softmmu: Support concurrent bounce buffers

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.

Signed-off-by: Mattias Nissler <mnissler@rivosinc.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Acked-by: Peter Xu <peterx@redhat.com>
Link: https://lore.kernel.org/r/20240819135455.2957406-1-mnissler@rivosinc.com
Signed-off-by: Peter Xu <peterx@redhat.com>

2 files changed, 60 insertions, 27 deletions

diff --git a/system/memory.c b/system/memory.c
index 5e6eb45..f6f6fee 100644
--- a/system/memory.c
+++ b/system/memory.c
@@ -3148,7 +3148,8 @@ 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");
@@ -3158,7 +3159,7 @@ 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 94600a3..971bfa0 100644
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -3095,6 +3095,20 @@ 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)
 {
@@ -3120,9 +3134,9 @@ void address_space_register_map_client(AddressSpace *as, QEMUBH *bh)
     QEMU_LOCK_GUARD(&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);
     }
 }
@@ -3251,28 +3265,40 @@ 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 used = qatomic_read(&as->bounce_buffer_size);
+        for (;;) {
+            hwaddr alloc = MIN(as->max_bounce_buffer_size - used, l);
+            size_t new_size = used + alloc;
+            size_t actual =
+                qatomic_cmpxchg(&as->bounce_buffer_size, used, new_size);
+            if (actual == used) {
+                l = alloc;
+                break;
+            }
+            used = actual;
+        }
+
+        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);
@@ -3287,12 +3313,11 @@ 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);
         }
@@ -3302,15 +3327,22 @@ 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);
 }