From: Zqiang qiang.zhang1211@gmail.com
mainline inclusion from mainline-v6.12-rc1 commit fd70e9f1d85f5323096ad313ba73f5fe3d15ea41 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IAYR9E CVE: CVE-2024-49926
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
For kernels built with CONFIG_FORCE_NR_CPUS=y, the nr_cpu_ids is defined as NR_CPUS instead of the number of possible cpus, this will cause the following system panic:
smpboot: Allowing 4 CPUs, 0 hotplug CPUs ... setup_percpu: NR_CPUS:512 nr_cpumask_bits:512 nr_cpu_ids:512 nr_node_ids:1 ... BUG: unable to handle page fault for address: ffffffff9911c8c8 Oops: 0000 [#1] PREEMPT SMP PTI CPU: 0 PID: 15 Comm: rcu_tasks_trace Tainted: G W 6.6.21 #1 5dc7acf91a5e8e9ac9dcfc35bee0245691283ea6 RIP: 0010:rcu_tasks_need_gpcb+0x25d/0x2c0 RSP: 0018:ffffa371c00a3e60 EFLAGS: 00010082 CR2: ffffffff9911c8c8 CR3: 000000040fa20005 CR4: 00000000001706f0 Call Trace: <TASK> ? __die+0x23/0x80 ? page_fault_oops+0xa4/0x180 ? exc_page_fault+0x152/0x180 ? asm_exc_page_fault+0x26/0x40 ? rcu_tasks_need_gpcb+0x25d/0x2c0 ? __pfx_rcu_tasks_kthread+0x40/0x40 rcu_tasks_one_gp+0x69/0x180 rcu_tasks_kthread+0x94/0xc0 kthread+0xe8/0x140 ? __pfx_kthread+0x40/0x40 ret_from_fork+0x34/0x80 ? __pfx_kthread+0x40/0x40 ret_from_fork_asm+0x1b/0x80 </TASK>
Considering that there may be holes in the CPU numbers, use the maximum possible cpu number, instead of nr_cpu_ids, for configuring enqueue and dequeue limits.
[ neeraj.upadhyay: Fix htmldocs build error reported by Stephen Rothwell ]
Closes: https://lore.kernel.org/linux-input/CALMA0xaTSMN+p4xUXkzrtR5r6k7hgoswcaXx7ba... Reported-by: Zhixu Liu zhixu.liu@gmail.com Signed-off-by: Zqiang qiang.zhang1211@gmail.com Signed-off-by: Neeraj Upadhyay neeraj.upadhyay@kernel.org
Conflicts: kernel/rcu/tasks.h [commit bfe93930ea1ea3c6c115a7d44af6e4fea609067e("rcu-tasks: Add data to eliminate RCU-tasks/do_exit() deadlocks") was not merged] [commit e62d8ae4620865411d1b2347980aa28ccf891a3d("rcu-tasks: Pull sampling of ->percpu_dequeue_lim out of loop") was not merged] Signed-off-by: liwei liwei728@huawei.com --- kernel/rcu/tasks.h | 83 ++++++++++++++++++++++++++++++---------------- 1 file changed, 54 insertions(+), 29 deletions(-)
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index df81506cf2bd..fbfa0f90f884 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -33,6 +33,7 @@ typedef void (*postgp_func_t)(struct rcu_tasks *rtp); * @barrier_q_head: RCU callback for barrier operation. * @rtp_blkd_tasks: List of tasks blocked as readers. * @cpu: CPU number corresponding to this entry. + * @index: Index of this CPU in rtpcp_array of the rcu_tasks structure. * @rtpp: Pointer to the rcu_tasks structure. */ struct rcu_tasks_percpu { @@ -47,6 +48,7 @@ struct rcu_tasks_percpu { struct rcu_head barrier_q_head; struct list_head rtp_blkd_tasks; int cpu; + int index; struct rcu_tasks *rtpp; };
@@ -73,6 +75,7 @@ struct rcu_tasks_percpu { * @postgp_func: This flavor's post-grace-period function (optional). * @call_func: This flavor's call_rcu()-equivalent function. * @rtpcpu: This flavor's rcu_tasks_percpu structure. + * @rtpcp_array: Array of pointers to rcu_tasks_percpu structure of CPUs in cpu_possible_mask. * @percpu_enqueue_shift: Shift down CPU ID this much when enqueuing callbacks. * @percpu_enqueue_lim: Number of per-CPU callback queues in use for enqueuing. * @percpu_dequeue_lim: Number of per-CPU callback queues in use for dequeuing. @@ -106,6 +109,7 @@ struct rcu_tasks { postgp_func_t postgp_func; call_rcu_func_t call_func; struct rcu_tasks_percpu __percpu *rtpcpu; + struct rcu_tasks_percpu **rtpcp_array; int percpu_enqueue_shift; int percpu_enqueue_lim; int percpu_dequeue_lim; @@ -179,6 +183,8 @@ module_param(rcu_task_collapse_lim, int, 0444); static int rcu_task_lazy_lim __read_mostly = 32; module_param(rcu_task_lazy_lim, int, 0444);
+static int rcu_task_cpu_ids; + /* RCU tasks grace-period state for debugging. */ #define RTGS_INIT 0 #define RTGS_WAIT_WAIT_CBS 1 @@ -243,6 +249,8 @@ static void cblist_init_generic(struct rcu_tasks *rtp) unsigned long flags; int lim; int shift; + int maxcpu; + int index = 0;
if (rcu_task_enqueue_lim < 0) { rcu_task_enqueue_lim = 1; @@ -252,14 +260,9 @@ static void cblist_init_generic(struct rcu_tasks *rtp) } lim = rcu_task_enqueue_lim;
- if (lim > nr_cpu_ids) - lim = nr_cpu_ids; - shift = ilog2(nr_cpu_ids / lim); - if (((nr_cpu_ids - 1) >> shift) >= lim) - shift++; - WRITE_ONCE(rtp->percpu_enqueue_shift, shift); - WRITE_ONCE(rtp->percpu_dequeue_lim, lim); - smp_store_release(&rtp->percpu_enqueue_lim, lim); + rtp->rtpcp_array = kcalloc(num_possible_cpus(), sizeof(struct rcu_tasks_percpu *), GFP_KERNEL); + BUG_ON(!rtp->rtpcp_array); + for_each_possible_cpu(cpu) { struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
@@ -273,12 +276,28 @@ static void cblist_init_generic(struct rcu_tasks *rtp) INIT_WORK(&rtpcp->rtp_work, rcu_tasks_invoke_cbs_wq); rtpcp->cpu = cpu; rtpcp->rtpp = rtp; + rtpcp->index = index; + rtp->rtpcp_array[index] = rtpcp; + index++; if (!rtpcp->rtp_blkd_tasks.next) INIT_LIST_HEAD(&rtpcp->rtp_blkd_tasks); + + maxcpu = cpu; }
- pr_info("%s: Setting shift to %d and lim to %d rcu_task_cb_adjust=%d.\n", rtp->name, - data_race(rtp->percpu_enqueue_shift), data_race(rtp->percpu_enqueue_lim), rcu_task_cb_adjust); + rcu_task_cpu_ids = maxcpu + 1; + if (lim > rcu_task_cpu_ids) + lim = rcu_task_cpu_ids; + shift = ilog2(rcu_task_cpu_ids / lim); + if (((rcu_task_cpu_ids - 1) >> shift) >= lim) + shift++; + WRITE_ONCE(rtp->percpu_enqueue_shift, shift); + WRITE_ONCE(rtp->percpu_dequeue_lim, lim); + smp_store_release(&rtp->percpu_enqueue_lim, lim); + + pr_info("%s: Setting shift to %d and lim to %d rcu_task_cb_adjust=%d rcu_task_cpu_ids=%d.\n", + rtp->name, data_race(rtp->percpu_enqueue_shift), data_race(rtp->percpu_enqueue_lim), + rcu_task_cb_adjust, rcu_task_cpu_ids); }
// Compute wakeup time for lazy callback timer. @@ -346,7 +365,7 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func, rtpcp->rtp_n_lock_retries = 0; } if (rcu_task_cb_adjust && ++rtpcp->rtp_n_lock_retries > rcu_task_contend_lim && - READ_ONCE(rtp->percpu_enqueue_lim) != nr_cpu_ids) + READ_ONCE(rtp->percpu_enqueue_lim) != rcu_task_cpu_ids) needadjust = true; // Defer adjustment to avoid deadlock. } // Queuing callbacks before initialization not yet supported. @@ -366,10 +385,10 @@ static void call_rcu_tasks_generic(struct rcu_head *rhp, rcu_callback_t func, raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags); if (unlikely(needadjust)) { raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags); - if (rtp->percpu_enqueue_lim != nr_cpu_ids) { + if (rtp->percpu_enqueue_lim != rcu_task_cpu_ids) { WRITE_ONCE(rtp->percpu_enqueue_shift, 0); - WRITE_ONCE(rtp->percpu_dequeue_lim, nr_cpu_ids); - smp_store_release(&rtp->percpu_enqueue_lim, nr_cpu_ids); + WRITE_ONCE(rtp->percpu_dequeue_lim, rcu_task_cpu_ids); + smp_store_release(&rtp->percpu_enqueue_lim, rcu_task_cpu_ids); pr_info("Switching %s to per-CPU callback queuing.\n", rtp->name); } raw_spin_unlock_irqrestore(&rtp->cbs_gbl_lock, flags); @@ -440,6 +459,8 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp) int needgpcb = 0;
for (cpu = 0; cpu < smp_load_acquire(&rtp->percpu_dequeue_lim); cpu++) { + if (!cpu_possible(cpu)) + continue; struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
/* Advance and accelerate any new callbacks. */ @@ -477,7 +498,7 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp) if (rcu_task_cb_adjust && ncbs <= rcu_task_collapse_lim) { raw_spin_lock_irqsave(&rtp->cbs_gbl_lock, flags); if (rtp->percpu_enqueue_lim > 1) { - WRITE_ONCE(rtp->percpu_enqueue_shift, order_base_2(nr_cpu_ids)); + WRITE_ONCE(rtp->percpu_enqueue_shift, order_base_2(rcu_task_cpu_ids)); smp_store_release(&rtp->percpu_enqueue_lim, 1); rtp->percpu_dequeue_gpseq = get_state_synchronize_rcu(); gpdone = false; @@ -492,7 +513,9 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp) pr_info("Completing switch %s to CPU-0 callback queuing.\n", rtp->name); } if (rtp->percpu_dequeue_lim == 1) { - for (cpu = rtp->percpu_dequeue_lim; cpu < nr_cpu_ids; cpu++) { + for (cpu = rtp->percpu_dequeue_lim; cpu < rcu_task_cpu_ids; cpu++) { + if (!cpu_possible(cpu)) + continue; struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu);
WARN_ON_ONCE(rcu_segcblist_n_cbs(&rtpcp->cblist)); @@ -507,30 +530,32 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp) // Advance callbacks and invoke any that are ready. static void rcu_tasks_invoke_cbs(struct rcu_tasks *rtp, struct rcu_tasks_percpu *rtpcp) { - int cpu; - int cpunext; int cpuwq; unsigned long flags; int len; + int index; struct rcu_head *rhp; struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl); struct rcu_tasks_percpu *rtpcp_next;
- cpu = rtpcp->cpu; - cpunext = cpu * 2 + 1; - if (cpunext < smp_load_acquire(&rtp->percpu_dequeue_lim)) { - rtpcp_next = per_cpu_ptr(rtp->rtpcpu, cpunext); - cpuwq = rcu_cpu_beenfullyonline(cpunext) ? cpunext : WORK_CPU_UNBOUND; - queue_work_on(cpuwq, system_wq, &rtpcp_next->rtp_work); - cpunext++; - if (cpunext < smp_load_acquire(&rtp->percpu_dequeue_lim)) { - rtpcp_next = per_cpu_ptr(rtp->rtpcpu, cpunext); - cpuwq = rcu_cpu_beenfullyonline(cpunext) ? cpunext : WORK_CPU_UNBOUND; + index = rtpcp->index * 2 + 1; + if (index < num_possible_cpus()) { + rtpcp_next = rtp->rtpcp_array[index]; + if (rtpcp_next->cpu < smp_load_acquire(&rtp->percpu_dequeue_lim)) { + cpuwq = rcu_cpu_beenfullyonline(rtpcp_next->cpu) ? rtpcp_next->cpu : WORK_CPU_UNBOUND; queue_work_on(cpuwq, system_wq, &rtpcp_next->rtp_work); + index++; + if (index < num_possible_cpus()) { + rtpcp_next = rtp->rtpcp_array[index]; + if (rtpcp_next->cpu < smp_load_acquire(&rtp->percpu_dequeue_lim)) { + cpuwq = rcu_cpu_beenfullyonline(rtpcp_next->cpu) ? rtpcp_next->cpu : WORK_CPU_UNBOUND; + queue_work_on(cpuwq, system_wq, &rtpcp_next->rtp_work); + } + } } }
- if (rcu_segcblist_empty(&rtpcp->cblist) || !cpu_possible(cpu)) + if (rcu_segcblist_empty(&rtpcp->cblist)) return; raw_spin_lock_irqsave_rcu_node(rtpcp, flags); rcu_segcblist_advance(&rtpcp->cblist, rcu_seq_current(&rtp->tasks_gp_seq));