hw/mem/cxl-type3: Add CXL CDAT Data Object Exchange

The CDAT can be specified in two ways. One is to add ",cdat=<filename>"
in "-device cxl-type3"'s command option. The file is required to provide
the whole CDAT table in binary mode. The other is to use the default
that provides some 'reasonable' numbers based on type of memory and
size.

The DOE capability supporting CDAT is added to hw/mem/cxl_type3.c with
capability offset 0x190. The config read/write to this capability range
can be generated in the OS to request the CDAT data.

Signed-off-by: Huai-Cheng Kuo <hchkuo@avery-design.com.tw>
Signed-off-by: Chris Browy <cbrowy@avery-design.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

Message-Id: <20221014151045.24781-5-Jonathan.Cameron@huawei.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

hw/mem/cxl_type3.c

@@ -12,9 +12,246 @@
 #include "qemu/range.h"
 #include "qemu/rcu.h"
 #include "sysemu/hostmem.h"
+#include "sysemu/numa.h"
 #include "hw/cxl/cxl.h"
 #include "hw/pci/msix.h"
 
+#define DWORD_BYTE 4
+
+/* Default CDAT entries for a memory region */
+enum {
+    CT3_CDAT_DSMAS,
+    CT3_CDAT_DSLBIS0,
+    CT3_CDAT_DSLBIS1,
+    CT3_CDAT_DSLBIS2,
+    CT3_CDAT_DSLBIS3,
+    CT3_CDAT_DSEMTS,
+    CT3_CDAT_NUM_ENTRIES
+};
+
+static int ct3_build_cdat_entries_for_mr(CDATSubHeader **cdat_table,
+                                         int dsmad_handle, MemoryRegion *mr)
+{
+    g_autofree CDATDsmas *dsmas = NULL;
+    g_autofree CDATDslbis *dslbis0 = NULL;
+    g_autofree CDATDslbis *dslbis1 = NULL;
+    g_autofree CDATDslbis *dslbis2 = NULL;
+    g_autofree CDATDslbis *dslbis3 = NULL;
+    g_autofree CDATDsemts *dsemts = NULL;
+
+    dsmas = g_malloc(sizeof(*dsmas));
+    if (!dsmas) {
+        return -ENOMEM;
+    }
+    *dsmas = (CDATDsmas) {
+        .header = {
+            .type = CDAT_TYPE_DSMAS,
+            .length = sizeof(*dsmas),
+        },
+        .DSMADhandle = dsmad_handle,
+        .flags = CDAT_DSMAS_FLAG_NV,
+        .DPA_base = 0,
+        .DPA_length = int128_get64(mr->size),
+    };
+
+    /* For now, no memory side cache, plausiblish numbers */
+    dslbis0 = g_malloc(sizeof(*dslbis0));
+    if (!dslbis0) {
+        return -ENOMEM;
+    }
+    *dslbis0 = (CDATDslbis) {
+        .header = {
+            .type = CDAT_TYPE_DSLBIS,
+            .length = sizeof(*dslbis0),
+        },
+        .handle = dsmad_handle,
+        .flags = HMAT_LB_MEM_MEMORY,
+        .data_type = HMAT_LB_DATA_READ_LATENCY,
+        .entry_base_unit = 10000, /* 10ns base */
+        .entry[0] = 15, /* 150ns */
+    };
+
+    dslbis1 = g_malloc(sizeof(*dslbis1));
+    if (!dslbis1) {
+        return -ENOMEM;
+    }
+    *dslbis1 = (CDATDslbis) {
+        .header = {
+            .type = CDAT_TYPE_DSLBIS,
+            .length = sizeof(*dslbis1),
+        },
+        .handle = dsmad_handle,
+        .flags = HMAT_LB_MEM_MEMORY,
+        .data_type = HMAT_LB_DATA_WRITE_LATENCY,
+        .entry_base_unit = 10000,
+        .entry[0] = 25, /* 250ns */
+    };
+
+    dslbis2 = g_malloc(sizeof(*dslbis2));
+    if (!dslbis2) {
+        return -ENOMEM;
+    }
+    *dslbis2 = (CDATDslbis) {
+        .header = {
+            .type = CDAT_TYPE_DSLBIS,
+            .length = sizeof(*dslbis2),
+        },
+        .handle = dsmad_handle,
+        .flags = HMAT_LB_MEM_MEMORY,
+        .data_type = HMAT_LB_DATA_READ_BANDWIDTH,
+        .entry_base_unit = 1000, /* GB/s */
+        .entry[0] = 16,
+    };
+
+    dslbis3 = g_malloc(sizeof(*dslbis3));
+    if (!dslbis3) {
+        return -ENOMEM;
+    }
+    *dslbis3 = (CDATDslbis) {
+        .header = {
+            .type = CDAT_TYPE_DSLBIS,
+            .length = sizeof(*dslbis3),
+        },
+        .handle = dsmad_handle,
+        .flags = HMAT_LB_MEM_MEMORY,
+        .data_type = HMAT_LB_DATA_WRITE_BANDWIDTH,
+        .entry_base_unit = 1000, /* GB/s */
+        .entry[0] = 16,
+    };
+
+    dsemts = g_malloc(sizeof(*dsemts));
+    if (!dsemts) {
+        return -ENOMEM;
+    }
+    *dsemts = (CDATDsemts) {
+        .header = {
+            .type = CDAT_TYPE_DSEMTS,
+            .length = sizeof(*dsemts),
+        },
+        .DSMAS_handle = dsmad_handle,
+        /* Reserved - the non volatile from DSMAS matters */
+        .EFI_memory_type_attr = 2,
+        .DPA_offset = 0,
+        .DPA_length = int128_get64(mr->size),
+    };
+
+    /* Header always at start of structure */
+    cdat_table[CT3_CDAT_DSMAS] = g_steal_pointer(&dsmas);
+    cdat_table[CT3_CDAT_DSLBIS0] = g_steal_pointer(&dslbis0);
+    cdat_table[CT3_CDAT_DSLBIS1] = g_steal_pointer(&dslbis1);
+    cdat_table[CT3_CDAT_DSLBIS2] = g_steal_pointer(&dslbis2);
+    cdat_table[CT3_CDAT_DSLBIS3] = g_steal_pointer(&dslbis3);
+    cdat_table[CT3_CDAT_DSEMTS] = g_steal_pointer(&dsemts);
+
+    return 0;
+}
+
+static int ct3_build_cdat_table(CDATSubHeader ***cdat_table, void *priv)
+{
+    g_autofree CDATSubHeader **table = NULL;
+    MemoryRegion *nonvolatile_mr;
+    CXLType3Dev *ct3d = priv;
+    int dsmad_handle = 0;
+    int rc;
+
+    if (!ct3d->hostmem) {
+        return 0;
+    }
+
+    nonvolatile_mr = host_memory_backend_get_memory(ct3d->hostmem);
+    if (!nonvolatile_mr) {
+        return -EINVAL;
+    }
+
+    table = g_malloc0(CT3_CDAT_NUM_ENTRIES * sizeof(*table));
+    if (!table) {
+        return -ENOMEM;
+    }
+
+    rc = ct3_build_cdat_entries_for_mr(table, dsmad_handle++, nonvolatile_mr);
+    if (rc < 0) {
+        return rc;
+    }
+
+    *cdat_table = g_steal_pointer(&table);
+
+    return CT3_CDAT_NUM_ENTRIES;
+}
+
+static void ct3_free_cdat_table(CDATSubHeader **cdat_table, int num, void *priv)
+{
+    int i;
+
+    for (i = 0; i < num; i++) {
+        g_free(cdat_table[i]);
+    }
+    g_free(cdat_table);
+}
+
+static bool cxl_doe_cdat_rsp(DOECap *doe_cap)
+{
+    CDATObject *cdat = &CXL_TYPE3(doe_cap->pdev)->cxl_cstate.cdat;
+    uint16_t ent;
+    void *base;
+    uint32_t len;
+    CDATReq *req = pcie_doe_get_write_mbox_ptr(doe_cap);
+    CDATRsp rsp;
+
+    assert(cdat->entry_len);
+
+    /* Discard if request length mismatched */
+    if (pcie_doe_get_obj_len(req) <
+        DIV_ROUND_UP(sizeof(CDATReq), DWORD_BYTE)) {
+        return false;
+    }
+
+    ent = req->entry_handle;
+    base = cdat->entry[ent].base;
+    len = cdat->entry[ent].length;
+
+    rsp = (CDATRsp) {
+        .header = {
+            .vendor_id = CXL_VENDOR_ID,
+            .data_obj_type = CXL_DOE_TABLE_ACCESS,
+            .reserved = 0x0,
+            .length = DIV_ROUND_UP((sizeof(rsp) + len), DWORD_BYTE),
+        },
+        .rsp_code = CXL_DOE_TAB_RSP,
+        .table_type = CXL_DOE_TAB_TYPE_CDAT,
+        .entry_handle = (ent < cdat->entry_len - 1) ?
+                        ent + 1 : CXL_DOE_TAB_ENT_MAX,
+    };
+
+    memcpy(doe_cap->read_mbox, &rsp, sizeof(rsp));
+    memcpy(doe_cap->read_mbox + DIV_ROUND_UP(sizeof(rsp), DWORD_BYTE),
+           base, len);
+
+    doe_cap->read_mbox_len += rsp.header.length;
+
+    return true;
+}
+
+static uint32_t ct3d_config_read(PCIDevice *pci_dev, uint32_t addr, int size)
+{
+    CXLType3Dev *ct3d = CXL_TYPE3(pci_dev);
+    uint32_t val;
+
+    if (pcie_doe_read_config(&ct3d->doe_cdat, addr, size, &val)) {
+        return val;
+    }
+
+    return pci_default_read_config(pci_dev, addr, size);
+}
+
+static void ct3d_config_write(PCIDevice *pci_dev, uint32_t addr, uint32_t val,
+                              int size)
+{
+    CXLType3Dev *ct3d = CXL_TYPE3(pci_dev);
+
+    pcie_doe_write_config(&ct3d->doe_cdat, addr, val, size);
+    pci_default_write_config(pci_dev, addr, val, size);
+}
+
 /*
  * Null value of all Fs suggested by IEEE RA guidelines for use of
  * EU, OUI and CID
@@ -140,6 +377,11 @@ static bool cxl_setup_memory(CXLType3Dev *ct3d, Error **errp)
     return true;
 }
 
+static DOEProtocol doe_cdat_prot[] = {
+    { CXL_VENDOR_ID, CXL_DOE_TABLE_ACCESS, cxl_doe_cdat_rsp },
+    { }
+};
+
 static void ct3_realize(PCIDevice *pci_dev, Error **errp)
 {
     CXLType3Dev *ct3d = CXL_TYPE3(pci_dev);
@@ -189,6 +431,14 @@ static void ct3_realize(PCIDevice *pci_dev, Error **errp)
     for (i = 0; i < msix_num; i++) {
         msix_vector_use(pci_dev, i);
     }
+
+    /* DOE Initailization */
+    pcie_doe_init(pci_dev, &ct3d->doe_cdat, 0x190, doe_cdat_prot, true, 0);
+
+    cxl_cstate->cdat.build_cdat_table = ct3_build_cdat_table;
+    cxl_cstate->cdat.free_cdat_table = ct3_free_cdat_table;
+    cxl_cstate->cdat.private = ct3d;
+    cxl_doe_cdat_init(cxl_cstate, errp);
 }
 
 static void ct3_exit(PCIDevice *pci_dev)
@@ -197,6 +447,7 @@ static void ct3_exit(PCIDevice *pci_dev)
     CXLComponentState *cxl_cstate = &ct3d->cxl_cstate;
     ComponentRegisters *regs = &cxl_cstate->crb;
 
+    cxl_doe_cdat_release(cxl_cstate);
     g_free(regs->special_ops);
     address_space_destroy(&ct3d->hostmem_as);
 }
@@ -296,6 +547,7 @@ static Property ct3_props[] = {
     DEFINE_PROP_LINK("lsa", CXLType3Dev, lsa, TYPE_MEMORY_BACKEND,
                      HostMemoryBackend *),
     DEFINE_PROP_UINT64("sn", CXLType3Dev, sn, UI64_NULL),
+    DEFINE_PROP_STRING("cdat", CXLType3Dev, cxl_cstate.cdat.filename),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -361,6 +613,9 @@ static void ct3_class_init(ObjectClass *oc, void *data)
     pc->device_id = 0xd93; /* LVF for now */
     pc->revision = 1;
 
+    pc->config_write = ct3d_config_write;
+    pc->config_read = ct3d_config_read;
+
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
     dc->desc = "CXL PMEM Device (Type 3)";
     dc->reset = ct3d_reset;