March 2025 - Linux-stable-mirror

[PATCH v3] clocksource: stm32-lptimer: use wakeup capable instead of init wakeup

by Fabrice Gasnier

From: Alexandre Torgue <alexandre.torgue(a)foss.st.com> "wakeup-source" property describes a device which has wakeup capability but should not force this device as a wakeup source. Fixes: 48b41c5e2de6 ("clocksource: Add Low Power STM32 timers driver") Cc: stable(a)vger.kernel.org Signed-off-by: Alexandre Torgue <alexandre.torgue(a)foss.st.com> Signed-off-by: Fabrice Gasnier <fabrice.gasnier(a)foss.st.com> --- drivers/clocksource/timer-stm32-lp.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/clocksource/timer-stm32-lp.c b/drivers/clocksource/timer-stm32-lp.c index a4c95161cb22..193e4f643358 100644 --- a/drivers/clocksource/timer-stm32-lp.c +++ b/drivers/clocksource/timer-stm32-lp.c @@ -168,9 +168,7 @@ static int stm32_clkevent_lp_probe(struct platform_device *pdev) } if (of_property_read_bool(pdev->dev.parent->of_node, "wakeup-source")) { - ret = device_init_wakeup(&pdev->dev, true); - if (ret) - goto out_clk_disable; + device_set_wakeup_capable(&pdev->dev, true); ret = dev_pm_set_wake_irq(&pdev->dev, irq); if (ret) -- 2.25.1

9 months, 1 week

3
2
0 0

[PATCH v3] remoteproc: Add device awake calls in rproc boot and shutdown path

by Souradeep Chowdhury

Add device awake calls in case of rproc boot and rproc shutdown path. Currently, device awake call is only present in the recovery path of remoteproc. If a user stops and starts rproc by using the sysfs interface, then on pm suspension the firmware loading fails. Keep the device awake in such a case just like it is done for the recovery path. Fixes: a781e5aa59110 ("remoteproc: core: Prevent system suspend during remoteproc recovery") Signed-off-by: Souradeep Chowdhury <quic_schowdhu(a)quicinc.com> Cc: stable(a)vger.kernel.org --- Changes in v3 *Add the stability mailing list in commit message drivers/remoteproc/remoteproc_core.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/remoteproc/remoteproc_core.c b/drivers/remoteproc/remoteproc_core.c index c2cf0d277729..908a7b8f6c7e 100644 --- a/drivers/remoteproc/remoteproc_core.c +++ b/drivers/remoteproc/remoteproc_core.c @@ -1916,7 +1916,8 @@ int rproc_boot(struct rproc *rproc) pr_err("invalid rproc handle\n"); return -EINVAL; } - + + pm_stay_awake(rproc->dev.parent); dev = &rproc->dev; ret = mutex_lock_interruptible(&rproc->lock); @@ -1961,6 +1962,7 @@ int rproc_boot(struct rproc *rproc) atomic_dec(&rproc->power); unlock_mutex: mutex_unlock(&rproc->lock); + pm_relax(rproc->dev.parent); return ret; } EXPORT_SYMBOL(rproc_boot); @@ -1991,6 +1993,7 @@ int rproc_shutdown(struct rproc *rproc) struct device *dev = &rproc->dev; int ret = 0; + pm_stay_awake(rproc->dev.parent); ret = mutex_lock_interruptible(&rproc->lock); if (ret) { dev_err(dev, "can't lock rproc %s: %d\n", rproc->name, ret); @@ -2027,6 +2030,7 @@ int rproc_shutdown(struct rproc *rproc) rproc->table_ptr = NULL; out: mutex_unlock(&rproc->lock); + pm_relax(rproc->dev.parent); return ret; } EXPORT_SYMBOL(rproc_shutdown); -- 2.34.1

9 months, 1 week

2
2
0 0

[PATCH 5.15] net: defer final 'struct net' free in netns dismantle

by Vasiliy Kovalev

From: Eric Dumazet <edumazet(a)google.com> commit 0f6ede9fbc747e2553612271bce108f7517e7a45 upstream. Ilya reported a slab-use-after-free in dst_destroy [1] Issue is in xfrm6_net_init() and xfrm4_net_init() : They copy xfrm[46]_dst_ops_template into net->xfrm.xfrm[46]_dst_ops. But net structure might be freed before all the dst callbacks are called. So when dst_destroy() calls later : if (dst->ops->destroy) dst->ops->destroy(dst); dst->ops points to the old net->xfrm.xfrm[46]_dst_ops, which has been freed. See a relevant issue fixed in : ac888d58869b ("net: do not delay dst_entries_add() in dst_release()") A fix is to queue the 'struct net' to be freed after one another cleanup_net() round (and existing rcu_barrier()) [1] BUG: KASAN: slab-use-after-free in dst_destroy (net/core/dst.c:112) Read of size 8 at addr ffff8882137ccab0 by task swapper/37/0 Dec 03 05:46:18 kernel: CPU: 37 UID: 0 PID: 0 Comm: swapper/37 Kdump: loaded Not tainted 6.12.0 #67 Hardware name: Red Hat KVM/RHEL, BIOS 1.16.1-1.el9 04/01/2014 Call Trace: <IRQ> dump_stack_lvl (lib/dump_stack.c:124) print_address_description.constprop.0 (mm/kasan/report.c:378) ? dst_destroy (net/core/dst.c:112) print_report (mm/kasan/report.c:489) ? dst_destroy (net/core/dst.c:112) ? kasan_addr_to_slab (mm/kasan/common.c:37) kasan_report (mm/kasan/report.c:603) ? dst_destroy (net/core/dst.c:112) ? rcu_do_batch (kernel/rcu/tree.c:2567) dst_destroy (net/core/dst.c:112) rcu_do_batch (kernel/rcu/tree.c:2567) ? __pfx_rcu_do_batch (kernel/rcu/tree.c:2491) ? lockdep_hardirqs_on_prepare (kernel/locking/lockdep.c:4339 kernel/locking/lockdep.c:4406) rcu_core (kernel/rcu/tree.c:2825) handle_softirqs (kernel/softirq.c:554) __irq_exit_rcu (kernel/softirq.c:589 kernel/softirq.c:428 kernel/softirq.c:637) irq_exit_rcu (kernel/softirq.c:651) sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1049 arch/x86/kernel/apic/apic.c:1049) </IRQ> <TASK> asm_sysvec_apic_timer_interrupt (./arch/x86/include/asm/idtentry.h:702) RIP: 0010:default_idle (./arch/x86/include/asm/irqflags.h:37 ./arch/x86/include/asm/irqflags.h:92 arch/x86/kernel/process.c:743) Code: 00 4d 29 c8 4c 01 c7 4c 29 c2 e9 6e ff ff ff 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 66 90 0f 00 2d c7 c9 27 00 fb f4 <fa> c3 cc cc cc cc 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 90 RSP: 0018:ffff888100d2fe00 EFLAGS: 00000246 RAX: 00000000001870ed RBX: 1ffff110201a5fc2 RCX: ffffffffb61a3e46 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffffffb3d4d123 RBP: 0000000000000000 R08: 0000000000000001 R09: ffffed11c7e1835d R10: ffff888e3f0c1aeb R11: 0000000000000000 R12: 0000000000000000 R13: ffff888100d20000 R14: dffffc0000000000 R15: 0000000000000000 ? ct_kernel_exit.constprop.0 (kernel/context_tracking.c:148) ? cpuidle_idle_call (kernel/sched/idle.c:186) default_idle_call (./include/linux/cpuidle.h:143 kernel/sched/idle.c:118) cpuidle_idle_call (kernel/sched/idle.c:186) ? __pfx_cpuidle_idle_call (kernel/sched/idle.c:168) ? lock_release (kernel/locking/lockdep.c:467 kernel/locking/lockdep.c:5848) ? lockdep_hardirqs_on_prepare (kernel/locking/lockdep.c:4347 kernel/locking/lockdep.c:4406) ? tsc_verify_tsc_adjust (arch/x86/kernel/tsc_sync.c:59) do_idle (kernel/sched/idle.c:326) cpu_startup_entry (kernel/sched/idle.c:423 (discriminator 1)) start_secondary (arch/x86/kernel/smpboot.c:202 arch/x86/kernel/smpboot.c:282) ? __pfx_start_secondary (arch/x86/kernel/smpboot.c:232) ? soft_restart_cpu (arch/x86/kernel/head_64.S:452) common_startup_64 (arch/x86/kernel/head_64.S:414) </TASK> Dec 03 05:46:18 kernel: Allocated by task 12184: kasan_save_stack (mm/kasan/common.c:48) kasan_save_track (./arch/x86/include/asm/current.h:49 mm/kasan/common.c:60 mm/kasan/common.c:69) __kasan_slab_alloc (mm/kasan/common.c:319 mm/kasan/common.c:345) kmem_cache_alloc_noprof (mm/slub.c:4085 mm/slub.c:4134 mm/slub.c:4141) copy_net_ns (net/core/net_namespace.c:421 net/core/net_namespace.c:480) create_new_namespaces (kernel/nsproxy.c:110) unshare_nsproxy_namespaces (kernel/nsproxy.c:228 (discriminator 4)) ksys_unshare (kernel/fork.c:3313) __x64_sys_unshare (kernel/fork.c:3382) do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Dec 03 05:46:18 kernel: Freed by task 11: kasan_save_stack (mm/kasan/common.c:48) kasan_save_track (./arch/x86/include/asm/current.h:49 mm/kasan/common.c:60 mm/kasan/common.c:69) kasan_save_free_info (mm/kasan/generic.c:582) __kasan_slab_free (mm/kasan/common.c:271) kmem_cache_free (mm/slub.c:4579 mm/slub.c:4681) cleanup_net (net/core/net_namespace.c:456 net/core/net_namespace.c:446 net/core/net_namespace.c:647) process_one_work (kernel/workqueue.c:3229) worker_thread (kernel/workqueue.c:3304 kernel/workqueue.c:3391) kthread (kernel/kthread.c:389) ret_from_fork (arch/x86/kernel/process.c:147) ret_from_fork_asm (arch/x86/entry/entry_64.S:257) Dec 03 05:46:18 kernel: Last potentially related work creation: kasan_save_stack (mm/kasan/common.c:48) __kasan_record_aux_stack (mm/kasan/generic.c:541) insert_work (./include/linux/instrumented.h:68 ./include/asm-generic/bitops/instrumented-non-atomic.h:141 kernel/workqueue.c:788 kernel/workqueue.c:795 kernel/workqueue.c:2186) __queue_work (kernel/workqueue.c:2340) queue_work_on (kernel/workqueue.c:2391) xfrm_policy_insert (net/xfrm/xfrm_policy.c:1610) xfrm_add_policy (net/xfrm/xfrm_user.c:2116) xfrm_user_rcv_msg (net/xfrm/xfrm_user.c:3321) netlink_rcv_skb (net/netlink/af_netlink.c:2536) xfrm_netlink_rcv (net/xfrm/xfrm_user.c:3344) netlink_unicast (net/netlink/af_netlink.c:1316 net/netlink/af_netlink.c:1342) netlink_sendmsg (net/netlink/af_netlink.c:1886) sock_write_iter (net/socket.c:729 net/socket.c:744 net/socket.c:1165) vfs_write (fs/read_write.c:590 fs/read_write.c:683) ksys_write (fs/read_write.c:736) do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Dec 03 05:46:18 kernel: Second to last potentially related work creation: kasan_save_stack (mm/kasan/common.c:48) __kasan_record_aux_stack (mm/kasan/generic.c:541) insert_work (./include/linux/instrumented.h:68 ./include/asm-generic/bitops/instrumented-non-atomic.h:141 kernel/workqueue.c:788 kernel/workqueue.c:795 kernel/workqueue.c:2186) __queue_work (kernel/workqueue.c:2340) queue_work_on (kernel/workqueue.c:2391) __xfrm_state_insert (./include/linux/workqueue.h:723 net/xfrm/xfrm_state.c:1150 net/xfrm/xfrm_state.c:1145 net/xfrm/xfrm_state.c:1513) xfrm_state_update (./include/linux/spinlock.h:396 net/xfrm/xfrm_state.c:1940) xfrm_add_sa (net/xfrm/xfrm_user.c:912) xfrm_user_rcv_msg (net/xfrm/xfrm_user.c:3321) netlink_rcv_skb (net/netlink/af_netlink.c:2536) xfrm_netlink_rcv (net/xfrm/xfrm_user.c:3344) netlink_unicast (net/netlink/af_netlink.c:1316 net/netlink/af_netlink.c:1342) netlink_sendmsg (net/netlink/af_netlink.c:1886) sock_write_iter (net/socket.c:729 net/socket.c:744 net/socket.c:1165) vfs_write (fs/read_write.c:590 fs/read_write.c:683) ksys_write (fs/read_write.c:736) do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Fixes: a8a572a6b5f2 ("xfrm: dst_entries_init() per-net dst_ops") Reported-by: Ilya Maximets <i.maximets(a)ovn.org> Closes: https://lore.kernel.org/netdev/CANn89iKKYDVpB=MtmfH7nyv2p=rJWSLedO5k7wSZgtY… Signed-off-by: Eric Dumazet <edumazet(a)google.com> Acked-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Link: https://patch.msgid.link/20241204125455.3871859-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Vasiliy Kovalev <kovalev(a)altlinux.org> --- Backport to fix CVE-2024-56658 Link: https://www.cve.org/CVERecord/?id=CVE-2024-56658 --- include/net/net_namespace.h | 1 + net/core/net_namespace.c | 21 ++++++++++++++++++++- 2 files changed, 21 insertions(+), 1 deletion(-) diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index c47baa623ba586..a5d6e04c8e8b55 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -80,6 +80,7 @@ struct net { * or to unregister pernet ops * (pernet_ops_rwsem write locked). */ + struct llist_node defer_free_list; struct llist_node cleanup_list; /* namespaces on death row */ #ifdef CONFIG_KEYS diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 3addbce20f8ed0..0217dd2635cdb4 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -430,11 +430,28 @@ static struct net *net_alloc(void) goto out; } +static LLIST_HEAD(defer_free_list); + +static void net_complete_free(void) +{ + struct llist_node *kill_list; + struct net *net, *next; + + /* Get the list of namespaces to free from last round. */ + kill_list = llist_del_all(&defer_free_list); + + llist_for_each_entry_safe(net, next, kill_list, defer_free_list) + kmem_cache_free(net_cachep, net); + +} + static void net_free(struct net *net) { if (refcount_dec_and_test(&net->passive)) { kfree(rcu_access_pointer(net->gen)); - kmem_cache_free(net_cachep, net); + + /* Wait for an extra rcu_barrier() before final free. */ + llist_add(&net->defer_free_list, &defer_free_list); } } @@ -609,6 +626,8 @@ static void cleanup_net(struct work_struct *work) */ rcu_barrier(); + net_complete_free(); + /* Finally it is safe to free my network namespace structure */ list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { list_del_init(&net->exit_list); -- 2.33.8

9 months, 1 week

4
3
0 0

[PATCH v3 1/2] string: Add load_unaligned_zeropad() code path to sized_strscpy()

by Peter Collingbourne

The call to read_word_at_a_time() in sized_strscpy() is problematic with MTE because it may trigger a tag check fault when reading across a tag granule (16 bytes) boundary. To make this code MTE compatible, let's start using load_unaligned_zeropad() on architectures where it is available (i.e. architectures that define CONFIG_DCACHE_WORD_ACCESS). Because load_unaligned_zeropad() takes care of page boundaries as well as tag granule boundaries, also disable the code preventing crossing page boundaries when using load_unaligned_zeropad(). Signed-off-by: Peter Collingbourne <pcc(a)google.com> Link: https://linux-review.googlesource.com/id/If4b22e43b5a4ca49726b4bf98ada827fd… Fixes: 94ab5b61ee16 ("kasan, arm64: enable CONFIG_KASAN_HW_TAGS") Cc: stable(a)vger.kernel.org --- v2: - new approach lib/string.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/lib/string.c b/lib/string.c index eb4486ed40d25..b632c71df1a50 100644 --- a/lib/string.c +++ b/lib/string.c @@ -119,6 +119,7 @@ ssize_t sized_strscpy(char *dest, const char *src, size_t count) if (count == 0 || WARN_ON_ONCE(count > INT_MAX)) return -E2BIG; +#ifndef CONFIG_DCACHE_WORD_ACCESS #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS /* * If src is unaligned, don't cross a page boundary, @@ -133,12 +134,14 @@ ssize_t sized_strscpy(char *dest, const char *src, size_t count) /* If src or dest is unaligned, don't do word-at-a-time. */ if (((long) dest | (long) src) & (sizeof(long) - 1)) max = 0; +#endif #endif /* - * read_word_at_a_time() below may read uninitialized bytes after the - * trailing zero and use them in comparisons. Disable this optimization - * under KMSAN to prevent false positive reports. + * load_unaligned_zeropad() or read_word_at_a_time() below may read + * uninitialized bytes after the trailing zero and use them in + * comparisons. Disable this optimization under KMSAN to prevent + * false positive reports. */ if (IS_ENABLED(CONFIG_KMSAN)) max = 0; @@ -146,7 +149,11 @@ ssize_t sized_strscpy(char *dest, const char *src, size_t count) while (max >= sizeof(unsigned long)) { unsigned long c, data; +#ifdef CONFIG_DCACHE_WORD_ACCESS + c = load_unaligned_zeropad(src+res); +#else c = read_word_at_a_time(src+res); +#endif if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); -- 2.49.0.395.g12beb8f557-goog

9 months, 1 week

1
0
0 0

[for-next][PATCH 2/3] tracing: Fix use-after-free in print_graph_function_flags during tracer switching

by Steven Rostedt

From: Tengda Wu <wutengda(a)huaweicloud.com> Kairui reported a UAF issue in print_graph_function_flags() during ftrace stress testing [1]. This issue can be reproduced if puting a 'mdelay(10)' after 'mutex_unlock(&trace_types_lock)' in s_start(), and executing the following script: $ echo function_graph > current_tracer $ cat trace > /dev/null & $ sleep 5 # Ensure the 'cat' reaches the 'mdelay(10)' point $ echo timerlat > current_tracer The root cause lies in the two calls to print_graph_function_flags within print_trace_line during each s_show(): * One through 'iter->trace->print_line()'; * Another through 'event->funcs->trace()', which is hidden in print_trace_fmt() before print_trace_line returns. Tracer switching only updates the former, while the latter continues to use the print_line function of the old tracer, which in the script above is print_graph_function_flags. Moreover, when switching from the 'function_graph' tracer to the 'timerlat' tracer, s_start only calls graph_trace_close of the 'function_graph' tracer to free 'iter->private', but does not set it to NULL. This provides an opportunity for 'event->funcs->trace()' to use an invalid 'iter->private'. To fix this issue, set 'iter->private' to NULL immediately after freeing it in graph_trace_close(), ensuring that an invalid pointer is not passed to other tracers. Additionally, clean up the unnecessary 'iter->private = NULL' during each 'cat trace' when using wakeup and irqsoff tracers. [1] https://lore.kernel.org/all/20231112150030.84609-1-ryncsn@gmail.com/ Cc: stable(a)vger.kernel.org Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Zheng Yejian <zhengyejian1(a)huawei.com> Link: https://lore.kernel.org/20250320122137.23635-1-wutengda@huaweicloud.com Fixes: eecb91b9f98d ("tracing: Fix memleak due to race between current_tracer and trace") Closes: https://lore.kernel.org/all/CAMgjq7BW79KDSCyp+tZHjShSzHsScSiJxn5ffskp-QzVM0… Reported-by: Kairui Song <kasong(a)tencent.com> Signed-off-by: Tengda Wu <wutengda(a)huaweicloud.com> Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- kernel/trace/trace_functions_graph.c | 1 + kernel/trace/trace_irqsoff.c | 2 -- kernel/trace/trace_sched_wakeup.c | 2 -- 3 files changed, 1 insertion(+), 4 deletions(-) diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index ed61ff719aa4..2f077d4158e5 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -1611,6 +1611,7 @@ void graph_trace_close(struct trace_iterator *iter) if (data) { free_percpu(data->cpu_data); kfree(data); + iter->private = NULL; } } diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index c8bfa7310a91..40c39e946940 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -250,8 +250,6 @@ static void irqsoff_trace_open(struct trace_iterator *iter) { if (is_graph(iter->tr)) graph_trace_open(iter); - else - iter->private = NULL; } static void irqsoff_trace_close(struct trace_iterator *iter) diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index c9ba4259e03e..a0db3404f7f7 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -188,8 +188,6 @@ static void wakeup_trace_open(struct trace_iterator *iter) { if (is_graph(iter->tr)) graph_trace_open(iter); - else - iter->private = NULL; } static void wakeup_trace_close(struct trace_iterator *iter) -- 2.47.2

9 months, 1 week

1
0
0 0

[PATCH v2] mm: zswap: fix crypto_free_acomp() deadlock in zswap_cpu_comp_dead()

by Yosry Ahmed

Currently, zswap_cpu_comp_dead() calls crypto_free_acomp() while holding the per-CPU acomp_ctx mutex. crypto_free_acomp() then holds scomp_lock (through crypto_exit_scomp_ops_async()). On the other hand, crypto_alloc_acomp_node() holds the scomp_lock (through crypto_scomp_init_tfm()), and then allocates memory. If the allocation results in reclaim, we may attempt to hold the per-CPU acomp_ctx mutex. The above dependencies can cause an ABBA deadlock. For example in the following scenario: (1) Task A running on CPU #1: crypto_alloc_acomp_node() Holds scomp_lock Enters reclaim Reads per_cpu_ptr(pool->acomp_ctx, 1) (2) Task A is descheduled (3) CPU #1 goes offline zswap_cpu_comp_dead(CPU #1) Holds per_cpu_ptr(pool->acomp_ctx, 1)) Calls crypto_free_acomp() Waits for scomp_lock (4) Task A running on CPU #2: Waits for per_cpu_ptr(pool->acomp_ctx, 1) // Read on CPU #1 DEADLOCK Since there is no requirement to call crypto_free_acomp() with the per-CPU acomp_ctx mutex held in zswap_cpu_comp_dead(), move it after the mutex is unlocked. Also move the acomp_request_free() and kfree() calls for consistency and to avoid any potential sublte locking dependencies in the future. With this, only setting acomp_ctx fields to NULL occurs with the mutex held. This is similar to how zswap_cpu_comp_prepare() only initializes acomp_ctx fields with the mutex held, after performing all allocations before holding the mutex. Opportunistically, move the NULL check on acomp_ctx so that it takes place before the mutex dereference. Fixes: 12dcb0ef5406 ("mm: zswap: properly synchronize freeing resources during CPU hotunplug") Reported-by: syzbot+1a517ccfcbc6a7ab0f82(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/all/67bcea51.050a0220.bbfd1.0096.GAE@google.com/ Cc: <stable(a)vger.kernel.org> Co-developed-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: Yosry Ahmed <yosry.ahmed(a)linux.dev> Acked-by: Herbert Xu <herbert(a)gondor.apana.org.au> --- v1 -> v2: - Explained the problem more clearly in the commit message. - Moved all freeing calls outside the lock critical section. v1: https://lore.kernel.org/all/Z72FJnbA39zWh4zS@gondor.apana.org.au/ --- mm/zswap.c | 30 ++++++++++++++++++++++-------- 1 file changed, 22 insertions(+), 8 deletions(-) diff --git a/mm/zswap.c b/mm/zswap.c index ac9d299e7d0c1..adf745c66aa1d 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -881,18 +881,32 @@ static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node) { struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node); struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu); + struct acomp_req *req; + struct crypto_acomp *acomp; + u8 *buffer; + + if (IS_ERR_OR_NULL(acomp_ctx)) + return 0; mutex_lock(&acomp_ctx->mutex); - if (!IS_ERR_OR_NULL(acomp_ctx)) { - if (!IS_ERR_OR_NULL(acomp_ctx->req)) - acomp_request_free(acomp_ctx->req); - acomp_ctx->req = NULL; - if (!IS_ERR_OR_NULL(acomp_ctx->acomp)) - crypto_free_acomp(acomp_ctx->acomp); - kfree(acomp_ctx->buffer); - } + req = acomp_ctx->req; + acomp = acomp_ctx->acomp; + buffer = acomp_ctx->buffer; + acomp_ctx->req = NULL; + acomp_ctx->acomp = NULL; + acomp_ctx->buffer = NULL; mutex_unlock(&acomp_ctx->mutex); + /* + * Do the actual freeing after releasing the mutex to avoid subtle + * locking dependencies causing deadlocks. + */ + if (!IS_ERR_OR_NULL(req)) + acomp_request_free(req); + if (!IS_ERR_OR_NULL(acomp)) + crypto_free_acomp(acomp); + kfree(buffer); + return 0; } -- 2.48.1.658.g4767266eb4-goog

9 months, 1 week

4
10
0 0

FAILED: patch "[PATCH] Revert "sched/core: Reduce cost of sched_move_task when" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 76f970ce51c80f625eb6ddbb24e9cb51b977b598 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025032422-giblet-smelting-2a62@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 76f970ce51c80f625eb6ddbb24e9cb51b977b598 Mon Sep 17 00:00:00 2001 From: Dietmar Eggemann <dietmar.eggemann(a)arm.com> Date: Fri, 14 Mar 2025 16:13:45 +0100 Subject: [PATCH] Revert "sched/core: Reduce cost of sched_move_task when config autogroup" This reverts commit eff6c8ce8d4d7faef75f66614dd20bb50595d261. Hazem reported a 30% drop in UnixBench spawn test with commit eff6c8ce8d4d ("sched/core: Reduce cost of sched_move_task when config autogroup") on a m6g.xlarge AWS EC2 instance with 4 vCPUs and 16 GiB RAM (aarch64) (single level MC sched domain): https://lkml.kernel.org/r/20250205151026.13061-1-hagarhem@amazon.com There is an early bail from sched_move_task() if p->sched_task_group is equal to p's 'cpu cgroup' (sched_get_task_group()). E.g. both are pointing to taskgroup '/user.slice/user-1000.slice/session-1.scope' (Ubuntu '22.04.5 LTS'). So in: do_exit() sched_autogroup_exit_task() sched_move_task() if sched_get_task_group(p) == p->sched_task_group return /* p is enqueued */ dequeue_task() \ sched_change_group() | task_change_group_fair() | detach_task_cfs_rq() | (1) set_task_rq() | attach_task_cfs_rq() | enqueue_task() / (1) isn't called for p anymore. Turns out that the regression is related to sgs->group_util in group_is_overloaded() and group_has_capacity(). If (1) isn't called for all the 'spawn' tasks then sgs->group_util is ~900 and sgs->group_capacity = 1024 (single CPU sched domain) and this leads to group_is_overloaded() returning true (2) and group_has_capacity() false (3) much more often compared to the case when (1) is called. I.e. there are much more cases of 'group_is_overloaded' and 'group_fully_busy' in WF_FORK wakeup sched_balance_find_dst_cpu() which then returns much more often a CPU != smp_processor_id() (5). This isn't good for these extremely short running tasks (FORK + EXIT) and also involves calling sched_balance_find_dst_group_cpu() unnecessary (single CPU sched domain). Instead if (1) is called for 'p->flags & PF_EXITING' then the path (4),(6) is taken much more often. select_task_rq_fair(..., wake_flags = WF_FORK) cpu = smp_processor_id() new_cpu = sched_balance_find_dst_cpu(..., cpu, ...) group = sched_balance_find_dst_group(..., cpu) do { update_sg_wakeup_stats() sgs->group_type = group_classify() if group_is_overloaded() (2) return group_overloaded if !group_has_capacity() (3) return group_fully_busy return group_has_spare (4) } while group if local_sgs.group_type > idlest_sgs.group_type return idlest (5) case group_has_spare: if local_sgs.idle_cpus >= idlest_sgs.idle_cpus return NULL (6) Unixbench Tests './Run -c 4 spawn' on: (a) VM AWS instance (m7gd.16xlarge) with v6.13 ('maxcpus=4 nr_cpus=4') and Ubuntu 22.04.5 LTS (aarch64). Shell & test run in '/user.slice/user-1000.slice/session-1.scope'. w/o patch w/ patch 21005 27120 (b) i7-13700K with tip/sched/core ('nosmt maxcpus=8 nr_cpus=8') and Ubuntu 22.04.5 LTS (x86_64). Shell & test run in '/A'. w/o patch w/ patch 67675 88806 CONFIG_SCHED_AUTOGROUP=y & /sys/proc/kernel/sched_autogroup_enabled equal 0 or 1. Reported-by: Hazem Mohamed Abuelfotoh <abuehaze(a)amazon.com> Signed-off-by: Dietmar Eggemann <dietmar.eggemann(a)arm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Reviewed-by: Vincent Guittot <vincent.guittot(a)linaro.org> Tested-by: Hagar Hemdan <hagarhem(a)amazon.com> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Link: https://lore.kernel.org/r/20250314151345.275739-1-dietmar.eggemann@arm.com diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 67189907214d..042351c7afce 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9016,7 +9016,7 @@ void sched_release_group(struct task_group *tg) spin_unlock_irqrestore(&task_group_lock, flags); } -static struct task_group *sched_get_task_group(struct task_struct *tsk) +static void sched_change_group(struct task_struct *tsk) { struct task_group *tg; @@ -9028,13 +9028,7 @@ static struct task_group *sched_get_task_group(struct task_struct *tsk) tg = container_of(task_css_check(tsk, cpu_cgrp_id, true), struct task_group, css); tg = autogroup_task_group(tsk, tg); - - return tg; -} - -static void sched_change_group(struct task_struct *tsk, struct task_group *group) -{ - tsk->sched_task_group = group; + tsk->sched_task_group = tg; #ifdef CONFIG_FAIR_GROUP_SCHED if (tsk->sched_class->task_change_group) @@ -9055,20 +9049,11 @@ void sched_move_task(struct task_struct *tsk, bool for_autogroup) { int queued, running, queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; - struct task_group *group; struct rq *rq; CLASS(task_rq_lock, rq_guard)(tsk); rq = rq_guard.rq; - /* - * Esp. with SCHED_AUTOGROUP enabled it is possible to get superfluous - * group changes. - */ - group = sched_get_task_group(tsk); - if (group == tsk->sched_task_group) - return; - update_rq_clock(rq); running = task_current_donor(rq, tsk); @@ -9079,7 +9064,7 @@ void sched_move_task(struct task_struct *tsk, bool for_autogroup) if (running) put_prev_task(rq, tsk); - sched_change_group(tsk, group); + sched_change_group(tsk); if (!for_autogroup) scx_cgroup_move_task(tsk);

9 months, 1 week

1
0
0 0

[PATCH net] gve: unlink old napi only if page pool exists

by Harshitha Ramamurthy

Commit de70981f295e ("gve: unlink old napi when stopping a queue using queue API") unlinks the old napi when stopping a queue. But this breaks QPL mode of the driver which does not use page pool. Fix this by checking that there's a page pool associated with the ring. Cc: stable(a)vger.kernel.org Fixes: de70981f295e ("gve: unlink old napi when stopping a queue using queue API") Reviewed-by: Joshua Washington <joshwash(a)google.com> Signed-off-by: Harshitha Ramamurthy <hramamurthy(a)google.com> --- drivers/net/ethernet/google/gve/gve_rx_dqo.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index 2c03c39..0fcf4c9 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -114,7 +114,8 @@ void gve_rx_stop_ring_dqo(struct gve_priv *priv, int idx) if (!gve_rx_was_added_to_block(priv, idx)) return; - page_pool_disable_direct_recycling(rx->dqo.page_pool); + if (rx->dqo.page_pool) + page_pool_disable_direct_recycling(rx->dqo.page_pool); gve_remove_napi(priv, ntfy_idx); gve_rx_remove_from_block(priv, idx); gve_rx_reset_ring_dqo(priv, idx); -- 2.49.0.rc1.451.g8f38331e32-goog

9 months, 1 week

3
2
0 0

FAILED: patch "[PATCH] proc: fix UAF in proc_get_inode()" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 654b33ada4ab5e926cd9c570196fefa7bec7c1df # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2025032409-unnamable-entertain-9026@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 654b33ada4ab5e926cd9c570196fefa7bec7c1df Mon Sep 17 00:00:00 2001 From: Ye Bin <yebin10(a)huawei.com> Date: Sat, 1 Mar 2025 15:06:24 +0300 Subject: [PATCH] proc: fix UAF in proc_get_inode() Fix race between rmmod and /proc/XXX's inode instantiation. The bug is that pde->proc_ops don't belong to /proc, it belongs to a module, therefore dereferencing it after /proc entry has been registered is a bug unless use_pde/unuse_pde() pair has been used. use_pde/unuse_pde can be avoided (2 atomic ops!) because pde->proc_ops never changes so information necessary for inode instantiation can be saved _before_ proc_register() in PDE itself and used later, avoiding pde->proc_ops->... dereference. rmmod lookup sys_delete_module proc_lookup_de pde_get(de); proc_get_inode(dir->i_sb, de); mod->exit() proc_remove remove_proc_subtree proc_entry_rundown(de); free_module(mod); if (S_ISREG(inode->i_mode)) if (de->proc_ops->proc_read_iter) --> As module is already freed, will trigger UAF BUG: unable to handle page fault for address: fffffbfff80a702b PGD 817fc4067 P4D 817fc4067 PUD 817fc0067 PMD 102ef4067 PTE 0 Oops: Oops: 0000 [#1] PREEMPT SMP KASAN PTI CPU: 26 UID: 0 PID: 2667 Comm: ls Tainted: G Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) RIP: 0010:proc_get_inode+0x302/0x6e0 RSP: 0018:ffff88811c837998 EFLAGS: 00010a06 RAX: dffffc0000000000 RBX: ffffffffc0538140 RCX: 0000000000000007 RDX: 1ffffffff80a702b RSI: 0000000000000001 RDI: ffffffffc0538158 RBP: ffff8881299a6000 R08: 0000000067bbe1e5 R09: 1ffff11023906f20 R10: ffffffffb560ca07 R11: ffffffffb2b43a58 R12: ffff888105bb78f0 R13: ffff888100518048 R14: ffff8881299a6004 R15: 0000000000000001 FS: 00007f95b9686840(0000) GS:ffff8883af100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffbfff80a702b CR3: 0000000117dd2000 CR4: 00000000000006f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> proc_lookup_de+0x11f/0x2e0 __lookup_slow+0x188/0x350 walk_component+0x2ab/0x4f0 path_lookupat+0x120/0x660 filename_lookup+0x1ce/0x560 vfs_statx+0xac/0x150 __do_sys_newstat+0x96/0x110 do_syscall_64+0x5f/0x170 entry_SYSCALL_64_after_hwframe+0x76/0x7e [adobriyan(a)gmail.com: don't do 2 atomic ops on the common path] Link: https://lkml.kernel.org/r/3d25ded0-1739-447e-812b-e34da7990dcf@p183 Fixes: 778f3dd5a13c ("Fix procfs compat_ioctl regression") Signed-off-by: Ye Bin <yebin10(a)huawei.com> Signed-off-by: Alexey Dobriyan <adobriyan(a)gmail.com> Cc: Al Viro <viro(a)zeniv.linux.org.uk> Cc: David S. Miller <davem(a)davemloft.net> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 8ec90826a49e..a3e22803cddf 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -559,10 +559,16 @@ struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode, return p; } -static inline void pde_set_flags(struct proc_dir_entry *pde) +static void pde_set_flags(struct proc_dir_entry *pde) { if (pde->proc_ops->proc_flags & PROC_ENTRY_PERMANENT) pde->flags |= PROC_ENTRY_PERMANENT; + if (pde->proc_ops->proc_read_iter) + pde->flags |= PROC_ENTRY_proc_read_iter; +#ifdef CONFIG_COMPAT + if (pde->proc_ops->proc_compat_ioctl) + pde->flags |= PROC_ENTRY_proc_compat_ioctl; +#endif } struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, @@ -626,6 +632,7 @@ struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode, p->proc_ops = &proc_seq_ops; p->seq_ops = ops; p->state_size = state_size; + pde_set_flags(p); return proc_register(parent, p); } EXPORT_SYMBOL(proc_create_seq_private); @@ -656,6 +663,7 @@ struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode, return NULL; p->proc_ops = &proc_single_ops; p->single_show = show; + pde_set_flags(p); return proc_register(parent, p); } EXPORT_SYMBOL(proc_create_single_data); diff --git a/fs/proc/inode.c b/fs/proc/inode.c index 626ad7bd94f2..a3eb3b740f76 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -656,13 +656,13 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de) if (S_ISREG(inode->i_mode)) { inode->i_op = de->proc_iops; - if (de->proc_ops->proc_read_iter) + if (pde_has_proc_read_iter(de)) inode->i_fop = &proc_iter_file_ops; else inode->i_fop = &proc_reg_file_ops; #ifdef CONFIG_COMPAT - if (de->proc_ops->proc_compat_ioctl) { - if (de->proc_ops->proc_read_iter) + if (pde_has_proc_compat_ioctl(de)) { + if (pde_has_proc_read_iter(de)) inode->i_fop = &proc_iter_file_ops_compat; else inode->i_fop = &proc_reg_file_ops_compat; diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 1695509370b8..77a517f91821 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -85,6 +85,20 @@ static inline void pde_make_permanent(struct proc_dir_entry *pde) pde->flags |= PROC_ENTRY_PERMANENT; } +static inline bool pde_has_proc_read_iter(const struct proc_dir_entry *pde) +{ + return pde->flags & PROC_ENTRY_proc_read_iter; +} + +static inline bool pde_has_proc_compat_ioctl(const struct proc_dir_entry *pde) +{ +#ifdef CONFIG_COMPAT + return pde->flags & PROC_ENTRY_proc_compat_ioctl; +#else + return false; +#endif +} + extern struct kmem_cache *proc_dir_entry_cache; void pde_free(struct proc_dir_entry *pde); diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 0b2a89854440..ea62201c74c4 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -20,10 +20,13 @@ enum { * If in doubt, ignore this flag. */ #ifdef MODULE - PROC_ENTRY_PERMANENT = 0U, + PROC_ENTRY_PERMANENT = 0U, #else - PROC_ENTRY_PERMANENT = 1U << 0, + PROC_ENTRY_PERMANENT = 1U << 0, #endif + + PROC_ENTRY_proc_read_iter = 1U << 1, + PROC_ENTRY_proc_compat_ioctl = 1U << 2, }; struct proc_ops {

9 months, 1 week

2
1
0 0

[PATCH net v2] net: stmmac: Fix accessing freed irq affinity_hint

by Qingfang Deng

The cpumask should not be a local variable, since its pointer is saved to irq_desc and may be accessed from procfs. To fix it, use the persistent mask cpumask_of(cpu#). Cc: stable(a)vger.kernel.org Fixes: 8deec94c6040 ("net: stmmac: set IRQ affinity hint for multi MSI vectors") Signed-off-by: Qingfang Deng <dqfext(a)gmail.com> --- v2: use cpumask_of() drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index b22417167cac..ec63452187d0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3667,7 +3667,6 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); enum request_irq_err irq_err; - cpumask_t cpu_mask; int irq_idx = 0; char *int_name; int ret; @@ -3796,9 +3795,8 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev) irq_idx = i; goto irq_error; } - cpumask_clear(&cpu_mask); - cpumask_set_cpu(i % num_online_cpus(), &cpu_mask); - irq_set_affinity_hint(priv->rx_irq[i], &cpu_mask); + irq_set_affinity_hint(priv->rx_irq[i], + cpumask_of(i % num_online_cpus())); } /* Request Tx MSI irq */ @@ -3821,9 +3819,8 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev) irq_idx = i; goto irq_error; } - cpumask_clear(&cpu_mask); - cpumask_set_cpu(i % num_online_cpus(), &cpu_mask); - irq_set_affinity_hint(priv->tx_irq[i], &cpu_mask); + irq_set_affinity_hint(priv->tx_irq[i], + cpumask_of(i % num_online_cpus())); } return 0; -- 2.43.0

9 months, 1 week

4
3
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror March 2025