Re: [PATCH v12 3/3] ACPI: APEI: handle synchronous exceptions in task work

["Jarkko Sakkinen" <jarkko@kernel.org>]

On Mon Sep 2, 2024 at 6:00 AM EEST, Shuai Xue wrote:
> The memory uncorrected error could be signaled by asynchronous interrupt
> (specifically, SPI in arm64 platform), e.g. when an error is detected by
> a background scrubber, or signaled by synchronous exception
> (specifically, data abort excepction in arm64 platform), e.g. when a CPU
> tries to access a poisoned cache line. Currently, both synchronous and
> asynchronous error use memory_failure_queue() to schedule
> memory_failure() exectute in kworker context.
>
> As a result, when a user-space process is accessing a poisoned data, a
> data abort is taken and the memory_failure() is executed in the kworker
> context:
>
>   - will send wrong si_code by SIGBUS signal in early_kill mode, and
>   - can not kill the user-space in some cases resulting a synchronous
>     error infinite loop
>
> Issue 1: send wrong si_code in early_kill mode
>
> Since commit a70297d22132 ("ACPI: APEI: set memory failure flags as
> MF_ACTION_REQUIRED on synchronous events")', the flag MF_ACTION_REQUIRED
> could be used to determine whether a synchronous exception occurs on
> ARM64 platform.  When a synchronous exception is detected, the kernel is
> expected to terminate the current process which has accessed poisoned
> page. This is done by sending a SIGBUS signal with an error code
> BUS_MCEERR_AR, indicating an action-required machine check error on
> read.
>
> However, when kill_proc() is called to terminate the processes who have
> the poisoned page mapped, it sends the incorrect SIGBUS error code
> BUS_MCEERR_AO because the context in which it operates is not the one
> where the error was triggered.
>
> To reproduce this problem:
>
>   # STEP1: enable early kill mode
>   #sysctl -w vm.memory_failure_early_kill=1
>   vm.memory_failure_early_kill = 1
>
>   # STEP2: inject an UCE error and consume it to trigger a synchronous error
>   #einj_mem_uc single
>   0: single   vaddr = 0xffffb0d75400 paddr = 4092d55b400
>   injecting ...
>   triggering ...
>   signal 7 code 5 addr 0xffffb0d75000
>   page not present
>   Test passed
>
> The si_code (code 5) from einj_mem_uc indicates that it is BUS_MCEERR_AO
> error and it is not fact.
>
> To fix it, queue memory_failure() as a task_work so that it runs in
> the context of the process that is actually consuming the poisoned data.
>
> After this patch set:

s/patch set/patch/

>
>   # STEP1: enable early kill mode
>   #sysctl -w vm.memory_failure_early_kill=1
>   vm.memory_failure_early_kill = 1
>
>   # STEP2: inject an UCE error and consume it to trigger a synchronous error
>   #einj_mem_uc single
>   0: single   vaddr = 0xffffb0d75400 paddr = 4092d55b400
>   injecting ...
>   triggering ...
>   signal 7 code 4 addr 0xffffb0d75000
>   page not present
>   Test passed
>
> The si_code (code 4) from einj_mem_uc indicates that it is BUS_MCEERR_AR
> error as we expected.
>
> Issue 2: a synchronous error infinite loop due to memory_failure() failed
>
> If a user-space process, e.g. devmem, a poisoned page which has been set
> HWPosion flag, kill_accessing_process() is called to send SIGBUS to the
> current processs with error info. Because the memory_failure() is
> executed in the kworker contex, it will just do nothing but return
> EFAULT. So, devmem will access the posioned page and trigger an
> excepction again, resulting in a synchronous error infinite loop. Such
> loop may cause platform firmware to exceed some threshold and reboot
> when Linux could have recovered from this error.
>
> To reproduce this problem:
>
>   # STEP 1: inject an UCE error, and kernel will set HWPosion flag for related page
>   #einj_mem_uc single
>   0: single   vaddr = 0xffffb0d75400 paddr = 4092d55b400
>   injecting ...
>   triggering ...
>   signal 7 code 4 addr 0xffffb0d75000
>   page not present
>   Test passed
>
>   # STEP 2: access the same page and it will trigger a synchronous error infinite loop
>   devmem 0x4092d55b400
>
> To fix it, if memory_failure() failed, perform a force kill to current process.
>
> Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
> Tested-by: Ma Wupeng <mawupeng1@huawei.com>
> Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com>
> Reviewed-by: Xiaofei Tan <tanxiaofei@huawei.com>
> Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
> ---
>  drivers/acpi/apei/ghes.c | 78 +++++++++++++++++++++++-----------------
>  include/acpi/ghes.h      |  3 --
>  include/linux/mm.h       |  1 -
>  mm/memory-failure.c      | 13 -------
>  4 files changed, 45 insertions(+), 50 deletions(-)
>
> diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
> index b0b20ee533d9..b956e9ed020f 100644
> --- a/drivers/acpi/apei/ghes.c
> +++ b/drivers/acpi/apei/ghes.c
> @@ -467,28 +467,42 @@ static void ghes_clear_estatus(struct ghes *ghes,
>  }
>  
>  /*
> - * Called as task_work before returning to user-space.
> - * Ensure any queued work has been done before we return to the context that
> - * triggered the notification.
> + * struct task_work - for synchronous RAS event
> + *
> + * @twork:                callback_head for task work
> + * @pfn:                  page frame number of corrupted page
> + * @flags:                work control flags
> + *
> + * Structure to pass task work to be handled before
> + * returning to user-space via task_work_add().
>   */
> -static void ghes_kick_task_work(struct callback_head *head)
> +struct task_work {
> +	struct callback_head twork;
> +	u64 pfn;
> +	int flags;
> +};
> +
> +static void memory_failure_cb(struct callback_head *twork)
>  {
> -	struct acpi_hest_generic_status *estatus;
> -	struct ghes_estatus_node *estatus_node;
> -	u32 node_len;
> +	struct task_work *twcb = container_of(twork, struct task_work, twork);
> +	unsigned long pfn = twcb->pfn;
> +	int ret;
>  
> -	estatus_node = container_of(head, struct ghes_estatus_node, task_work);
> -	if (IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
> -		memory_failure_queue_kick(estatus_node->task_work_cpu);
> +	ret = memory_failure(twcb->pfn, twcb->flags);
> +	gen_pool_free(ghes_estatus_pool, (unsigned long)twcb, sizeof(*twcb));
>  
> -	estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
> -	node_len = GHES_ESTATUS_NODE_LEN(cper_estatus_len(estatus));
> -	gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node, node_len);
> +	if (!ret || ret == -EHWPOISON || ret == -EOPNOTSUPP)
> +		return;
> +
> +	pr_err("%#lx: Sending SIGBUS to %s:%d due to hardware memory corruption\n",
> +			pfn, current->comm, task_pid_nr(current));
> +	force_sig(SIGBUS);
>  }
>  
>  static bool ghes_do_memory_failure(u64 physical_addr, int flags)
>  {
>  	unsigned long pfn;
> +	struct task_work *twcb;
>  
>  	if (!IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
>  		return false;
> @@ -501,6 +515,18 @@ static bool ghes_do_memory_failure(u64 physical_addr, int flags)
>  		return false;
>  	}
>  
> +	if (flags == MF_ACTION_REQUIRED && current->mm) {
> +		twcb = (void *)gen_pool_alloc(ghes_estatus_pool, sizeof(*twcb));
> +		if (!twcb)
> +			return false;
> +
> +		twcb->pfn = pfn;
> +		twcb->flags = flags;
> +		init_task_work(&twcb->twork, memory_failure_cb);
> +		task_work_add(current, &twcb->twork, TWA_RESUME);
> +		return true;
> +	}
> +
>  	memory_failure_queue(pfn, flags);
>  	return true;
>  }
> @@ -745,7 +771,7 @@ int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd)
>  }
>  EXPORT_SYMBOL_NS_GPL(cxl_cper_kfifo_get, CXL);
>  
> -static bool ghes_do_proc(struct ghes *ghes,
> +static void ghes_do_proc(struct ghes *ghes,
>  			 const struct acpi_hest_generic_status *estatus)
>  {
>  	int sev, sec_sev;
> @@ -810,8 +836,6 @@ static bool ghes_do_proc(struct ghes *ghes,
>  			current->comm, task_pid_nr(current));
>  		force_sig(SIGBUS);
>  	}
> -
> -	return queued;
>  }
>  
>  static void __ghes_print_estatus(const char *pfx,
> @@ -1113,9 +1137,7 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
>  	struct ghes_estatus_node *estatus_node;
>  	struct acpi_hest_generic *generic;
>  	struct acpi_hest_generic_status *estatus;
> -	bool task_work_pending;
>  	u32 len, node_len;
> -	int ret;
>  
>  	llnode = llist_del_all(&ghes_estatus_llist);
>  	/*
> @@ -1130,25 +1152,16 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
>  		estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
>  		len = cper_estatus_len(estatus);
>  		node_len = GHES_ESTATUS_NODE_LEN(len);
> -		task_work_pending = ghes_do_proc(estatus_node->ghes, estatus);
> +
> +		ghes_do_proc(estatus_node->ghes, estatus);
> +
>  		if (!ghes_estatus_cached(estatus)) {
>  			generic = estatus_node->generic;
>  			if (ghes_print_estatus(NULL, generic, estatus))
>  				ghes_estatus_cache_add(generic, estatus);
>  		}
> -
> -		if (task_work_pending && current->mm) {
> -			estatus_node->task_work.func = ghes_kick_task_work;
> -			estatus_node->task_work_cpu = smp_processor_id();
> -			ret = task_work_add(current, &estatus_node->task_work,
> -					    TWA_RESUME);
> -			if (ret)
> -				estatus_node->task_work.func = NULL;
> -		}
> -
> -		if (!estatus_node->task_work.func)
> -			gen_pool_free(ghes_estatus_pool,
> -				      (unsigned long)estatus_node, node_len);
> +		gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node,
> +			      node_len);
>  
>  		llnode = next;
>  	}
> @@ -1209,7 +1222,6 @@ static int ghes_in_nmi_queue_one_entry(struct ghes *ghes,
>  
>  	estatus_node->ghes = ghes;
>  	estatus_node->generic = ghes->generic;
> -	estatus_node->task_work.func = NULL;
>  	estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
>  
>  	if (__ghes_read_estatus(estatus, buf_paddr, fixmap_idx, len)) {
> diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
> index be1dd4c1a917..ebd21b05fe6e 100644
> --- a/include/acpi/ghes.h
> +++ b/include/acpi/ghes.h
> @@ -35,9 +35,6 @@ struct ghes_estatus_node {
>  	struct llist_node llnode;
>  	struct acpi_hest_generic *generic;
>  	struct ghes *ghes;
> -
> -	int task_work_cpu;
> -	struct callback_head task_work;
>  };
>  
>  struct ghes_estatus_cache {
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index 6549d0979b28..f5f1d6a8a07d 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -3981,7 +3981,6 @@ enum mf_flags {
>  int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
>  		      unsigned long count, int mf_flags);
>  extern int memory_failure(unsigned long pfn, int flags);
> -extern void memory_failure_queue_kick(int cpu);
>  extern int unpoison_memory(unsigned long pfn);
>  extern atomic_long_t num_poisoned_pages __read_mostly;
>  extern int soft_offline_page(unsigned long pfn, int flags);
> diff --git a/mm/memory-failure.c b/mm/memory-failure.c
> index df26e2ff5e06..e369aae2da1f 100644
> --- a/mm/memory-failure.c
> +++ b/mm/memory-failure.c
> @@ -2486,19 +2486,6 @@ static void memory_failure_work_func(struct work_struct *work)
>  	}
>  }
>  
> -/*
> - * Process memory_failure work queued on the specified CPU.
> - * Used to avoid return-to-userspace racing with the memory_failure workqueue.
> - */
> -void memory_failure_queue_kick(int cpu)
> -{
> -	struct memory_failure_cpu *mf_cpu;
> -
> -	mf_cpu = &per_cpu(memory_failure_cpu, cpu);
> -	cancel_work_sync(&mf_cpu->work);
> -	memory_failure_work_func(&mf_cpu->work);
> -}
> -
>  static int __init memory_failure_init(void)
>  {
>  	struct memory_failure_cpu *mf_cpu;


BR, Jarkko