Merge branch 'for-6.19/cxl-misc' into cxl-for-next

Misc patches for CXL 6.19
- Remove incorrect page-allocator quirk section in documentation.
- Remove unused devm_cxl_port_enumerate_dports() function.
- Fix typo in cdat.c code comment.
- Replace use of system_wq with system_percpu_wq
- Add locked decoder support
- Return when generic target updated
- Rename region_res_match_cxl_range() to spa_maps_hpa()
- Clarify comment in spa_maps_hpa()

Author: davejiang

Documentation/driver-api/cxl/allocation/page-allocator.rst

@@ -41,37 +41,6 @@ To simplify this, the page allocator will prefer :code:`ZONE_MOVABLE` over
 will fallback to allocate from :code:`ZONE_NORMAL`.
 
 
-Zone and Node Quirks
-====================
-Let's consider a configuration where the local DRAM capacity is largely onlined
-into :code:`ZONE_NORMAL`, with no :code:`ZONE_MOVABLE` capacity present. The
-CXL capacity has the opposite configuration - all onlined in
-:code:`ZONE_MOVABLE`.
-
-Under the default allocation policy, the page allocator will completely skip
-:code:`ZONE_MOVABLE` as a valid allocation target.  This is because, as of
-Linux v6.15, the page allocator does (approximately) the following: ::
-
-  for (each zone in local_node):
-
-    for (each node in fallback_order):
-
-      attempt_allocation(gfp_flags);
-
-Because the local node does not have :code:`ZONE_MOVABLE`, the CXL node is
-functionally unreachable for direct allocation.  As a result, the only way
-for CXL capacity to be used is via `demotion` in the reclaim path.
-
-This configuration also means that if the DRAM ndoe has :code:`ZONE_MOVABLE`
-capacity - when that capacity is depleted, the page allocator will actually
-prefer CXL :code:`ZONE_MOVABLE` pages over DRAM :code:`ZONE_NORMAL` pages.
-
-We may wish to invert this priority in future Linux versions.
-
-If `demotion` and `swap` are disabled, Linux will begin to cause OOM crashes
-when the DRAM nodes are depleted. See the reclaim section for more details.
-
-
 CGroups and CPUSets
 ===================
 Finally, assuming CXL memory is reachable via the page allocation (i.e. onlined

drivers/acpi/numa/hmat.c

@@ -888,12 +888,13 @@ static void hmat_register_target(struct memory_target *target)
 	 * Register generic port perf numbers. The nid may not be
 	 * initialized and is still NUMA_NO_NODE.
 	 */
-	mutex_lock(&target_lock);
-	if (*(u16 *)target->gen_port_device_handle) {
-		hmat_update_generic_target(target);
-		target->registered = true;
+	scoped_guard(mutex, &target_lock) {
+		if (*(u16 *)target->gen_port_device_handle) {
+			hmat_update_generic_target(target);
+			target->registered = true;
+			return;
+		}
 	}
-	mutex_unlock(&target_lock);
 
 	/*
 	 * Skip offline nodes. This can happen when memory

drivers/cxl/core/cdat.c

@@ -826,7 +826,7 @@ static struct xarray *cxl_switch_gather_bandwidth(struct cxl_region *cxlr,
 		cxl_coordinates_combine(coords, coords, ctx->coord);
 
 		/*
-		 * Take the min of the calculated bandwdith and the upstream
+		 * Take the min of the calculated bandwidth and the upstream
 		 * switch SSLBIS bandwidth if there's a parent switch
 		 */
 		if (!is_root)
@@ -949,7 +949,7 @@ static struct xarray *cxl_hb_gather_bandwidth(struct xarray *xa)
 /**
  * cxl_region_update_bandwidth - Update the bandwidth access coordinates of a region
  * @cxlr: The region being operated on
- * @input_xa: xarray holds cxl_perf_ctx wht calculated bandwidth per ACPI0017 instance
+ * @input_xa: xarray holds cxl_perf_ctx with calculated bandwidth per ACPI0017 instance
  */
 static void cxl_region_update_bandwidth(struct cxl_region *cxlr,
 					struct xarray *input_xa)

drivers/cxl/core/hdm.c

@@ -905,6 +905,9 @@ static void cxl_decoder_reset(struct cxl_decoder *cxld)
 	if ((cxld->flags & CXL_DECODER_F_ENABLE) == 0)
 		return;
 
+	if (test_bit(CXL_DECODER_F_LOCK, &cxld->flags))
+		return;
+
 	if (port->commit_end == id)
 		cxl_port_commit_reap(cxld);
 	else

drivers/cxl/core/pci.c

@@ -71,85 +71,6 @@ struct cxl_dport *__devm_cxl_add_dport_by_dev(struct cxl_port *port,
 }
 EXPORT_SYMBOL_NS_GPL(__devm_cxl_add_dport_by_dev, "CXL");
 
-struct cxl_walk_context {
-	struct pci_bus *bus;
-	struct cxl_port *port;
-	int type;
-	int error;
-	int count;
-};
-
-static int match_add_dports(struct pci_dev *pdev, void *data)
-{
-	struct cxl_walk_context *ctx = data;
-	struct cxl_port *port = ctx->port;
-	int type = pci_pcie_type(pdev);
-	struct cxl_register_map map;
-	struct cxl_dport *dport;
-	u32 lnkcap, port_num;
-	int rc;
-
-	if (pdev->bus != ctx->bus)
-		return 0;
-	if (!pci_is_pcie(pdev))
-		return 0;
-	if (type != ctx->type)
-		return 0;
-	if (pci_read_config_dword(pdev, pci_pcie_cap(pdev) + PCI_EXP_LNKCAP,
-				  &lnkcap))
-		return 0;
-
-	rc = cxl_find_regblock(pdev, CXL_REGLOC_RBI_COMPONENT, &map);
-	if (rc)
-		dev_dbg(&port->dev, "failed to find component registers\n");
-
-	port_num = FIELD_GET(PCI_EXP_LNKCAP_PN, lnkcap);
-	dport = devm_cxl_add_dport(port, &pdev->dev, port_num, map.resource);
-	if (IS_ERR(dport)) {
-		ctx->error = PTR_ERR(dport);
-		return PTR_ERR(dport);
-	}
-	ctx->count++;
-
-	return 0;
-}
-
-/**
- * devm_cxl_port_enumerate_dports - enumerate downstream ports of the upstream port
- * @port: cxl_port whose ->uport_dev is the upstream of dports to be enumerated
- *
- * Returns a positive number of dports enumerated or a negative error
- * code.
- */
-int devm_cxl_port_enumerate_dports(struct cxl_port *port)
-{
-	struct pci_bus *bus = cxl_port_to_pci_bus(port);
-	struct cxl_walk_context ctx;
-	int type;
-
-	if (!bus)
-		return -ENXIO;
-
-	if (pci_is_root_bus(bus))
-		type = PCI_EXP_TYPE_ROOT_PORT;
-	else
-		type = PCI_EXP_TYPE_DOWNSTREAM;
-
-	ctx = (struct cxl_walk_context) {
-		.port = port,
-		.bus = bus,
-		.type = type,
-	};
-	pci_walk_bus(bus, match_add_dports, &ctx);
-
-	if (ctx.count == 0)
-		return -ENODEV;
-	if (ctx.error)
-		return ctx.error;
-	return ctx.count;
-}
-EXPORT_SYMBOL_NS_GPL(devm_cxl_port_enumerate_dports, "CXL");
-
 static int cxl_dvsec_mem_range_valid(struct cxl_dev_state *cxlds, int id)
 {
 	struct pci_dev *pdev = to_pci_dev(cxlds->dev);
@@ -1217,6 +1138,14 @@ int cxl_gpf_port_setup(struct cxl_dport *dport)
 	return 0;
 }
 
+struct cxl_walk_context {
+	struct pci_bus *bus;
+	struct cxl_port *port;
+	int type;
+	int error;
+	int count;
+};
+
 static int count_dports(struct pci_dev *pdev, void *data)
 {
 	struct cxl_walk_context *ctx = data;

drivers/cxl/core/region.c

@@ -245,6 +245,9 @@ static void cxl_region_decode_reset(struct cxl_region *cxlr, int count)
 	struct cxl_region_params *p = &cxlr->params;
 	int i;
 
+	if (test_bit(CXL_REGION_F_LOCK, &cxlr->flags))
+		return;
+
 	/*
 	 * Before region teardown attempt to flush, evict any data cached for
 	 * this region, or scream loudly about missing arch / platform support
@@ -419,6 +422,9 @@ static ssize_t commit_store(struct device *dev, struct device_attribute *attr,
 		return len;
 	}
 
+	if (test_bit(CXL_REGION_F_LOCK, &cxlr->flags))
+		return -EPERM;
+
 	rc = queue_reset(cxlr);
 	if (rc)
 		return rc;
@@ -838,16 +844,16 @@ static int match_free_decoder(struct device *dev, const void *data)
 	return 1;
 }
 
-static bool region_res_match_cxl_range(const struct cxl_region_params *p,
-				       const struct range *range)
+static bool spa_maps_hpa(const struct cxl_region_params *p,
+			 const struct range *range)
 {
 	if (!p->res)
 		return false;
 
 	/*
-	 * If an extended linear cache region then the CXL range is assumed
-	 * to be fronted by the DRAM range in current known implementation.
-	 * This assumption will be made until a variant implementation exists.
+	 * The extended linear cache region is constructed by a 1:1 ratio
+	 * where the SPA maps equal amounts of DRAM and CXL HPA capacity with
+	 * CXL decoders at the high end of the SPA range.
 	 */
 	return p->res->start + p->cache_size == range->start &&
 		p->res->end == range->end;
@@ -865,7 +871,7 @@ static int match_auto_decoder(struct device *dev, const void *data)
 	cxld = to_cxl_decoder(dev);
 	r = &cxld->hpa_range;
 
-	if (region_res_match_cxl_range(p, r))
+	if (spa_maps_hpa(p, r))
 		return 1;
 
 	return 0;
@@ -1059,6 +1065,16 @@ static int cxl_rr_assign_decoder(struct cxl_port *port, struct cxl_region *cxlr,
 	return 0;
 }
 
+static void cxl_region_set_lock(struct cxl_region *cxlr,
+				struct cxl_decoder *cxld)
+{
+	if (!test_bit(CXL_DECODER_F_LOCK, &cxld->flags))
+		return;
+
+	set_bit(CXL_REGION_F_LOCK, &cxlr->flags);
+	clear_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags);
+}
+
 /**
  * cxl_port_attach_region() - track a region's interest in a port by endpoint
  * @port: port to add a new region reference 'struct cxl_region_ref'
@@ -1170,6 +1186,8 @@ static int cxl_port_attach_region(struct cxl_port *port,
 		}
 	}
 
+	cxl_region_set_lock(cxlr, cxld);
+
 	rc = cxl_rr_ep_add(cxl_rr, cxled);
 	if (rc) {
 		dev_dbg(&cxlr->dev,
@@ -1465,7 +1483,7 @@ static int cxl_port_setup_targets(struct cxl_port *port,
 	if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) {
 		if (cxld->interleave_ways != iw ||
 		    (iw > 1 && cxld->interleave_granularity != ig) ||
-		    !region_res_match_cxl_range(p, &cxld->hpa_range) ||
+		    !spa_maps_hpa(p, &cxld->hpa_range) ||
 		    ((cxld->flags & CXL_DECODER_F_ENABLE) == 0)) {
 			dev_err(&cxlr->dev,
 				"%s:%s %s expected iw: %d ig: %d %pr\n",
@@ -2439,6 +2457,7 @@ static struct cxl_region *cxl_region_alloc(struct cxl_root_decoder *cxlrd, int i
 	dev->bus = &cxl_bus_type;
 	dev->type = &cxl_region_type;
 	cxlr->id = id;
+	cxl_region_set_lock(cxlr, &cxlrd->cxlsd.cxld);
 
 	return cxlr;
 }
@@ -3398,7 +3417,7 @@ static int match_region_by_range(struct device *dev, const void *data)
 	p = &cxlr->params;
 
 	guard(rwsem_read)(&cxl_rwsem.region);
-	return region_res_match_cxl_range(p, r);
+	return spa_maps_hpa(p, r);
 }
 
 static int cxl_extended_linear_cache_resize(struct cxl_region *cxlr,

drivers/cxl/cxl.h

@@ -517,6 +517,14 @@ enum cxl_partition_mode {
  */
 #define CXL_REGION_F_NEEDS_RESET 1
 
+/*
+ * Indicate whether this region is locked due to 1 or more decoders that have
+ * been locked. The approach of all or nothing is taken with regard to the
+ * locked attribute. CXL_REGION_F_NEEDS_RESET should not be set if this flag is
+ * set.
+ */
+#define CXL_REGION_F_LOCK 2
+
 /**
  * struct cxl_region - CXL region
  * @dev: This region's device

drivers/cxl/cxlpci.h

@@ -127,7 +127,6 @@ static inline bool cxl_pci_flit_256(struct pci_dev *pdev)
 	return lnksta2 & PCI_EXP_LNKSTA2_FLIT;
 }
 
-int devm_cxl_port_enumerate_dports(struct cxl_port *port);
 struct cxl_dev_state;
 void read_cdat_data(struct cxl_port *port);
 void cxl_cor_error_detected(struct pci_dev *pdev);

drivers/cxl/pci.c

@@ -136,7 +136,7 @@ static irqreturn_t cxl_pci_mbox_irq(int irq, void *id)
 	if (opcode == CXL_MBOX_OP_SANITIZE) {
 		mutex_lock(&cxl_mbox->mbox_mutex);
 		if (mds->security.sanitize_node)
-			mod_delayed_work(system_wq, &mds->security.poll_dwork, 0);
+			mod_delayed_work(system_percpu_wq, &mds->security.poll_dwork, 0);
 		mutex_unlock(&cxl_mbox->mbox_mutex);
 	} else {
 		/* short-circuit the wait in __cxl_pci_mbox_send_cmd() */

tools/testing/cxl/Kbuild

@@ -4,7 +4,6 @@ ldflags-y += --wrap=is_acpi_device_node
 ldflags-y += --wrap=acpi_evaluate_integer
 ldflags-y += --wrap=acpi_pci_find_root
 ldflags-y += --wrap=nvdimm_bus_register
-ldflags-y += --wrap=devm_cxl_port_enumerate_dports
 ldflags-y += --wrap=cxl_await_media_ready
 ldflags-y += --wrap=devm_cxl_add_rch_dport
 ldflags-y += --wrap=cxl_rcd_component_reg_phys