

22 Aug '24

From: Rob Clark <robdclark(a)chromium.org> stable inclusion from stable-v5.10.164 commit 68bcd063857075d2f9edfed6024387ac377923e2 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALIA1 CVE: CVE-2022-48899 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 52531258318ed59a2dc5a43df2eaf0eb1d65438e ] Userspace can guess the handle value and try to race GEM object creation with handle close, resulting in a use-after-free if we dereference the object after dropping the handle's reference. For that reason, dropping the handle's reference must be done *after* we are done dereferencing the object. Signed-off-by: Rob Clark <robdclark(a)chromium.org> Reviewed-by: Chia-I Wu <olvaffe(a)gmail.com> Fixes: 62fb7a5e1096 ("virtio-gpu: add 3d/virgl support") Cc: stable(a)vger.kernel.org Signed-off-by: Dmitry Osipenko <dmitry.osipenko(a)collabora.com> Link: https://patchwork.freedesktop.org/patch/msgid/20221216233355.542197-2-robdc… Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- drivers/gpu/drm/virtio/virtgpu_ioctl.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 33b8ebab178a..36efa273155d 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -279,10 +279,18 @@ static int virtio_gpu_resource_create_ioctl(struct drm_device *dev, void *data, drm_gem_object_release(obj); return ret; } - drm_gem_object_put(obj); rc->res_handle = qobj->hw_res_handle; /* similiar to a VM address */ rc->bo_handle = handle; + + /* + * The handle owns the reference now. But we must drop our + * remaining reference *after* we no longer need to dereference + * the obj. Otherwise userspace could guess the handle and + * race closing it from another thread. + */ + drm_gem_object_put(obj); + return 0; } -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS] drm/virtio: Fix GEM handle creation UAF
by Zeng Heng 22 Aug '24

22 Aug '24

From: Rob Clark <robdclark(a)chromium.org> stable inclusion from stable-v4.19.270 commit 19ec87d06acfab2313ee82b2a689bf0c154e57ea category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALIA1 CVE: CVE-2022-48899 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 52531258318ed59a2dc5a43df2eaf0eb1d65438e ] Userspace can guess the handle value and try to race GEM object creation with handle close, resulting in a use-after-free if we dereference the object after dropping the handle's reference. For that reason, dropping the handle's reference must be done *after* we are done dereferencing the object. Signed-off-by: Rob Clark <robdclark(a)chromium.org> Reviewed-by: Chia-I Wu <olvaffe(a)gmail.com> Fixes: 62fb7a5e1096 ("virtio-gpu: add 3d/virgl support") Cc: stable(a)vger.kernel.org Signed-off-by: Dmitry Osipenko <dmitry.osipenko(a)collabora.com> Link: https://patchwork.freedesktop.org/patch/msgid/20221216233355.542197-2-robdc… Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Zeng Heng <zengheng4(a)huawei.com> --- drivers/gpu/drm/virtio/virtgpu_ioctl.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c index 8d2f5ded86d6..a539843a03ba 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ioctl.c +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -309,7 +309,6 @@ static int virtio_gpu_resource_create_ioctl(struct drm_device *dev, void *data, } return ret; } - drm_gem_object_put_unlocked(obj); rc->res_handle = res_id; /* similiar to a VM address */ rc->bo_handle = handle; @@ -318,6 +317,15 @@ static int virtio_gpu_resource_create_ioctl(struct drm_device *dev, void *data, virtio_gpu_unref_list(&validate_list); dma_fence_put(&fence->f); } + + /* + * The handle owns the reference now. But we must drop our + * remaining reference *after* we no longer need to dereference + * the obj. Otherwise userspace could guess the handle and + * race closing it from another thread. + */ + drm_gem_object_put_unlocked(obj); + return 0; fail_unref: if (vgdev->has_virgl_3d) { -- 2.25.1

2 1

[PATCH 1/1] libhns:Fixes several bugs for hns
by Chengchang Tang 22 Aug '24

22 Aug '24

From: Xinghai Cen <cenxinghai(a)h-partners.com> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/IALOAP ---------------------------------------------------------------------- Fixes several bugs for hns: libhns: Fix overwritten SL in DSCP mode libhns: Support returning the final value of SL configuration libhns: Fix memory leakage when DCA is enabled libhns: Fix the exception branch of wr_start() is not locked Signed-off-by: Xinghai Cen <cenxinghai(a)h-partners.com> --- ...bhns-Fix-overwritten-SL-in-DSCP-mode.patch | 44 +++++++++++++++++++ ...eturning-the-final-value-of-SL-confi.patch | 34 ++++++++++++++ ...x-memory-leakage-when-DCA-is-enabled.patch | 34 ++++++++++++++ ...xception-branch-of-wr_start-is-not-l.patch | 35 +++++++++++++++ rdma-core.spec | 12 ++++- 5 files changed, 158 insertions(+), 1 deletion(-) create mode 100644 0083-libhns-Fix-overwritten-SL-in-DSCP-mode.patch create mode 100644 0084-libhns-Support-returning-the-final-value-of-SL-confi.patch create mode 100644 0085-libhns-Fix-memory-leakage-when-DCA-is-enabled.patch create mode 100644 0086-libhns-Fix-the-exception-branch-of-wr_start-is-not-l.patch diff --git a/0083-libhns-Fix-overwritten-SL-in-DSCP-mode.patch b/0083-libhns-Fix-overwritten-SL-in-DSCP-mode.patch new file mode 100644 index 0000000..c600d2b --- /dev/null +++ b/0083-libhns-Fix-overwritten-SL-in-DSCP-mode.patch @@ -0,0 +1,44 @@ +From 40e7e1643cd67bbdd0865372c4ff64d42d1aaf0b Mon Sep 17 00:00:00 2001 +From: Luoyouming <luoyouming(a)huawei.com> +Date: Mon, 29 Jan 2024 15:38:18 +0800 +Subject: [PATCH 1/4] libhns: Fix overwritten SL in DSCP mode + +After configuring the DSCP mode, the driver needs to use the +priority as the SL instead of the user-configured SL. +Adjusting the assignment order ensures that the priority is +used as the SL in DSCP mode. + +Fixes: 6ec5d1f3f04c ("libhns: Support DSCP") +Signed-off-by: Luoyouming <luoyouming(a)huawei.com> +--- + providers/hns/hns_roce_u_hw_v2.c | 7 +++---- + 1 file changed, 3 insertions(+), 4 deletions(-) + +diff --git a/providers/hns/hns_roce_u_hw_v2.c b/providers/hns/hns_roce_u_hw_v2.c +index 8f071e1..42b4f32 100644 +--- a/providers/hns/hns_roce_u_hw_v2.c ++++ b/providers/hns/hns_roce_u_hw_v2.c +@@ -1896,7 +1896,9 @@ static void record_qp_attr(struct ibv_qp *qp, struct ibv_qp_attr *attr, + if (attr_mask & IBV_QP_PORT) + hr_qp->port_num = attr->port_num; + +- if (attr_mask & IBV_QP_AV) ++ if (hr_qp->tc_mode == HNS_ROCE_TC_MAP_MODE_DSCP) ++ hr_qp->sl = hr_qp->priority; ++ else if (attr_mask & IBV_QP_AV) + hr_qp->sl = attr->ah_attr.sl; + + if (attr_mask & IBV_QP_QKEY) +@@ -1959,9 +1961,6 @@ static int hns_roce_u_v2_modify_qp(struct ibv_qp *qp, struct ibv_qp_attr *attr, + hns_roce_init_qp_indices(to_hr_qp(qp)); + } + +- if (hr_qp->tc_mode == HNS_ROCE_TC_MAP_MODE_DSCP) +- hr_qp->sl = hr_qp->priority; +- + /* Try to shrink the DCA mem */ + if (ctx->dca_ctx.mem_cnt > 0) + hns_roce_shrink_dca_mem(ctx); +-- +2.33.0 + diff --git a/0084-libhns-Support-returning-the-final-value-of-SL-confi.patch b/0084-libhns-Support-returning-the-final-value-of-SL-confi.patch new file mode 100644 index 0000000..2b01cd6 --- /dev/null +++ b/0084-libhns-Support-returning-the-final-value-of-SL-confi.patch @@ -0,0 +1,34 @@ +From fc50769b446a5418767058cd2a5b5e7a9724a391 Mon Sep 17 00:00:00 2001 +From: Luoyouming <luoyouming(a)huawei.com> +Date: Mon, 29 Jan 2024 16:12:55 +0800 +Subject: [PATCH 2/4] libhns: Support returning the final value of SL + configuration +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit + +Returns the real SL used in HW to user��which can be used in variety of scenarios. +E.g. The STARS mode. + +Signed-off-by: Luoyouming <luoyouming(a)huawei.com> +--- + providers/hns/hns_roce_u_hw_v2.c | 3 +++ + 1 file changed, 3 insertions(+) + +diff --git a/providers/hns/hns_roce_u_hw_v2.c b/providers/hns/hns_roce_u_hw_v2.c +index 42b4f32..af25e6e 100644 +--- a/providers/hns/hns_roce_u_hw_v2.c ++++ b/providers/hns/hns_roce_u_hw_v2.c +@@ -1967,6 +1967,9 @@ static int hns_roce_u_v2_modify_qp(struct ibv_qp *qp, struct ibv_qp_attr *attr, + + record_qp_attr(qp, attr, attr_mask); + ++ // Update the SL value and return it to the user. ++ attr->ah_attr.sl = hr_qp->sl; ++ + return ret; + } + +-- +2.33.0 + diff --git a/0085-libhns-Fix-memory-leakage-when-DCA-is-enabled.patch b/0085-libhns-Fix-memory-leakage-when-DCA-is-enabled.patch new file mode 100644 index 0000000..aa4aa63 --- /dev/null +++ b/0085-libhns-Fix-memory-leakage-when-DCA-is-enabled.patch @@ -0,0 +1,34 @@ +From 485a60f8850630c37856f68be3fbf37bfa9ac019 Mon Sep 17 00:00:00 2001 +From: wenglianfa <wenglianfa(a)huawei.com> +Date: Thu, 25 Jul 2024 11:06:01 +0800 +Subject: [PATCH 3/4] libhns: Fix memory leakage when DCA is enabled + +After DCA is enabled and a QP is created, the memory block +applied for DCA is not free when the QP is destroyed. Here +fix it. + +Fixes: 3aa4683ef700 ("libhns: Add support for attaching QP's WQE buffer") +Signed-off-by: wenglianfa <wenglianfa(a)huawei.com> +--- + providers/hns/hns_roce_u_verbs.c | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +diff --git a/providers/hns/hns_roce_u_verbs.c b/providers/hns/hns_roce_u_verbs.c +index 090efbf..dae8298 100644 +--- a/providers/hns/hns_roce_u_verbs.c ++++ b/providers/hns/hns_roce_u_verbs.c +@@ -1617,7 +1617,10 @@ static void qp_free_wqe(struct hns_roce_qp *qp) + + if (qp->rq.wqe_cnt) + free(qp->rq.wrid); +- hns_roce_free_buf(&qp->buf); ++ if (qp->dca_wqe.bufs) ++ free(qp->dca_wqe.bufs); ++ else ++ hns_roce_free_buf(&qp->buf); + } + + static int qp_alloc_wqe(struct ibv_qp_init_attr_ex *attr, +-- +2.33.0 + diff --git a/0086-libhns-Fix-the-exception-branch-of-wr_start-is-not-l.patch b/0086-libhns-Fix-the-exception-branch-of-wr_start-is-not-l.patch new file mode 100644 index 0000000..e3e4d29 --- /dev/null +++ b/0086-libhns-Fix-the-exception-branch-of-wr_start-is-not-l.patch @@ -0,0 +1,35 @@ +From 41592115435779d7c41e7f1677520b9c641289d9 Mon Sep 17 00:00:00 2001 +From: wenglianfa <wenglianfa(a)huawei.com> +Date: Wed, 12 Jun 2024 17:11:13 +0800 +Subject: [PATCH 4/4] libhns: Fix the exception branch of wr_start() is not + locked + +The provider should provide locking to ensure that ibv_wr_start() +and ibv_wr_complete()/abort() form a per-QP critical section +where no other threads can enter. + +The exception branch of wr_start() is not locked, fix it here. +Because check_qp_send () does not require lock protection, +hns_roce_spin_lock () is placed after check_qp_send (). + +Fixes: 36446a56eea5 ("libhns: Extended QP supports the new post send mechanism") +Signed-off-by: wenglianfa <wenglianfa(a)huawei.com> +--- + providers/hns/hns_roce_u_hw_v2.c | 1 + + 1 file changed, 1 insertion(+) + +diff --git a/providers/hns/hns_roce_u_hw_v2.c b/providers/hns/hns_roce_u_hw_v2.c +index af25e6e..79f225c 100644 +--- a/providers/hns/hns_roce_u_hw_v2.c ++++ b/providers/hns/hns_roce_u_hw_v2.c +@@ -2975,6 +2975,7 @@ static void wr_start(struct ibv_qp_ex *ibv_qp) + + ret = check_qp_send(qp, ctx); + if (ret) { ++ hns_roce_spin_lock(&qp->sq.hr_lock); + qp->err = ret; + return; + } +-- +2.33.0 + diff --git a/rdma-core.spec b/rdma-core.spec index f0de576..8caac46 100644 --- a/rdma-core.spec +++ b/rdma-core.spec @@ -1,6 +1,6 @@ Name: rdma-core Version: 41.0 -Release: 26 +Release: 27 Summary: RDMA core userspace libraries and daemons License: GPLv2 or BSD Url: https://github.com/linux-rdma/rdma-core @@ -88,6 +88,10 @@ patch79: 0079-libhns-Removes-a-repeated-initialization-of-a-spinlo.patch patch80: 0080-libhns-Fix-owner-bit-when-SQ-wraps-around-in-new-IO.patch patch81: 0081-libhns-Fix-missing-DB-when-compiler-does-not-support.patch patch82: 0082-ibnetdisc-Fix-leak-in-add_to_portlid_hash.patch +patch83: 0083-libhns-Fix-overwritten-SL-in-DSCP-mode.patch +patch84: 0084-libhns-Support-returning-the-final-value-of-SL-confi.patch +patch85: 0085-libhns-Fix-memory-leakage-when-DCA-is-enabled.patch +patch86: 0086-libhns-Fix-the-exception-branch-of-wr_start-is-not-l.patch BuildRequires: binutils cmake >= 2.8.11 gcc libudev-devel pkgconfig pkgconfig(libnl-3.0) BuildRequires: pkgconfig(libnl-route-3.0) valgrind-devel systemd systemd-devel @@ -335,6 +339,12 @@ fi %{_mandir}/* %changelog +* Thu Aug 22 2024 Xinghai Cen <cenxinghai(a)h-partners.com> - 41.0-27 +- Type: bugfix +- ID: NA +- SUG: NA +- DESC: Fixes several bugs for hns + * Thu Aug 8 2024 yanshuai <yanshuai01(a)kylinos.cn> - 41.0-26 - Type: bugfix - ID: NA -- 2.33.0

1 0

[PATCH openEuler-1.0-LTS 0/3] Fix CVE-2024-39501
by Chen Jun 22 Aug '24

22 Aug '24

*** BLURB HERE *** Amit Cohen (1): selftests: forwarding: devlink_lib: Wait for udev events after reloading Dan Williams (1): driver core: Fix uevent_show() vs driver detach race Dirk Behme (1): drivers: core: synchronize really_probe() and dev_uevent() drivers/base/core.c | 10 ++++++++-- drivers/base/module.c | 4 ++++ tools/testing/selftests/net/forwarding/devlink_lib.sh | 2 ++ 3 files changed, 14 insertions(+), 2 deletions(-) -- 2.17.1

2 4

[PATCH openEuler-22.03-LTS-SP1] xhci: Fix null pointer dereference when host dies
by Zheng Yejian 22 Aug '24

22 Aug '24

From: Mathias Nyman <mathias.nyman(a)linux.intel.com> stable inclusion from stable-v5.10.165 commit 081105213ff6f661c114781d469233c7d0e09c2e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IALLDG CVE: CVE-2023-52898 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit a2bc47c43e70cf904b1af49f76d572326c08bca7 upstream. Make sure xhci_free_dev() and xhci_kill_endpoint_urbs() do not race and cause null pointer dereference when host suddenly dies. Usb core may call xhci_free_dev() which frees the xhci->devs[slot_id] virt device at the same time that xhci_kill_endpoint_urbs() tries to loop through all the device's endpoints, checking if there are any cancelled urbs left to give back. hold the xhci spinlock while freeing the virt device Cc: stable(a)vger.kernel.org Signed-off-by: Mathias Nyman <mathias.nyman(a)linux.intel.com> Link: https://lore.kernel.org/r/20230116142216.1141605-4-mathias.nyman@linux.inte… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: sanglipeng <sanglipeng1(a)jd.com> Signed-off-by: Zheng Yejian <zhengyejian1(a)huawei.com> --- drivers/usb/host/xhci.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 9ed196947967..57ca3c21e527 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -3913,6 +3913,7 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev) struct xhci_hcd *xhci = hcd_to_xhci(hcd); struct xhci_virt_device *virt_dev; struct xhci_slot_ctx *slot_ctx; + unsigned long flags; int i, ret; /* @@ -3941,7 +3942,11 @@ static void xhci_free_dev(struct usb_hcd *hcd, struct usb_device *udev) } virt_dev->udev = NULL; xhci_disable_slot(xhci, udev->slot_id); + + spin_lock_irqsave(&xhci->lock, flags); xhci_free_virt_device(xhci, udev->slot_id); + spin_unlock_irqrestore(&xhci->lock, flags); + } int xhci_disable_slot(struct xhci_hcd *xhci, u32 slot_id) -- 2.25.1

2 1

[PATCH openEuler-1.0-LTS] i2c: pnx: Fix potential deadlock warning from del_timer_sync() call in isr
by Lin RuiFeng 22 Aug '24

22 Aug '24

From: Piotr Wojtaszczyk <piotr.wojtaszczyk(a)timesys.com> stable inclusion from stable-v4.19.318 commit a349e5ab4dc9954746e836cd10b407ce48f9b2f6 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAGS5X CVE: CVE-2024-42153 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit f63b94be6942ba82c55343e196bd09b53227618e ] When del_timer_sync() is called in an interrupt context it throws a warning because of potential deadlock. The timer is used only to exit from wait_for_completion() after a timeout so replacing the call with wait_for_completion_timeout() allows to remove the problematic timer and its related functions altogether. Fixes: 41561f28e76a ("i2c: New Philips PNX bus driver") Signed-off-by: Piotr Wojtaszczyk <piotr.wojtaszczyk(a)timesys.com> Signed-off-by: Andi Shyti <andi.shyti(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Lin RuiFeng <linruifeng4(a)huawei.com> --- drivers/i2c/busses/i2c-pnx.c | 48 ++++++++---------------------------- 1 file changed, 10 insertions(+), 38 deletions(-) diff --git a/drivers/i2c/busses/i2c-pnx.c b/drivers/i2c/busses/i2c-pnx.c index 6e0e546ef83f..4d09665a72e5 100644 --- a/drivers/i2c/busses/i2c-pnx.c +++ b/drivers/i2c/busses/i2c-pnx.c @@ -15,7 +15,6 @@ #include <linux/ioport.h> #include <linux/delay.h> #include <linux/i2c.h> -#include <linux/timer.h> #include <linux/completion.h> #include <linux/platform_device.h> #include <linux/io.h> @@ -32,7 +31,6 @@ struct i2c_pnx_mif { int ret; /* Return value */ int mode; /* Interface mode */ struct completion complete; /* I/O completion */ - struct timer_list timer; /* Timeout */ u8 * buf; /* Data buffer */ int len; /* Length of data buffer */ int order; /* RX Bytes to order via TX */ @@ -117,24 +115,6 @@ static inline int wait_reset(struct i2c_pnx_algo_data *data) return (timeout <= 0); } -static inline void i2c_pnx_arm_timer(struct i2c_pnx_algo_data *alg_data) -{ - struct timer_list *timer = &alg_data->mif.timer; - unsigned long expires = msecs_to_jiffies(alg_data->timeout); - - if (expires <= 1) - expires = 2; - - del_timer_sync(timer); - - dev_dbg(&alg_data->adapter.dev, "Timer armed at %lu plus %lu jiffies.\n", - jiffies, expires); - - timer->expires = jiffies + expires; - - add_timer(timer); -} - /** * i2c_pnx_start - start a device * @slave_addr: slave address @@ -259,8 +239,6 @@ static int i2c_pnx_master_xmit(struct i2c_pnx_algo_data *alg_data) ~(mcntrl_afie | mcntrl_naie | mcntrl_drmie), I2C_REG_CTL(alg_data)); - del_timer_sync(&alg_data->mif.timer); - dev_dbg(&alg_data->adapter.dev, "%s(): Waking up xfer routine.\n", __func__); @@ -276,8 +254,6 @@ static int i2c_pnx_master_xmit(struct i2c_pnx_algo_data *alg_data) ~(mcntrl_afie | mcntrl_naie | mcntrl_drmie), I2C_REG_CTL(alg_data)); - /* Stop timer. */ - del_timer_sync(&alg_data->mif.timer); dev_dbg(&alg_data->adapter.dev, "%s(): Waking up xfer routine after zero-xfer.\n", __func__); @@ -364,8 +340,6 @@ static int i2c_pnx_master_rcv(struct i2c_pnx_algo_data *alg_data) mcntrl_drmie | mcntrl_daie); iowrite32(ctl, I2C_REG_CTL(alg_data)); - /* Kill timer. */ - del_timer_sync(&alg_data->mif.timer); complete(&alg_data->mif.complete); } } @@ -400,8 +374,6 @@ static irqreturn_t i2c_pnx_interrupt(int irq, void *dev_id) mcntrl_drmie); iowrite32(ctl, I2C_REG_CTL(alg_data)); - /* Stop timer, to prevent timeout. */ - del_timer_sync(&alg_data->mif.timer); complete(&alg_data->mif.complete); } else if (stat & mstatus_nai) { /* Slave did not acknowledge, generate a STOP */ @@ -419,8 +391,6 @@ static irqreturn_t i2c_pnx_interrupt(int irq, void *dev_id) /* Our return value. */ alg_data->mif.ret = -EIO; - /* Stop timer, to prevent timeout. */ - del_timer_sync(&alg_data->mif.timer); complete(&alg_data->mif.complete); } else { /* @@ -453,9 +423,8 @@ static irqreturn_t i2c_pnx_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } -static void i2c_pnx_timeout(struct timer_list *t) +static void i2c_pnx_timeout(struct i2c_pnx_algo_data *alg_data) { - struct i2c_pnx_algo_data *alg_data = from_timer(alg_data, t, mif.timer); u32 ctl; dev_err(&alg_data->adapter.dev, @@ -472,7 +441,6 @@ static void i2c_pnx_timeout(struct timer_list *t) iowrite32(ctl, I2C_REG_CTL(alg_data)); wait_reset(alg_data); alg_data->mif.ret = -EIO; - complete(&alg_data->mif.complete); } static inline void bus_reset_if_active(struct i2c_pnx_algo_data *alg_data) @@ -514,6 +482,7 @@ i2c_pnx_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) struct i2c_msg *pmsg; int rc = 0, completed = 0, i; struct i2c_pnx_algo_data *alg_data = adap->algo_data; + unsigned long time_left; u32 stat; dev_dbg(&alg_data->adapter.dev, @@ -548,7 +517,6 @@ i2c_pnx_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) dev_dbg(&alg_data->adapter.dev, "%s(): mode %d, %d bytes\n", __func__, alg_data->mif.mode, alg_data->mif.len); - i2c_pnx_arm_timer(alg_data); /* initialize the completion var */ init_completion(&alg_data->mif.complete); @@ -564,7 +532,10 @@ i2c_pnx_xfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num) break; /* Wait for completion */ - wait_for_completion(&alg_data->mif.complete); + time_left = wait_for_completion_timeout(&alg_data->mif.complete, + alg_data->timeout); + if (time_left == 0) + i2c_pnx_timeout(alg_data); if (!(rc = alg_data->mif.ret)) completed++; @@ -657,7 +628,10 @@ static int i2c_pnx_probe(struct platform_device *pdev) alg_data->adapter.algo_data = alg_data; alg_data->adapter.nr = pdev->id; - alg_data->timeout = I2C_PNX_TIMEOUT_DEFAULT; + alg_data->timeout = msecs_to_jiffies(I2C_PNX_TIMEOUT_DEFAULT); + if (alg_data->timeout <= 1) + alg_data->timeout = 2; + #ifdef CONFIG_OF alg_data->adapter.dev.of_node = of_node_get(pdev->dev.of_node); if (pdev->dev.of_node) { @@ -677,8 +651,6 @@ static int i2c_pnx_probe(struct platform_device *pdev) if (IS_ERR(alg_data->clk)) return PTR_ERR(alg_data->clk); - timer_setup(&alg_data->mif.timer, i2c_pnx_timeout, 0); - snprintf(alg_data->adapter.name, sizeof(alg_data->adapter.name), "%s", pdev->name); -- 2.17.1

2 1

[PATCH openEuler-1.0-LTS] ocfs2: add bounds checking to ocfs2_check_dir_entry()
by Zhang Zekun 22 Aug '24

22 Aug '24

From: lei lu <llfamsec(a)gmail.com> stable inclusion from stable-v4.19.319 commit 13d38c00df97289e6fba2e54193959293fd910d2 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAG8VL CVE: CVE-2024-41015 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… --------------------------------------------- commit 255547c6bb8940a97eea94ef9d464ea5967763fb upstream. This adds sanity checks for ocfs2_dir_entry to make sure all members of ocfs2_dir_entry don't stray beyond valid memory region. Link: https://lkml.kernel.org/r/20240626104433.163270-1-llfamsec@gmail.com Signed-off-by: lei lu <llfamsec(a)gmail.com> Reviewed-by: Heming Zhao <heming.zhao(a)suse.com> Reviewed-by: Joseph Qi <joseph.qi(a)linux.alibaba.com> Cc: Mark Fasheh <mark(a)fasheh.com> Cc: Joel Becker <jlbec(a)evilplan.org> Cc: Junxiao Bi <junxiao.bi(a)oracle.com> Cc: Changwei Ge <gechangwei(a)live.cn> Cc: Gang He <ghe(a)suse.com> Cc: Jun Piao <piaojun(a)huawei.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zhang Zekun <zhangzekun11(a)huawei.com> --- fs/ocfs2/dir.c | 46 +++++++++++++++++++++++++++++----------------- 1 file changed, 29 insertions(+), 17 deletions(-) diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c index c121abbdfc7d..80389eece0fd 100644 --- a/fs/ocfs2/dir.c +++ b/fs/ocfs2/dir.c @@ -314,13 +314,16 @@ static void ocfs2_dx_dir_name_hash(struct inode *dir, const char *name, int len, * bh passed here can be an inode block or a dir data block, depending * on the inode inline data flag. */ -static int ocfs2_check_dir_entry(struct inode * dir, - struct ocfs2_dir_entry * de, - struct buffer_head * bh, +static int ocfs2_check_dir_entry(struct inode *dir, + struct ocfs2_dir_entry *de, + struct buffer_head *bh, + char *buf, + unsigned int size, unsigned long offset) { const char *error_msg = NULL; const int rlen = le16_to_cpu(de->rec_len); + const unsigned long next_offset = ((char *) de - buf) + rlen; if (unlikely(rlen < OCFS2_DIR_REC_LEN(1))) error_msg = "rec_len is smaller than minimal"; @@ -328,9 +331,11 @@ static int ocfs2_check_dir_entry(struct inode * dir, error_msg = "rec_len % 4 != 0"; else if (unlikely(rlen < OCFS2_DIR_REC_LEN(de->name_len))) error_msg = "rec_len is too small for name_len"; - else if (unlikely( - ((char *) de - bh->b_data) + rlen > dir->i_sb->s_blocksize)) - error_msg = "directory entry across blocks"; + else if (unlikely(next_offset > size)) + error_msg = "directory entry overrun"; + else if (unlikely(next_offset > size - OCFS2_DIR_REC_LEN(1)) && + next_offset != size) + error_msg = "directory entry too close to end"; if (unlikely(error_msg != NULL)) mlog(ML_ERROR, "bad entry in directory #%llu: %s - " @@ -372,16 +377,17 @@ static inline int ocfs2_search_dirblock(struct buffer_head *bh, de_buf = first_de; dlimit = de_buf + bytes; - while (de_buf < dlimit) { + while (de_buf < dlimit - OCFS2_DIR_MEMBER_LEN) { /* this code is executed quadratically often */ /* do minimal checking `by hand' */ de = (struct ocfs2_dir_entry *) de_buf; - if (de_buf + namelen <= dlimit && + if (de->name + namelen <= dlimit && ocfs2_match(namelen, name, de)) { /* found a match - just to be sure, do a full check */ - if (!ocfs2_check_dir_entry(dir, de, bh, offset)) { + if (!ocfs2_check_dir_entry(dir, de, bh, first_de, + bytes, offset)) { ret = -1; goto bail; } @@ -1158,7 +1164,7 @@ static int __ocfs2_delete_entry(handle_t *handle, struct inode *dir, pde = NULL; de = (struct ocfs2_dir_entry *) first_de; while (i < bytes) { - if (!ocfs2_check_dir_entry(dir, de, bh, i)) { + if (!ocfs2_check_dir_entry(dir, de, bh, first_de, bytes, i)) { status = -EIO; mlog_errno(status); goto bail; @@ -1658,7 +1664,8 @@ int __ocfs2_add_entry(handle_t *handle, /* These checks should've already been passed by the * prepare function, but I guess we can leave them * here anyway. */ - if (!ocfs2_check_dir_entry(dir, de, insert_bh, offset)) { + if (!ocfs2_check_dir_entry(dir, de, insert_bh, data_start, + size, offset)) { retval = -ENOENT; goto bail; } @@ -1796,7 +1803,8 @@ static int ocfs2_dir_foreach_blk_id(struct inode *inode, } de = (struct ocfs2_dir_entry *) (data->id_data + ctx->pos); - if (!ocfs2_check_dir_entry(inode, de, di_bh, ctx->pos)) { + if (!ocfs2_check_dir_entry(inode, de, di_bh, (char *)data->id_data, + i_size_read(inode), ctx->pos)) { /* On error, skip the f_pos to the end. */ ctx->pos = i_size_read(inode); break; @@ -1893,7 +1901,8 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode, while (ctx->pos < i_size_read(inode) && offset < sb->s_blocksize) { de = (struct ocfs2_dir_entry *) (bh->b_data + offset); - if (!ocfs2_check_dir_entry(inode, de, bh, offset)) { + if (!ocfs2_check_dir_entry(inode, de, bh, bh->b_data, + sb->s_blocksize, offset)) { /* On error, skip the f_pos to the next block. */ ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1; @@ -3369,7 +3378,7 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh, struct super_block *sb = dir->i_sb; struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data; struct ocfs2_dir_entry *de, *last_de = NULL; - char *de_buf, *limit; + char *first_de, *de_buf, *limit; unsigned long offset = 0; unsigned int rec_len, new_rec_len, free_space = dir->i_sb->s_blocksize; @@ -3382,14 +3391,16 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh, else free_space = dir->i_sb->s_blocksize - i_size_read(dir); - de_buf = di->id2.i_data.id_data; + first_de = di->id2.i_data.id_data; + de_buf = first_de; limit = de_buf + i_size_read(dir); rec_len = OCFS2_DIR_REC_LEN(namelen); while (de_buf < limit) { de = (struct ocfs2_dir_entry *)de_buf; - if (!ocfs2_check_dir_entry(dir, de, di_bh, offset)) { + if (!ocfs2_check_dir_entry(dir, de, di_bh, first_de, + i_size_read(dir), offset)) { ret = -ENOENT; goto out; } @@ -3471,7 +3482,8 @@ static int ocfs2_find_dir_space_el(struct inode *dir, const char *name, /* move to next block */ de = (struct ocfs2_dir_entry *) bh->b_data; } - if (!ocfs2_check_dir_entry(dir, de, bh, offset)) { + if (!ocfs2_check_dir_entry(dir, de, bh, bh->b_data, blocksize, + offset)) { status = -ENOENT; goto bail; } -- 2.17.1

2 1

[PATCH openEuler-1.0-LTS 0/2] Fix CVE-2023-52898
by Zheng Yejian 22 Aug '24

22 Aug '24

Mathias Nyman (2): xhci: avoid race between disable slot command and host runtime suspend xhci: Fix null pointer dereference when host dies drivers/usb/host/xhci-hub.c | 1 + drivers/usb/host/xhci-ring.c | 1 - drivers/usb/host/xhci.c | 27 ++++++++++++++++++++------- 3 files changed, 21 insertions(+), 8 deletions(-) -- 2.25.1

2 3

[PATCH openEuler-1.0-LTS] parisc: Fix data TLB miss in sba_unmap_sg
by Guo Mengqi 22 Aug '24

22 Aug '24

From: John David Anglin <dave.anglin(a)bell.net> stable inclusion from stable-v4.19.231 commit 867e50231c7605547d9334904d70a181f39f2d9e category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IADGAR CVE: CVE-2022-48795 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit b7d6f44a0fa716a82969725516dc0b16bc7cd514 upstream. Rolf Eike Beer reported the following bug: [1274934.746891] Bad Address (null pointer deref?): Code=15 (Data TLB miss fault) at addr 0000004140000018 [1274934.746891] CPU: 3 PID: 5549 Comm: cmake Not tainted 5.15.4-gentoo-parisc64 #4 [1274934.746891] Hardware name: 9000/785/C8000 [1274934.746891] [1274934.746891] YZrvWESTHLNXBCVMcbcbcbcbOGFRQPDI [1274934.746891] PSW: 00001000000001001111111000001110 Not tainted [1274934.746891] r00-03 000000ff0804fe0e 0000000040bc9bc0 00000000406760e4 0000004140000000 [1274934.746891] r04-07 0000000040b693c0 0000004140000000 000000004a2b08b0 0000000000000001 [1274934.746891] r08-11 0000000041f98810 0000000000000000 000000004a0a7000 0000000000000001 [1274934.746891] r12-15 0000000040bddbc0 0000000040c0cbc0 0000000040bddbc0 0000000040bddbc0 [1274934.746891] r16-19 0000000040bde3c0 0000000040bddbc0 0000000040bde3c0 0000000000000007 [1274934.746891] r20-23 0000000000000006 000000004a368950 0000000000000000 0000000000000001 [1274934.746891] r24-27 0000000000001fff 000000000800000e 000000004a1710f0 0000000040b693c0 [1274934.746891] r28-31 0000000000000001 0000000041f988b0 0000000041f98840 000000004a171118 [1274934.746891] sr00-03 00000000066e5800 0000000000000000 0000000000000000 00000000066e5800 [1274934.746891] sr04-07 0000000000000000 0000000000000000 0000000000000000 0000000000000000 [1274934.746891] [1274934.746891] IASQ: 0000000000000000 0000000000000000 IAOQ: 00000000406760e8 00000000406760ec [1274934.746891] IIR: 48780030 ISR: 0000000000000000 IOR: 0000004140000018 [1274934.746891] CPU: 3 CR30: 00000040e3a9c000 CR31: ffffffffffffffff [1274934.746891] ORIG_R28: 0000000040acdd58 [1274934.746891] IAOQ[0]: sba_unmap_sg+0xb0/0x118 [1274934.746891] IAOQ[1]: sba_unmap_sg+0xb4/0x118 [1274934.746891] RP(r2): sba_unmap_sg+0xac/0x118 [1274934.746891] Backtrace: [1274934.746891] [<00000000402740cc>] dma_unmap_sg_attrs+0x6c/0x70 [1274934.746891] [<000000004074d6bc>] scsi_dma_unmap+0x54/0x60 [1274934.746891] [<00000000407a3488>] mptscsih_io_done+0x150/0xd70 [1274934.746891] [<0000000040798600>] mpt_interrupt+0x168/0xa68 [1274934.746891] [<0000000040255a48>] __handle_irq_event_percpu+0xc8/0x278 [1274934.746891] [<0000000040255c34>] handle_irq_event_percpu+0x3c/0xd8 [1274934.746891] [<000000004025ecb4>] handle_percpu_irq+0xb4/0xf0 [1274934.746891] [<00000000402548e0>] generic_handle_irq+0x50/0x70 [1274934.746891] [<000000004019a254>] call_on_stack+0x18/0x24 [1274934.746891] [1274934.746891] Kernel panic - not syncing: Bad Address (null pointer deref?) The bug is caused by overrunning the sglist and incorrectly testing sg_dma_len(sglist) before nents. Normally this doesn't cause a crash, but in this case sglist crossed a page boundary. This occurs in the following code: while (sg_dma_len(sglist) && nents--) { The fix is simply to test nents first and move the decrement of nents into the loop. Reported-by: Rolf Eike Beer <eike-kernel(a)sf-tec.de> Signed-off-by: John David Anglin <dave.anglin(a)bell.net> Cc: stable(a)vger.kernel.org Signed-off-by: Helge Deller <deller(a)gmx.de> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> --- drivers/parisc/sba_iommu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/parisc/sba_iommu.c b/drivers/parisc/sba_iommu.c index 6dd1780a5885..41269ad84d16 100644 --- a/drivers/parisc/sba_iommu.c +++ b/drivers/parisc/sba_iommu.c @@ -1063,7 +1063,7 @@ sba_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents, spin_unlock_irqrestore(&ioc->res_lock, flags); #endif - while (sg_dma_len(sglist) && nents--) { + while (nents && sg_dma_len(sglist)) { sba_unmap_page(dev, sg_dma_address(sglist), sg_dma_len(sglist), direction, 0); @@ -1072,6 +1072,7 @@ sba_unmap_sg(struct device *dev, struct scatterlist *sglist, int nents, ioc->usingle_calls--; /* kluge since call is unmap_sg() */ #endif ++sglist; + nents--; } DBG_RUN_SG("%s() DONE (nents %d)\n", __func__, nents); -- 2.17.1

2 1

[PATCH openEuler-22.03-LTS-SP1] drm/amdgpu: change vm->task_info handling
by Guo Mengqi 22 Aug '24

22 Aug '24

From: Shashank Sharma <shashank.sharma(a)amd.com> mainline inclusion from mainline-v6.9-rc1 commit b8f67b9ddf4f8fe6dd536590712b5912ad78f99c category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IADDFV CVE: CVE-2024-41008 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ----------------------------------------------------------- This patch changes the handling and lifecycle of vm->task_info object. The major changes are: - vm->task_info is a dynamically allocated ptr now, and its uasge is reference counted. - introducing two new helper funcs for task_info lifecycle management - amdgpu_vm_get_task_info: reference counts up task_info before returning this info - amdgpu_vm_put_task_info: reference counts down task_info - last put to task_info() frees task_info from the vm. This patch also does logistical changes required for existing usage of vm->task_info. V2: Do not block all the prints when task_info not found (Felix) V3: Fixed review comments from Felix - Fix wrong indentation - No debug message for -ENOMEM - Add NULL check for task_info - Do not duplicate the debug messages (ti vs no ti) - Get first reference of task_info in vm_init(), put last in vm_fini() V4: Fixed review comments from Felix - fix double reference increment in create_task_info - change amdgpu_vm_get_task_info_pasid - additional changes in amdgpu_gem.c while porting Cc: Christian Koenig <christian.koenig(a)amd.com> Cc: Alex Deucher <alexander.deucher(a)amd.com> Cc: Felix Kuehling <Felix.Kuehling(a)amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling(a)amd.com> Signed-off-by: Shashank Sharma <shashank.sharma(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Conflicts: drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c drivers/gpu/drm/amd/amdgpu/amdgpu_job.c [1. Some drivers does not use struct task_info, so they are no need to modify 2. use idr instead of xarray in amdgpu_vm_get_vm_from_pasid(), because there are no functional changes] Signed-off-by: Zhang Zekun <zhangzekun11(a)huawei.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 18 ++- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 161 ++++++++++++++------ drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 21 ++- drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 22 +-- drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c | 20 ++- drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 24 +-- drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c | 18 ++- 7 files changed, 191 insertions(+), 93 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index dcfe8a3b03ff..d45e84faed00 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -32,11 +32,9 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job) { struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched); struct amdgpu_job *job = to_amdgpu_job(s_job); - struct amdgpu_task_info ti; + struct amdgpu_task_info *ti; struct amdgpu_device *adev = ring->adev; - memset(&ti, 0, sizeof(struct amdgpu_task_info)); - if (amdgpu_gpu_recovery && amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) { DRM_ERROR("ring %s timeout, but soft recovered\n", @@ -44,12 +42,16 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job) return; } - amdgpu_vm_get_task_info(ring->adev, job->pasid, &ti); DRM_ERROR("ring %s timeout, signaled seq=%u, emitted seq=%u\n", - job->base.sched->name, atomic_read(&ring->fence_drv.last_seq), - ring->fence_drv.sync_seq); - DRM_ERROR("Process information: process %s pid %d thread %s pid %d\n", - ti.process_name, ti.tgid, ti.task_name, ti.pid); + job->base.sched->name, atomic_read(&ring->fence_drv.last_seq), + ring->fence_drv.sync_seq); + + ti = amdgpu_vm_get_task_info_pasid(ring->adev, job->pasid); + if (ti) { + DRM_ERROR("Process information: process %s pid %d thread %s pid %d\n", + ti->process_name, ti->tgid, ti->task_name, ti->pid); + amdgpu_vm_put_task_info(ti); + } if (amdgpu_device_should_recover_gpu(ring->adev)) { amdgpu_device_gpu_recover(ring->adev, job); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index 635601d8b131..bd248c152ee2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1525,16 +1525,20 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params, uint64_t upd_end = min(entry_end, frag_end); unsigned nptes = (upd_end - frag_start) >> shift; uint64_t upd_flags = flags | AMDGPU_PTE_FRAG(frag); + struct amdgpu_task_info *ti = amdgpu_vm_get_task_info_vm(vm); /* This can happen when we set higher level PDs to * silent to stop fault floods. */ nptes = max(nptes, 1u); - trace_amdgpu_vm_update_ptes(params, frag_start, upd_end, - nptes, dst, incr, upd_flags, - vm->task_info.pid, - vm->immediate.fence_context); + if (ti) { + trace_amdgpu_vm_update_ptes(params, frag_start, upd_end, + nptes, dst, incr, upd_flags, + ti->pid, + vm->immediate.fence_context); + amdgpu_vm_put_task_info(ti); + } amdgpu_vm_update_flags(params, pt, cursor.level, pe_start, dst, nptes, incr, upd_flags); @@ -2799,6 +2803,108 @@ long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout) return dma_fence_wait_timeout(vm->last_unlocked, true, timeout); } +static void amdgpu_vm_destroy_task_info(struct kref *kref) +{ + struct amdgpu_task_info *ti = container_of(kref, struct amdgpu_task_info, refcount); + + kfree(ti); +} + +static inline struct amdgpu_vm * +amdgpu_vm_get_vm_from_pasid(struct amdgpu_device *adev, u32 pasid) +{ + struct amdgpu_vm *vm; + unsigned long flags; + + spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags); + vm = idr_find(&adev->vm_manager.pasid_idr, pasid); + spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags); + + return vm; +} + +/** + * amdgpu_vm_put_task_info - reference down the vm task_info ptr + * + * @task_info: task_info struct under discussion. + * + * frees the vm task_info ptr at the last put + */ +void amdgpu_vm_put_task_info(struct amdgpu_task_info *task_info) +{ + kref_put(&task_info->refcount, amdgpu_vm_destroy_task_info); +} + +/** + * amdgpu_vm_get_task_info_vm - Extracts task info for a vm. + * + * @vm: VM to get info from + * + * Returns the reference counted task_info structure, which must be + * referenced down with amdgpu_vm_put_task_info. + */ +struct amdgpu_task_info * +amdgpu_vm_get_task_info_vm(struct amdgpu_vm *vm) +{ + struct amdgpu_task_info *ti = NULL; + + if (vm) { + ti = vm->task_info; + kref_get(&vm->task_info->refcount); + } + + return ti; +} + +/** + * amdgpu_vm_get_task_info_pasid - Extracts task info for a PASID. + * + * @adev: drm device pointer + * @pasid: PASID identifier for VM + * + * Returns the reference counted task_info structure, which must be + * referenced down with amdgpu_vm_put_task_info. + */ +struct amdgpu_task_info * +amdgpu_vm_get_task_info_pasid(struct amdgpu_device *adev, u32 pasid) +{ + return amdgpu_vm_get_task_info_vm( + amdgpu_vm_get_vm_from_pasid(adev, pasid)); +} + +static int amdgpu_vm_create_task_info(struct amdgpu_vm *vm) +{ + vm->task_info = kzalloc(sizeof(struct amdgpu_task_info), GFP_KERNEL); + if (!vm->task_info) + return -ENOMEM; + + kref_init(&vm->task_info->refcount); + return 0; +} + +/** + * amdgpu_vm_set_task_info - Sets VMs task info. + * + * @vm: vm for which to set the info + */ +void amdgpu_vm_set_task_info(struct amdgpu_vm *vm) +{ + if (!vm->task_info) + return; + + if (vm->task_info->pid == current->pid) + return; + + vm->task_info->pid = current->pid; + get_task_comm(vm->task_info->task_name, current); + + if (current->group_leader->mm != current->mm) + return; + + vm->task_info->tgid = current->group_leader->pid; + get_task_comm(vm->task_info->process_name, current->group_leader); +} + /** * amdgpu_vm_init - initialize a vm instance * @@ -2894,6 +3000,10 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (r) goto error_unreserve; + r = amdgpu_vm_create_task_info(vm); + if (r) + DRM_DEBUG("Failed to create task info for VM\n"); + amdgpu_bo_unreserve(vm->root.base.bo); if (pasid) { @@ -3121,6 +3231,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) root = amdgpu_bo_ref(vm->root.base.bo); amdgpu_bo_reserve(root, true); + amdgpu_vm_put_task_info(vm->task_info); if (vm->pasid) { unsigned long flags; @@ -3281,48 +3392,6 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) return 0; } -/** - * amdgpu_vm_get_task_info - Extracts task info for a PASID. - * - * @adev: drm device pointer - * @pasid: PASID identifier for VM - * @task_info: task_info to fill. - */ -void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid, - struct amdgpu_task_info *task_info) -{ - struct amdgpu_vm *vm; - unsigned long flags; - - spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags); - - vm = idr_find(&adev->vm_manager.pasid_idr, pasid); - if (vm) - *task_info = vm->task_info; - - spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags); -} - -/** - * amdgpu_vm_set_task_info - Sets VMs task info. - * - * @vm: vm for which to set the info - */ -void amdgpu_vm_set_task_info(struct amdgpu_vm *vm) -{ - if (vm->task_info.pid) - return; - - vm->task_info.pid = current->pid; - get_task_comm(vm->task_info.task_name, current); - - if (current->group_leader->mm != current->mm) - return; - - vm->task_info.tgid = current->group_leader->pid; - get_task_comm(vm->task_info.process_name, current->group_leader); -} - /** * amdgpu_vm_handle_fault - graceful handling of VM faults. * @adev: amdgpu device pointer diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index c4218800e043..0e663464f1d6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -180,10 +180,11 @@ struct amdgpu_vm_pte_funcs { }; struct amdgpu_task_info { - char process_name[TASK_COMM_LEN]; - char task_name[TASK_COMM_LEN]; - pid_t pid; - pid_t tgid; + char process_name[TASK_COMM_LEN]; + char task_name[TASK_COMM_LEN]; + pid_t pid; + pid_t tgid; + struct kref refcount; }; /** @@ -311,7 +312,7 @@ struct amdgpu_vm { uint64_t pd_phys_addr; /* Some basic info about the task */ - struct amdgpu_task_info task_info; + struct amdgpu_task_info *task_info; /* Store positions of group of BOs */ struct ttm_lru_bulk_move lru_bulk_move; @@ -431,8 +432,14 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring, struct amdgpu_job *job); void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev); -void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid, - struct amdgpu_task_info *task_info); +struct amdgpu_task_info * +amdgpu_vm_get_task_info_pasid(struct amdgpu_device *adev, u32 pasid); + +struct amdgpu_task_info * +amdgpu_vm_get_task_info_vm(struct amdgpu_vm *vm); + +void amdgpu_vm_put_task_info(struct amdgpu_task_info *task_info); + bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, uint64_t addr); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 2aa9242c58ab..67d7ca92d95a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -114,18 +114,22 @@ static int gmc_v10_0_process_interrupt(struct amdgpu_device *adev, } if (printk_ratelimit()) { - struct amdgpu_task_info task_info; - - memset(&task_info, 0, sizeof(struct amdgpu_task_info)); - amdgpu_vm_get_task_info(adev, entry->pasid, &task_info); + struct amdgpu_task_info *task_info; dev_err(adev->dev, - "[%s] page fault (src_id:%u ring:%u vmid:%u pasid:%u, " - "for process %s pid %d thread %s pid %d)\n", + "[%s] page fault (src_id:%u ring:%u vmid:%u pasid:%u)\n", entry->vmid_src ? "mmhub" : "gfxhub", - entry->src_id, entry->ring_id, entry->vmid, - entry->pasid, task_info.process_name, task_info.tgid, - task_info.task_name, task_info.pid); + entry->src_id, entry->ring_id, entry->vmid, entry->pasid); + + task_info = amdgpu_vm_get_task_info_pasid(adev, entry->pasid); + if (task_info) { + dev_err(adev->dev, + " in process %s pid %d thread %s pid %d\n", + task_info->process_name, task_info->tgid, + task_info->task_name, task_info->pid); + amdgpu_vm_put_task_info(task_info); + } + dev_err(adev->dev, " in page starting at address 0x%016llx from client %d\n", addr, entry->client_id); if (!amdgpu_sriov_vf(adev)) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 873bc33912e2..a7d80bdec5c0 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -1469,18 +1469,24 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev, gmc_v8_0_set_fault_enable_default(adev, false); if (printk_ratelimit()) { - struct amdgpu_task_info task_info; + struct amdgpu_task_info *task_info; - memset(&task_info, 0, sizeof(struct amdgpu_task_info)); - amdgpu_vm_get_task_info(adev, entry->pasid, &task_info); + dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n", + entry->src_id, entry->src_data[0]); + + task_info = amdgpu_vm_get_task_info_pasid(adev, entry->pasid); + if (task_info) { + dev_err(adev->dev, " for process %s pid %d thread %s pid %d\n", + task_info->process_name, task_info->tgid, + task_info->task_name, task_info->pid); + amdgpu_vm_put_task_info(task_info); + } - dev_err(adev->dev, "GPU fault detected: %d 0x%08x for process %s pid %d thread %s pid %d\n", - entry->src_id, entry->src_data[0], task_info.process_name, - task_info.tgid, task_info.task_name, task_info.pid); dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n", - addr); + addr); dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n", status); + gmc_v8_0_vm_decode_fault(adev, status, addr, mc_client, entry->pasid); } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 1673bf3bae55..6fd785c435e5 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -561,18 +561,22 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev, } if (printk_ratelimit()) { - struct amdgpu_task_info task_info; - - memset(&task_info, 0, sizeof(struct amdgpu_task_info)); - amdgpu_vm_get_task_info(adev, entry->pasid, &task_info); + struct amdgpu_task_info *task_info; dev_err(adev->dev, - "[%s] %s page fault (src_id:%u ring:%u vmid:%u " - "pasid:%u, for process %s pid %d thread %s pid %d)\n", - hub_name, retry_fault ? "retry" : "no-retry", - entry->src_id, entry->ring_id, entry->vmid, - entry->pasid, task_info.process_name, task_info.tgid, - task_info.task_name, task_info.pid); + "[%s] %s page fault (src_id:%u ring:%u vmid:%u pasid:%u)\n", hub_name, + retry_fault ? "retry" : "no-retry", + entry->src_id, entry->ring_id, entry->vmid, entry->pasid); + + task_info = amdgpu_vm_get_task_info_pasid(adev, entry->pasid); + if (task_info) { + dev_err(adev->dev, + " for process %s pid %d thread %s pid %d)\n", + task_info->process_name, task_info->tgid, + task_info->task_name, task_info->pid); + amdgpu_vm_put_task_info(task_info); + } + dev_err(adev->dev, " in page starting at address 0x%016llx from client %d\n", addr, entry->client_id); if (!amdgpu_sriov_vf(adev)) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c index bd4caa36ab2e..a79a5da24392 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c @@ -231,7 +231,7 @@ void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev, void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid) { struct amdgpu_device *adev = (struct amdgpu_device *)dev->kgd; - struct amdgpu_task_info task_info; + struct amdgpu_task_info *task_info; /* VmFault msg = (hex)uint32_pid(8) + :(1) + task name(16) = 25 */ /* 1 byte event + 1 byte space + 25 bytes msg + 1 byte \n + * 1 byte \0 = 29 @@ -242,14 +242,20 @@ void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid) if (list_empty(&dev->smi_clients)) return; - memset(&task_info, 0, sizeof(struct amdgpu_task_info)); - amdgpu_vm_get_task_info(adev, pasid, &task_info); + task_info = amdgpu_vm_get_task_info_pasid(adev, pasid); + if (!task_info) + return; + /* Report VM faults from user applications, not retry from kernel */ - if (!task_info.pid) + if (!task_info->pid) { + amdgpu_vm_put_task_info(task_info); return; + } - len = snprintf(fifo_in, sizeof(fifo_in), "%x %x:%s\n", KFD_SMI_EVENT_VMFAULT, - task_info.pid, task_info.task_name); + len = snprintf(fifo_in, sizeof(fifo_in), "%x %x:%s\n", + KFD_SMI_EVENT_VMFAULT, task_info->pid, + task_info->task_name); + amdgpu_vm_put_task_info(task_info); add_event_to_kfifo(dev, KFD_SMI_EVENT_VMFAULT, fifo_in, len); } -- 2.17.1

2 1

[PATCH OLK-5.10] drm/amdgpu: change vm->task_info handling
by Guo Mengqi 22 Aug '24

22 Aug '24

From: Shashank Sharma <shashank.sharma(a)amd.com> mainline inclusion from mainline-v6.9-rc1 commit b8f67b9ddf4f8fe6dd536590712b5912ad78f99c category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IADDFV CVE: CVE-2024-41008 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ----------------------------------------------------------- This patch changes the handling and lifecycle of vm->task_info object. The major changes are: - vm->task_info is a dynamically allocated ptr now, and its uasge is reference counted. - introducing two new helper funcs for task_info lifecycle management - amdgpu_vm_get_task_info: reference counts up task_info before returning this info - amdgpu_vm_put_task_info: reference counts down task_info - last put to task_info() frees task_info from the vm. This patch also does logistical changes required for existing usage of vm->task_info. V2: Do not block all the prints when task_info not found (Felix) V3: Fixed review comments from Felix - Fix wrong indentation - No debug message for -ENOMEM - Add NULL check for task_info - Do not duplicate the debug messages (ti vs no ti) - Get first reference of task_info in vm_init(), put last in vm_fini() V4: Fixed review comments from Felix - fix double reference increment in create_task_info - change amdgpu_vm_get_task_info_pasid - additional changes in amdgpu_gem.c while porting Cc: Christian Koenig <christian.koenig(a)amd.com> Cc: Alex Deucher <alexander.deucher(a)amd.com> Cc: Felix Kuehling <Felix.Kuehling(a)amd.com> Reviewed-by: Felix Kuehling <Felix.Kuehling(a)amd.com> Signed-off-by: Shashank Sharma <shashank.sharma(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Conflicts: drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c drivers/gpu/drm/amd/amdgpu/amdgpu_reset.c drivers/gpu/drm/amd/amdgpu/amdgpu_job.c [1. Some drivers does not use struct task_info, so they are no need to modify 2. use idr instead of xarray in amdgpu_vm_get_vm_from_pasid(), because there are no functional changes] Signed-off-by: Zhang Zekun <zhangzekun11(a)huawei.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 18 ++- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 161 ++++++++++++++------ drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 21 ++- drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 22 +-- drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c | 20 ++- drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 24 +-- drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c | 18 ++- 7 files changed, 191 insertions(+), 93 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c index dcfe8a3b03ff..d45e84faed00 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -32,11 +32,9 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job) { struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched); struct amdgpu_job *job = to_amdgpu_job(s_job); - struct amdgpu_task_info ti; + struct amdgpu_task_info *ti; struct amdgpu_device *adev = ring->adev; - memset(&ti, 0, sizeof(struct amdgpu_task_info)); - if (amdgpu_gpu_recovery && amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) { DRM_ERROR("ring %s timeout, but soft recovered\n", @@ -44,12 +42,16 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job) return; } - amdgpu_vm_get_task_info(ring->adev, job->pasid, &ti); DRM_ERROR("ring %s timeout, signaled seq=%u, emitted seq=%u\n", - job->base.sched->name, atomic_read(&ring->fence_drv.last_seq), - ring->fence_drv.sync_seq); - DRM_ERROR("Process information: process %s pid %d thread %s pid %d\n", - ti.process_name, ti.tgid, ti.task_name, ti.pid); + job->base.sched->name, atomic_read(&ring->fence_drv.last_seq), + ring->fence_drv.sync_seq); + + ti = amdgpu_vm_get_task_info_pasid(ring->adev, job->pasid); + if (ti) { + DRM_ERROR("Process information: process %s pid %d thread %s pid %d\n", + ti->process_name, ti->tgid, ti->task_name, ti->pid); + amdgpu_vm_put_task_info(ti); + } if (amdgpu_device_should_recover_gpu(ring->adev)) { amdgpu_device_gpu_recover(ring->adev, job); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index ad3de971a087..a05eb8f393dc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1525,16 +1525,20 @@ static int amdgpu_vm_update_ptes(struct amdgpu_vm_update_params *params, uint64_t upd_end = min(entry_end, frag_end); unsigned nptes = (upd_end - frag_start) >> shift; uint64_t upd_flags = flags | AMDGPU_PTE_FRAG(frag); + struct amdgpu_task_info *ti = amdgpu_vm_get_task_info_vm(vm); /* This can happen when we set higher level PDs to * silent to stop fault floods. */ nptes = max(nptes, 1u); - trace_amdgpu_vm_update_ptes(params, frag_start, upd_end, - nptes, dst, incr, upd_flags, - vm->task_info.pid, - vm->immediate.fence_context); + if (ti) { + trace_amdgpu_vm_update_ptes(params, frag_start, upd_end, + nptes, dst, incr, upd_flags, + ti->pid, + vm->immediate.fence_context); + amdgpu_vm_put_task_info(ti); + } amdgpu_vm_update_flags(params, pt, cursor.level, pe_start, dst, nptes, incr, upd_flags); @@ -2819,6 +2823,108 @@ long amdgpu_vm_wait_idle(struct amdgpu_vm *vm, long timeout) return dma_fence_wait_timeout(vm->last_unlocked, true, timeout); } +static void amdgpu_vm_destroy_task_info(struct kref *kref) +{ + struct amdgpu_task_info *ti = container_of(kref, struct amdgpu_task_info, refcount); + + kfree(ti); +} + +static inline struct amdgpu_vm * +amdgpu_vm_get_vm_from_pasid(struct amdgpu_device *adev, u32 pasid) +{ + struct amdgpu_vm *vm; + unsigned long flags; + + spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags); + vm = idr_find(&adev->vm_manager.pasid_idr, pasid); + spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags); + + return vm; +} + +/** + * amdgpu_vm_put_task_info - reference down the vm task_info ptr + * + * @task_info: task_info struct under discussion. + * + * frees the vm task_info ptr at the last put + */ +void amdgpu_vm_put_task_info(struct amdgpu_task_info *task_info) +{ + kref_put(&task_info->refcount, amdgpu_vm_destroy_task_info); +} + +/** + * amdgpu_vm_get_task_info_vm - Extracts task info for a vm. + * + * @vm: VM to get info from + * + * Returns the reference counted task_info structure, which must be + * referenced down with amdgpu_vm_put_task_info. + */ +struct amdgpu_task_info * +amdgpu_vm_get_task_info_vm(struct amdgpu_vm *vm) +{ + struct amdgpu_task_info *ti = NULL; + + if (vm) { + ti = vm->task_info; + kref_get(&vm->task_info->refcount); + } + + return ti; +} + +/** + * amdgpu_vm_get_task_info_pasid - Extracts task info for a PASID. + * + * @adev: drm device pointer + * @pasid: PASID identifier for VM + * + * Returns the reference counted task_info structure, which must be + * referenced down with amdgpu_vm_put_task_info. + */ +struct amdgpu_task_info * +amdgpu_vm_get_task_info_pasid(struct amdgpu_device *adev, u32 pasid) +{ + return amdgpu_vm_get_task_info_vm( + amdgpu_vm_get_vm_from_pasid(adev, pasid)); +} + +static int amdgpu_vm_create_task_info(struct amdgpu_vm *vm) +{ + vm->task_info = kzalloc(sizeof(struct amdgpu_task_info), GFP_KERNEL); + if (!vm->task_info) + return -ENOMEM; + + kref_init(&vm->task_info->refcount); + return 0; +} + +/** + * amdgpu_vm_set_task_info - Sets VMs task info. + * + * @vm: vm for which to set the info + */ +void amdgpu_vm_set_task_info(struct amdgpu_vm *vm) +{ + if (!vm->task_info) + return; + + if (vm->task_info->pid == current->pid) + return; + + vm->task_info->pid = current->pid; + get_task_comm(vm->task_info->task_name, current); + + if (current->group_leader->mm != current->mm) + return; + + vm->task_info->tgid = current->group_leader->pid; + get_task_comm(vm->task_info->process_name, current->group_leader); +} + /** * amdgpu_vm_init - initialize a vm instance * @@ -2914,6 +3020,10 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm, if (r) goto error_unreserve; + r = amdgpu_vm_create_task_info(vm); + if (r) + DRM_DEBUG("Failed to create task info for VM\n"); + amdgpu_bo_unreserve(vm->root.base.bo); if (pasid) { @@ -3141,6 +3251,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm) root = amdgpu_bo_ref(vm->root.base.bo); amdgpu_bo_reserve(root, true); + amdgpu_vm_put_task_info(vm->task_info); if (vm->pasid) { unsigned long flags; @@ -3309,48 +3420,6 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) return 0; } -/** - * amdgpu_vm_get_task_info - Extracts task info for a PASID. - * - * @adev: drm device pointer - * @pasid: PASID identifier for VM - * @task_info: task_info to fill. - */ -void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid, - struct amdgpu_task_info *task_info) -{ - struct amdgpu_vm *vm; - unsigned long flags; - - spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags); - - vm = idr_find(&adev->vm_manager.pasid_idr, pasid); - if (vm) - *task_info = vm->task_info; - - spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags); -} - -/** - * amdgpu_vm_set_task_info - Sets VMs task info. - * - * @vm: vm for which to set the info - */ -void amdgpu_vm_set_task_info(struct amdgpu_vm *vm) -{ - if (vm->task_info.pid) - return; - - vm->task_info.pid = current->pid; - get_task_comm(vm->task_info.task_name, current); - - if (current->group_leader->mm != current->mm) - return; - - vm->task_info.tgid = current->group_leader->pid; - get_task_comm(vm->task_info.process_name, current->group_leader); -} - /** * amdgpu_vm_handle_fault - graceful handling of VM faults. * @adev: amdgpu device pointer diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index c4218800e043..0e663464f1d6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -180,10 +180,11 @@ struct amdgpu_vm_pte_funcs { }; struct amdgpu_task_info { - char process_name[TASK_COMM_LEN]; - char task_name[TASK_COMM_LEN]; - pid_t pid; - pid_t tgid; + char process_name[TASK_COMM_LEN]; + char task_name[TASK_COMM_LEN]; + pid_t pid; + pid_t tgid; + struct kref refcount; }; /** @@ -311,7 +312,7 @@ struct amdgpu_vm { uint64_t pd_phys_addr; /* Some basic info about the task */ - struct amdgpu_task_info task_info; + struct amdgpu_task_info *task_info; /* Store positions of group of BOs */ struct ttm_lru_bulk_move lru_bulk_move; @@ -431,8 +432,14 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring, struct amdgpu_job *job); void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev); -void amdgpu_vm_get_task_info(struct amdgpu_device *adev, u32 pasid, - struct amdgpu_task_info *task_info); +struct amdgpu_task_info * +amdgpu_vm_get_task_info_pasid(struct amdgpu_device *adev, u32 pasid); + +struct amdgpu_task_info * +amdgpu_vm_get_task_info_vm(struct amdgpu_vm *vm); + +void amdgpu_vm_put_task_info(struct amdgpu_task_info *task_info); + bool amdgpu_vm_handle_fault(struct amdgpu_device *adev, u32 pasid, uint64_t addr); diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 2aa9242c58ab..67d7ca92d95a 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -114,18 +114,22 @@ static int gmc_v10_0_process_interrupt(struct amdgpu_device *adev, } if (printk_ratelimit()) { - struct amdgpu_task_info task_info; - - memset(&task_info, 0, sizeof(struct amdgpu_task_info)); - amdgpu_vm_get_task_info(adev, entry->pasid, &task_info); + struct amdgpu_task_info *task_info; dev_err(adev->dev, - "[%s] page fault (src_id:%u ring:%u vmid:%u pasid:%u, " - "for process %s pid %d thread %s pid %d)\n", + "[%s] page fault (src_id:%u ring:%u vmid:%u pasid:%u)\n", entry->vmid_src ? "mmhub" : "gfxhub", - entry->src_id, entry->ring_id, entry->vmid, - entry->pasid, task_info.process_name, task_info.tgid, - task_info.task_name, task_info.pid); + entry->src_id, entry->ring_id, entry->vmid, entry->pasid); + + task_info = amdgpu_vm_get_task_info_pasid(adev, entry->pasid); + if (task_info) { + dev_err(adev->dev, + " in process %s pid %d thread %s pid %d\n", + task_info->process_name, task_info->tgid, + task_info->task_name, task_info->pid); + amdgpu_vm_put_task_info(task_info); + } + dev_err(adev->dev, " in page starting at address 0x%016llx from client %d\n", addr, entry->client_id); if (!amdgpu_sriov_vf(adev)) diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 873bc33912e2..a7d80bdec5c0 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -1469,18 +1469,24 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev, gmc_v8_0_set_fault_enable_default(adev, false); if (printk_ratelimit()) { - struct amdgpu_task_info task_info; + struct amdgpu_task_info *task_info; - memset(&task_info, 0, sizeof(struct amdgpu_task_info)); - amdgpu_vm_get_task_info(adev, entry->pasid, &task_info); + dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n", + entry->src_id, entry->src_data[0]); + + task_info = amdgpu_vm_get_task_info_pasid(adev, entry->pasid); + if (task_info) { + dev_err(adev->dev, " for process %s pid %d thread %s pid %d\n", + task_info->process_name, task_info->tgid, + task_info->task_name, task_info->pid); + amdgpu_vm_put_task_info(task_info); + } - dev_err(adev->dev, "GPU fault detected: %d 0x%08x for process %s pid %d thread %s pid %d\n", - entry->src_id, entry->src_data[0], task_info.process_name, - task_info.tgid, task_info.task_name, task_info.pid); dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_ADDR 0x%08X\n", - addr); + addr); dev_err(adev->dev, " VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n", status); + gmc_v8_0_vm_decode_fault(adev, status, addr, mc_client, entry->pasid); } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 945cbdbc2f99..41f0075c70a9 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -561,18 +561,22 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev, } if (printk_ratelimit()) { - struct amdgpu_task_info task_info; - - memset(&task_info, 0, sizeof(struct amdgpu_task_info)); - amdgpu_vm_get_task_info(adev, entry->pasid, &task_info); + struct amdgpu_task_info *task_info; dev_err(adev->dev, - "[%s] %s page fault (src_id:%u ring:%u vmid:%u " - "pasid:%u, for process %s pid %d thread %s pid %d)\n", - hub_name, retry_fault ? "retry" : "no-retry", - entry->src_id, entry->ring_id, entry->vmid, - entry->pasid, task_info.process_name, task_info.tgid, - task_info.task_name, task_info.pid); + "[%s] %s page fault (src_id:%u ring:%u vmid:%u pasid:%u)\n", hub_name, + retry_fault ? "retry" : "no-retry", + entry->src_id, entry->ring_id, entry->vmid, entry->pasid); + + task_info = amdgpu_vm_get_task_info_pasid(adev, entry->pasid); + if (task_info) { + dev_err(adev->dev, + " for process %s pid %d thread %s pid %d)\n", + task_info->process_name, task_info->tgid, + task_info->task_name, task_info->pid); + amdgpu_vm_put_task_info(task_info); + } + dev_err(adev->dev, " in page starting at address 0x%016llx from client %d\n", addr, entry->client_id); if (!amdgpu_sriov_vf(adev)) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c index bd4caa36ab2e..a79a5da24392 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_smi_events.c @@ -231,7 +231,7 @@ void kfd_smi_event_update_thermal_throttling(struct kfd_dev *dev, void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid) { struct amdgpu_device *adev = (struct amdgpu_device *)dev->kgd; - struct amdgpu_task_info task_info; + struct amdgpu_task_info *task_info; /* VmFault msg = (hex)uint32_pid(8) + :(1) + task name(16) = 25 */ /* 1 byte event + 1 byte space + 25 bytes msg + 1 byte \n + * 1 byte \0 = 29 @@ -242,14 +242,20 @@ void kfd_smi_event_update_vmfault(struct kfd_dev *dev, uint16_t pasid) if (list_empty(&dev->smi_clients)) return; - memset(&task_info, 0, sizeof(struct amdgpu_task_info)); - amdgpu_vm_get_task_info(adev, pasid, &task_info); + task_info = amdgpu_vm_get_task_info_pasid(adev, pasid); + if (!task_info) + return; + /* Report VM faults from user applications, not retry from kernel */ - if (!task_info.pid) + if (!task_info->pid) { + amdgpu_vm_put_task_info(task_info); return; + } - len = snprintf(fifo_in, sizeof(fifo_in), "%x %x:%s\n", KFD_SMI_EVENT_VMFAULT, - task_info.pid, task_info.task_name); + len = snprintf(fifo_in, sizeof(fifo_in), "%x %x:%s\n", + KFD_SMI_EVENT_VMFAULT, task_info->pid, + task_info->task_name); + amdgpu_vm_put_task_info(task_info); add_event_to_kfifo(dev, KFD_SMI_EVENT_VMFAULT, fifo_in, len); } -- 2.17.1

2 1

[PATCH OLK-5.10] scsi: mpt3sas: Avoid test/set_bit() operating in non-allocated memory
by Guo Mengqi 22 Aug '24

22 Aug '24

From: Breno Leitao <leitao(a)debian.org> stable inclusion from stable-v5.10.221 commit 0081d2b3ae0a17a86b8cc0fa3c8bdc54e233ba16 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IACZL6 CVE: CVE-2024-40901 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 4254dfeda82f20844299dca6c38cbffcfd499f41 upstream. There is a potential out-of-bounds access when using test_bit() on a single word. The test_bit() and set_bit() functions operate on long values, and when testing or setting a single word, they can exceed the word boundary. KASAN detects this issue and produces a dump: BUG: KASAN: slab-out-of-bounds in _scsih_add_device.constprop.0 (./arch/x86/include/asm/bitops.h:60 ./include/asm-generic/bitops/instrumented-atomic.h:29 drivers/scsi/mpt3sas/mpt3sas_scsih.c:7331) mpt3sas Write of size 8 at addr ffff8881d26e3c60 by task kworker/u1536:2/2965 For full log, please look at [1]. Make the allocation at least the size of sizeof(unsigned long) so that set_bit() and test_bit() have sufficient room for read/write operations without overwriting unallocated memory. [1] Link: https://lore.kernel.org/all/ZkNcALr3W3KGYYJG@gmail.com/ Fixes: c696f7b83ede ("scsi: mpt3sas: Implement device_remove_in_progress check in IOCTL path") Cc: stable(a)vger.kernel.org Suggested-by: Keith Busch <kbusch(a)kernel.org> Signed-off-by: Breno Leitao <leitao(a)debian.org> Link: https://lore.kernel.org/r/20240605085530.499432-1-leitao@debian.org Reviewed-by: Keith Busch <kbusch(a)kernel.org> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Wang Wensheng <wangwensheng4(a)huawei.com> --- drivers/scsi/mpt3sas/mpt3sas_base.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 55200f5db150..04c0b2fb65d5 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -7440,6 +7440,12 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc) ioc->pd_handles_sz = (ioc->facts.MaxDevHandle / 8); if (ioc->facts.MaxDevHandle % 8) ioc->pd_handles_sz++; + /* + * pd_handles_sz should have, at least, the minimal room for + * set_bit()/test_bit(), otherwise out-of-memory touch may occur. + */ + ioc->pd_handles_sz = ALIGN(ioc->pd_handles_sz, sizeof(unsigned long)); + ioc->pd_handles = kzalloc(ioc->pd_handles_sz, GFP_KERNEL); if (!ioc->pd_handles) { @@ -7457,6 +7463,13 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc) ioc->pend_os_device_add_sz = (ioc->facts.MaxDevHandle / 8); if (ioc->facts.MaxDevHandle % 8) ioc->pend_os_device_add_sz++; + + /* + * pend_os_device_add_sz should have, at least, the minimal room for + * set_bit()/test_bit(), otherwise out-of-memory may occur. + */ + ioc->pend_os_device_add_sz = ALIGN(ioc->pend_os_device_add_sz, + sizeof(unsigned long)); ioc->pend_os_device_add = kzalloc(ioc->pend_os_device_add_sz, GFP_KERNEL); if (!ioc->pend_os_device_add) { @@ -7747,6 +7760,12 @@ _base_check_ioc_facts_changes(struct MPT3SAS_ADAPTER *ioc) if (ioc->facts.MaxDevHandle % 8) pd_handles_sz++; + /* + * pd_handles should have, at least, the minimal room for + * set_bit()/test_bit(), otherwise out-of-memory touch may + * occur. + */ + pd_handles_sz = ALIGN(pd_handles_sz, sizeof(unsigned long)); pd_handles = krealloc(ioc->pd_handles, pd_handles_sz, GFP_KERNEL); if (!pd_handles) { -- 2.17.1

2 1

[PATCH openEuler-22.03-LTS-SP1] scsi: mpt3sas: Avoid test/set_bit() operating in non-allocated memory
by Guo Mengqi 22 Aug '24

22 Aug '24

From: Breno Leitao <leitao(a)debian.org> stable inclusion from stable-v5.10.221 commit 0081d2b3ae0a17a86b8cc0fa3c8bdc54e233ba16 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IACZL6 CVE: CVE-2024-40901 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 4254dfeda82f20844299dca6c38cbffcfd499f41 upstream. There is a potential out-of-bounds access when using test_bit() on a single word. The test_bit() and set_bit() functions operate on long values, and when testing or setting a single word, they can exceed the word boundary. KASAN detects this issue and produces a dump: BUG: KASAN: slab-out-of-bounds in _scsih_add_device.constprop.0 (./arch/x86/include/asm/bitops.h:60 ./include/asm-generic/bitops/instrumented-atomic.h:29 drivers/scsi/mpt3sas/mpt3sas_scsih.c:7331) mpt3sas Write of size 8 at addr ffff8881d26e3c60 by task kworker/u1536:2/2965 For full log, please look at [1]. Make the allocation at least the size of sizeof(unsigned long) so that set_bit() and test_bit() have sufficient room for read/write operations without overwriting unallocated memory. [1] Link: https://lore.kernel.org/all/ZkNcALr3W3KGYYJG@gmail.com/ Fixes: c696f7b83ede ("scsi: mpt3sas: Implement device_remove_in_progress check in IOCTL path") Cc: stable(a)vger.kernel.org Suggested-by: Keith Busch <kbusch(a)kernel.org> Signed-off-by: Breno Leitao <leitao(a)debian.org> Link: https://lore.kernel.org/r/20240605085530.499432-1-leitao@debian.org Reviewed-by: Keith Busch <kbusch(a)kernel.org> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Wang Wensheng <wangwensheng4(a)huawei.com> --- drivers/scsi/mpt3sas/mpt3sas_base.c | 19 +++++++++++++++++++ 1 file changed, 19 insertions(+) diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 55200f5db150..04c0b2fb65d5 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -7440,6 +7440,12 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc) ioc->pd_handles_sz = (ioc->facts.MaxDevHandle / 8); if (ioc->facts.MaxDevHandle % 8) ioc->pd_handles_sz++; + /* + * pd_handles_sz should have, at least, the minimal room for + * set_bit()/test_bit(), otherwise out-of-memory touch may occur. + */ + ioc->pd_handles_sz = ALIGN(ioc->pd_handles_sz, sizeof(unsigned long)); + ioc->pd_handles = kzalloc(ioc->pd_handles_sz, GFP_KERNEL); if (!ioc->pd_handles) { @@ -7457,6 +7463,13 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc) ioc->pend_os_device_add_sz = (ioc->facts.MaxDevHandle / 8); if (ioc->facts.MaxDevHandle % 8) ioc->pend_os_device_add_sz++; + + /* + * pend_os_device_add_sz should have, at least, the minimal room for + * set_bit()/test_bit(), otherwise out-of-memory may occur. + */ + ioc->pend_os_device_add_sz = ALIGN(ioc->pend_os_device_add_sz, + sizeof(unsigned long)); ioc->pend_os_device_add = kzalloc(ioc->pend_os_device_add_sz, GFP_KERNEL); if (!ioc->pend_os_device_add) { @@ -7747,6 +7760,12 @@ _base_check_ioc_facts_changes(struct MPT3SAS_ADAPTER *ioc) if (ioc->facts.MaxDevHandle % 8) pd_handles_sz++; + /* + * pd_handles should have, at least, the minimal room for + * set_bit()/test_bit(), otherwise out-of-memory touch may + * occur. + */ + pd_handles_sz = ALIGN(pd_handles_sz, sizeof(unsigned long)); pd_handles = krealloc(ioc->pd_handles, pd_handles_sz, GFP_KERNEL); if (!pd_handles) { -- 2.17.1

2 1

[PATCH OLK-5.10] phonet: fix rtm_phonet_notify() skb allocation
by Guo Mengqi 22 Aug '24

22 Aug '24

From: Eric Dumazet <edumazet(a)google.com> mainline inclusion from mainline-v6.9 commit d8cac8568618dcb8a51af3db1103e8d4cc4aeea7 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9U4L2 CVE: CVE-2024-36946 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- fill_route() stores three components in the skb: - struct rtmsg - RTA_DST (u8) - RTA_OIF (u32) Therefore, rtm_phonet_notify() should use NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(1) + nla_total_size(4) Fixes: f062f41d0657 ("Phonet: routing table Netlink interface") Signed-off-by: Eric Dumazet <edumazet(a)google.com> Acked-by: Rémi Denis-Courmont <courmisch(a)gmail.com> Link: https://lore.kernel.org/r/20240502161700.1804476-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Wang Wensheng <wangwensheng4(a)huawei.com> --- net/phonet/pn_netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index 59aebe296890..dd4c7e9a634f 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -193,7 +193,7 @@ void rtm_phonet_notify(int event, struct net_device *dev, u8 dst) struct sk_buff *skb; int err = -ENOBUFS; - skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + + skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct rtmsg)) + nla_total_size(1) + nla_total_size(4), GFP_KERNEL); if (skb == NULL) goto errout; -- 2.17.1

2 1

[PATCH OLK-5.10] m68k: Fix spinlock race in kernel thread creation
by Guo Mengqi 22 Aug '24

22 Aug '24

From: Michael Schmitz <schmitzmic(a)gmail.com> stable inclusion from stable-v5.10.219 commit 4eeffecc8e3cce25bb559502c2fd94a948bcde82 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IA6SFZ CVE: CVE-2024-38613 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit da89ce46f02470ef08f0f580755d14d547da59ed ] Context switching does take care to retain the correct lock owner across the switch from 'prev' to 'next' tasks. This does rely on interrupts remaining disabled for the entire duration of the switch. This condition is guaranteed for normal process creation and context switching between already running processes, because both 'prev' and 'next' already have interrupts disabled in their saved copies of the status register. The situation is different for newly created kernel threads. The status register is set to PS_S in copy_thread(), which does leave the IPL at 0. Upon restoring the 'next' thread's status register in switch_to() aka resume(), interrupts then become enabled prematurely. resume() then returns via ret_from_kernel_thread() and schedule_tail() where run queue lock is released (see finish_task_switch() and finish_lock_switch()). A timer interrupt calling scheduler_tick() before the lock is released in finish_task_switch() will find the lock already taken, with the current task as lock owner. This causes a spinlock recursion warning as reported by Guenter Roeck. As far as I can ascertain, this race has been opened in commit 533e6903bea0 ("m68k: split ret_from_fork(), simplify kernel_thread()") but I haven't done a detailed study of kernel history so it may well predate that commit. Interrupts cannot be disabled in the saved status register copy for kernel threads (init will complain about interrupts disabled when finally starting user space). Disable interrupts temporarily when switching the tasks' register sets in resume(). Note that a simple oriw 0x700,%sr after restoring sr is not enough here - this leaves enough of a race for the 'spinlock recursion' warning to still be observed. Tested on ARAnyM and qemu (Quadra 800 emulation). Fixes: 533e6903bea0 ("m68k: split ret_from_fork(), simplify kernel_thread()") Reported-by: Guenter Roeck <linux(a)roeck-us.net> Closes: https://lore.kernel.org/all/07811b26-677c-4d05-aeb4-996cd880b789@roeck-us.n… Signed-off-by: Michael Schmitz <schmitzmic(a)gmail.com> Tested-by: Guenter Roeck <linux(a)roeck-us.net> Reviewed-by: Geert Uytterhoeven <geert(a)linux-m68k.org> Link: https://lore.kernel.org/r/20240411033631.16335-1-schmitzmic@gmail.com Signed-off-by: Geert Uytterhoeven <geert(a)linux-m68k.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Wensheng <wangwensheng4(a)huawei.com> --- arch/m68k/kernel/entry.S | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/m68k/kernel/entry.S b/arch/m68k/kernel/entry.S index 546bab6bfc27..d0ca4df43528 100644 --- a/arch/m68k/kernel/entry.S +++ b/arch/m68k/kernel/entry.S @@ -432,7 +432,9 @@ resume: movec %a0,%dfc /* restore status register */ - movew %a1@(TASK_THREAD+THREAD_SR),%sr + movew %a1@(TASK_THREAD+THREAD_SR),%d0 + oriw #0x0700,%d0 + movew %d0,%sr rts -- 2.17.1

2 1