[PATCH AUTOSEL 6.6 12/22] cxl/region: Handle endpoint decoders in cxl_region_find_decoder()

[PATCH AUTOSEL 6.6 12/22] cxl/region: Handle endpoint decoders in cxl_region_find_decoder()

[Sasha Levin]

From: Alison Schofield <alison.schofield@intel.com>

[ Upstream commit 453a7fde8031a5192ed2f9646ad048c1a5e930dc ]

In preparation for adding a new caller of cxl_region_find_decoders()
teach it to find a decoder from a cxl_endpoint_decoder structure.

Combining switch and endpoint decoder lookup in one function prevents
code duplication in call sites.

Update the existing caller.

Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Tested-by: Wonjae Lee <wj28.lee@samsung.com>
Link: https://lore.kernel.org/r/79ae6d72978ef9f3ceec9722e1cb793820553c8e.1706736863.git.alison.schofield@intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/cxl/core/region.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 6ebd12f7970bc..a3d82ef5599e8 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -729,12 +729,17 @@ static int match_auto_decoder(struct device *dev, void *data)
 	return 0;
 }
 
-static struct cxl_decoder *cxl_region_find_decoder(struct cxl_port *port,
-						   struct cxl_region *cxlr)
+static struct cxl_decoder *
+cxl_region_find_decoder(struct cxl_port *port,
+			struct cxl_endpoint_decoder *cxled,
+			struct cxl_region *cxlr)
 {
 	struct device *dev;
 	int id = 0;
 
+	if (port == cxled_to_port(cxled))
+		return &cxled->cxld;
+
 	if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags))
 		dev = device_find_child(&port->dev, &cxlr->params,
 					match_auto_decoder);
@@ -852,10 +857,7 @@ static int cxl_rr_alloc_decoder(struct cxl_port *port, struct cxl_region *cxlr,
 {
 	struct cxl_decoder *cxld;
 
-	if (port == cxled_to_port(cxled))
-		cxld = &cxled->cxld;
-	else
-		cxld = cxl_region_find_decoder(port, cxlr);
+	cxld = cxl_region_find_decoder(port, cxled, cxlr);
 	if (!cxld) {
 		dev_dbg(&cxlr->dev, "%s: no decoder available\n",
 			dev_name(&port->dev));
-- 
2.43.0

[PATCH AUTOSEL 6.6 13/22] cxl/region: Allow out of order assembly of autodiscovered regions

[Sasha Levin]

From: Alison Schofield <alison.schofield@intel.com>

[ Upstream commit cb66b1d60c283bb340a2fc19deff7de8acea74b1 ]

Autodiscovered regions can fail to assemble if they are not discovered
in HPA decode order. The user will see failure messages like:

[] cxl region0: endpoint5: HPA order violation region1
[] cxl region0: endpoint5: failed to allocate region reference

The check that is causing the failure helps the CXL driver enforce
a CXL spec mandate that decoders be committed in HPA order. The
check is needless for autodiscovered regions since their decoders
are already programmed. Trying to enforce order in the assembly of
these regions is useless because they are assembled once all their
member endpoints arrive, and there is no guarantee on the order in
which endpoints are discovered during probe.

Keep the existing check, but for autodiscovered regions, allow the
out of order assembly after a sanity check that the lesser numbered
decoder has the lesser HPA starting address.

Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Tested-by: Wonjae Lee <wj28.lee@samsung.com>
Link: https://lore.kernel.org/r/3dec69ee97524ab229a20c6739272c3000b18408.1706736863.git.alison.schofield@intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/cxl/core/region.c | 48 +++++++++++++++++++++++++++++++--------
 1 file changed, 38 insertions(+), 10 deletions(-)

diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index a3d82ef5599e8..e2a82ee4ff0cf 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -757,8 +757,31 @@ cxl_region_find_decoder(struct cxl_port *port,
 	return to_cxl_decoder(dev);
 }
 
-static struct cxl_region_ref *alloc_region_ref(struct cxl_port *port,
-					       struct cxl_region *cxlr)
+static bool auto_order_ok(struct cxl_port *port, struct cxl_region *cxlr_iter,
+			  struct cxl_decoder *cxld)
+{
+	struct cxl_region_ref *rr = cxl_rr_load(port, cxlr_iter);
+	struct cxl_decoder *cxld_iter = rr->decoder;
+
+	/*
+	 * Allow the out of order assembly of auto-discovered regions.
+	 * Per CXL Spec 3.1 8.2.4.20.12 software must commit decoders
+	 * in HPA order. Confirm that the decoder with the lesser HPA
+	 * starting address has the lesser id.
+	 */
+	dev_dbg(&cxld->dev, "check for HPA violation %s:%d < %s:%d\n",
+		dev_name(&cxld->dev), cxld->id,
+		dev_name(&cxld_iter->dev), cxld_iter->id);
+
+	if (cxld_iter->id > cxld->id)
+		return true;
+
+	return false;
+}
+
+static struct cxl_region_ref *
+alloc_region_ref(struct cxl_port *port, struct cxl_region *cxlr,
+		 struct cxl_endpoint_decoder *cxled)
 {
 	struct cxl_region_params *p = &cxlr->params;
 	struct cxl_region_ref *cxl_rr, *iter;
@@ -768,16 +791,21 @@ static struct cxl_region_ref *alloc_region_ref(struct cxl_port *port,
 	xa_for_each(&port->regions, index, iter) {
 		struct cxl_region_params *ip = &iter->region->params;
 
-		if (!ip->res)
+		if (!ip->res || ip->res->start < p->res->start)
 			continue;
 
-		if (ip->res->start > p->res->start) {
-			dev_dbg(&cxlr->dev,
-				"%s: HPA order violation %s:%pr vs %pr\n",
-				dev_name(&port->dev),
-				dev_name(&iter->region->dev), ip->res, p->res);
-			return ERR_PTR(-EBUSY);
+		if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) {
+			struct cxl_decoder *cxld;
+
+			cxld = cxl_region_find_decoder(port, cxled, cxlr);
+			if (auto_order_ok(port, iter->region, cxld))
+				continue;
 		}
+		dev_dbg(&cxlr->dev, "%s: HPA order violation %s:%pr vs %pr\n",
+			dev_name(&port->dev),
+			dev_name(&iter->region->dev), ip->res, p->res);
+
+		return ERR_PTR(-EBUSY);
 	}
 
 	cxl_rr = kzalloc(sizeof(*cxl_rr), GFP_KERNEL);
@@ -954,7 +982,7 @@ static int cxl_port_attach_region(struct cxl_port *port,
 			nr_targets_inc = true;
 		}
 	} else {
-		cxl_rr = alloc_region_ref(port, cxlr);
+		cxl_rr = alloc_region_ref(port, cxlr, cxled);
 		if (IS_ERR(cxl_rr)) {
 			dev_dbg(&cxlr->dev,
 				"%s: failed to allocate region reference\n",
-- 
2.43.0

[PATCH AUTOSEL 6.6 15/22] perf: CXL: fix CPMU filter value mask length

[Sasha Levin]

From: Hojin Nam <hj96.nam@samsung.com>

[ Upstream commit 802379b8f9e169293e9ba7089e5f1a6340e2e7a3 ]

CPMU filter value is described as 4B length in CXL r3.0 8.2.7.2.2.
However, it is used as 2B length in code and comments.

Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Hojin Nam <hj96.nam@samsung.com>
Link: https://lore.kernel.org/r/20240216014522.32321-1-hj96.nam@samsung.com
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/perf/cxl_pmu.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/perf/cxl_pmu.c b/drivers/perf/cxl_pmu.c
index bc0d414a6aff9..308c9969642e1 100644
--- a/drivers/perf/cxl_pmu.c
+++ b/drivers/perf/cxl_pmu.c
@@ -59,7 +59,7 @@
 #define   CXL_PMU_COUNTER_CFG_EVENT_GRP_ID_IDX_MSK	GENMASK_ULL(63, 59)
 
 #define CXL_PMU_FILTER_CFG_REG(n, f)	(0x400 + 4 * ((f) + (n) * 8))
-#define   CXL_PMU_FILTER_CFG_VALUE_MSK			GENMASK(15, 0)
+#define   CXL_PMU_FILTER_CFG_VALUE_MSK			GENMASK(31, 0)
 
 #define CXL_PMU_COUNTER_REG(n)		(0xc00 + 8 * (n))
 
@@ -314,9 +314,9 @@ static bool cxl_pmu_config1_get_edge(struct perf_event *event)
 }
 
 /*
- * CPMU specification allows for 8 filters, each with a 16 bit value...
- * So we need to find 8x16bits to store it in.
- * As the value used for disable is 0xffff, a separate enable switch
+ * CPMU specification allows for 8 filters, each with a 32 bit value...
+ * So we need to find 8x32bits to store it in.
+ * As the value used for disable is 0xffff_ffff, a separate enable switch
  * is needed.
  */
 
@@ -642,7 +642,7 @@ static void cxl_pmu_event_start(struct perf_event *event, int flags)
 		if (cxl_pmu_config1_hdm_filter_en(event))
 			cfg = cxl_pmu_config2_get_hdm_decoder(event);
 		else
-			cfg = GENMASK(15, 0); /* No filtering if 0xFFFF_FFFF */
+			cfg = GENMASK(31, 0); /* No filtering if 0xFFFF_FFFF */
 		writeq(cfg, base + CXL_PMU_FILTER_CFG_REG(hwc->idx, 0));
 	}
 
-- 
2.43.0