hw/cxl: Multi-Region CXL Type-3 Devices (Volatile and Persistent)

This commit enables each CXL Type-3 device to contain one volatile
memory region and one persistent region.

Two new properties have been added to cxl-type3 device initialization:
    [volatile-memdev] and [persistent-memdev]

The existing [memdev] property has been deprecated and will default the
memory region to a persistent memory region (although a user may assign
the region to a ram or file backed region). It cannot be used in
combination with the new [persistent-memdev] property.

Partitioning volatile memory from persistent memory is not yet supported.

Volatile memory is mapped at DPA(0x0), while Persistent memory is mapped
at DPA(vmem->size), per CXL Spec 8.2.9.8.2.0 - Get Partition Info.

Signed-off-by: Gregory Price <gregory.price@memverge.com>
Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
Reviewed-by: Fan Ni <fan.ni@samsung.com>
Tested-by: Fan Ni <fan.ni@samsung.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

Message-Id: <20230421160827.2227-4-Jonathan.Cameron@huawei.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

1 files changed, 223 insertions, 73 deletions

diff --git a/hw/mem/cxl_type3.c b/hw/mem/cxl_type3.c
index 2db7568..2adacbd 100644
--- a/hw/mem/cxl_type3.c
+++ b/hw/mem/cxl_type3.c
@@ -31,7 +31,8 @@ enum {
 };
 
 static int ct3_build_cdat_entries_for_mr(CDATSubHeader **cdat_table,
-                                         int dsmad_handle, MemoryRegion *mr)
+                                         int dsmad_handle, MemoryRegion *mr,
+                                         bool is_pmem, uint64_t dpa_base)
 {
     g_autofree CDATDsmas *dsmas = NULL;
     g_autofree CDATDslbis *dslbis0 = NULL;
@@ -50,8 +51,8 @@ static int ct3_build_cdat_entries_for_mr(CDATSubHeader **cdat_table,
             .length = sizeof(*dsmas),
         },
         .DSMADhandle = dsmad_handle,
-        .flags = CDAT_DSMAS_FLAG_NV,
-        .DPA_base = 0,
+        .flags = is_pmem ? CDAT_DSMAS_FLAG_NV : 0,
+        .DPA_base = dpa_base,
         .DPA_length = memory_region_size(mr),
     };
 
@@ -130,8 +131,11 @@ static int ct3_build_cdat_entries_for_mr(CDATSubHeader **cdat_table,
             .length = sizeof(*dsemts),
         },
         .DSMAS_handle = dsmad_handle,
-        /* Reserved - the non volatile from DSMAS matters */
-        .EFI_memory_type_attr = 2,
+        /*
+         * NV: Reserved - the non volatile from DSMAS matters
+         * V: EFI_MEMORY_SP
+         */
+        .EFI_memory_type_attr = is_pmem ? 2 : 1,
         .DPA_offset = 0,
         .DPA_length = memory_region_size(mr),
     };
@@ -150,33 +154,68 @@ static int ct3_build_cdat_entries_for_mr(CDATSubHeader **cdat_table,
 static int ct3_build_cdat_table(CDATSubHeader ***cdat_table, void *priv)
 {
     g_autofree CDATSubHeader **table = NULL;
-    MemoryRegion *nonvolatile_mr;
     CXLType3Dev *ct3d = priv;
+    MemoryRegion *volatile_mr = NULL, *nonvolatile_mr = NULL;
     int dsmad_handle = 0;
-    int rc;
+    int cur_ent = 0;
+    int len = 0;
+    int rc, i;
 
-    if (!ct3d->hostmem) {
+    if (!ct3d->hostpmem && !ct3d->hostvmem) {
         return 0;
     }
 
-    nonvolatile_mr = host_memory_backend_get_memory(ct3d->hostmem);
-    if (!nonvolatile_mr) {
-        return -EINVAL;
+    if (ct3d->hostvmem) {
+        volatile_mr = host_memory_backend_get_memory(ct3d->hostvmem);
+        if (!volatile_mr) {
+            return -EINVAL;
+        }
+        len += CT3_CDAT_NUM_ENTRIES;
+    }
+
+    if (ct3d->hostpmem) {
+        nonvolatile_mr = host_memory_backend_get_memory(ct3d->hostpmem);
+        if (!nonvolatile_mr) {
+            return -EINVAL;
+        }
+        len += CT3_CDAT_NUM_ENTRIES;
     }
 
-    table = g_malloc0(CT3_CDAT_NUM_ENTRIES * sizeof(*table));
+    table = g_malloc0(len * sizeof(*table));
     if (!table) {
         return -ENOMEM;
     }
 
-    rc = ct3_build_cdat_entries_for_mr(table, dsmad_handle++, nonvolatile_mr);
-    if (rc < 0) {
-        return rc;
+    /* Now fill them in */
+    if (volatile_mr) {
+        rc = ct3_build_cdat_entries_for_mr(table, dsmad_handle++, volatile_mr,
+                                           false, 0);
+        if (rc < 0) {
+            return rc;
+        }
+        cur_ent = CT3_CDAT_NUM_ENTRIES;
     }
 
+    if (nonvolatile_mr) {
+        rc = ct3_build_cdat_entries_for_mr(&(table[cur_ent]), dsmad_handle++,
+                                           nonvolatile_mr, true,
+                                           (volatile_mr ?
+                                            memory_region_size(volatile_mr) : 0));
+        if (rc < 0) {
+            goto error_cleanup;
+        }
+        cur_ent += CT3_CDAT_NUM_ENTRIES;
+    }
+    assert(len == cur_ent);
+
     *cdat_table = g_steal_pointer(&table);
 
-    return CT3_CDAT_NUM_ENTRIES;
+    return len;
+error_cleanup:
+    for (i = 0; i < cur_ent; i++) {
+        g_free(table[i]);
+    }
+    return rc;
 }
 
 static void ct3_free_cdat_table(CDATSubHeader **cdat_table, int num, void *priv)
@@ -264,16 +303,42 @@ static void build_dvsecs(CXLType3Dev *ct3d)
 {
     CXLComponentState *cxl_cstate = &ct3d->cxl_cstate;
     uint8_t *dvsec;
+    uint32_t range1_size_hi, range1_size_lo,
+             range1_base_hi = 0, range1_base_lo = 0,
+             range2_size_hi = 0, range2_size_lo = 0,
+             range2_base_hi = 0, range2_base_lo = 0;
+
+    /*
+     * Volatile memory is mapped as (0x0)
+     * Persistent memory is mapped at (volatile->size)
+     */
+    if (ct3d->hostvmem) {
+        range1_size_hi = ct3d->hostvmem->size >> 32;
+        range1_size_lo = (2 << 5) | (2 << 2) | 0x3 |
+                         (ct3d->hostvmem->size & 0xF0000000);
+        if (ct3d->hostpmem) {
+            range2_size_hi = ct3d->hostpmem->size >> 32;
+            range2_size_lo = (2 << 5) | (2 << 2) | 0x3 |
+                             (ct3d->hostpmem->size & 0xF0000000);
+        }
+    } else {
+        range1_size_hi = ct3d->hostpmem->size >> 32;
+        range1_size_lo = (2 << 5) | (2 << 2) | 0x3 |
+                         (ct3d->hostpmem->size & 0xF0000000);
+    }
 
     dvsec = (uint8_t *)&(CXLDVSECDevice){
         .cap = 0x1e,
         .ctrl = 0x2,
         .status2 = 0x2,
-        .range1_size_hi = ct3d->hostmem->size >> 32,
-        .range1_size_lo = (2 << 5) | (2 << 2) | 0x3 |
-        (ct3d->hostmem->size & 0xF0000000),
-        .range1_base_hi = 0,
-        .range1_base_lo = 0,
+        .range1_size_hi = range1_size_hi,
+        .range1_size_lo = range1_size_lo,
+        .range1_base_hi = range1_base_hi,
+        .range1_base_lo = range1_base_lo,
+        .range2_size_hi = range2_size_hi,
+        .range2_size_lo = range2_size_lo,
+        .range2_base_hi = range2_base_hi,
+        .range2_base_lo = range2_base_lo,
     };
     cxl_component_create_dvsec(cxl_cstate, CXL2_TYPE3_DEVICE,
                                PCIE_CXL_DEVICE_DVSEC_LENGTH,
@@ -514,36 +579,69 @@ static void ct3d_reg_write(void *opaque, hwaddr offset, uint64_t value,
 static bool cxl_setup_memory(CXLType3Dev *ct3d, Error **errp)
 {
     DeviceState *ds = DEVICE(ct3d);
-    MemoryRegion *mr;
-    char *name;
 
-    if (!ct3d->hostmem) {
-        error_setg(errp, "memdev property must be set");
+    if (!ct3d->hostmem && !ct3d->hostvmem && !ct3d->hostpmem) {
+        error_setg(errp, "at least one memdev property must be set");
         return false;
+    } else if (ct3d->hostmem && ct3d->hostpmem) {
+        error_setg(errp, "[memdev] cannot be used with new "
+                         "[persistent-memdev] property");
+        return false;
+    } else if (ct3d->hostmem) {
+        /* Use of hostmem property implies pmem */
+        ct3d->hostpmem = ct3d->hostmem;
+        ct3d->hostmem = NULL;
     }
 
-    mr = host_memory_backend_get_memory(ct3d->hostmem);
-    if (!mr) {
-        error_setg(errp, "memdev property must be set");
+    if (ct3d->hostpmem && !ct3d->lsa) {
+        error_setg(errp, "lsa property must be set for persistent devices");
         return false;
     }
-    memory_region_set_nonvolatile(mr, true);
-    memory_region_set_enabled(mr, true);
-    host_memory_backend_set_mapped(ct3d->hostmem, true);
 
-    if (ds->id) {
-        name = g_strdup_printf("cxl-type3-dpa-space:%s", ds->id);
-    } else {
-        name = g_strdup("cxl-type3-dpa-space");
+    if (ct3d->hostvmem) {
+        MemoryRegion *vmr;
+        char *v_name;
+
+        vmr = host_memory_backend_get_memory(ct3d->hostvmem);
+        if (!vmr) {
+            error_setg(errp, "volatile memdev must have backing device");
+            return false;
+        }
+        memory_region_set_nonvolatile(vmr, false);
+        memory_region_set_enabled(vmr, true);
+        host_memory_backend_set_mapped(ct3d->hostvmem, true);
+        if (ds->id) {
+            v_name = g_strdup_printf("cxl-type3-dpa-vmem-space:%s", ds->id);
+        } else {
+            v_name = g_strdup("cxl-type3-dpa-vmem-space");
+        }
+        address_space_init(&ct3d->hostvmem_as, vmr, v_name);
+        ct3d->cxl_dstate.vmem_size = memory_region_size(vmr);
+        ct3d->cxl_dstate.mem_size += memory_region_size(vmr);
+        g_free(v_name);
     }
-    address_space_init(&ct3d->hostmem_as, mr, name);
-    g_free(name);
 
-    ct3d->cxl_dstate.pmem_size = ct3d->hostmem->size;
+    if (ct3d->hostpmem) {
+        MemoryRegion *pmr;
+        char *p_name;
 
-    if (!ct3d->lsa) {
-        error_setg(errp, "lsa property must be set");
-        return false;
+        pmr = host_memory_backend_get_memory(ct3d->hostpmem);
+        if (!pmr) {
+            error_setg(errp, "persistent memdev must have backing device");
+            return false;
+        }
+        memory_region_set_nonvolatile(pmr, true);
+        memory_region_set_enabled(pmr, true);
+        host_memory_backend_set_mapped(ct3d->hostpmem, true);
+        if (ds->id) {
+            p_name = g_strdup_printf("cxl-type3-dpa-pmem-space:%s", ds->id);
+        } else {
+            p_name = g_strdup("cxl-type3-dpa-pmem-space");
+        }
+        address_space_init(&ct3d->hostpmem_as, pmr, p_name);
+        ct3d->cxl_dstate.pmem_size = memory_region_size(pmr);
+        ct3d->cxl_dstate.mem_size += memory_region_size(pmr);
+        g_free(p_name);
     }
 
     return true;
@@ -633,7 +731,12 @@ err_release_cdat:
 err_free_special_ops:
     g_free(regs->special_ops);
 err_address_space_free:
-    address_space_destroy(&ct3d->hostmem_as);
+    if (ct3d->hostpmem) {
+        address_space_destroy(&ct3d->hostpmem_as);
+    }
+    if (ct3d->hostvmem) {
+        address_space_destroy(&ct3d->hostvmem_as);
+    }
     return;
 }
 
@@ -646,7 +749,12 @@ static void ct3_exit(PCIDevice *pci_dev)
     pcie_aer_exit(pci_dev);
     cxl_doe_cdat_release(cxl_cstate);
     g_free(regs->special_ops);
-    address_space_destroy(&ct3d->hostmem_as);
+    if (ct3d->hostpmem) {
+        address_space_destroy(&ct3d->hostpmem_as);
+    }
+    if (ct3d->hostvmem) {
+        address_space_destroy(&ct3d->hostvmem_as);
+    }
 }
 
 /* TODO: Support multiple HDM decoders and DPA skip */
@@ -681,51 +789,77 @@ static bool cxl_type3_dpa(CXLType3Dev *ct3d, hwaddr host_addr, uint64_t *dpa)
     return true;
 }
 
-MemTxResult cxl_type3_read(PCIDevice *d, hwaddr host_addr, uint64_t *data,
-                           unsigned size, MemTxAttrs attrs)
+static int cxl_type3_hpa_to_as_and_dpa(CXLType3Dev *ct3d,
+                                       hwaddr host_addr,
+                                       unsigned int size,
+                                       AddressSpace **as,
+                                       uint64_t *dpa_offset)
 {
-    CXLType3Dev *ct3d = CXL_TYPE3(d);
-    uint64_t dpa_offset;
-    MemoryRegion *mr;
+    MemoryRegion *vmr = NULL, *pmr = NULL;
 
-    /* TODO support volatile region */
-    mr = host_memory_backend_get_memory(ct3d->hostmem);
-    if (!mr) {
-        return MEMTX_ERROR;
+    if (ct3d->hostvmem) {
+        vmr = host_memory_backend_get_memory(ct3d->hostvmem);
+    }
+    if (ct3d->hostpmem) {
+        pmr = host_memory_backend_get_memory(ct3d->hostpmem);
     }
 
-    if (!cxl_type3_dpa(ct3d, host_addr, &dpa_offset)) {
-        return MEMTX_ERROR;
+    if (!vmr && !pmr) {
+        return -ENODEV;
+    }
+
+    if (!cxl_type3_dpa(ct3d, host_addr, dpa_offset)) {
+        return -EINVAL;
+    }
+
+    if (*dpa_offset > ct3d->cxl_dstate.mem_size) {
+        return -EINVAL;
+    }
+
+    if (vmr) {
+        if (*dpa_offset < memory_region_size(vmr)) {
+            *as = &ct3d->hostvmem_as;
+        } else {
+            *as = &ct3d->hostpmem_as;
+            *dpa_offset -= memory_region_size(vmr);
+        }
+    } else {
+        *as = &ct3d->hostpmem_as;
     }
 
-    if (dpa_offset > memory_region_size(mr)) {
+    return 0;
+}
+
+MemTxResult cxl_type3_read(PCIDevice *d, hwaddr host_addr, uint64_t *data,
+                           unsigned size, MemTxAttrs attrs)
+{
+    uint64_t dpa_offset = 0;
+    AddressSpace *as = NULL;
+    int res;
+
+    res = cxl_type3_hpa_to_as_and_dpa(CXL_TYPE3(d), host_addr, size,
+                                      &as, &dpa_offset);
+    if (res) {
         return MEMTX_ERROR;
     }
 
-    return address_space_read(&ct3d->hostmem_as, dpa_offset, attrs, data, size);
+    return address_space_read(as, dpa_offset, attrs, data, size);
 }
 
 MemTxResult cxl_type3_write(PCIDevice *d, hwaddr host_addr, uint64_t data,
                             unsigned size, MemTxAttrs attrs)
 {
-    CXLType3Dev *ct3d = CXL_TYPE3(d);
-    uint64_t dpa_offset;
-    MemoryRegion *mr;
-
-    mr = host_memory_backend_get_memory(ct3d->hostmem);
-    if (!mr) {
-        return MEMTX_OK;
-    }
+    uint64_t dpa_offset = 0;
+    AddressSpace *as = NULL;
+    int res;
 
-    if (!cxl_type3_dpa(ct3d, host_addr, &dpa_offset)) {
-        return MEMTX_OK;
+    res = cxl_type3_hpa_to_as_and_dpa(CXL_TYPE3(d), host_addr, size,
+                                      &as, &dpa_offset);
+    if (res) {
+        return MEMTX_ERROR;
     }
 
-    if (dpa_offset > memory_region_size(mr)) {
-        return MEMTX_OK;
-    }
-    return address_space_write(&ct3d->hostmem_as, dpa_offset, attrs,
-                               &data, size);
+    return address_space_write(as, dpa_offset, attrs, &data, size);
 }
 
 static void ct3d_reset(DeviceState *dev)
@@ -740,7 +874,11 @@ static void ct3d_reset(DeviceState *dev)
 
 static Property ct3_props[] = {
     DEFINE_PROP_LINK("memdev", CXLType3Dev, hostmem, TYPE_MEMORY_BACKEND,
-                     HostMemoryBackend *),
+                     HostMemoryBackend *), /* for backward compatibility */
+    DEFINE_PROP_LINK("persistent-memdev", CXLType3Dev, hostpmem,
+                     TYPE_MEMORY_BACKEND, HostMemoryBackend *),
+    DEFINE_PROP_LINK("volatile-memdev", CXLType3Dev, hostvmem,
+                     TYPE_MEMORY_BACKEND, HostMemoryBackend *),
     DEFINE_PROP_LINK("lsa", CXLType3Dev, lsa, TYPE_MEMORY_BACKEND,
                      HostMemoryBackend *),
     DEFINE_PROP_UINT64("sn", CXLType3Dev, sn, UI64_NULL),
@@ -752,6 +890,10 @@ static uint64_t get_lsa_size(CXLType3Dev *ct3d)
 {
     MemoryRegion *mr;
 
+    if (!ct3d->lsa) {
+        return 0;
+    }
+
     mr = host_memory_backend_get_memory(ct3d->lsa);
     return memory_region_size(mr);
 }
@@ -769,6 +911,10 @@ static uint64_t get_lsa(CXLType3Dev *ct3d, void *buf, uint64_t size,
     MemoryRegion *mr;
     void *lsa;
 
+    if (!ct3d->lsa) {
+        return 0;
+    }
+
     mr = host_memory_backend_get_memory(ct3d->lsa);
     validate_lsa_access(mr, size, offset);
 
@@ -784,6 +930,10 @@ static void set_lsa(CXLType3Dev *ct3d, const void *buf, uint64_t size,
     MemoryRegion *mr;
     void *lsa;
 
+    if (!ct3d->lsa) {
+        return;
+    }
+
     mr = host_memory_backend_get_memory(ct3d->lsa);
     validate_lsa_access(mr, size, offset);
 
@@ -955,7 +1105,7 @@ static void ct3_class_init(ObjectClass *oc, void *data)
     pc->config_read = ct3d_config_read;
 
     set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
-    dc->desc = "CXL PMEM Device (Type 3)";
+    dc->desc = "CXL Memory Device (Type 3)";
     dc->reset = ct3d_reset;
     device_class_set_props(dc, ct3_props);