diff mbox series

[v3,11/20] cxl: define a driver interface for HPA free space enumaration

Message ID 20240907081836.5801-12-alejandro.lucero-palau@amd.com (mailing list archive)
State Changes Requested
Headers show
Series cxl: add Type2 device support | expand

Checks

Context Check Description
netdev/series_format fail Series longer than 15 patches
netdev/tree_selection success Guessed tree name to be net-next
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 18 this patch: 18
netdev/build_tools success Errors and warnings before: 0 this patch: 0
netdev/cc_maintainers warning 6 maintainers not CCed: alison.schofield@intel.com vishal.l.verma@intel.com ira.weiny@intel.com dave.jiang@intel.com jonathan.cameron@huawei.com dave@stgolabs.net
netdev/build_clang success Errors and warnings before: 18 this patch: 18
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 18 this patch: 18
netdev/checkpatch warning WARNING: Co-developed-by and Signed-off-by: name/email do not match WARNING: line length of 81 exceeds 80 columns
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc fail Errors and warnings before: 1 this patch: 2
netdev/source_inline success Was 0 now: 0

Commit Message

Lucero Palau, Alejandro Sept. 7, 2024, 8:18 a.m. UTC
From: Alejandro Lucero <alucerop@amd.com>

CXL region creation involves allocating capacity from device DPA
(device-physical-address space) and assigning it to decode a given HPA
(host-physical-address space). Before determining how much DPA to
allocate the amount of available HPA must be determined. Also, not all
HPA is create equal, some specifically targets RAM, some target PMEM,
some is prepared for device-memory flows like HDM-D and HDM-DB, and some
is host-only (HDM-H).

Wrap all of those concerns into an API that retrieves a root decoder
(platform CXL window) that fits the specified constraints and the
capacity available for a new region.

Based on https://lore.kernel.org/linux-cxl/168592159290.1948938.13522227102445462976.stgit@dwillia2-xfh.jf.intel.com/

Signed-off-by: Alejandro Lucero <alucerop@amd.com>
Co-developed-by: Dan Williams <dan.j.williams@intel.com>
---
 drivers/cxl/core/region.c | 141 ++++++++++++++++++++++++++++++++++++++
 drivers/cxl/cxl.h         |   3 +
 drivers/cxl/cxlmem.h      |   3 +
 include/linux/cxl/cxl.h   |   8 +++
 4 files changed, 155 insertions(+)

Comments

Jonathan Cameron Sept. 13, 2024, 5:52 p.m. UTC | #1
On Sat, 7 Sep 2024 09:18:27 +0100
alejandro.lucero-palau@amd.com wrote:

> From: Alejandro Lucero <alucerop@amd.com>
> 
> CXL region creation involves allocating capacity from device DPA
> (device-physical-address space) and assigning it to decode a given HPA
> (host-physical-address space). Before determining how much DPA to
> allocate the amount of available HPA must be determined. Also, not all
> HPA is create equal, some specifically targets RAM, some target PMEM,
> some is prepared for device-memory flows like HDM-D and HDM-DB, and some
> is host-only (HDM-H).
> 
> Wrap all of those concerns into an API that retrieves a root decoder
> (platform CXL window) that fits the specified constraints and the
> capacity available for a new region.
> 
> Based on https://lore.kernel.org/linux-cxl/168592159290.1948938.13522227102445462976.stgit@dwillia2-xfh.jf.intel.com/
> 
> Signed-off-by: Alejandro Lucero <alucerop@amd.com>
> Co-developed-by: Dan Williams <dan.j.williams@intel.com>
Trivial comment inline.

J
> ---
>  drivers/cxl/core/region.c | 141 ++++++++++++++++++++++++++++++++++++++
>  drivers/cxl/cxl.h         |   3 +
>  drivers/cxl/cxlmem.h      |   3 +
>  include/linux/cxl/cxl.h   |   8 +++
>  4 files changed, 155 insertions(+)
> 
> diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
> index 21ad5f242875..bb227bf894c4 100644
> --- a/drivers/cxl/core/region.c
> +++ b/drivers/cxl/core/region.c
> @@ -703,6 +703,147 @@ static int free_hpa(struct cxl_region *cxlr)
>  	return 0;
>  }
>  
> +struct cxlrd_max_context {
> +	struct device *host_bridge;
> +	unsigned long flags;
> +	resource_size_t max_hpa;
> +	struct cxl_root_decoder *cxlrd;
> +};
> +
> +static int find_max_hpa(struct device *dev, void *data)
> +{
> +	struct cxlrd_max_context *ctx = data;
> +	struct cxl_switch_decoder *cxlsd;
> +	struct cxl_root_decoder *cxlrd;
> +	struct resource *res, *prev;
> +	struct cxl_decoder *cxld;
> +	resource_size_t max;
> +
> +	if (!is_root_decoder(dev))
> +		return 0;
> +
> +	cxlrd = to_cxl_root_decoder(dev);
> +	cxld = &cxlrd->cxlsd.cxld;
> +	if ((cxld->flags & ctx->flags) != ctx->flags) {
> +		dev_dbg(dev, "%s, flags not matching: %08lx vs %08lx\n",
> +			__func__, cxld->flags, ctx->flags);
> +		return 0;
> +	}
> +
> +	/* An accelerator can not be part of an interleaved HPA range. */
> +	if (cxld->interleave_ways != 1) {
> +		dev_dbg(dev, "%s, interleave_ways not matching\n", __func__);
> +		return 0;
> +	}
> +
> +	cxlsd = &cxlrd->cxlsd;

Perhaps move this before the 
cxld = and use it there as well?

> +
> +	guard(rwsem_read)(&cxl_region_rwsem);
> +	if (ctx->host_bridge != cxlsd->target[0]->dport_dev) {
> +		dev_dbg(dev, "%s, HOST BRIDGE DOES NOT MATCH\n", __func__);
Capitals seem a bit ott.

> +		return 0;
> +	}
> +
> +	/*
> +	 * Walk the root decoder resource range relying on cxl_region_rwsem to
> +	 * preclude sibling arrival/departure and find the largest free space
> +	 * gap.
> +	 */
> +	lockdep_assert_held_read(&cxl_region_rwsem);
> +	max = 0;
> +	res = cxlrd->res->child;
> +	if (!res)
> +		max = resource_size(cxlrd->res);
> +	else
> +		max = 0;
> +
> +	for (prev = NULL; res; prev = res, res = res->sibling) {
> +		struct resource *next = res->sibling;
> +		resource_size_t free = 0;
> +
> +		if (!prev && res->start > cxlrd->res->start) {
> +			free = res->start - cxlrd->res->start;
> +			max = max(free, max);
> +		}
> +		if (prev && res->start > prev->end + 1) {
> +			free = res->start - prev->end + 1;
> +			max = max(free, max);
> +		}
> +		if (next && res->end + 1 < next->start) {
> +			free = next->start - res->end + 1;
> +			max = max(free, max);
> +		}
> +		if (!next && res->end + 1 < cxlrd->res->end + 1) {
> +			free = cxlrd->res->end + 1 - res->end + 1;
> +			max = max(free, max);
> +		}
> +	}
> +
> +	dev_dbg(CXLRD_DEV(cxlrd), "%s, found %pa bytes of free space\n",
> +		__func__, &max);
> +	if (max > ctx->max_hpa) {
> +		if (ctx->cxlrd)
> +			put_device(CXLRD_DEV(ctx->cxlrd));
> +		get_device(CXLRD_DEV(cxlrd));
> +		ctx->cxlrd = cxlrd;
> +		ctx->max_hpa = max;
> +		dev_dbg(CXLRD_DEV(cxlrd), "%s, found %pa bytes of free space\n",
> +			__func__, &max);
> +	}
> +	return 0;
> +}
Alejandro Lucero Palau Sept. 16, 2024, 2:09 p.m. UTC | #2
On 9/13/24 18:52, Jonathan Cameron wrote:
> On Sat, 7 Sep 2024 09:18:27 +0100
> alejandro.lucero-palau@amd.com wrote:
>
>> From: Alejandro Lucero <alucerop@amd.com>
>>
>> CXL region creation involves allocating capacity from device DPA
>> (device-physical-address space) and assigning it to decode a given HPA
>> (host-physical-address space). Before determining how much DPA to
>> allocate the amount of available HPA must be determined. Also, not all
>> HPA is create equal, some specifically targets RAM, some target PMEM,
>> some is prepared for device-memory flows like HDM-D and HDM-DB, and some
>> is host-only (HDM-H).
>>
>> Wrap all of those concerns into an API that retrieves a root decoder
>> (platform CXL window) that fits the specified constraints and the
>> capacity available for a new region.
>>
>> Based on https://lore.kernel.org/linux-cxl/168592159290.1948938.13522227102445462976.stgit@dwillia2-xfh.jf.intel.com/
>>
>> Signed-off-by: Alejandro Lucero <alucerop@amd.com>
>> Co-developed-by: Dan Williams <dan.j.williams@intel.com>
> Trivial comment inline.
>
> J
>> ---
>>   drivers/cxl/core/region.c | 141 ++++++++++++++++++++++++++++++++++++++
>>   drivers/cxl/cxl.h         |   3 +
>>   drivers/cxl/cxlmem.h      |   3 +
>>   include/linux/cxl/cxl.h   |   8 +++
>>   4 files changed, 155 insertions(+)
>>
>> diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
>> index 21ad5f242875..bb227bf894c4 100644
>> --- a/drivers/cxl/core/region.c
>> +++ b/drivers/cxl/core/region.c
>> @@ -703,6 +703,147 @@ static int free_hpa(struct cxl_region *cxlr)
>>   	return 0;
>>   }
>>   
>> +struct cxlrd_max_context {
>> +	struct device *host_bridge;
>> +	unsigned long flags;
>> +	resource_size_t max_hpa;
>> +	struct cxl_root_decoder *cxlrd;
>> +};
>> +
>> +static int find_max_hpa(struct device *dev, void *data)
>> +{
>> +	struct cxlrd_max_context *ctx = data;
>> +	struct cxl_switch_decoder *cxlsd;
>> +	struct cxl_root_decoder *cxlrd;
>> +	struct resource *res, *prev;
>> +	struct cxl_decoder *cxld;
>> +	resource_size_t max;
>> +
>> +	if (!is_root_decoder(dev))
>> +		return 0;
>> +
>> +	cxlrd = to_cxl_root_decoder(dev);
>> +	cxld = &cxlrd->cxlsd.cxld;
>> +	if ((cxld->flags & ctx->flags) != ctx->flags) {
>> +		dev_dbg(dev, "%s, flags not matching: %08lx vs %08lx\n",
>> +			__func__, cxld->flags, ctx->flags);
>> +		return 0;
>> +	}
>> +
>> +	/* An accelerator can not be part of an interleaved HPA range. */
>> +	if (cxld->interleave_ways != 1) {
>> +		dev_dbg(dev, "%s, interleave_ways not matching\n", __func__);
>> +		return 0;
>> +	}
>> +
>> +	cxlsd = &cxlrd->cxlsd;
> Perhaps move this before the
> cxld = and use it there as well?
>

Yes, I'll do.


>> +
>> +	guard(rwsem_read)(&cxl_region_rwsem);
>> +	if (ctx->host_bridge != cxlsd->target[0]->dport_dev) {
>> +		dev_dbg(dev, "%s, HOST BRIDGE DOES NOT MATCH\n", __func__);
> Capitals seem a bit ott.


I agree!

Thanks


>> +		return 0;
>> +	}
>> +
>> +	/*
>> +	 * Walk the root decoder resource range relying on cxl_region_rwsem to
>> +	 * preclude sibling arrival/departure and find the largest free space
>> +	 * gap.
>> +	 */
>> +	lockdep_assert_held_read(&cxl_region_rwsem);
>> +	max = 0;
>> +	res = cxlrd->res->child;
>> +	if (!res)
>> +		max = resource_size(cxlrd->res);
>> +	else
>> +		max = 0;
>> +
>> +	for (prev = NULL; res; prev = res, res = res->sibling) {
>> +		struct resource *next = res->sibling;
>> +		resource_size_t free = 0;
>> +
>> +		if (!prev && res->start > cxlrd->res->start) {
>> +			free = res->start - cxlrd->res->start;
>> +			max = max(free, max);
>> +		}
>> +		if (prev && res->start > prev->end + 1) {
>> +			free = res->start - prev->end + 1;
>> +			max = max(free, max);
>> +		}
>> +		if (next && res->end + 1 < next->start) {
>> +			free = next->start - res->end + 1;
>> +			max = max(free, max);
>> +		}
>> +		if (!next && res->end + 1 < cxlrd->res->end + 1) {
>> +			free = cxlrd->res->end + 1 - res->end + 1;
>> +			max = max(free, max);
>> +		}
>> +	}
>> +
>> +	dev_dbg(CXLRD_DEV(cxlrd), "%s, found %pa bytes of free space\n",
>> +		__func__, &max);
>> +	if (max > ctx->max_hpa) {
>> +		if (ctx->cxlrd)
>> +			put_device(CXLRD_DEV(ctx->cxlrd));
>> +		get_device(CXLRD_DEV(cxlrd));
>> +		ctx->cxlrd = cxlrd;
>> +		ctx->max_hpa = max;
>> +		dev_dbg(CXLRD_DEV(cxlrd), "%s, found %pa bytes of free space\n",
>> +			__func__, &max);
>> +	}
>> +	return 0;
>> +}
diff mbox series

Patch

diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 21ad5f242875..bb227bf894c4 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -703,6 +703,147 @@  static int free_hpa(struct cxl_region *cxlr)
 	return 0;
 }
 
+struct cxlrd_max_context {
+	struct device *host_bridge;
+	unsigned long flags;
+	resource_size_t max_hpa;
+	struct cxl_root_decoder *cxlrd;
+};
+
+static int find_max_hpa(struct device *dev, void *data)
+{
+	struct cxlrd_max_context *ctx = data;
+	struct cxl_switch_decoder *cxlsd;
+	struct cxl_root_decoder *cxlrd;
+	struct resource *res, *prev;
+	struct cxl_decoder *cxld;
+	resource_size_t max;
+
+	if (!is_root_decoder(dev))
+		return 0;
+
+	cxlrd = to_cxl_root_decoder(dev);
+	cxld = &cxlrd->cxlsd.cxld;
+	if ((cxld->flags & ctx->flags) != ctx->flags) {
+		dev_dbg(dev, "%s, flags not matching: %08lx vs %08lx\n",
+			__func__, cxld->flags, ctx->flags);
+		return 0;
+	}
+
+	/* An accelerator can not be part of an interleaved HPA range. */
+	if (cxld->interleave_ways != 1) {
+		dev_dbg(dev, "%s, interleave_ways not matching\n", __func__);
+		return 0;
+	}
+
+	cxlsd = &cxlrd->cxlsd;
+
+	guard(rwsem_read)(&cxl_region_rwsem);
+	if (ctx->host_bridge != cxlsd->target[0]->dport_dev) {
+		dev_dbg(dev, "%s, HOST BRIDGE DOES NOT MATCH\n", __func__);
+		return 0;
+	}
+
+	/*
+	 * Walk the root decoder resource range relying on cxl_region_rwsem to
+	 * preclude sibling arrival/departure and find the largest free space
+	 * gap.
+	 */
+	lockdep_assert_held_read(&cxl_region_rwsem);
+	max = 0;
+	res = cxlrd->res->child;
+	if (!res)
+		max = resource_size(cxlrd->res);
+	else
+		max = 0;
+
+	for (prev = NULL; res; prev = res, res = res->sibling) {
+		struct resource *next = res->sibling;
+		resource_size_t free = 0;
+
+		if (!prev && res->start > cxlrd->res->start) {
+			free = res->start - cxlrd->res->start;
+			max = max(free, max);
+		}
+		if (prev && res->start > prev->end + 1) {
+			free = res->start - prev->end + 1;
+			max = max(free, max);
+		}
+		if (next && res->end + 1 < next->start) {
+			free = next->start - res->end + 1;
+			max = max(free, max);
+		}
+		if (!next && res->end + 1 < cxlrd->res->end + 1) {
+			free = cxlrd->res->end + 1 - res->end + 1;
+			max = max(free, max);
+		}
+	}
+
+	dev_dbg(CXLRD_DEV(cxlrd), "%s, found %pa bytes of free space\n",
+		__func__, &max);
+	if (max > ctx->max_hpa) {
+		if (ctx->cxlrd)
+			put_device(CXLRD_DEV(ctx->cxlrd));
+		get_device(CXLRD_DEV(cxlrd));
+		ctx->cxlrd = cxlrd;
+		ctx->max_hpa = max;
+		dev_dbg(CXLRD_DEV(cxlrd), "%s, found %pa bytes of free space\n",
+			__func__, &max);
+	}
+	return 0;
+}
+
+/**
+ * cxl_get_hpa_freespace - find a root decoder with free capacity per constraints
+ * @endpoint: an endpoint that is mapped by the returned decoder
+ * @flags: CXL_DECODER_F flags for selecting RAM vs PMEM, and HDM-H vs HDM-D[B]
+ * @max_avail_contig: output parameter of max contiguous bytes available in the
+ *		      returned decoder
+ *
+ * The return tuple of a 'struct cxl_root_decoder' and 'bytes available (@max)'
+ * is a point in time snapshot. If by the time the caller goes to use this root
+ * decoder's capacity the capacity is reduced then caller needs to loop and
+ * retry.
+ *
+ * The returned root decoder has an elevated reference count that needs to be
+ * put with put_device(cxlrd_dev(cxlrd)). Locking context is with
+ * cxl_{acquire,release}_endpoint(), that ensures removal of the root decoder
+ * does not race.
+ */
+struct cxl_root_decoder *cxl_get_hpa_freespace(struct cxl_port *endpoint,
+					       unsigned long flags,
+					       resource_size_t *max_avail_contig)
+{
+	struct cxlrd_max_context ctx = {
+		.host_bridge = endpoint->host_bridge,
+		.flags = flags,
+	};
+	struct cxl_port *root_port;
+	struct cxl_root *root __free(put_cxl_root) = find_cxl_root(endpoint);
+
+	if (!is_cxl_endpoint(endpoint)) {
+		dev_dbg(&endpoint->dev, "hpa requestor is not an endpoint\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (!root) {
+		dev_dbg(&endpoint->dev, "endpoint can not be related to a root port\n");
+		return ERR_PTR(-ENXIO);
+	}
+
+	root_port = &root->port;
+	down_read(&cxl_region_rwsem);
+	device_for_each_child(&root_port->dev, &ctx, find_max_hpa);
+	up_read(&cxl_region_rwsem);
+
+	if (!ctx.cxlrd)
+		return ERR_PTR(-ENOMEM);
+
+	*max_avail_contig = ctx.max_hpa;
+	return ctx.cxlrd;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_get_hpa_freespace, CXL);
+
 static ssize_t size_store(struct device *dev, struct device_attribute *attr,
 			  const char *buf, size_t len)
 {
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 07c153aa3d77..5d83e4a960ef 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -772,6 +772,9 @@  static inline void cxl_setup_parent_dport(struct device *host,
 struct cxl_decoder *to_cxl_decoder(struct device *dev);
 struct cxl_root_decoder *to_cxl_root_decoder(struct device *dev);
 struct cxl_switch_decoder *to_cxl_switch_decoder(struct device *dev);
+
+#define CXLRD_DEV(cxlrd) (&(cxlrd)->cxlsd.cxld.dev)
+
 struct cxl_endpoint_decoder *to_cxl_endpoint_decoder(struct device *dev);
 bool is_root_decoder(struct device *dev);
 bool is_switch_decoder(struct device *dev);
diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index 37c043100300..07259840da8f 100644
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -875,4 +875,7 @@  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_root_decoder *cxl_get_hpa_freespace(struct cxl_port *endpoint,
+					       unsigned long flags,
+					       resource_size_t *max);
 #endif /* __CXL_MEM_H__ */
diff --git a/include/linux/cxl/cxl.h b/include/linux/cxl/cxl.h
index 7e4580fb8659..60a32f60401f 100644
--- a/include/linux/cxl/cxl.h
+++ b/include/linux/cxl/cxl.h
@@ -7,6 +7,10 @@ 
 #include <linux/device.h>
 #include <linux/pci.h>
 
+#define CXL_DECODER_F_RAM   BIT(0)
+#define CXL_DECODER_F_PMEM  BIT(1)
+#define CXL_DECODER_F_TYPE2 BIT(2)
+
 enum cxl_resource {
 	CXL_ACCEL_RES_DPA,
 	CXL_ACCEL_RES_RAM,
@@ -59,4 +63,8 @@  struct cxl_memdev *devm_cxl_add_memdev(struct device *host,
 				       struct cxl_dev_state *cxlds);
 struct cxl_port *cxl_acquire_endpoint(struct cxl_memdev *cxlmd);
 void cxl_release_endpoint(struct cxl_memdev *cxlmd, struct cxl_port *endpoint);
+
+struct cxl_root_decoder *cxl_get_hpa_freespace(struct cxl_port *endpoint,
+					       unsigned long flags,
+					       resource_size_t *max);
 #endif