Re: [PATCH v2 12/15] cxl: allow region creation by type2 drivers

[Alejandro Lucero Palau <alucerop@amd.com>]

On 8/22/24 14:12, Zhi Wang wrote:
> On Mon, 15 Jul 2024 18:28:32 +0100
> <alejandro.lucero-palau@amd.com> wrote:
>
>> From: Alejandro Lucero <alucerop@amd.com>
>>
>> Creating a CXL region requires userspace intervention through the cxl
>> sysfs files. Type2 support should allow accelerator drivers to create
>> such cxl region from kernel code.
>>
>> Adding that functionality and integrating it with current support for
>> memory expanders.
>>
>> Based on
>> https://lore.kernel.org/linux-cxl/168592149709.1948938.8663425987110396027.stgit@dwillia2-xfh.jf.intel.com/T/#m84598b534cc5664f5bb31521ba6e41c7bc213758
>> Signed-off-by: Alejandro Lucero <alucerop@amd.com> Signed-off-by: Dan
>> Williams <dan.j.williams@intel.com> ---
>>   drivers/cxl/core/region.c          | 265
>> ++++++++++++++++++++++------- drivers/cxl/cxl.h                  |
>> 1 + drivers/cxl/cxlmem.h               |   4 +-
>>   drivers/net/ethernet/sfc/efx_cxl.c |  15 +-
>>   include/linux/cxl_accel_mem.h      |   5 +
>>   5 files changed, 231 insertions(+), 59 deletions(-)
>>
>> diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
>> index 5cc71b8868bc..697c8df83a4b 100644
>> --- a/drivers/cxl/core/region.c
>> +++ b/drivers/cxl/core/region.c
>> @@ -479,22 +479,14 @@ static ssize_t interleave_ways_show(struct
>> device *dev,
>>   static const struct attribute_group
>> *get_cxl_region_target_group(void);
>> -static ssize_t interleave_ways_store(struct device *dev,
>> -				     struct device_attribute *attr,
>> -				     const char *buf, size_t len)
>> +static int set_interleave_ways(struct cxl_region *cxlr, int val)
>>   {
>> -	struct cxl_root_decoder *cxlrd =
>> to_cxl_root_decoder(dev->parent);
>> +	struct cxl_root_decoder *cxlrd =
>> to_cxl_root_decoder(cxlr->dev.parent); struct cxl_decoder *cxld =
>> &cxlrd->cxlsd.cxld;
>> -	struct cxl_region *cxlr = to_cxl_region(dev);
>>   	struct cxl_region_params *p = &cxlr->params;
>> -	unsigned int val, save;
>> -	int rc;
>> +	int save, rc;
>>   	u8 iw;
>>   
>> -	rc = kstrtouint(buf, 0, &val);
>> -	if (rc)
>> -		return rc;
>> -
>>   	rc = ways_to_eiw(val, &iw);
>>   	if (rc)
>>   		return rc;
>> @@ -509,25 +501,42 @@ static ssize_t interleave_ways_store(struct
>> device *dev, return -EINVAL;
>>   	}
>>   
>> -	rc = down_write_killable(&cxl_region_rwsem);
>> -	if (rc)
>> -		return rc;
>> -	if (p->state >= CXL_CONFIG_INTERLEAVE_ACTIVE) {
>> -		rc = -EBUSY;
>> -		goto out;
>> -	}
>> +	lockdep_assert_held_write(&cxl_region_rwsem);
>> +	if (p->state >= CXL_CONFIG_INTERLEAVE_ACTIVE)
>> +		return -EBUSY;
>>   
>>   	save = p->interleave_ways;
>>   	p->interleave_ways = val;
>>   	rc = sysfs_update_group(&cxlr->dev.kobj,
>> get_cxl_region_target_group()); if (rc)
>>   		p->interleave_ways = save;
>> -out:
>> +
>> +	return rc;
>> +}
>> +
>> +static ssize_t interleave_ways_store(struct device *dev,
>> +				     struct device_attribute *attr,
>> +				     const char *buf, size_t len)
>> +{
>> +	struct cxl_region *cxlr = to_cxl_region(dev);
>> +	unsigned int val;
>> +	int rc;
>> +
>> +	rc = kstrtouint(buf, 0, &val);
>> +	if (rc)
>> +		return rc;
>> +
>> +	rc = down_write_killable(&cxl_region_rwsem);
>> +	if (rc)
>> +		return rc;
>> +
>> +	rc = set_interleave_ways(cxlr, val);
>>   	up_write(&cxl_region_rwsem);
>>   	if (rc)
>>   		return rc;
>>   	return len;
>>   }
>> +
>>   static DEVICE_ATTR_RW(interleave_ways);
>>   
>>   static ssize_t interleave_granularity_show(struct device *dev,
>> @@ -547,21 +556,14 @@ static ssize_t
>> interleave_granularity_show(struct device *dev, return rc;
>>   }
>>   
>> -static ssize_t interleave_granularity_store(struct device *dev,
>> -					    struct device_attribute
>> *attr,
>> -					    const char *buf, size_t
>> len) +static int set_interleave_granularity(struct cxl_region *cxlr,
>> int val) {
>> -	struct cxl_root_decoder *cxlrd =
>> to_cxl_root_decoder(dev->parent);
>> +	struct cxl_root_decoder *cxlrd =
>> to_cxl_root_decoder(cxlr->dev.parent); struct cxl_decoder *cxld =
>> &cxlrd->cxlsd.cxld;
>> -	struct cxl_region *cxlr = to_cxl_region(dev);
>>   	struct cxl_region_params *p = &cxlr->params;
>> -	int rc, val;
>> +	int rc;
>>   	u16 ig;
>>   
>> -	rc = kstrtoint(buf, 0, &val);
>> -	if (rc)
>> -		return rc;
>> -
>>   	rc = granularity_to_eig(val, &ig);
>>   	if (rc)
>>   		return rc;
>> @@ -577,21 +579,36 @@ static ssize_t
>> interleave_granularity_store(struct device *dev, if
>> (cxld->interleave_ways > 1 && val != cxld->interleave_granularity)
>> return -EINVAL;
>> +	lockdep_assert_held_write(&cxl_region_rwsem);
>> +	if (p->state >= CXL_CONFIG_INTERLEAVE_ACTIVE)
>> +		return -EBUSY;
>> +
>> +	p->interleave_granularity = val;
>> +	return 0;
>> +}
>> +
>> +static ssize_t interleave_granularity_store(struct device *dev,
>> +					    struct device_attribute
>> *attr,
>> +					    const char *buf, size_t
>> len) +{
>> +	struct cxl_region *cxlr = to_cxl_region(dev);
>> +	int rc, val;
>> +
>> +	rc = kstrtoint(buf, 0, &val);
>> +	if (rc)
>> +		return rc;
>> +
>>   	rc = down_write_killable(&cxl_region_rwsem);
>>   	if (rc)
>>   		return rc;
>> -	if (p->state >= CXL_CONFIG_INTERLEAVE_ACTIVE) {
>> -		rc = -EBUSY;
>> -		goto out;
>> -	}
>>   
>> -	p->interleave_granularity = val;
>> -out:
>> +	rc = set_interleave_granularity(cxlr, val);
>>   	up_write(&cxl_region_rwsem);
>>   	if (rc)
>>   		return rc;
>>   	return len;
>>   }
>> +
>>   static DEVICE_ATTR_RW(interleave_granularity);
>>   
>>   static ssize_t resource_show(struct device *dev, struct
>> device_attribute *attr, @@ -2193,7 +2210,7 @@ static int
>> cxl_region_attach(struct cxl_region *cxlr, return 0;
>>   }
>>   
>> -static int cxl_region_detach(struct cxl_endpoint_decoder *cxled)
>> +int cxl_region_detach(struct cxl_endpoint_decoder *cxled)
>>   {
>>   	struct cxl_port *iter, *ep_port = cxled_to_port(cxled);
>>   	struct cxl_region *cxlr = cxled->cxld.region;
>> @@ -2252,6 +2269,7 @@ static int cxl_region_detach(struct
>> cxl_endpoint_decoder *cxled) put_device(&cxlr->dev);
>>   	return rc;
>>   }
>> +EXPORT_SYMBOL_NS_GPL(cxl_region_detach, CXL);
>>   
>>   void cxl_decoder_kill_region(struct cxl_endpoint_decoder *cxled)
>>   {
>> @@ -2746,6 +2764,14 @@ cxl_find_region_by_name(struct
>> cxl_root_decoder *cxlrd, const char *name) return
>> to_cxl_region(region_dev); }
>>   
>> +static void drop_region(struct cxl_region *cxlr)
>> +{
>> +	struct cxl_root_decoder *cxlrd =
>> to_cxl_root_decoder(cxlr->dev.parent);
>> +	struct cxl_port *port = cxlrd_to_port(cxlrd);
>> +
>> +	devm_release_action(port->uport_dev, unregister_region,
>> cxlr); +}
>> +
>>   static ssize_t delete_region_store(struct device *dev,
>>   				   struct device_attribute *attr,
>>   				   const char *buf, size_t len)
>> @@ -3353,17 +3379,18 @@ static int match_region_by_range(struct
>> device *dev, void *data) return rc;
>>   }
>>   
>> -/* Establish an empty region covering the given HPA range */
>> -static struct cxl_region *construct_region(struct cxl_root_decoder
>> *cxlrd,
>> -					   struct
>> cxl_endpoint_decoder *cxled) +static void construct_region_end(void)
>> +{
>> +	up_write(&cxl_region_rwsem);
>> +}
>> +
>> +static struct cxl_region *construct_region_begin(struct
>> cxl_root_decoder *cxlrd,
>> +						 struct
>> cxl_endpoint_decoder *cxled) {
>>   	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
>> -	struct cxl_port *port = cxlrd_to_port(cxlrd);
>> -	struct range *hpa = &cxled->cxld.hpa_range;
>>   	struct cxl_region_params *p;
>>   	struct cxl_region *cxlr;
>> -	struct resource *res;
>> -	int rc;
>> +	int err = 0;
>>   
>>   	do {
>>   		cxlr = __create_region(cxlrd, cxled->mode,
>> @@ -3372,8 +3399,7 @@ static struct cxl_region
>> *construct_region(struct cxl_root_decoder *cxlrd, } while
>> (IS_ERR(cxlr) && PTR_ERR(cxlr) == -EBUSY);
>>   	if (IS_ERR(cxlr)) {
>> -		dev_err(cxlmd->dev.parent,
>> -			"%s:%s: %s failed assign region: %ld\n",
>> +		dev_err(cxlmd->dev.parent,"%s:%s: %s failed assign
>> region: %ld\n", dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev),
>>   			__func__, PTR_ERR(cxlr));
>>   		return cxlr;
>> @@ -3383,23 +3409,47 @@ static struct cxl_region
>> *construct_region(struct cxl_root_decoder *cxlrd, p = &cxlr->params;
>>   	if (p->state >= CXL_CONFIG_INTERLEAVE_ACTIVE) {
>>   		dev_err(cxlmd->dev.parent,
>> -			"%s:%s: %s autodiscovery interrupted\n",
>> +			"%s:%s: %s region setup interrupted\n",
>>   			dev_name(&cxlmd->dev),
>> dev_name(&cxled->cxld.dev), __func__);
>> -		rc = -EBUSY;
>> -		goto err;
>> +		err = -EBUSY;
>> +	}
>> +
>> +	if (err) {
>> +		construct_region_end();
>> +		drop_region(cxlr);
>> +		return ERR_PTR(err);
>>   	}
>> +	return cxlr;
>> +}
>> +
>> +
>> +/* Establish an empty region covering the given HPA range */
>> +static struct cxl_region *construct_region(struct cxl_root_decoder
>> *cxlrd,
>> +					   struct
>> cxl_endpoint_decoder *cxled) +{
>> +	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
>> +	struct range *hpa = &cxled->cxld.hpa_range;
>> +	struct cxl_region_params *p;
>> +	struct cxl_region *cxlr;
>> +	struct resource *res;
>> +	int rc;
>> +
>> +	cxlr = construct_region_begin(cxlrd, cxled);
>> +	if (IS_ERR(cxlr))
>> +		return cxlr;
>>   
>>   	set_bit(CXL_REGION_F_AUTO, &cxlr->flags);
>>   
>>   	res = kmalloc(sizeof(*res), GFP_KERNEL);
>>   	if (!res) {
>>   		rc = -ENOMEM;
>> -		goto err;
>> +		goto out;
>>   	}
>>   
>>   	*res = DEFINE_RES_MEM_NAMED(hpa->start, range_len(hpa),
>>   				    dev_name(&cxlr->dev));
>> +
>>   	rc = insert_resource(cxlrd->res, res);
>>   	if (rc) {
>>   		/*
>> @@ -3412,6 +3462,7 @@ static struct cxl_region
>> *construct_region(struct cxl_root_decoder *cxlrd, __func__,
>> dev_name(&cxlr->dev)); }
>>   
>> +	p = &cxlr->params;
>>   	p->res = res;
>>   	p->interleave_ways = cxled->cxld.interleave_ways;
>>   	p->interleave_granularity =
>> cxled->cxld.interleave_granularity; @@ -3419,24 +3470,124 @@ static
>> struct cxl_region *construct_region(struct cxl_root_decoder *cxlrd,
>>   	rc = sysfs_update_group(&cxlr->dev.kobj,
>> get_cxl_region_target_group()); if (rc)
>> -		goto err;
>> +		goto out;
>>   
>>   	dev_dbg(cxlmd->dev.parent, "%s:%s: %s %s res: %pr iw: %d ig:
>> %d\n",
>> -		dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev),
>> __func__,
>> -		dev_name(&cxlr->dev), p->res, p->interleave_ways,
>> -		p->interleave_granularity);
>> +				   dev_name(&cxlmd->dev),
>> +				   dev_name(&cxled->cxld.dev),
>> __func__,
>> +				   dev_name(&cxlr->dev), p->res,
>> +				   p->interleave_ways,
>> +				   p->interleave_granularity);
>>   
>>   	/* ...to match put_device() in cxl_add_to_region() */
>>   	get_device(&cxlr->dev);
>>   	up_write(&cxl_region_rwsem);
>> +out:
>> +	construct_region_end();
>> +	if (rc) {
>> +		drop_region(cxlr);
>> +		return ERR_PTR(rc);
>> +	}
>> +	return cxlr;
>> +}
>> +
>> +static struct cxl_region *
>> +__construct_new_region(struct cxl_root_decoder *cxlrd,
>> +		       struct cxl_endpoint_decoder **cxled, int ways)
>> +{
>> +	struct cxl_decoder *cxld = &cxlrd->cxlsd.cxld;
>> +	struct cxl_region_params *p;
>> +	resource_size_t size = 0;
>> +	struct cxl_region *cxlr;
>> +	int rc, i;
>> +
>> +	/* If interleaving is not supported, why does ways need to
>> be at least 1? */
>> +	if (ways < 1)
>> +		return ERR_PTR(-EINVAL);
>> +
>> +	cxlr = construct_region_begin(cxlrd, cxled[0]);
>> +	if (IS_ERR(cxlr))
>> +		return cxlr;
>> +
>> +	rc = set_interleave_ways(cxlr, ways);
>> +	if (rc)
>> +		goto out;
>> +
>> +	rc = set_interleave_granularity(cxlr,
>> cxld->interleave_granularity);
>> +	if (rc)
>> +		goto out;
>> +
>> +	down_read(&cxl_dpa_rwsem);
>> +	for (i = 0; i < ways; i++) {
>> +		if (!cxled[i]->dpa_res)
>> +			break;
>> +		size += resource_size(cxled[i]->dpa_res);
>> +	}
>> +	up_read(&cxl_dpa_rwsem);
>> +
>> +	if (i < ways)
>> +		goto out;
>> +
>> +	rc = alloc_hpa(cxlr, size);
>> +	if (rc)
>> +		goto out;
>> +
>> +	down_read(&cxl_dpa_rwsem);
>> +	for (i = 0; i < ways; i++) {
>> +		rc = cxl_region_attach(cxlr, cxled[i], i);
>> +		if (rc)
>> +			break;
>> +	}
>> +	up_read(&cxl_dpa_rwsem);
>> +
>> +	if (rc)
>> +		goto out;
>> +
>> +	rc = cxl_region_decode_commit(cxlr);
>> +	if (rc)
>> +		goto out;
>>   
>> +	p = &cxlr->params;
>> +	p->state = CXL_CONFIG_COMMIT;
>> +out:
>> +	construct_region_end();
>> +	if (rc) {
>> +		drop_region(cxlr);
>> +		return ERR_PTR(rc);
>> +	}
>>   	return cxlr;
>> +}
>>   
>> -err:
>> -	up_write(&cxl_region_rwsem);
>> -	devm_release_action(port->uport_dev, unregister_region,
>> cxlr);
>> -	return ERR_PTR(rc);
>> +/**
>> + * cxl_create_region - Establish a region given an array of endpoint
>> decoders
>> + * @cxlrd: root decoder to allocate HPA
>> + * @cxled: array of endpoint decoders with reserved DPA capacity
>> + * @ways: size of @cxled array
>> + *
>> + * Returns a fully formed region in the commit state and attached to
>> the
>> + * cxl_region driver.
>> + */
>> +struct cxl_region *cxl_create_region(struct cxl_root_decoder *cxlrd,
>> +				     struct cxl_endpoint_decoder
>> **cxled,
>> +				     int ways)
>> +{
>> +	struct cxl_region *cxlr;
>> +
>> +	mutex_lock(&cxlrd->range_lock);
>> +	cxlr = __construct_new_region(cxlrd, cxled, ways);
>> +	mutex_unlock(&cxlrd->range_lock);
>> +
>> +	if (IS_ERR(cxlr))
>> +		return cxlr;
>> +
>> +	if (device_attach(&cxlr->dev) <= 0) {
>> +		dev_err(&cxlr->dev, "failed to create region\n");
>> +		drop_region(cxlr);
>> +		return ERR_PTR(-ENODEV);
>> +	}
>> +	return cxlr;
>>   }
>> +EXPORT_SYMBOL_NS_GPL(cxl_create_region, CXL);
>>   
>>   int cxl_add_to_region(struct cxl_port *root, struct
>> cxl_endpoint_decoder *cxled) {
>> diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
>> index d3fdd2c1e066..1bf3b74ff959 100644
>> --- a/drivers/cxl/cxl.h
>> +++ b/drivers/cxl/cxl.h
>> @@ -905,6 +905,7 @@ void cxl_coordinates_combine(struct
>> access_coordinate *out,
>>   bool cxl_endpoint_decoder_reset_detected(struct cxl_port *port);
>>   
>> +int cxl_region_detach(struct cxl_endpoint_decoder *cxled);
>>   /*
>>    * Unit test builds overrides this to __weak, find the 'strong'
>> version
>>    * of these symbols in tools/testing/cxl/.
>> diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
>> index a0e0795ec064..377bb3cd2d47 100644
>> --- a/drivers/cxl/cxlmem.h
>> +++ b/drivers/cxl/cxlmem.h
>> @@ -881,5 +881,7 @@ struct cxl_root_decoder
>> *cxl_get_hpa_freespace(struct cxl_port *endpoint, int interleave_ways,
>>   					       unsigned long flags,
>>   					       resource_size_t *max);
>> -
>> +struct cxl_region *cxl_create_region(struct cxl_root_decoder *cxlrd,
>> +				     struct cxl_endpoint_decoder
>> **cxled,
>> +				     int ways);
>>   #endif /* __CXL_MEM_H__ */
>> diff --git a/drivers/net/ethernet/sfc/efx_cxl.c
>> b/drivers/net/ethernet/sfc/efx_cxl.c index b5626d724b52..4012e3faa298
>> 100644 --- a/drivers/net/ethernet/sfc/efx_cxl.c
>> +++ b/drivers/net/ethernet/sfc/efx_cxl.c
>> @@ -92,8 +92,18 @@ void efx_cxl_init(struct efx_nic *efx)
>>   
>>   	cxl->cxled = cxl_request_dpa(cxl->endpoint, true,
>> EFX_CTPIO_BUFFER_SIZE, EFX_CTPIO_BUFFER_SIZE);
>> -	if (IS_ERR(cxl->cxled))
>> +	if (IS_ERR(cxl->cxled)) {
>>   		pci_info(pci_dev, "CXL accel request DPA failed");
>> +		return;
>> +	}
>> +
>> +	cxl->efx_region = cxl_create_region(cxl->cxlrd, &cxl->cxled,
>> 1);
>> +	if (!cxl->efx_region) {
> if (IS_ERR(cxl->efx_region))
>

I'll fix it.

Thanks