Re: [PATCH v2 3/3] mm: don't panic when links can't be created in sysfs

[Laurent Dufour <ldufour@linux.ibm.com>]

Le 15/09/2020 à 09:23, David Hildenbrand a écrit :
> On 14.09.20 18:50, Laurent Dufour wrote:
>> At boot time, or when doing memory hot-add operations, if the links in
>> sysfs can't be created, the system is still able to run, so just report the
>> error in the kernel log rather than BUG_ON and potentially make system
>> unusable because the callpath can be called with locks held.
>>
>> Since the number of memory blocks managed could be high, the messages are
>> rate limited.
>>
>> As a consequence, link_mem_sections() has no status to report anymore.
>>
>> Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
>> Acked-by: Michal Hocko <mhocko@suse.com>
>> Cc: David Hildenbrand <david@redhat.com>
>> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
>> ---
>>   drivers/base/node.c  | 33 +++++++++++++++++++++------------
>>   include/linux/node.h | 16 +++++++---------
>>   mm/memory_hotplug.c  |  5 ++---
>>   3 files changed, 30 insertions(+), 24 deletions(-)
>>
>> diff --git a/drivers/base/node.c b/drivers/base/node.c
>> index 01ee73c9d675..249b2ba6dc81 100644
>> --- a/drivers/base/node.c
>> +++ b/drivers/base/node.c
>> @@ -761,8 +761,8 @@ static int __ref get_nid_for_pfn(unsigned long pfn)
>>   	return pfn_to_nid(pfn);
>>   }
>>   
>> -static int do_register_memory_block_under_node(int nid,
>> -					       struct memory_block *mem_blk)
>> +static void do_register_memory_block_under_node(int nid,
>> +						struct memory_block *mem_blk)
>>   {
>>   	int ret;
>>   
>> @@ -775,12 +775,19 @@ static int do_register_memory_block_under_node(int nid,
>>   	ret = sysfs_create_link_nowarn(&node_devices[nid]->dev.kobj,
>>   				       &mem_blk->dev.kobj,
>>   				       kobject_name(&mem_blk->dev.kobj));
>> -	if (ret)
>> -		return ret;
>> +	if (ret && ret != -EEXIST)
>> +		dev_err_ratelimited(&node_devices[nid]->dev,
>> +				    "can't create link to %s in sysfs (%d)\n",
>> +				    kobject_name(&mem_blk->dev.kobj), ret);
>>   
>> -	return sysfs_create_link_nowarn(&mem_blk->dev.kobj,
>> +	ret = sysfs_create_link_nowarn(&mem_blk->dev.kobj,
>>   				&node_devices[nid]->dev.kobj,
>>   				kobject_name(&node_devices[nid]->dev.kobj));
>> +	if (ret && ret != -EEXIST)
>> +		dev_err_ratelimited(&mem_blk->dev,
>> +				    "can't create link to %s in sysfs (%d)\n",
>> +				    kobject_name(&node_devices[nid]->dev.kobj),
>> +				    ret);
>>   }
>>   
>>   /* register memory section under specified node if it spans that node */
>> @@ -817,7 +824,8 @@ static int register_mem_block_under_node_early(struct memory_block *mem_blk,
>>   			continue;
>>   
>>   		/* The memory block is registered to the first matching node */
>> -		return do_register_memory_block_under_node(nid, mem_blk);
>> +		do_register_memory_block_under_node(nid, mem_blk);
>> +		return 0;
>>   	}
>>   	/* mem section does not span the specified node */
>>   	return 0;
>> @@ -832,7 +840,8 @@ static int register_mem_block_under_node_hotplug(struct memory_block *mem_blk,
>>   {
>>   	int nid = *(int *)arg;
>>   
>> -	return do_register_memory_block_under_node(nid, mem_blk);
>> +	do_register_memory_block_under_node(nid, mem_blk);
>> +	return 0;
>>   }
>>   
>>   /*
>> @@ -850,8 +859,8 @@ void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
>>   			  kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
>>   }
>>   
>> -int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn,
>> -		      enum meminit_context context)
>> +void link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn,
>> +		       enum meminit_context context)
>>   {
>>   	walk_memory_blocks_func_t func;
>>   
>> @@ -860,9 +869,9 @@ int link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn,
>>   	else
>>   		func = register_mem_block_under_node_early;
>>   
>> -	return walk_memory_blocks(PFN_PHYS(start_pfn),
>> -				  PFN_PHYS(end_pfn - start_pfn), (void *)&nid,
>> -				  func);
>> +	walk_memory_blocks(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn),
>> +			   (void *)&nid, func);
>> +	return;
>>   }
>>   
>>   #ifdef CONFIG_HUGETLBFS
>> diff --git a/include/linux/node.h b/include/linux/node.h
>> index 014ba3ab2efd..8e5a29897936 100644
>> --- a/include/linux/node.h
>> +++ b/include/linux/node.h
>> @@ -99,15 +99,14 @@ extern struct node *node_devices[];
>>   typedef  void (*node_registration_func_t)(struct node *);
>>   
>>   #if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA)
>> -int link_mem_sections(int nid, unsigned long start_pfn,
>> -		      unsigned long end_pfn,
>> -		      enum meminit_context context);
>> +void link_mem_sections(int nid, unsigned long start_pfn,
>> +		       unsigned long end_pfn,
>> +		       enum meminit_context context);
>>   #else
>> -static inline int link_mem_sections(int nid, unsigned long start_pfn,
>> -				    unsigned long end_pfn,
>> -				    enum meminit_context context)
>> +static inline void link_mem_sections(int nid, unsigned long start_pfn,
>> +				     unsigned long end_pfn,
>> +				     enum meminit_context context)
>>   {
>> -	return 0;
>>   }
>>   #endif
>>   
>> @@ -130,8 +129,7 @@ static inline int register_one_node(int nid)
>>   		if (error)
>>   			return error;
>>   		/* link memory sections under this node */
>> -		error = link_mem_sections(nid, start_pfn, end_pfn,
>> -					  MEMINIT_EARLY);
>> +		link_mem_sections(nid, start_pfn, end_pfn, MEMINIT_EARLY);
>>   	}
>>   
>>   	return error;
>> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
>> index 03df20078827..01e01a530d38 100644
>> --- a/mm/memory_hotplug.c
>> +++ b/mm/memory_hotplug.c
>> @@ -1080,9 +1080,8 @@ int __ref add_memory_resource(int nid, struct resource *res)
>>   	}
>>   
>>   	/* link memory sections under this node.*/
>> -	ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1),
>> -				MEMINIT_HOTPLUG);
>> -	BUG_ON(ret);
>> +	link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1),
>> +			  MEMINIT_HOTPLUG);
>>   
>>   	/* create new memmap entry */
>>   	if (!strcmp(res->name, "System RAM"))
>>
> 
> I just remember that I still have some cleanup patches lying around that
> rework the whole node onlining on the add_memory() path, being able to
> fail in a nice way rather than ignoring errors. Anyhow, this is good
> enough for now
> 
> Acked-by: David Hildenbrand <david@redhat.com>
> 

Thanks David.