cxl: Move cxl_await_media_ready() to before capacity info retrieval

Move cxl_await_media_ready() to cxl_pci probe before driver starts issuing
IDENTIFY and retrieving memory device information to ensure that the
device is ready to provide the information. Allow cxl_pci_probe() to succeed
even if media is not ready. Cache the media failure in cxlds and don't ask
the device for any media information.

The rationale for proceeding in the !media_ready case is to allow for
mailbox operations to interrogate and/or remediate the device. After
media is repaired then rebinding the cxl_pci driver is expected to
restart the capacity scan.

Suggested-by: Dan Williams <dan.j.williams@intel.com>
Fixes: b39cb1052a5c ("cxl/mem: Register CXL memX devices")
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/168445310026.3251520.8124296540679268206.stgit@djiang5-mobl3
[djbw: fixup cxl_test]
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 23b9ff9..2c8dc7e 100644 (file)
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -1028,7 +1028,7 @@ static int cxl_mem_get_partition_info(struct cxl_dev_state *cxlds)
  * cxl_dev_state_identify() - Send the IDENTIFY command to the device.
  * @cxlds: The device data for the operation
  *
- * Return: 0 if identify was executed successfully.
+ * Return: 0 if identify was executed successfully or media not ready.
  *
  * This will dispatch the identify command to the device and on success populate
  * structures to be exported to sysfs.
@@ -1041,6 +1041,9 @@ int cxl_dev_state_identify(struct cxl_dev_state *cxlds)
        u32 val;
        int rc;
 
+       if (!cxlds->media_ready)
+               return 0;
+
        mbox_cmd = (struct cxl_mbox_cmd) {
                .opcode = CXL_MBOX_OP_IDENTIFY,
                .size_out = sizeof(id),
@@ -1115,10 +1118,12 @@ int cxl_mem_create_range_info(struct cxl_dev_state *cxlds)
                                   cxlds->persistent_only_bytes, "pmem");
        }
 
-       rc = cxl_mem_get_partition_info(cxlds);
-       if (rc) {
-               dev_err(dev, "Failed to query partition information\n");
-               return rc;
+       if (cxlds->media_ready) {
+               rc = cxl_mem_get_partition_info(cxlds);
+               if (rc) {
+                       dev_err(dev, "Failed to query partition information\n");
+                       return rc;
+               }
        }
 
        rc = add_dpa_res(dev, &cxlds->dpa_res, &cxlds->ram_res, 0,

diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
index db12b63..a2845a7 100644 (file)
--- a/drivers/cxl/cxlmem.h
+++ b/drivers/cxl/cxlmem.h
@@ -266,6 +266,7 @@ struct cxl_poison_state {
  * @regs: Parsed register blocks
  * @cxl_dvsec: Offset to the PCIe device DVSEC
  * @rcd: operating in RCD mode (CXL 3.0 9.11.8 CXL Devices Attached to an RCH)
+ * @media_ready: Indicate whether the device media is usable
  * @payload_size: Size of space for payload
  *                (CXL 2.0 8.2.8.4.3 Mailbox Capabilities Register)
  * @lsa_size: Size of Label Storage Area
@@ -303,6 +304,7 @@ struct cxl_dev_state {
        int cxl_dvsec;
 
        bool rcd;
+       bool media_ready;
        size_t payload_size;
        size_t lsa_size;
        struct mutex mbox_mutex; /* Protects device mailbox and firmware */

diff --git a/drivers/cxl/mem.c b/drivers/cxl/mem.c
index 10caf18..519edd0 100644 (file)
--- a/drivers/cxl/mem.c
+++ b/drivers/cxl/mem.c
@@ -124,6 +124,9 @@ static int cxl_mem_probe(struct device *dev)
        struct dentry *dentry;
        int rc;
 
+       if (!cxlds->media_ready)
+               return -EBUSY;
+
        /*
         * Someone is trying to reattach this device after it lost its port
         * connection (an endpoint port previously registered by this memdev was

diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index f7a5b8e..0872f22 100644 (file)
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -708,6 +708,12 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
        if (rc)
                dev_dbg(&pdev->dev, "Failed to map RAS capability.\n");
 
+       rc = cxl_await_media_ready(cxlds);
+       if (rc == 0)
+               cxlds->media_ready = true;
+       else
+               dev_warn(&pdev->dev, "Media not active (%d)\n", rc);
+
        rc = cxl_pci_setup_mailbox(cxlds);
        if (rc)
                return rc;

diff --git a/drivers/cxl/port.c b/drivers/cxl/port.c
index 17a95f4..c23b616 100644 (file)
--- a/drivers/cxl/port.c
+++ b/drivers/cxl/port.c
@@ -117,12 +117,6 @@ static int cxl_endpoint_port_probe(struct cxl_port *port)
        if (rc)
                return rc;
 
-       rc = cxl_await_media_ready(cxlds);
-       if (rc) {
-               dev_err(&port->dev, "Media not active (%d)\n", rc);
-               return rc;
-       }
-
        rc = devm_cxl_enumerate_decoders(cxlhdm, &info);
        if (rc)
                return rc;

diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c
index ba572d0..34b4802 100644 (file)
--- a/tools/testing/cxl/test/mem.c
+++ b/tools/testing/cxl/test/mem.c
@@ -1256,6 +1256,7 @@ static int cxl_mock_mem_probe(struct platform_device *pdev)
        if (rc)
                return rc;
 
+       cxlds->media_ready = true;
        rc = cxl_dev_state_identify(cxlds);
        if (rc)
                return rc;