diff mbox series

[v4,10/14] vfio-user: handle PCI BAR accesses

Message ID da25f11aa2c7f4aeb2eec3d6930e491051794ecf.1639549843.git.jag.raman@oracle.com (mailing list archive)
State New, archived
Headers show
Series vfio-user server in QEMU | expand

Commit Message

Jag Raman Dec. 15, 2021, 3:35 p.m. UTC
Determine the BARs used by the PCI device and register handlers to
manage the access to the same.

Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 hw/remote/vfio-user-obj.c | 90 +++++++++++++++++++++++++++++++++++++++
 hw/remote/trace-events    |  3 ++
 2 files changed, 93 insertions(+)

Comments

Stefan Hajnoczi Dec. 16, 2021, 2:10 p.m. UTC | #1
On Wed, Dec 15, 2021 at 10:35:34AM -0500, Jagannathan Raman wrote:
> +static ssize_t vfu_object_bar_rw(PCIDevice *pci_dev, hwaddr addr, size_t count,
> +                                 char * const buf, const bool is_write,
> +                                 bool is_io)
> +{
> +    AddressSpace *as = NULL;
> +    MemTxResult res;
> +
> +    if (is_io) {
> +        as = &address_space_io;
> +    } else {
> +        as = pci_device_iommu_address_space(pci_dev);

This access is not initiated by the device, it's coming from the CPU. It
shouldn't go through the IOMMU address space.
Jag Raman Dec. 17, 2021, 7:12 p.m. UTC | #2
> On Dec 16, 2021, at 9:10 AM, Stefan Hajnoczi <stefanha@redhat.com> wrote:
> 
> On Wed, Dec 15, 2021 at 10:35:34AM -0500, Jagannathan Raman wrote:
>> +static ssize_t vfu_object_bar_rw(PCIDevice *pci_dev, hwaddr addr, size_t count,
>> +                                 char * const buf, const bool is_write,
>> +                                 bool is_io)
>> +{
>> +    AddressSpace *as = NULL;
>> +    MemTxResult res;
>> +
>> +    if (is_io) {
>> +        as = &address_space_io;
>> +    } else {
>> +        as = pci_device_iommu_address_space(pci_dev);
> 
> This access is not initiated by the device, it's coming from the CPU. It
> shouldn't go through the IOMMU address space.

Got it, thank you!
--
Jag
diff mbox series

Patch

diff --git a/hw/remote/vfio-user-obj.c b/hw/remote/vfio-user-obj.c
index 46f2251a68..9399e87cbe 100644
--- a/hw/remote/vfio-user-obj.c
+++ b/hw/remote/vfio-user-obj.c
@@ -249,6 +249,94 @@  static void dma_unregister(vfu_ctx_t *vfu_ctx, vfu_dma_info_t *info)
     trace_vfu_dma_unregister((uint64_t)info->iova.iov_base);
 }
 
+static ssize_t vfu_object_bar_rw(PCIDevice *pci_dev, hwaddr addr, size_t count,
+                                 char * const buf, const bool is_write,
+                                 bool is_io)
+{
+    AddressSpace *as = NULL;
+    MemTxResult res;
+
+    if (is_io) {
+        as = &address_space_io;
+    } else {
+        as = pci_device_iommu_address_space(pci_dev);
+    }
+
+    trace_vfu_bar_rw_enter(is_write ? "Write" : "Read", (uint64_t)addr);
+
+    res = address_space_rw(as, addr, MEMTXATTRS_UNSPECIFIED, (void *)buf,
+                           (hwaddr)count, is_write);
+    if (res != MEMTX_OK) {
+        warn_report("vfu: failed to %s 0x%"PRIx64"",
+                    is_write ? "write to" : "read from",
+                    addr);
+        return -1;
+    }
+
+    trace_vfu_bar_rw_exit(is_write ? "Write" : "Read", (uint64_t)addr);
+
+    return count;
+}
+
+/**
+ * VFU_OBJECT_BAR_HANDLER - macro for defining handlers for PCI BARs.
+ *
+ * To create handler for BAR number 2, VFU_OBJECT_BAR_HANDLER(2) would
+ * define vfu_object_bar2_handler
+ */
+#define VFU_OBJECT_BAR_HANDLER(BAR_NO)                                         \
+    static ssize_t vfu_object_bar##BAR_NO##_handler(vfu_ctx_t *vfu_ctx,        \
+                                        char * const buf, size_t count,        \
+                                        loff_t offset, const bool is_write)    \
+    {                                                                          \
+        VfuObject *o = vfu_get_private(vfu_ctx);                               \
+        PCIDevice *pci_dev = o->pci_dev;                                       \
+        hwaddr addr = (hwaddr)(pci_get_bar_addr(pci_dev, BAR_NO) + offset);    \
+        bool is_io = !!(pci_dev->io_regions[BAR_NO].type &                     \
+                        PCI_BASE_ADDRESS_SPACE);                               \
+                                                                               \
+        return vfu_object_bar_rw(pci_dev, addr, count, buf, is_write, is_io);  \
+    }                                                                          \
+
+VFU_OBJECT_BAR_HANDLER(0)
+VFU_OBJECT_BAR_HANDLER(1)
+VFU_OBJECT_BAR_HANDLER(2)
+VFU_OBJECT_BAR_HANDLER(3)
+VFU_OBJECT_BAR_HANDLER(4)
+VFU_OBJECT_BAR_HANDLER(5)
+
+static vfu_region_access_cb_t *vfu_object_bar_handlers[PCI_NUM_REGIONS] = {
+    &vfu_object_bar0_handler,
+    &vfu_object_bar1_handler,
+    &vfu_object_bar2_handler,
+    &vfu_object_bar3_handler,
+    &vfu_object_bar4_handler,
+    &vfu_object_bar5_handler,
+};
+
+/**
+ * vfu_object_register_bars - Identify active BAR regions of pdev and setup
+ *                            callbacks to handle read/write accesses
+ */
+static void vfu_object_register_bars(vfu_ctx_t *vfu_ctx, PCIDevice *pdev)
+{
+    int i;
+
+    for (i = 0; i < PCI_NUM_REGIONS; i++) {
+        if (!pdev->io_regions[i].size) {
+            continue;
+        }
+
+        vfu_setup_region(vfu_ctx, VFU_PCI_DEV_BAR0_REGION_IDX + i,
+                         (size_t)pdev->io_regions[i].size,
+                         vfu_object_bar_handlers[i],
+                         VFU_REGION_FLAG_RW, NULL, 0, -1, 0);
+
+        trace_vfu_bar_register(i, pdev->io_regions[i].addr,
+                               pdev->io_regions[i].size);
+    }
+}
+
 /*
  * TYPE_VFU_OBJECT depends on the availability of the 'socket' and 'device'
  * properties. It also depends on devices instantiated in QEMU. These
@@ -337,6 +425,8 @@  static void vfu_object_init_ctx(VfuObject *o, Error **errp)
         goto fail;
     }
 
+    vfu_object_register_bars(o->vfu_ctx, o->pci_dev);
+
     ret = vfu_realize_ctx(o->vfu_ctx);
     if (ret < 0) {
         error_setg(errp, "vfu: Failed to realize device %s- %s",
diff --git a/hw/remote/trace-events b/hw/remote/trace-events
index f945c7e33b..847d50d88f 100644
--- a/hw/remote/trace-events
+++ b/hw/remote/trace-events
@@ -9,3 +9,6 @@  vfu_cfg_read(uint32_t offset, uint32_t val) "vfu: cfg: 0x%u -> 0x%x"
 vfu_cfg_write(uint32_t offset, uint32_t val) "vfu: cfg: 0x%u <- 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_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""