Merge tag 'cxl-for-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl

Pull compute express link updates from Dan Williams:
 "DOE support is promoted from drivers/cxl/ to drivers/pci/ with Bjorn's
  blessing, and the CXL core continues to mature its media management
  capabilities with support for listing and injecting media errors. Some
  late fixes that missed v6.3-final are also included:

   - Refactor the DOE infrastructure (Data Object Exchange
     PCI-config-cycle mailbox) to be a facility of the PCI core rather
     than the CXL core.

     This is foundational for upcoming support for PCI
     device-attestation and PCIe / CXL link encryption.

   - Add support for retrieving and injecting poison for CXL memory
     expanders.

     This enabling uses trace-events to convey CXL media error records
     to user tooling. It includes translation of device-local addresses
     (DPA) to system physical addresses (SPA) and their corresponding
     CXL region.

   - Fixes for decoder enumeration that missed v6.3-final

   - Miscellaneous fixups"

* tag 'cxl-for-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl: (38 commits)
  cxl/test: Add mock test for set_timestamp
  cxl/mbox: Update CMD_RC_TABLE
  tools/testing/cxl: Require CONFIG_DEBUG_FS
  tools/testing/cxl: Add a sysfs attr to test poison inject limits
  tools/testing/cxl: Use injected poison for get poison list
  tools/testing/cxl: Mock the Clear Poison mailbox command
  tools/testing/cxl: Mock the Inject Poison mailbox command
  cxl/mem: Add debugfs attributes for poison inject and clear
  cxl/memdev: Trace inject and clear poison as cxl_poison events
  cxl/memdev: Warn of poison inject or clear to a mapped region
  cxl/memdev: Add support for the Clear Poison mailbox command
  cxl/memdev: Add support for the Inject Poison mailbox command
  tools/testing/cxl: Mock support for Get Poison List
  cxl/trace: Add an HPA to cxl_poison trace events
  cxl/region: Provide region info to the cxl_poison trace event
  cxl/memdev: Add trigger_poison_list sysfs attribute
  cxl/trace: Add TRACE support for CXL media-error records
  cxl/mbox: Add GET_POISON_LIST mailbox command
  cxl/mbox: Initialize the poison state
  cxl/mbox: Restrict poison cmds to debugfs cxl_raw_allow_all
  ...

Author: torvalds

.clang-format

@@ -521,7 +521,6 @@ ForEachMacros:
   - 'of_property_for_each_u32'
   - 'pci_bus_for_each_resource'
   - 'pci_dev_for_each_resource'
-  - 'pci_doe_for_each_off'
   - 'pcl_for_each_chunk'
   - 'pcl_for_each_segment'
   - 'pcm_for_each_format'

Documentation/ABI/testing/debugfs-cxl

@@ -0,0 +1,35 @@
+What:		/sys/kernel/debug/cxl/memX/inject_poison
+Date:		April, 2023
+KernelVersion:	v6.4
+Contact:	[email protected]
+Description:
+		(WO) When a Device Physical Address (DPA) is written to this
+		attribute, the memdev driver sends an inject poison command to
+		the device for the specified address. The DPA must be 64-byte
+		aligned and the length of the injected poison is 64-bytes. If
+		successful, the device returns poison when the address is
+		accessed through the CXL.mem bus. Injecting poison adds the
+		address to the device's Poison List and the error source is set
+		to Injected. In addition, the device adds a poison creation
+		event to its internal Informational Event log, updates the
+		Event Status register, and if configured, interrupts the host.
+		It is not an error to inject poison into an address that
+		already has poison present and no error is returned. The
+		inject_poison attribute is only visible for devices supporting
+		the capability.
+
+
+What:		/sys/kernel/debug/memX/clear_poison
+Date:		April, 2023
+KernelVersion:	v6.4
+Contact:	[email protected]
+Description:
+		(WO) When a Device Physical Address (DPA) is written to this
+		attribute, the memdev driver sends a clear poison command to
+		the device for the specified address. Clearing poison removes
+		the address from the device's Poison List and writes 0 (zero)
+		for 64 bytes starting at address. It is not an error to clear
+		poison from an address that does not have poison set. If the
+		device cannot clear poison from the address, -ENXIO is returned.
+		The clear_poison attribute is only visible for devices
+		supporting the capability.

Documentation/ABI/testing/sysfs-bus-cxl

@@ -415,3 +415,17 @@ Description:
 		1), and checks that the hardware accepts the commit request.
 		Reading this value indicates whether the region is committed or
 		not.
+
+
+What:		/sys/bus/cxl/devices/memX/trigger_poison_list
+Date:		April, 2023
+KernelVersion:	v6.4
+Contact:	[email protected]
+Description:
+		(WO) When a boolean 'true' is written to this attribute the
+		memdev driver retrieves the poison list from the device. The
+		list consists of addresses that are poisoned, or would result
+		in poison if accessed, and the source of the poison. This
+		attribute is only visible for devices supporting the
+		capability. The retrieved errors are logged as kernel
+		events when cxl_poison event tracing is enabled.

drivers/cxl/core/core.h

@@ -25,7 +25,12 @@ void cxl_decoder_kill_region(struct cxl_endpoint_decoder *cxled);
 #define CXL_DAX_REGION_TYPE(x) (&cxl_dax_region_type)
 int cxl_region_init(void);
 void cxl_region_exit(void);
+int cxl_get_poison_by_endpoint(struct cxl_port *port);
 #else
+static inline int cxl_get_poison_by_endpoint(struct cxl_port *port)
+{
+	return 0;
+}
 static inline void cxl_decoder_kill_region(struct cxl_endpoint_decoder *cxled)
 {
 }
@@ -64,4 +69,10 @@ int cxl_memdev_init(void);
 void cxl_memdev_exit(void);
 void cxl_mbox_init(void);
 
+enum cxl_poison_trace_type {
+	CXL_POISON_TRACE_LIST,
+	CXL_POISON_TRACE_INJECT,
+	CXL_POISON_TRACE_CLEAR,
+};
+
 #endif /* __CXL_CORE_H__ */

drivers/cxl/core/hdm.c

@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright(c) 2022 Intel Corporation. All rights reserved. */
-#include <linux/io-64-nonatomic-hi-lo.h>
 #include <linux/seq_file.h>
 #include <linux/device.h>
 #include <linux/delay.h>
@@ -93,8 +92,9 @@ static int map_hdm_decoder_regs(struct cxl_port *port, void __iomem *crb,
 
 	cxl_probe_component_regs(&port->dev, crb, &map.component_map);
 	if (!map.component_map.hdm_decoder.valid) {
-		dev_err(&port->dev, "HDM decoder registers invalid\n");
-		return -ENXIO;
+		dev_dbg(&port->dev, "HDM decoder registers not implemented\n");
+		/* unique error code to indicate no HDM decoder capability */
+		return -ENODEV;
 	}
 
 	return cxl_map_component_regs(&port->dev, regs, &map,
@@ -130,6 +130,14 @@ static bool should_emulate_decoders(struct cxl_endpoint_dvsec_info *info)
 	 */
 	for (i = 0; i < cxlhdm->decoder_count; i++) {
 		ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(i));
+		dev_dbg(&info->port->dev,
+			"decoder%d.%d: committed: %ld base: %#x_%.8x size: %#x_%.8x\n",
+			info->port->id, i,
+			FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl),
+			readl(hdm + CXL_HDM_DECODER0_BASE_HIGH_OFFSET(i)),
+			readl(hdm + CXL_HDM_DECODER0_BASE_LOW_OFFSET(i)),
+			readl(hdm + CXL_HDM_DECODER0_SIZE_HIGH_OFFSET(i)),
+			readl(hdm + CXL_HDM_DECODER0_SIZE_LOW_OFFSET(i)));
 		if (FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl))
 			return false;
 	}
@@ -269,8 +277,11 @@ static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
 
 	lockdep_assert_held_write(&cxl_dpa_rwsem);
 
-	if (!len)
-		goto success;
+	if (!len) {
+		dev_warn(dev, "decoder%d.%d: empty reservation attempted\n",
+			 port->id, cxled->cxld.id);
+		return -EINVAL;
+	}
 
 	if (cxled->dpa_res) {
 		dev_dbg(dev, "decoder%d.%d: existing allocation %pr assigned\n",
@@ -323,7 +334,6 @@ static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
 		cxled->mode = CXL_DECODER_MIXED;
 	}
 
-success:
 	port->hdm_end++;
 	get_device(&cxled->cxld.dev);
 	return 0;
@@ -783,8 +793,8 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 			    int *target_map, void __iomem *hdm, int which,
 			    u64 *dpa_base, struct cxl_endpoint_dvsec_info *info)
 {
+	u64 size, base, skip, dpa_size, lo, hi;
 	struct cxl_endpoint_decoder *cxled;
-	u64 size, base, skip, dpa_size;
 	bool committed;
 	u32 remainder;
 	int i, rc;
@@ -799,8 +809,12 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 							which, info);
 
 	ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(which));
-	base = ioread64_hi_lo(hdm + CXL_HDM_DECODER0_BASE_LOW_OFFSET(which));
-	size = ioread64_hi_lo(hdm + CXL_HDM_DECODER0_SIZE_LOW_OFFSET(which));
+	lo = readl(hdm + CXL_HDM_DECODER0_BASE_LOW_OFFSET(which));
+	hi = readl(hdm + CXL_HDM_DECODER0_BASE_HIGH_OFFSET(which));
+	base = (hi << 32) + lo;
+	lo = readl(hdm + CXL_HDM_DECODER0_SIZE_LOW_OFFSET(which));
+	hi = readl(hdm + CXL_HDM_DECODER0_SIZE_HIGH_OFFSET(which));
+	size = (hi << 32) + lo;
 	committed = !!(ctrl & CXL_HDM_DECODER0_CTRL_COMMITTED);
 	cxld->commit = cxl_decoder_commit;
 	cxld->reset = cxl_decoder_reset;
@@ -833,6 +847,13 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 				 port->id, cxld->id);
 			return -ENXIO;
 		}
+
+		if (size == 0) {
+			dev_warn(&port->dev,
+				 "decoder%d.%d: Committed with zero size\n",
+				 port->id, cxld->id);
+			return -ENXIO;
+		}
 		port->commit_end = cxld->id;
 	} else {
 		/* unless / until type-2 drivers arrive, assume type-3 */
@@ -855,9 +876,14 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 	if (rc)
 		return rc;
 
+	dev_dbg(&port->dev, "decoder%d.%d: range: %#llx-%#llx iw: %d ig: %d\n",
+		port->id, cxld->id, cxld->hpa_range.start, cxld->hpa_range.end,
+		cxld->interleave_ways, cxld->interleave_granularity);
+
 	if (!info) {
-		target_list.value =
-			ioread64_hi_lo(hdm + CXL_HDM_DECODER0_TL_LOW(which));
+		lo = readl(hdm + CXL_HDM_DECODER0_TL_LOW(which));
+		hi = readl(hdm + CXL_HDM_DECODER0_TL_HIGH(which));
+		target_list.value = (hi << 32) + lo;
 		for (i = 0; i < cxld->interleave_ways; i++)
 			target_map[i] = target_list.target_id[i];
 
@@ -874,7 +900,9 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 			port->id, cxld->id, size, cxld->interleave_ways);
 		return -ENXIO;
 	}
-	skip = ioread64_hi_lo(hdm + CXL_HDM_DECODER0_SKIP_LOW(which));
+	lo = readl(hdm + CXL_HDM_DECODER0_SKIP_LOW(which));
+	hi = readl(hdm + CXL_HDM_DECODER0_SKIP_HIGH(which));
+	skip = (hi << 32) + lo;
 	cxled = to_cxl_endpoint_decoder(&cxld->dev);
 	rc = devm_cxl_dpa_reserve(cxled, *dpa_base + skip, dpa_size, skip);
 	if (rc) {