[PATCH v10 6/7] vfio-user: Message-based DMA support

[Mattias Nissler <mnissler@rivosinc.com>]

Wire up support for DMA for the case where the vfio-user client does not
provide mmap()-able file descriptors, but DMA requests must be performed
via the VFIO-user protocol. This installs an indirect memory region,
which already works for pci_dma_{read,write}, and pci_dma_map works
thanks to the existing DMA bounce buffering support.

Note that while simple scenarios work with this patch, there's a known
race condition in libvfio-user that will mess up the communication
channel. See https://github.com/nutanix/libvfio-user/issues/279 for
details as well as a proposed fix.

Reviewed-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: Mattias Nissler <mnissler@rivosinc.com>
---
 hw/remote/trace-events    |   2 +
 hw/remote/vfio-user-obj.c | 100 ++++++++++++++++++++++++++++++++------
 2 files changed, 87 insertions(+), 15 deletions(-)

diff --git a/hw/remote/trace-events b/hw/remote/trace-events
index 0d1b7d56a5..358a68fb34 100644
--- a/hw/remote/trace-events
+++ b/hw/remote/trace-events
@@ -9,6 +9,8 @@ vfu_cfg_read(uint32_t offset, uint32_t val) "vfu: cfg: 0x%x -> 0x%x"
 vfu_cfg_write(uint32_t offset, uint32_t val) "vfu: cfg: 0x%x <- 0x%x"
 vfu_dma_register(uint64_t gpa, size_t len) "vfu: registering GPA 0x%"PRIx64", %zu bytes"
 vfu_dma_unregister(uint64_t gpa) "vfu: unregistering GPA 0x%"PRIx64""
+vfu_dma_read(uint64_t gpa, size_t len) "vfu: DMA read 0x%"PRIx64", %zu bytes"
+vfu_dma_write(uint64_t gpa, size_t len) "vfu: DMA write 0x%"PRIx64", %zu bytes"
 vfu_bar_register(int i, uint64_t addr, uint64_t size) "vfu: BAR %d: addr 0x%"PRIx64" size 0x%"PRIx64""
 vfu_bar_rw_enter(const char *op, uint64_t addr) "vfu: %s request for BAR address 0x%"PRIx64""
 vfu_bar_rw_exit(const char *op, uint64_t addr) "vfu: Finished %s of BAR address 0x%"PRIx64""
diff --git a/hw/remote/vfio-user-obj.c b/hw/remote/vfio-user-obj.c
index d9b879e056..a15e291c9a 100644
--- a/hw/remote/vfio-user-obj.c
+++ b/hw/remote/vfio-user-obj.c
@@ -300,6 +300,63 @@ static ssize_t vfu_object_cfg_access(vfu_ctx_t *vfu_ctx, char * const buf,
     return count;
 }
 
+static MemTxResult vfu_dma_read(void *opaque, hwaddr addr, uint64_t *val,
+                                unsigned size, MemTxAttrs attrs)
+{
+    MemoryRegion *region = opaque;
+    vfu_ctx_t *vfu_ctx = VFU_OBJECT(region->owner)->vfu_ctx;
+    uint8_t buf[sizeof(uint64_t)];
+
+    trace_vfu_dma_read(region->addr + addr, size);
+
+    g_autofree dma_sg_t *sg = g_malloc0(dma_sg_size());
+    vfu_dma_addr_t vfu_addr = (vfu_dma_addr_t)(region->addr + addr);
+    if (vfu_addr_to_sgl(vfu_ctx, vfu_addr, size, sg, 1, PROT_READ) < 0 ||
+        vfu_sgl_read(vfu_ctx, sg, 1, buf) != 0) {
+        return MEMTX_ERROR;
+    }
+
+    *val = ldn_he_p(buf, size);
+
+    return MEMTX_OK;
+}
+
+static MemTxResult vfu_dma_write(void *opaque, hwaddr addr, uint64_t val,
+                                 unsigned size, MemTxAttrs attrs)
+{
+    MemoryRegion *region = opaque;
+    vfu_ctx_t *vfu_ctx = VFU_OBJECT(region->owner)->vfu_ctx;
+    uint8_t buf[sizeof(uint64_t)];
+
+    trace_vfu_dma_write(region->addr + addr, size);
+
+    stn_he_p(buf, size, val);
+
+    g_autofree dma_sg_t *sg = g_malloc0(dma_sg_size());
+    vfu_dma_addr_t vfu_addr = (vfu_dma_addr_t)(region->addr + addr);
+    if (vfu_addr_to_sgl(vfu_ctx, vfu_addr, size, sg, 1, PROT_WRITE) < 0 ||
+        vfu_sgl_write(vfu_ctx, sg, 1, buf) != 0) {
+        return MEMTX_ERROR;
+    }
+
+    return MEMTX_OK;
+}
+
+static const MemoryRegionOps vfu_dma_ops = {
+    .read_with_attrs = vfu_dma_read,
+    .write_with_attrs = vfu_dma_write,
+    .endianness = DEVICE_HOST_ENDIAN,
+    .valid = {
+        .min_access_size = 1,
+        .max_access_size = 8,
+        .unaligned = true,
+    },
+    .impl = {
+        .min_access_size = 1,
+        .max_access_size = 8,
+    },
+};
+
 static void dma_register(vfu_ctx_t *vfu_ctx, vfu_dma_info_t *info)
 {
     VfuObject *o = vfu_get_private(vfu_ctx);
@@ -308,17 +365,30 @@ static void dma_register(vfu_ctx_t *vfu_ctx, vfu_dma_info_t *info)
     g_autofree char *name = NULL;
     struct iovec *iov = &info->iova;
 
-    if (!info->vaddr) {
-        return;
-    }
-
     name = g_strdup_printf("mem-%s-%"PRIx64"", o->device,
-                           (uint64_t)info->vaddr);
+                           (uint64_t)iov->iov_base);
 
     subregion = g_new0(MemoryRegion, 1);
 
-    memory_region_init_ram_ptr(subregion, NULL, name,
-                               iov->iov_len, info->vaddr);
+    if (info->vaddr) {
+        memory_region_init_ram_ptr(subregion, OBJECT(o), name,
+                                   iov->iov_len, info->vaddr);
+    } else {
+        /*
+         * Note that I/O regions' MemoryRegionOps handle accesses of at most 8
+         * bytes at a time, and larger accesses are broken down. However,
+         * many/most DMA accesses are larger than 8 bytes and VFIO-user can
+         * handle large DMA accesses just fine, thus this size restriction
+         * unnecessarily hurts performance, in particular given that each
+         * access causes a round trip on the VFIO-user socket.
+         *
+         * TODO: Investigate how to plumb larger accesses through memory
+         * regions, possibly by amending MemoryRegionOps or by creating a new
+         * memory region type.
+         */
+        memory_region_init_io(subregion, OBJECT(o), &vfu_dma_ops, subregion,
+                              name, iov->iov_len);
+    }
 
     dma_as = pci_device_iommu_address_space(o->pci_dev);
 
@@ -330,20 +400,20 @@ static void dma_register(vfu_ctx_t *vfu_ctx, vfu_dma_info_t *info)
 static void dma_unregister(vfu_ctx_t *vfu_ctx, vfu_dma_info_t *info)
 {
     VfuObject *o = vfu_get_private(vfu_ctx);
+    MemoryRegionSection mr_section;
     AddressSpace *dma_as = NULL;
-    MemoryRegion *mr = NULL;
-    ram_addr_t offset;
 
-    mr = memory_region_from_host(info->vaddr, &offset);
-    if (!mr) {
+    dma_as = pci_device_iommu_address_space(o->pci_dev);
+
+    mr_section =
+        memory_region_find(dma_as->root, (hwaddr)info->iova.iov_base, 1);
+    if (!mr_section.mr) {
         return;
     }
 
-    dma_as = pci_device_iommu_address_space(o->pci_dev);
-
-    memory_region_del_subregion(dma_as->root, mr);
+    memory_region_del_subregion(dma_as->root, mr_section.mr);
 
-    object_unparent((OBJECT(mr)));
+    object_unparent((OBJECT(mr_section.mr)));
 
     trace_vfu_dma_unregister((uint64_t)info->iova.iov_base);
 }
-- 
2.43.2