Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:5 as permitted sender) client-ip=2620:137:e000::3:5;
Message-ID: <831b9b12-08fe-f5dc-f21d-83284b0aee8a@redhat.com>
Date:   Mon, 9 Oct 2023 17:04:05 +0200
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:102.0) Gecko/20100101
 Thunderbird/102.15.1
Subject: Re: [PATCH v5 1/2] mm/memory_hotplug: split memmap_on_memory requests
 across memblocks
Content-Language: en-US
To:     "Huang, Ying" <ying.huang@intel.com>,
        Vishal Verma <vishal.l.verma@intel.com>
Cc:     Andrew Morton <akpm@linux-foundation.org>,
        Oscar Salvador <osalvador@suse.de>,
        Dan Williams <dan.j.williams@intel.com>,
        Dave Jiang <dave.jiang@intel.com>,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        nvdimm@lists.linux.dev, linux-cxl@vger.kernel.org,
        Dave Hansen <dave.hansen@linux.intel.com>,
        "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>,
        Michal Hocko <mhocko@suse.com>,
        Jonathan Cameron <Jonathan.Cameron@Huawei.com>,
        Jeff Moyer <jmoyer@redhat.com>
References: <20231005-vv-kmem_memmap-v5-0-a54d1981f0a3@intel.com>
 <20231005-vv-kmem_memmap-v5-1-a54d1981f0a3@intel.com>
 <87jzrylslk.fsf@yhuang6-desk2.ccr.corp.intel.com>
From:   David Hildenbrand <david@redhat.com>
Organization: Red Hat
In-Reply-To: <87jzrylslk.fsf@yhuang6-desk2.ccr.corp.intel.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 07.10.23 10:55, Huang, Ying wrote:
> Vishal Verma <vishal.l.verma@intel.com> writes:
> 
>> The MHP_MEMMAP_ON_MEMORY flag for hotplugged memory is restricted to
>> 'memblock_size' chunks of memory being added. Adding a larger span of
>> memory precludes memmap_on_memory semantics.
>>
>> For users of hotplug such as kmem, large amounts of memory might get
>> added from the CXL subsystem. In some cases, this amount may exceed the
>> available 'main memory' to store the memmap for the memory being added.
>> In this case, it is useful to have a way to place the memmap on the
>> memory being added, even if it means splitting the addition into
>> memblock-sized chunks.
>>
>> Change add_memory_resource() to loop over memblock-sized chunks of
>> memory if caller requested memmap_on_memory, and if other conditions for
>> it are met. Teach try_remove_memory() to also expect that a memory
>> range being removed might have been split up into memblock sized chunks,
>> and to loop through those as needed.
>>
>> Cc: Andrew Morton <akpm@linux-foundation.org>
>> Cc: David Hildenbrand <david@redhat.com>
>> Cc: Michal Hocko <mhocko@suse.com>
>> Cc: Oscar Salvador <osalvador@suse.de>
>> Cc: Dan Williams <dan.j.williams@intel.com>
>> Cc: Dave Jiang <dave.jiang@intel.com>
>> Cc: Dave Hansen <dave.hansen@linux.intel.com>
>> Cc: Huang Ying <ying.huang@intel.com>
>> Suggested-by: David Hildenbrand <david@redhat.com>
>> Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
>> ---
>>   mm/memory_hotplug.c | 162 ++++++++++++++++++++++++++++++++--------------------
>>   1 file changed, 99 insertions(+), 63 deletions(-)
>>
>> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
>> index f8d3e7427e32..77ec6f15f943 100644
>> --- a/mm/memory_hotplug.c
>> +++ b/mm/memory_hotplug.c
>> @@ -1380,6 +1380,44 @@ static bool mhp_supports_memmap_on_memory(unsigned long size)
>>   	return arch_supports_memmap_on_memory(vmemmap_size);
>>   }
>>   
>> +static int add_memory_create_devices(int nid, struct memory_group *group,
>> +				     u64 start, u64 size, mhp_t mhp_flags)
>> +{
>> +	struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
>> +	struct vmem_altmap mhp_altmap = {
>> +		.base_pfn =  PHYS_PFN(start),
>> +		.end_pfn  =  PHYS_PFN(start + size - 1),
>> +	};
>> +	int ret;
>> +
>> +	if ((mhp_flags & MHP_MEMMAP_ON_MEMORY)) {
>> +		mhp_altmap.free = memory_block_memmap_on_memory_pages();
>> +		params.altmap = kmalloc(sizeof(struct vmem_altmap), GFP_KERNEL);
>> +		if (!params.altmap)
>> +			return -ENOMEM;
>> +
>> +		memcpy(params.altmap, &mhp_altmap, sizeof(mhp_altmap));
>> +	}
>> +
>> +	/* call arch's memory hotadd */
>> +	ret = arch_add_memory(nid, start, size, &params);
>> +	if (ret < 0)
>> +		goto error;
>> +
>> +	/* create memory block devices after memory was added */
>> +	ret = create_memory_block_devices(start, size, params.altmap, group);
>> +	if (ret)
>> +		goto err_bdev;
>> +
>> +	return 0;
>> +
>> +err_bdev:
>> +	arch_remove_memory(start, size, NULL);
>> +error:
>> +	kfree(params.altmap);
>> +	return ret;
>> +}
>> +
>>   /*
>>    * NOTE: The caller must call lock_device_hotplug() to serialize hotplug
>>    * and online/offline operations (triggered e.g. by sysfs).
>> @@ -1388,14 +1426,10 @@ static bool mhp_supports_memmap_on_memory(unsigned long size)
>>    */
>>   int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
>>   {
>> -	struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
>> +	unsigned long memblock_size = memory_block_size_bytes();
>>   	enum memblock_flags memblock_flags = MEMBLOCK_NONE;
>> -	struct vmem_altmap mhp_altmap = {
>> -		.base_pfn =  PHYS_PFN(res->start),
>> -		.end_pfn  =  PHYS_PFN(res->end),
>> -	};
>>   	struct memory_group *group = NULL;
>> -	u64 start, size;
>> +	u64 start, size, cur_start;
>>   	bool new_node = false;
>>   	int ret;
>>   
>> @@ -1436,28 +1470,21 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
>>   	/*
>>   	 * Self hosted memmap array
>>   	 */
>> -	if (mhp_flags & MHP_MEMMAP_ON_MEMORY) {
>> -		if (mhp_supports_memmap_on_memory(size)) {
>> -			mhp_altmap.free = memory_block_memmap_on_memory_pages();
>> -			params.altmap = kmalloc(sizeof(struct vmem_altmap), GFP_KERNEL);
>> -			if (!params.altmap)
>> +	if ((mhp_flags & MHP_MEMMAP_ON_MEMORY) &&
>> +	    mhp_supports_memmap_on_memory(memblock_size)) {
>> +		for (cur_start = start; cur_start < start + size;
>> +		     cur_start += memblock_size) {
>> +			ret = add_memory_create_devices(nid, group, cur_start,
>> +							memblock_size,
>> +							mhp_flags);
>> +			if (ret)
>>   				goto error;
>> -
>> -			memcpy(params.altmap, &mhp_altmap, sizeof(mhp_altmap));
>>   		}
>> -		/* fallback to not using altmap  */
>> -	}
>> -
>> -	/* call arch's memory hotadd */
>> -	ret = arch_add_memory(nid, start, size, &params);
>> -	if (ret < 0)
>> -		goto error_free;
>> -
>> -	/* create memory block devices after memory was added */
>> -	ret = create_memory_block_devices(start, size, params.altmap, group);
>> -	if (ret) {
>> -		arch_remove_memory(start, size, NULL);
>> -		goto error_free;
>> +	} else {
>> +		ret = add_memory_create_devices(nid, group, start, size,
>> +						mhp_flags);
>> +		if (ret)
>> +			goto error;
>>   	}
>>   
>>   	if (new_node) {
>> @@ -1494,8 +1521,6 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
>>   		walk_memory_blocks(start, size, NULL, online_memory_block);
>>   
>>   	return ret;
>> -error_free:
>> -	kfree(params.altmap);
>>   error:
>>   	if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK))
>>   		memblock_remove(start, size);
>> @@ -2146,12 +2171,41 @@ void try_offline_node(int nid)
>>   }
>>   EXPORT_SYMBOL(try_offline_node);
>>   
>> -static int __ref try_remove_memory(u64 start, u64 size)
>> +static void __ref remove_memory_block_and_altmap(int nid, u64 start, u64 size)
>>   {
>> +	int rc = 0;
>>   	struct memory_block *mem;
>> -	int rc = 0, nid = NUMA_NO_NODE;
>>   	struct vmem_altmap *altmap = NULL;
>>   
>> +	rc = walk_memory_blocks(start, size, &mem, test_has_altmap_cb);
>> +	if (rc) {
>> +		altmap = mem->altmap;
>> +		/*
>> +		 * Mark altmap NULL so that we can add a debug
>> +		 * check on memblock free.
>> +		 */
>> +		mem->altmap = NULL;
>> +	}
>> +
>> +	/*
>> +	 * Memory block device removal under the device_hotplug_lock is
>> +	 * a barrier against racing online attempts.
>> +	 */
>> +	remove_memory_block_devices(start, size);
>> +
>> +	arch_remove_memory(start, size, altmap);
>> +
>> +	/* Verify that all vmemmap pages have actually been freed. */
>> +	if (altmap) {
>> +		WARN(altmap->alloc, "Altmap not fully unmapped");
>> +		kfree(altmap);
>> +	}
>> +}
>> +
>> +static int __ref try_remove_memory(u64 start, u64 size)
>> +{
>> +	int rc, nid = NUMA_NO_NODE;
>> +
>>   	BUG_ON(check_hotplug_memory_range(start, size));
>>   
>>   	/*
>> @@ -2167,47 +2221,28 @@ static int __ref try_remove_memory(u64 start, u64 size)
>>   	if (rc)
>>   		return rc;
>>   
>> +	mem_hotplug_begin();
>> +
>>   	/*
>> -	 * We only support removing memory added with MHP_MEMMAP_ON_MEMORY in
>> -	 * the same granularity it was added - a single memory block.
>> +	 * For memmap_on_memory, the altmaps could have been added on
>> +	 * a per-memblock basis. Loop through the entire range if so,
>> +	 * and remove each memblock and its altmap.
>>   	 */
>>   	if (mhp_memmap_on_memory()) {
> 
> IIUC, even if mhp_memmap_on_memory() returns true, it's still possible
> that the memmap is put in DRAM after [2/2].  So that,
> arch_remove_memory() are called for each memory block unnecessarily.  Can
> we detect this (via altmap?) and call remove_memory_block_and_altmap()
> for the whole range?

Good point. We should handle memblock-per-memblock onny if we have to 
handle the altmap. Otherwise, just call a separate function that doesn't 
care about -- e.g., called remove_memory_blocks_no_altmap().

We could simply walk all memory blocks and make sure either all have an 
altmap or none has an altmap. If there is a mix, we should bail out with 
WARN_ON_ONCE().

-- 
Cheers,

David / dhildenb