vfio-user: handle PCI BAR accesses

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>
Message-id: 3373e10b5be5f42846f0632d4382466e1698c505.1655151679.git.jag.raman@oracle.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

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""

hw/remote/vfio-user-obj.c

@@ -52,6 +52,7 @@
 #include "hw/qdev-core.h"
 #include "hw/pci/pci.h"
 #include "qemu/timer.h"
+#include "exec/memory.h"
 
 #define TYPE_VFU_OBJECT "x-vfio-user-server"
 OBJECT_DECLARE_TYPE(VfuObject, VfuObjectClass, VFU_OBJECT)
@@ -332,6 +333,193 @@ 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 int vfu_object_mr_rw(MemoryRegion *mr, uint8_t *buf, hwaddr offset,
+                            hwaddr size, const bool is_write)
+{
+    uint8_t *ptr = buf;
+    bool release_lock = false;
+    uint8_t *ram_ptr = NULL;
+    MemTxResult result;
+    int access_size;
+    uint64_t val;
+
+    if (memory_access_is_direct(mr, is_write)) {
+        /**
+         * Some devices expose a PCI expansion ROM, which could be buffer
+         * based as compared to other regions which are primarily based on
+         * MemoryRegionOps. memory_region_find() would already check
+         * for buffer overflow, we don't need to repeat it here.
+         */
+        ram_ptr = memory_region_get_ram_ptr(mr);
+
+        if (is_write) {
+            memcpy((ram_ptr + offset), buf, size);
+        } else {
+            memcpy(buf, (ram_ptr + offset), size);
+        }
+
+        return 0;
+    }
+
+    while (size) {
+        /**
+         * The read/write logic used below is similar to the ones in
+         * flatview_read/write_continue()
+         */
+        release_lock = prepare_mmio_access(mr);
+
+        access_size = memory_access_size(mr, size, offset);
+
+        if (is_write) {
+            val = ldn_he_p(ptr, access_size);
+
+            result = memory_region_dispatch_write(mr, offset, val,
+                                                  size_memop(access_size),
+                                                  MEMTXATTRS_UNSPECIFIED);
+        } else {
+            result = memory_region_dispatch_read(mr, offset, &val,
+                                                 size_memop(access_size),
+                                                 MEMTXATTRS_UNSPECIFIED);
+
+            stn_he_p(ptr, access_size, val);
+        }
+
+        if (release_lock) {
+            qemu_mutex_unlock_iothread();
+            release_lock = false;
+        }
+
+        if (result != MEMTX_OK) {
+            return -1;
+        }
+
+        size -= access_size;
+        ptr += access_size;
+        offset += access_size;
+    }
+
+    return 0;
+}
+
+static size_t vfu_object_bar_rw(PCIDevice *pci_dev, int pci_bar,
+                                hwaddr bar_offset, char * const buf,
+                                hwaddr len, const bool is_write)
+{
+    MemoryRegionSection section = { 0 };
+    uint8_t *ptr = (uint8_t *)buf;
+    MemoryRegion *section_mr = NULL;
+    uint64_t section_size;
+    hwaddr section_offset;
+    hwaddr size = 0;
+
+    while (len) {
+        section = memory_region_find(pci_dev->io_regions[pci_bar].memory,
+                                     bar_offset, len);
+
+        if (!section.mr) {
+            warn_report("vfu: invalid address 0x%"PRIx64"", bar_offset);
+            return size;
+        }
+
+        section_mr = section.mr;
+        section_offset = section.offset_within_region;
+        section_size = int128_get64(section.size);
+
+        if (is_write && section_mr->readonly) {
+            warn_report("vfu: attempting to write to readonly region in "
+                        "bar %d - [0x%"PRIx64" - 0x%"PRIx64"]",
+                        pci_bar, bar_offset,
+                        (bar_offset + section_size));
+            memory_region_unref(section_mr);
+            return size;
+        }
+
+        if (vfu_object_mr_rw(section_mr, ptr, section_offset,
+                             section_size, is_write)) {
+            warn_report("vfu: failed to %s "
+                        "[0x%"PRIx64" - 0x%"PRIx64"] in bar %d",
+                        is_write ? "write to" : "read from", bar_offset,
+                        (bar_offset + section_size), pci_bar);
+            memory_region_unref(section_mr);
+            return size;
+        }
+
+        size += section_size;
+        bar_offset += section_size;
+        ptr += section_size;
+        len -= section_size;
+
+        memory_region_unref(section_mr);
+    }
+
+    return size;
+}
+
+/**
+ * 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;                                       \
+                                                                               \
+        return vfu_object_bar_rw(pci_dev, BAR_NO, offset,                      \
+                                 buf, count, is_write);                        \
+    }                                                                          \
+
+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)
+VFU_OBJECT_BAR_HANDLER(6)
+
+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_bar6_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 flags = VFU_REGION_FLAG_RW;
+    int i;
+
+    for (i = 0; i < PCI_NUM_REGIONS; i++) {
+        if (!pdev->io_regions[i].size) {
+            continue;
+        }
+
+        if ((i == VFU_PCI_DEV_ROM_REGION_IDX) ||
+            pdev->io_regions[i].memory->readonly) {
+            flags &= ~VFU_REGION_FLAG_WRITE;
+        }
+
+        vfu_setup_region(vfu_ctx, VFU_PCI_DEV_BAR0_REGION_IDX + i,
+                         (size_t)pdev->io_regions[i].size,
+                         vfu_object_bar_handlers[i],
+                         flags, 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
@@ -442,6 +630,8 @@ 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",

include/exec/memory.h

@@ -2810,6 +2810,9 @@ MemTxResult address_space_write_cached_slow(MemoryRegionCache *cache,
                                             hwaddr addr, const void *buf,
                                             hwaddr len);
 
+int memory_access_size(MemoryRegion *mr, unsigned l, hwaddr addr);
+bool prepare_mmio_access(MemoryRegion *mr);
+
 static inline bool memory_access_is_direct(MemoryRegion *mr, bool is_write)
 {
     if (is_write) {

softmmu/physmem.c

@@ -2719,7 +2719,7 @@ void memory_region_flush_rom_device(MemoryRegion *mr, hwaddr addr, hwaddr size)
     invalidate_and_set_dirty(mr, addr, size);
 }
 
-static int memory_access_size(MemoryRegion *mr, unsigned l, hwaddr addr)
+int memory_access_size(MemoryRegion *mr, unsigned l, hwaddr addr)
 {
     unsigned access_size_max = mr->ops->valid.max_access_size;
 
@@ -2746,7 +2746,7 @@ static int memory_access_size(MemoryRegion *mr, unsigned l, hwaddr addr)
     return l;
 }
 
-static bool prepare_mmio_access(MemoryRegion *mr)
+bool prepare_mmio_access(MemoryRegion *mr)
 {
     bool release_lock = false;
 

tests/qtest/fuzz/generic_fuzz.c

@@ -144,7 +144,7 @@ static void *pattern_alloc(pattern p, size_t len)
     return buf;
 }
 
-static int memory_access_size(MemoryRegion *mr, unsigned l, hwaddr addr)
+static int fuzz_memory_access_size(MemoryRegion *mr, unsigned l, hwaddr addr)
 {
     unsigned access_size_max = mr->ops->valid.max_access_size;
 
@@ -242,11 +242,12 @@ void fuzz_dma_read_cb(size_t addr, size_t len, MemoryRegion *mr)
 
         /*
          *  If mr1 isn't RAM, address_space_translate doesn't update l. Use
-         *  memory_access_size to identify the number of bytes that it is safe
+         *  fuzz_memory_access_size to identify the number of bytes that it
-         *  to write without accidentally writing to another MemoryRegion.
+         *  is safe to write without accidentally writing to another
+         *  MemoryRegion.
          */
         if (!memory_region_is_ram(mr1)) {
-            l = memory_access_size(mr1, l, addr1);
+            l = fuzz_memory_access_size(mr1, l, addr1);
         }
         if (memory_region_is_ram(mr1) ||
             memory_region_is_romd(mr1) ||