[PATCH v2 0/3] CXL updates for v6.19

[PATCH v2 0/3] CXL updates for v6.19

[Robert Richter]

Sending optional and rather independent patches from v5 of the CXL
address translation series [1] separately in this series. The patches
could be applied together with early pick up candidates from the
address translation series (namely patch #1 to #4 or #5).

[1] https://patchwork.kernel.org/project/cxl/cover/20251112203143.1269944-1-rrichter@amd.com/

V2:
 * updated sob-chain,
 * spell fixes in description of patch #1,

Robert Richter (3):
  cxl: Simplify cxl_rd_ops allocation and handling
  cxl/acpi: Group xor arithmetric setup code in a single block
  cxl/region: Remove local variable @inc in cxl_port_setup_targets()

 drivers/cxl/acpi.c        | 15 ++++-----------
 drivers/cxl/core/region.c | 25 +++++++------------------
 drivers/cxl/cxl.h         |  2 +-
 3 files changed, 12 insertions(+), 30 deletions(-)

-- 
2.47.3

[PATCH v2 1/3] cxl: Simplify cxl_rd_ops allocation and handling

[Robert Richter]

A root decoder's callback handlers are collected in struct cxl_rd_ops.
The structure is dynamically allocated, though it contains only a few
pointers in it. This also requires to check two pointers for the
existence of a callback.

Simplify the allocation, release and handler check by embedding the
ops statically in struct cxl_root_decoder.

Implementation is equivalent to how struct cxl_root_ops handles the
callbacks.

Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Gregory Price <gourry@gourry.net>
Signed-off-by: Robert Richter <rrichter@amd.com>
---
 drivers/cxl/acpi.c        |  8 ++------
 drivers/cxl/core/region.c | 20 +++++---------------
 drivers/cxl/cxl.h         |  2 +-
 3 files changed, 8 insertions(+), 22 deletions(-)

diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
index d5119de7f5a9..fab736aa77dc 100644
--- a/drivers/cxl/acpi.c
+++ b/drivers/cxl/acpi.c
@@ -487,12 +487,8 @@ static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws,
 	cxlrd->qos_class = cfmws->qtg_id;
 
 	if (cfmws->interleave_arithmetic == ACPI_CEDT_CFMWS_ARITHMETIC_XOR) {
-		cxlrd->ops = kzalloc(sizeof(*cxlrd->ops), GFP_KERNEL);
-		if (!cxlrd->ops)
-			return -ENOMEM;
-
-		cxlrd->ops->hpa_to_spa = cxl_apply_xor_maps;
-		cxlrd->ops->spa_to_hpa = cxl_apply_xor_maps;
+		cxlrd->ops.hpa_to_spa = cxl_apply_xor_maps;
+		cxlrd->ops.spa_to_hpa = cxl_apply_xor_maps;
 	}
 
 	rc = cxl_decoder_add(cxld);
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 451e5492911c..2b5ae5d9a4b6 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -2958,16 +2958,6 @@ static bool cxl_is_hpa_in_chunk(u64 hpa, struct cxl_region *cxlr, int pos)
 	return false;
 }
 
-static bool has_hpa_to_spa(struct cxl_root_decoder *cxlrd)
-{
-	return cxlrd->ops && cxlrd->ops->hpa_to_spa;
-}
-
-static bool has_spa_to_hpa(struct cxl_root_decoder *cxlrd)
-{
-	return cxlrd->ops && cxlrd->ops->spa_to_hpa;
-}
-
 #define CXL_POS_ZERO 0
 /**
  * cxl_validate_translation_params
@@ -3141,8 +3131,8 @@ u64 cxl_dpa_to_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd,
 	hpa = hpa_offset + p->res->start + p->cache_size;
 
 	/* Root decoder translation overrides typical modulo decode */
-	if (has_hpa_to_spa(cxlrd))
-		hpa = cxlrd->ops->hpa_to_spa(cxlrd, hpa);
+	if (cxlrd->ops.hpa_to_spa)
+		hpa = cxlrd->ops.hpa_to_spa(cxlrd, hpa);
 
 	if (!cxl_resource_contains_addr(p->res, hpa)) {
 		dev_dbg(&cxlr->dev,
@@ -3151,7 +3141,7 @@ u64 cxl_dpa_to_hpa(struct cxl_region *cxlr, const struct cxl_memdev *cxlmd,
 	}
 
 	/* Simple chunk check, by pos & gran, only applies to modulo decodes */
-	if (!has_hpa_to_spa(cxlrd) && (!cxl_is_hpa_in_chunk(hpa, cxlr, pos)))
+	if (!cxlrd->ops.hpa_to_spa && !cxl_is_hpa_in_chunk(hpa, cxlr, pos))
 		return ULLONG_MAX;
 
 	return hpa;
@@ -3184,8 +3174,8 @@ static int region_offset_to_dpa_result(struct cxl_region *cxlr, u64 offset,
 	 * If the root decoder has SPA to CXL HPA callback, use it. Otherwise
 	 * CXL HPA is assumed to equal SPA.
 	 */
-	if (has_spa_to_hpa(cxlrd)) {
-		hpa = cxlrd->ops->spa_to_hpa(cxlrd, p->res->start + offset);
+	if (cxlrd->ops.spa_to_hpa) {
+		hpa = cxlrd->ops.spa_to_hpa(cxlrd, p->res->start + offset);
 		hpa_offset = hpa - p->res->start;
 	} else {
 		hpa_offset = offset;
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 0481679eb109..91ff47382111 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -451,7 +451,7 @@ struct cxl_root_decoder {
 	void *platform_data;
 	struct mutex range_lock;
 	int qos_class;
-	struct cxl_rd_ops *ops;
+	struct cxl_rd_ops ops;
 	struct cxl_switch_decoder cxlsd;
 };
 
-- 
2.47.3

[PATCH v2 2/3] cxl/acpi: Group xor arithmetric setup code in a single block

[Robert Richter]

Simplify the xor arithmetric setup code by grouping it in a single
block. No need to split the block for QoS setup.

It is safe to reorder the call of cxl_setup_extended_linear_cache()
because there are no dependencies.

Reviewed-by: Gregory Price <gourry@gourry.net>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Signed-off-by: Robert Richter <rrichter@amd.com>
---
 drivers/cxl/acpi.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
index fab736aa77dc..50c2987e0459 100644
--- a/drivers/cxl/acpi.c
+++ b/drivers/cxl/acpi.c
@@ -465,8 +465,6 @@ static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws,
 		ig = CXL_DECODER_MIN_GRANULARITY;
 	cxld->interleave_granularity = ig;
 
-	cxl_setup_extended_linear_cache(cxlrd);
-
 	if (cfmws->interleave_arithmetic == ACPI_CEDT_CFMWS_ARITHMETIC_XOR) {
 		if (ways != 1 && ways != 3) {
 			cxims_ctx = (struct cxl_cxims_context) {
@@ -482,15 +480,14 @@ static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws,
 				return -EINVAL;
 			}
 		}
-	}
-
-	cxlrd->qos_class = cfmws->qtg_id;
-
-	if (cfmws->interleave_arithmetic == ACPI_CEDT_CFMWS_ARITHMETIC_XOR) {
 		cxlrd->ops.hpa_to_spa = cxl_apply_xor_maps;
 		cxlrd->ops.spa_to_hpa = cxl_apply_xor_maps;
 	}
 
+	cxl_setup_extended_linear_cache(cxlrd);
+
+	cxlrd->qos_class = cfmws->qtg_id;
+
 	rc = cxl_decoder_add(cxld);
 	if (rc)
 		return rc;
-- 
2.47.3

[PATCH v2 3/3] cxl/region: Remove local variable @inc in cxl_port_setup_targets()

[Robert Richter]

Simplify the code by removing local variable @inc. The variable is not
used elsewhere, remove it and directly increment the target number.

Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Gregory Price <gourry@gourry.net>
Signed-off-by: Robert Richter <rrichter@amd.com>
---
 drivers/cxl/core/region.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 2b5ae5d9a4b6..e577b11bd889 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -1357,7 +1357,7 @@ static int cxl_port_setup_targets(struct cxl_port *port,
 				  struct cxl_endpoint_decoder *cxled)
 {
 	struct cxl_root_decoder *cxlrd = cxlr->cxlrd;
-	int parent_iw, parent_ig, ig, iw, rc, inc = 0, pos = cxled->pos;
+	int parent_iw, parent_ig, ig, iw, rc, pos = cxled->pos;
 	struct cxl_port *parent_port = to_cxl_port(port->dev.parent);
 	struct cxl_region_ref *cxl_rr = cxl_rr_load(port, cxlr);
 	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
@@ -1549,9 +1549,8 @@ static int cxl_port_setup_targets(struct cxl_port *port,
 		cxlsd->target[cxl_rr->nr_targets_set] = ep->dport;
 		cxlsd->cxld.target_map[cxl_rr->nr_targets_set] = ep->dport->port_id;
 	}
-	inc = 1;
+	cxl_rr->nr_targets_set++;
 out_target_set:
-	cxl_rr->nr_targets_set += inc;
 	dev_dbg(&cxlr->dev, "%s:%s target[%d] = %s for %s:%s @ %d\n",
 		dev_name(port->uport_dev), dev_name(&port->dev),
 		cxl_rr->nr_targets_set - 1, dev_name(ep->dport->dport_dev),
-- 
2.47.3