diff mbox series

[v8,2/5] softmmu: Support concurrent bounce buffers

Message ID 20240304100554.1143763-3-mnissler@rivosinc.com (mailing list archive)
State New, archived
Headers show
Series Support message-based DMA in vfio-user server | expand

Commit Message

Mattias Nissler March 4, 2024, 10:05 a.m. UTC 
When DMA memory can't be directly accessed, as is the case when
running the device model in a separate process without shareable DMA
file descriptors, bounce buffering is used.

It is not uncommon for device models to request mapping of several DMA
regions at the same time. Examples include:
 * net devices, e.g. when transmitting a packet that is split across
   several TX descriptors (observed with igb)
 * USB host controllers, when handling a packet with multiple data TRBs
   (observed with xhci)

Previously, qemu only provided a single bounce buffer per AddressSpace
and would fail DMA map requests while the buffer was already in use. In
turn, this would cause DMA failures that ultimately manifest as hardware
errors from the guest perspective.

This change allocates DMA bounce buffers dynamically instead of
supporting only a single buffer. Thus, multiple DMA mappings work
correctly also when RAM can't be mmap()-ed.

The total bounce buffer allocation size is limited individually for each
AddressSpace. The default limit is 4096 bytes, matching the previous
maximum buffer size. A new x-max-bounce-buffer-size parameter is
provided to configure the limit for PCI devices.

Reviewed-by: Peter Xu <peterx@redhat.com>
Tested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Mattias Nissler <mnissler@rivosinc.com>
---
 hw/pci/pci.c                |  8 ++++
 include/exec/memory.h       | 14 +++----
 include/hw/pci/pci_device.h |  3 ++
 system/memory.c             |  5 ++-
 system/physmem.c            | 80 +++++++++++++++++++++++++------------
 5 files changed, 74 insertions(+), 36 deletions(-)
diff mbox series

Patch

diff --git a/hw/pci/pci.c b/hw/pci/pci.c
index 6496d027ca..036b3ff822 100644
--- a/hw/pci/pci.c
+++ b/hw/pci/pci.c
@@ -85,6 +85,8 @@  static Property pci_props[] = {
                     QEMU_PCIE_ERR_UNC_MASK_BITNR, true),
     DEFINE_PROP_BIT("x-pcie-ari-nextfn-1", PCIDevice, cap_present,
                     QEMU_PCIE_ARI_NEXTFN_1_BITNR, false),
+    DEFINE_PROP_SIZE("x-max-bounce-buffer-size", PCIDevice,
+                     max_bounce_buffer_size, DEFAULT_MAX_BOUNCE_BUFFER_SIZE),
     DEFINE_PROP_END_OF_LIST()
 };
 
@@ -1203,6 +1205,8 @@  static PCIDevice *do_pci_register_device(PCIDevice *pci_dev,
                        "bus master container", UINT64_MAX);
     address_space_init(&pci_dev->bus_master_as,
                        &pci_dev->bus_master_container_region, pci_dev->name);
+    pci_dev->bus_master_as.max_bounce_buffer_size =
+        pci_dev->max_bounce_buffer_size;
 
     if (phase_check(PHASE_MACHINE_READY)) {
         pci_init_bus_master(pci_dev);
@@ -2632,6 +2636,10 @@  static void pci_device_class_init(ObjectClass *klass, void *data)
     k->unrealize = pci_qdev_unrealize;
     k->bus_type = TYPE_PCI_BUS;
     device_class_set_props(k, pci_props);
+    object_class_property_set_description(
+        klass, "x-max-bounce-buffer-size",
+        "Maximum buffer size allocated for bounce buffers used for mapped "
+        "access to indirect DMA memory");
 }
 
 static void pci_device_class_base_init(ObjectClass *klass, void *data)
diff --git a/include/exec/memory.h b/include/exec/memory.h
index 0658846555..3fe0e2824c 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -1111,13 +1111,7 @@  typedef struct AddressSpaceMapClient {
     QLIST_ENTRY(AddressSpaceMapClient) link;
 } AddressSpaceMapClient;
 
-typedef struct {
-    MemoryRegion *mr;
-    void *buffer;
-    hwaddr addr;
-    hwaddr len;
-    bool in_use;
-} BounceBuffer;
+#define DEFAULT_MAX_BOUNCE_BUFFER_SIZE (4096)
 
 /**
  * struct AddressSpace: describes a mapping of addresses to #MemoryRegion objects
@@ -1137,8 +1131,10 @@  struct AddressSpace {
     QTAILQ_HEAD(, MemoryListener) listeners;
     QTAILQ_ENTRY(AddressSpace) address_spaces_link;
 
-    /* Bounce buffer to use for this address space. */
-    BounceBuffer bounce;
+    /* Maximum DMA bounce buffer size used for indirect memory map requests */
+    uint64_t max_bounce_buffer_size;
+    /* Total size of bounce buffers currently allocated, atomically accessed */
+    uint64_t bounce_buffer_size;
     /* List of callbacks to invoke when buffers free up */
     QemuMutex map_client_list_lock;
     QLIST_HEAD(, AddressSpaceMapClient) map_client_list;
diff --git a/include/hw/pci/pci_device.h b/include/hw/pci/pci_device.h
index d3dd0f64b2..f4027c5379 100644
--- a/include/hw/pci/pci_device.h
+++ b/include/hw/pci/pci_device.h
@@ -160,6 +160,9 @@  struct PCIDevice {
     /* ID of standby device in net_failover pair */
     char *failover_pair_id;
     uint32_t acpi_index;
+
+    /* Maximum DMA bounce buffer size used for indirect memory map requests */
+    uint64_t max_bounce_buffer_size;
 };
 
 static inline int pci_intx(PCIDevice *pci_dev)
diff --git a/system/memory.c b/system/memory.c
index ad0caef1b8..1cf89654a1 100644
--- a/system/memory.c
+++ b/system/memory.c
@@ -3133,7 +3133,8 @@  void address_space_init(AddressSpace *as, MemoryRegion *root, const char *name)
     as->ioeventfds = NULL;
     QTAILQ_INIT(&as->listeners);
     QTAILQ_INSERT_TAIL(&address_spaces, as, address_spaces_link);
-    as->bounce.in_use = false;
+    as->max_bounce_buffer_size = DEFAULT_MAX_BOUNCE_BUFFER_SIZE;
+    as->bounce_buffer_size = 0;
     qemu_mutex_init(&as->map_client_list_lock);
     QLIST_INIT(&as->map_client_list);
     as->name = g_strdup(name ? name : "anonymous");
@@ -3143,7 +3144,7 @@  void address_space_init(AddressSpace *as, MemoryRegion *root, const char *name)
 
 static void do_address_space_destroy(AddressSpace *as)
 {
-    assert(!qatomic_read(&as->bounce.in_use));
+    assert(qatomic_read(&as->bounce_buffer_size) == 0);
     assert(QLIST_EMPTY(&as->map_client_list));
     qemu_mutex_destroy(&as->map_client_list_lock);
 
diff --git a/system/physmem.c b/system/physmem.c
index 2972b83ab0..5dcf4910cf 100644
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -2971,6 +2971,20 @@  void cpu_flush_icache_range(hwaddr start, hwaddr len)
                                      NULL, len, FLUSH_CACHE);
 }
 
+/*
+ * A magic value stored in the first 8 bytes of the bounce buffer struct. Used
+ * to detect illegal pointers passed to address_space_unmap.
+ */
+#define BOUNCE_BUFFER_MAGIC 0xb4017ceb4ffe12ed
+
+typedef struct {
+    uint64_t magic;
+    MemoryRegion *mr;
+    hwaddr addr;
+    size_t len;
+    uint8_t buffer[];
+} BounceBuffer;
+
 static void
 address_space_unregister_map_client_do(AddressSpaceMapClient *client)
 {
@@ -2996,9 +3010,9 @@  void address_space_register_map_client(AddressSpace *as, QEMUBH *bh)
     qemu_mutex_lock(&as->map_client_list_lock);
     client->bh = bh;
     QLIST_INSERT_HEAD(&as->map_client_list, client, link);
-    /* Write map_client_list before reading in_use.  */
+    /* Write map_client_list before reading bounce_buffer_size. */
     smp_mb();
-    if (!qatomic_read(&as->bounce.in_use)) {
+    if (qatomic_read(&as->bounce_buffer_size) < as->max_bounce_buffer_size) {
         address_space_notify_map_clients_locked(as);
     }
     qemu_mutex_unlock(&as->map_client_list_lock);
@@ -3128,28 +3142,38 @@  void *address_space_map(AddressSpace *as,
     mr = flatview_translate(fv, addr, &xlat, &l, is_write, attrs);
 
     if (!memory_access_is_direct(mr, is_write)) {
-        if (qatomic_xchg(&as->bounce.in_use, true)) {
+        size_t size = qatomic_add_fetch(&as->bounce_buffer_size, l);
+        if (size > as->max_bounce_buffer_size) {
+            /*
+             * Note that the overshot might be larger than l if threads are
+             * racing and bump bounce_buffer_size at the same time.
+             */
+            size_t excess = MIN(size - as->max_bounce_buffer_size, l);
+            l -= excess;
+            qatomic_sub(&as->bounce_buffer_size, excess);
+        }
+
+        if (l == 0) {
             *plen = 0;
             return NULL;
         }
-        /* Avoid unbounded allocations */
-        l = MIN(l, TARGET_PAGE_SIZE);
-        as->bounce.buffer = qemu_memalign(TARGET_PAGE_SIZE, l);
-        as->bounce.addr = addr;
-        as->bounce.len = l;
 
+        BounceBuffer *bounce = g_malloc0(l + sizeof(BounceBuffer));
+        bounce->magic = BOUNCE_BUFFER_MAGIC;
         memory_region_ref(mr);
-        as->bounce.mr = mr;
+        bounce->mr = mr;
+        bounce->addr = addr;
+        bounce->len = l;
+
         if (!is_write) {
             flatview_read(fv, addr, MEMTXATTRS_UNSPECIFIED,
-                          as->bounce.buffer, l);
+                          bounce->buffer, l);
         }
 
         *plen = l;
-        return as->bounce.buffer;
+        return bounce->buffer;
     }
 
-
     memory_region_ref(mr);
     *plen = flatview_extend_translation(fv, addr, len, mr, xlat,
                                         l, is_write, attrs);
@@ -3164,12 +3188,11 @@  void *address_space_map(AddressSpace *as,
 void address_space_unmap(AddressSpace *as, void *buffer, hwaddr len,
                          bool is_write, hwaddr access_len)
 {
-    if (buffer != as->bounce.buffer) {
-        MemoryRegion *mr;
-        ram_addr_t addr1;
+    MemoryRegion *mr;
+    ram_addr_t addr1;
 
-        mr = memory_region_from_host(buffer, &addr1);
-        assert(mr != NULL);
+    mr = memory_region_from_host(buffer, &addr1);
+    if (mr != NULL) {
         if (is_write) {
             invalidate_and_set_dirty(mr, addr1, access_len);
         }
@@ -3179,15 +3202,22 @@  void address_space_unmap(AddressSpace *as, void *buffer, hwaddr len,
         memory_region_unref(mr);
         return;
     }
+
+
+    BounceBuffer *bounce = container_of(buffer, BounceBuffer, buffer);
+    assert(bounce->magic == BOUNCE_BUFFER_MAGIC);
+
     if (is_write) {
-        address_space_write(as, as->bounce.addr, MEMTXATTRS_UNSPECIFIED,
-                            as->bounce.buffer, access_len);
-    }
-    qemu_vfree(as->bounce.buffer);
-    as->bounce.buffer = NULL;
-    memory_region_unref(as->bounce.mr);
-    /* Clear in_use before reading map_client_list.  */
-    qatomic_set_mb(&as->bounce.in_use, false);
+        address_space_write(as, bounce->addr, MEMTXATTRS_UNSPECIFIED,
+                            bounce->buffer, access_len);
+    }
+
+    qatomic_sub(&as->bounce_buffer_size, bounce->len);
+    bounce->magic = ~BOUNCE_BUFFER_MAGIC;
+    memory_region_unref(bounce->mr);
+    g_free(bounce);
+    /* Write bounce_buffer_size before reading map_client_list. */
+    smp_mb();
     address_space_notify_map_clients(as);
 }