[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20241119223705.00001c1d@nvidia.com>
Date: Tue, 19 Nov 2024 22:37:05 +0200
From: Zhi Wang <zhiw@...dia.com>
To: <alejandro.lucero-palau@....com>
CC: <linux-cxl@...r.kernel.org>, <netdev@...r.kernel.org>,
<dan.j.williams@...el.com>, <martin.habets@...inx.com>,
<edward.cree@....com>, <davem@...emloft.net>, <kuba@...nel.org>,
<pabeni@...hat.com>, <edumazet@...gle.com>, Alejandro Lucero
<alucerop@....com>
Subject: Re: [PATCH v5 22/27] cxl: allow region creation by type2 drivers
On Mon, 18 Nov 2024 16:44:29 +0000
<alejandro.lucero-palau@....com> wrote:
> From: Alejandro Lucero <alucerop@....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/168592159835.1948938.1647215579839222774.stgit@dwillia2-xfh.jf.intel.com/
>
> Signed-off-by: Alejandro Lucero <alucerop@....com>
> Signed-off-by: Dan Williams <dan.j.williams@...el.com>
> ---
> drivers/cxl/core/region.c | 147 ++++++++++++++++++++++++++++++++++----
> drivers/cxl/cxlmem.h | 2 +
> drivers/cxl/port.c | 5 +-
> include/cxl/cxl.h | 4 ++
> 4 files changed, 142 insertions(+), 16 deletions(-)
>
> diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
> index 6652887ea396..70549d42c2e3 100644
> --- a/drivers/cxl/core/region.c
> +++ b/drivers/cxl/core/region.c
> @@ -2256,6 +2256,18 @@ static int cxl_region_detach(struct cxl_endpoint_decoder *cxled)
> return rc;
> }
>
> +int cxl_accel_region_detach(struct cxl_endpoint_decoder *cxled)
> +{
> + int rc;
> +
> + down_write(&cxl_region_rwsem);
> + cxled->mode = CXL_DECODER_DEAD;
> + rc = cxl_region_detach(cxled);
> + up_write(&cxl_region_rwsem);
> + return rc;
> +}
> +EXPORT_SYMBOL_NS_GPL(cxl_accel_region_detach, CXL);
> +
> void cxl_decoder_kill_region(struct cxl_endpoint_decoder *cxled)
> {
> down_write(&cxl_region_rwsem);
> @@ -2770,6 +2782,14 @@ 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)
> @@ -3376,17 +3396,18 @@ 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;
maybe let's keep the original name "rc".
>
> do {
> cxlr = __create_region(cxlrd, cxled->mode,
> @@ -3395,8 +3416,7 @@ 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;
> @@ -3406,13 +3426,33 @@ 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;
> + 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);
> @@ -3435,6 +3475,7 @@ 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;
> @@ -3452,15 +3493,91 @@ static struct cxl_region *construct_region(struct cxl_root_decoder *cxlrd,
> /* ...to match put_device() in cxl_add_to_region() */
> get_device(&cxlr->dev);
> up_write(&cxl_region_rwsem);
> -
> + construct_region_end();
cxl_region_rwsem seems got up_write() two times. Guess you should remove
it like below since it is now done in construct_region_end().
> return cxlr;
>
> err:
> - up_write(&cxl_region_rwsem);
> - devm_release_action(port->uport_dev, unregister_region, cxlr);
> + construct_region_end();
> + drop_region(cxlr);
> + return ERR_PTR(rc);
> +}
> +
> +static struct cxl_region *
> +__construct_new_region(struct cxl_root_decoder *cxlrd,
> + struct cxl_endpoint_decoder *cxled)
> +{
> + struct cxl_decoder *cxld = &cxlrd->cxlsd.cxld;
> + struct cxl_region_params *p;
> + struct cxl_region *cxlr;
> + int rc;
> +
> + cxlr = construct_region_begin(cxlrd, cxled);
> + if (IS_ERR(cxlr))
> + return cxlr;
> +
> + rc = set_interleave_ways(cxlr, 1);
> + if (rc)
> + goto err;
> +
> + rc = set_interleave_granularity(cxlr, cxld->interleave_granularity);
> + if (rc)
> + goto err;
> +
> + rc = alloc_hpa(cxlr, resource_size(cxled->dpa_res));
> + if (rc)
> + goto err;
> +
> + down_read(&cxl_dpa_rwsem);
> + rc = cxl_region_attach(cxlr, cxled, 0);
> + up_read(&cxl_dpa_rwsem);
> +
> + if (rc)
> + goto err;
> +
> + rc = cxl_region_decode_commit(cxlr);
> + if (rc)
> + goto err;
> +
> + p = &cxlr->params;
> + p->state = CXL_CONFIG_COMMIT;
> +
> + construct_region_end();
> + return cxlr;
> +err:
> + construct_region_end();
> + drop_region(cxlr);
> return ERR_PTR(rc);
> }
>
> +/**
> + * cxl_create_region - Establish a region given an endpoint decoder
> + * @cxlrd: root decoder to allocate HPA
> + * @cxled: endpoint decoder with reserved DPA capacity
> + *
> + * 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)
> +{
> + struct cxl_region *cxlr;
> +
> + mutex_lock(&cxlrd->range_lock);
> + cxlr = __construct_new_region(cxlrd, cxled);
> + 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)
> {
> struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
> diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
> index 4c1c53c29544..9d874f1cb3bf 100644
> --- a/drivers/cxl/cxlmem.h
> +++ b/drivers/cxl/cxlmem.h
> @@ -874,4 +874,6 @@ struct cxl_hdm {
> struct seq_file;
> struct dentry *cxl_debugfs_create_dir(const char *dir);
> void cxl_dpa_debug(struct seq_file *file, struct cxl_dev_state *cxlds);
> +struct cxl_region *cxl_create_region(struct cxl_root_decoder *cxlrd,
> + struct cxl_endpoint_decoder *cxled);
> #endif /* __CXL_MEM_H__ */
> diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c
> index acf2ac70f343..ec1f0cfb11a5 100644
> --- a/drivers/cxl/port.c
> +++ b/drivers/cxl/port.c
> @@ -33,6 +33,7 @@ static void schedule_detach(void *cxlmd)
> static int discover_region(struct device *dev, void *root)
> {
> struct cxl_endpoint_decoder *cxled;
> + struct cxl_memdev *cxlmd;
> int rc;
>
> if (!is_endpoint_decoder(dev))
> @@ -42,7 +43,9 @@ static int discover_region(struct device *dev, void *root)
> if ((cxled->cxld.flags & CXL_DECODER_F_ENABLE) == 0)
> return 0;
>
> - if (cxled->state != CXL_DECODER_STATE_AUTO)
> + cxlmd = cxled_to_memdev(cxled);
> + if (cxled->state != CXL_DECODER_STATE_AUTO ||
> + cxlmd->cxlds->type == CXL_DEVTYPE_DEVMEM)
> return 0;
>
> /*
> diff --git a/include/cxl/cxl.h b/include/cxl/cxl.h
> index 9b5b5472a86b..d295af4f5f9e 100644
> --- a/include/cxl/cxl.h
> +++ b/include/cxl/cxl.h
> @@ -72,4 +72,8 @@ struct cxl_endpoint_decoder *cxl_request_dpa(struct cxl_memdev *cxlmd,
> resource_size_t min,
> resource_size_t max);
> int cxl_dpa_free(struct cxl_endpoint_decoder *cxled);
> +struct cxl_region *cxl_create_region(struct cxl_root_decoder *cxlrd,
> + struct cxl_endpoint_decoder *cxled);
> +
> +int cxl_accel_region_detach(struct cxl_endpoint_decoder *cxled);
> #endif
Powered by blists - more mailing lists