From: Prakruthi Deepak Heragu quic_pheragu@quicinc.com
stable inclusion from stable-v5.10.118 commit a817f78ed69bba10d724587dab84a164dac05900 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5L686
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
commit 19bef63f951e47dd4ba54810e6f7c7ff9344a3ef upstream.
During hotplug, the stolen time data structure is unmapped and memset. There is a possibility of the timer IRQ being triggered before memset and stolen time is getting updated as part of this timer IRQ handler. This causes the below crash in timer handler -
[ 3457.473139][ C5] Unable to handle kernel paging request at virtual address ffffffc03df05148 ... [ 3458.154398][ C5] Call trace: [ 3458.157648][ C5] para_steal_clock+0x30/0x50 [ 3458.162319][ C5] irqtime_account_process_tick+0x30/0x194 [ 3458.168148][ C5] account_process_tick+0x3c/0x280 [ 3458.173274][ C5] update_process_times+0x5c/0xf4 [ 3458.178311][ C5] tick_sched_timer+0x180/0x384 [ 3458.183164][ C5] __run_hrtimer+0x160/0x57c [ 3458.187744][ C5] hrtimer_interrupt+0x258/0x684 [ 3458.192698][ C5] arch_timer_handler_virt+0x5c/0xa0 [ 3458.198002][ C5] handle_percpu_devid_irq+0xdc/0x414 [ 3458.203385][ C5] handle_domain_irq+0xa8/0x168 [ 3458.208241][ C5] gic_handle_irq.34493+0x54/0x244 [ 3458.213359][ C5] call_on_irq_stack+0x40/0x70 [ 3458.218125][ C5] do_interrupt_handler+0x60/0x9c [ 3458.223156][ C5] el1_interrupt+0x34/0x64 [ 3458.227560][ C5] el1h_64_irq_handler+0x1c/0x2c [ 3458.232503][ C5] el1h_64_irq+0x7c/0x80 [ 3458.236736][ C5] free_vmap_area_noflush+0x108/0x39c [ 3458.242126][ C5] remove_vm_area+0xbc/0x118 [ 3458.246714][ C5] vm_remove_mappings+0x48/0x2a4 [ 3458.251656][ C5] __vunmap+0x154/0x278 [ 3458.255796][ C5] stolen_time_cpu_down_prepare+0xc0/0xd8 [ 3458.261542][ C5] cpuhp_invoke_callback+0x248/0xc34 [ 3458.266842][ C5] cpuhp_thread_fun+0x1c4/0x248 [ 3458.271696][ C5] smpboot_thread_fn+0x1b0/0x400 [ 3458.276638][ C5] kthread+0x17c/0x1e0 [ 3458.280691][ C5] ret_from_fork+0x10/0x20
As a fix, introduce rcu lock to update stolen time structure.
Fixes: 75df529bec91 ("arm64: paravirt: Initialize steal time when cpu is online") Cc: stable@vger.kernel.org Suggested-by: Will Deacon will@kernel.org Signed-off-by: Prakruthi Deepak Heragu quic_pheragu@quicinc.com Signed-off-by: Elliot Berman quic_eberman@quicinc.com Reviewed-by: Srivatsa S. Bhat (VMware) srivatsa@csail.mit.edu Link: https://lore.kernel.org/r/20220513174654.362169-1-quic_eberman@quicinc.com Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com Acked-by: Xie XiuQi xiexiuqi@huawei.com --- arch/arm64/kernel/paravirt.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-)
diff --git a/arch/arm64/kernel/paravirt.c b/arch/arm64/kernel/paravirt.c index ecbd2bf2e6fb..45df16e9d8bc 100644 --- a/arch/arm64/kernel/paravirt.c +++ b/arch/arm64/kernel/paravirt.c @@ -41,7 +41,7 @@ struct paravirt_patch_template pv_ops = { EXPORT_SYMBOL(pv_ops);
struct pv_time_stolen_time_region { - struct pvclock_vcpu_stolen_time *kaddr; + struct pvclock_vcpu_stolen_time __rcu *kaddr; };
static DEFINE_PER_CPU(struct pv_time_stolen_time_region, stolen_time_region); @@ -58,7 +58,9 @@ early_param("no-steal-acc", parse_no_stealacc); /* return stolen time in ns by asking the hypervisor */ static u64 pv_steal_clock(int cpu) { + struct pvclock_vcpu_stolen_time *kaddr = NULL; struct pv_time_stolen_time_region *reg; + u64 ret = 0;
reg = per_cpu_ptr(&stolen_time_region, cpu);
@@ -67,28 +69,37 @@ static u64 pv_steal_clock(int cpu) * online notification callback runs. Until the callback * has run we just return zero. */ - if (!reg->kaddr) + rcu_read_lock(); + kaddr = rcu_dereference(reg->kaddr); + if (!kaddr) { + rcu_read_unlock(); return 0; + }
- return le64_to_cpu(READ_ONCE(reg->kaddr->stolen_time)); + ret = le64_to_cpu(READ_ONCE(kaddr->stolen_time)); + rcu_read_unlock(); + return ret; }
static int stolen_time_cpu_down_prepare(unsigned int cpu) { + struct pvclock_vcpu_stolen_time *kaddr = NULL; struct pv_time_stolen_time_region *reg;
reg = this_cpu_ptr(&stolen_time_region); if (!reg->kaddr) return 0;
- memunmap(reg->kaddr); - memset(reg, 0, sizeof(*reg)); + kaddr = rcu_replace_pointer(reg->kaddr, NULL, true); + synchronize_rcu(); + memunmap(kaddr);
return 0; }
static int stolen_time_cpu_online(unsigned int cpu) { + struct pvclock_vcpu_stolen_time *kaddr = NULL; struct pv_time_stolen_time_region *reg; struct arm_smccc_res res;
@@ -99,17 +110,19 @@ static int stolen_time_cpu_online(unsigned int cpu) if (res.a0 == SMCCC_RET_NOT_SUPPORTED) return -EINVAL;
- reg->kaddr = memremap(res.a0, + kaddr = memremap(res.a0, sizeof(struct pvclock_vcpu_stolen_time), MEMREMAP_WB);
+ rcu_assign_pointer(reg->kaddr, kaddr); + if (!reg->kaddr) { pr_warn("Failed to map stolen time data structure\n"); return -ENOMEM; }
- if (le32_to_cpu(reg->kaddr->revision) != 0 || - le32_to_cpu(reg->kaddr->attributes) != 0) { + if (le32_to_cpu(kaddr->revision) != 0 || + le32_to_cpu(kaddr->attributes) != 0) { pr_warn_once("Unexpected revision or attributes in stolen time data\n"); return -ENXIO; }