cxl/mbox: Add GET_POISON_LIST mailbox command

CXL devices maintain a list of locations that are poisoned or result
in poison if the addresses are accessed by the host.

Per the spec, (CXL 3.0 8.2.9.8.4.1), the device returns this Poison
list as a set of Media Error Records that include the source of the
error, the starting device physical address, and length. The length is
the number of adjacent DPAs in the record and is in units of 64 bytes.

Retrieve the poison list.

Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/a1f332e817834ef8e89c0ff32e760308fb903346.1681838291.git.alison.schofield@intel.com
Tested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

Author: AlisonSchofield

drivers/cxl/core/mbox.c

@@ -5,6 +5,7 @@
 #include <linux/debugfs.h>
 #include <linux/ktime.h>
 #include <linux/mutex.h>
+#include <asm/unaligned.h>
 #include <cxlpci.h>
 #include <cxlmem.h>
 #include <cxl.h>
@@ -1038,6 +1039,7 @@ int cxl_dev_state_identify(struct cxl_dev_state *cxlds)
 	/* See CXL 2.0 Table 175 Identify Memory Device Output Payload */
 	struct cxl_mbox_identify id;
 	struct cxl_mbox_cmd mbox_cmd;
+	u32 val;
 	int rc;
 
 	mbox_cmd = (struct cxl_mbox_cmd) {
@@ -1061,6 +1063,11 @@ int cxl_dev_state_identify(struct cxl_dev_state *cxlds)
 	cxlds->lsa_size = le32_to_cpu(id.lsa_size);
 	memcpy(cxlds->firmware_version, id.fw_revision, sizeof(id.fw_revision));
 
+	if (test_bit(CXL_POISON_ENABLED_LIST, cxlds->poison.enabled_cmds)) {
+		val = get_unaligned_le24(id.poison_list_max_mer);
+		cxlds->poison.max_errors = min_t(u32, val, CXL_POISON_LIST_MAX);
+	}
+
 	return 0;
 }
 EXPORT_SYMBOL_NS_GPL(cxl_dev_state_identify, CXL);
@@ -1151,6 +1158,54 @@ int cxl_set_timestamp(struct cxl_dev_state *cxlds)
 }
 EXPORT_SYMBOL_NS_GPL(cxl_set_timestamp, CXL);
 
+int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len,
+		       struct cxl_region *cxlr)
+{
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	struct cxl_mbox_poison_out *po;
+	struct cxl_mbox_poison_in pi;
+	struct cxl_mbox_cmd mbox_cmd;
+	int nr_records = 0;
+	int rc;
+
+	rc = mutex_lock_interruptible(&cxlds->poison.lock);
+	if (rc)
+		return rc;
+
+	po = cxlds->poison.list_out;
+	pi.offset = cpu_to_le64(offset);
+	pi.length = cpu_to_le64(len / CXL_POISON_LEN_MULT);
+
+	mbox_cmd = (struct cxl_mbox_cmd) {
+		.opcode = CXL_MBOX_OP_GET_POISON,
+		.size_in = sizeof(pi),
+		.payload_in = &pi,
+		.size_out = cxlds->payload_size,
+		.payload_out = po,
+		.min_out = struct_size(po, record, 0),
+	};
+
+	do {
+		rc = cxl_internal_send_cmd(cxlds, &mbox_cmd);
+		if (rc)
+			break;
+
+		/* TODO TRACE the media error records */
+
+		/* Protect against an uncleared _FLAG_MORE */
+		nr_records = nr_records + le16_to_cpu(po->count);
+		if (nr_records >= cxlds->poison.max_errors) {
+			dev_dbg(&cxlmd->dev, "Max Error Records reached: %d\n",
+				nr_records);
+			break;
+		}
+	} while (po->flags & CXL_POISON_FLAG_MORE);
+
+	mutex_unlock(&cxlds->poison.lock);
+	return rc;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_mem_get_poison, CXL);
+
 static void free_poison_buf(void *buf)
 {
 	kvfree(buf);

drivers/cxl/cxlmem.h

@@ -571,6 +571,50 @@ struct cxl_mbox_set_timestamp_in {
 
 } __packed;
 
+/* Get Poison List  CXL 3.0 Spec 8.2.9.8.4.1 */
+struct cxl_mbox_poison_in {
+	__le64 offset;
+	__le64 length;
+} __packed;
+
+struct cxl_mbox_poison_out {
+	u8 flags;
+	u8 rsvd1;
+	__le64 overflow_ts;
+	__le16 count;
+	u8 rsvd2[20];
+	struct cxl_poison_record {
+		__le64 address;
+		__le32 length;
+		__le32 rsvd;
+	} __packed record[];
+} __packed;
+
+/*
+ * Get Poison List address field encodes the starting
+ * address of poison, and the source of the poison.
+ */
+#define CXL_POISON_START_MASK		GENMASK_ULL(63, 6)
+#define CXL_POISON_SOURCE_MASK		GENMASK(2, 0)
+
+/* Get Poison List record length is in units of 64 bytes */
+#define CXL_POISON_LEN_MULT	64
+
+/* Kernel defined maximum for a list of poison errors */
+#define CXL_POISON_LIST_MAX	1024
+
+/* Get Poison List: Payload out flags */
+#define CXL_POISON_FLAG_MORE            BIT(0)
+#define CXL_POISON_FLAG_OVERFLOW        BIT(1)
+#define CXL_POISON_FLAG_SCANNING        BIT(2)
+
+/* Get Poison List: Poison Source */
+#define CXL_POISON_SOURCE_UNKNOWN	0
+#define CXL_POISON_SOURCE_EXTERNAL	1
+#define CXL_POISON_SOURCE_INTERNAL	2
+#define CXL_POISON_SOURCE_INJECTED	3
+#define CXL_POISON_SOURCE_VENDOR	7
+
 /**
  * struct cxl_mem_command - Driver representation of a memory device command
  * @info: Command information as it exists for the UAPI
@@ -642,6 +686,8 @@ void clear_exclusive_cxl_commands(struct cxl_dev_state *cxlds, unsigned long *cm
 void cxl_mem_get_event_records(struct cxl_dev_state *cxlds, u32 status);
 int cxl_set_timestamp(struct cxl_dev_state *cxlds);
 int cxl_poison_state_init(struct cxl_dev_state *cxlds);
+int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len,
+		       struct cxl_region *cxlr);
 
 #ifdef CONFIG_CXL_SUSPEND
 void cxl_mem_active_inc(void);