All ram device regions were turned to be indirectly accessible by commit
4a2e242bbb ("memory: Don't use memcpy for ram_device regions"). This leads
to guest hang on attempt to build 'cuda-samples' as reported by Julia. The
guest is started by the following command lines, with GH100 GPU card passed
from the host.
host$ lspci | grep GH100
0009:01:00.0 3D controller: NVIDIA Corporation GH100 [GH200 120GB / 480GB]
(rev a1)
host$ /home/sandbox/gavin/qemu.main/build/qemu-system-aarch64 \
-machine virt,gic-version=host,ras=on,highmem-mmio-size=4T \
-accel kvm -cpu host -smp cpus=48 -m size=8G \
-drive file=/home/gavin/sandbox/images/disk.qcow2,if=none,id=d0 \
-device virtio-blk-pci,id=vb0,bus=pcie.0,drive=d0,num-queues=4 \
-device vfio-pci-nohotplug,host=0009:01:00.0,bus=pcie.1.0
:
guest$ cd cuda-samples/build
guest$ make -j 20 clean
guest$ make -j 20
:
[ 54%] Linking CUDA executable graphMemoryNodes
[ 54%] Built target graphMemoryNodes
<no more output afterwards, guest becomes frozen here>
guest$ qemu-system-aarch64: virtio: bogus descriptor or out of resources
[ 555.814025] virtio_blk virtio0: [vda] new size: 268435456 512-byte
logical blocks (137 GB/128 GiB)
When the GPU's driver (NVidia open driver) is loaded on guest bootup,
the memory blocks residing in the PCI BAR#4 of the GH100 GPU card can
be presented to the guest through memory hot-add. The page cache can
then be allocated from the hot added memory blocks when cuda-samples
is being built. Afterwards, the page cache is sent to QEMU's virtio-blk
device as part of the DMA request, the bounce buffer has to be used to
accomodate the request as the corresponding memory region (MemoryRegion)
is an indirectly accessible ram device region in qemu. However, the max
bounce bufer size is only 4096 bytes by default and that is exhausted
quickly, leading to a reset on the virtio-blk device and frozen guest
eventually.
QEMU
====
virtio_blk_handle_output
virtio_blk_handle_vq
virtio_blk_get_request
virtqueue_pop
virtqueue_split_pop
virtqueue_map_desc
address_space_map
memory_access_is_direct # Return false
memory_region_supports_direct_access
(qemu) info mtree
memory-region: pci_bridge_pci
0000000000000000-ffffffffffffffff (prio 0, container): pci_bridge_pci
0000042000000000-0000043fffffffff (prio 1, i/o): 0009:01:00.0 base BAR 4
0000042000000000-0000043fffffffff (prio 0, i/o): 0009:01:00.0 BAR 4
0000042000000000-000004379fffffff (prio 0, ramd): 0009:01:00.0 BAR
4 mmaps[0]
This adds qemu_ram_{copy, move}() and replaces {memcpy, memmove}() with
them in the ram device memory region accessors, similar to what's done
in commit 4a2e242bbb so that the issue (MMIO access instructions were
optimized to SSE instructions) covered by that commit is fixed. This
makes 'ram_device_mem_ops' redundant, paving the way to revert that
commit to make ram device region directly accessible again in the next
patch.
Reported-by: Julia Graham <[email protected]>
Suggested-by: Michael S. Tsirkin <[email protected]>
Suggested-by: Peter Xu <[email protected]>
Suggested-by: Richard Henderson <[email protected]>
Suggested-by: Peter Maydell <[email protected]>
Signed-off-by: Gavin Shan <[email protected]>
---
v3: Documentation for qemu_ram_{copy, move} (Peter/Michael)
Support qemu_ram_move() for overlapped src/dest (Richard)
Use {memcpy, memmove} if step is 16-bytes or more (Michael)
Code improvements (Richard/Michael)
---
hw/remote/vfio-user-obj.c | 4 +-
include/system/memory.h | 32 ++++++-
system/physmem.c | 178 +++++++++++++++++++++++++++++++++++++-
3 files changed, 207 insertions(+), 7 deletions(-)
diff --git a/hw/remote/vfio-user-obj.c b/hw/remote/vfio-user-obj.c
index 87fa7b6572..97a6c88780 100644
--- a/hw/remote/vfio-user-obj.c
+++ b/hw/remote/vfio-user-obj.c
@@ -375,9 +375,9 @@ static int vfu_object_mr_rw(MemoryRegion *mr, uint8_t *buf,
hwaddr offset,
ram_ptr = memory_region_get_ram_ptr(mr);
if (is_write) {
- memcpy((ram_ptr + offset), buf, size);
+ qemu_ram_copy(ram_ptr + offset, buf, size);
} else {
- memcpy(buf, (ram_ptr + offset), size);
+ qemu_ram_copy(buf, ram_ptr + offset, size);
}
return 0;
diff --git a/include/system/memory.h b/include/system/memory.h
index 1417132f6d..84203c312d 100644
--- a/include/system/memory.h
+++ b/include/system/memory.h
@@ -2897,6 +2897,36 @@ void address_space_register_map_client(AddressSpace *as,
QEMUBH *bh);
void address_space_unregister_map_client(AddressSpace *as, QEMUBH *bh);
/* Internal functions, part of the implementation of address_space_read. */
+
+/**
+ * qemu_ram_copy: copy data to ramblock
+ *
+ * @dst: destination where the data is copied to
+ * @src: source where the data is copied from
+ * @n: length of data to be copied
+ *
+ *
+ * Copy @n bytes from @src to @dst with the assumption that @src and @dst
+ * do not overlap. Handles special cases such as uncacheable ramblocks
+ * correctly. Use this for accessing ramblock in response to DMA/VCPU IO,
+ * in preference to memcpy().
+ */
+void qemu_ram_copy(void *dest, const void *src, size_t n);
+
+/**
+ * qemu_ram_move: move data to ramblock
+ *
+ * @dst: destination where the data is moved to
+ * @src: source where the data is moved from
+ * @n: length of data to be moved
+ *
+ * Move @n bytes from @src to @dst with the assumption that @src and @dst
+ * can overlap. Handles special cases such as uncacheable ramblocks
+ * correctly. Use this for accessing ramblock in response to DMA/VCPU IO,
+ * in preference to memmove().
+ */
+void qemu_ram_move(void *dest, const void *src, size_t n);
+
MemTxResult address_space_read_full(AddressSpace *as, hwaddr addr,
MemTxAttrs attrs, void *buf, hwaddr len);
MemTxResult flatview_read_continue(FlatView *fv, hwaddr addr,
@@ -2970,7 +3000,7 @@ MemTxResult address_space_read(AddressSpace *as, hwaddr
addr,
mr = flatview_translate(fv, addr, &addr1, &l, false, attrs);
if (len == l && memory_access_is_direct(mr, false, attrs)) {
ptr = qemu_map_ram_ptr(mr->ram_block, addr1);
- memcpy(buf, ptr, len);
+ qemu_ram_copy(buf, ptr, len);
} else {
result = flatview_read_continue(fv, addr, attrs, buf, len,
addr1, l, mr);
diff --git a/system/physmem.c b/system/physmem.c
index 7bcbf87573..45a17cd580 100644
--- a/system/physmem.c
+++ b/system/physmem.c
@@ -3160,6 +3160,177 @@ void memory_region_flush_rom_device(MemoryRegion *mr,
hwaddr addr, hwaddr size)
invalidate_and_set_dirty(mr, addr, size);
}
+static void qemu_ram_copy_aligned(void *dst, const void *src, size_t n)
+{
+ switch (n) {
+ case 1:
+ __builtin_memcpy(dst, src, 1);
+ break;
+ case 2:
+ __builtin_memcpy(dst, src, 2);
+ break;
+ case 4:
+ __builtin_memcpy(dst, src, 4);
+ break;
+ case 8:
+ __builtin_memcpy(dst, src, 8);
+ break;
+ default:
+ memcpy(dst, src, n);
+ }
+}
+
+static void qemu_ram_move_aligned(void *dst, const void *src, size_t n)
+{
+ switch (n) {
+ case 1:
+ __builtin_memmove(dst, src, 1);
+ break;
+ case 2:
+ __builtin_memmove(dst, src, 2);
+ break;
+ case 4:
+ __builtin_memmove(dst, src, 4);
+ break;
+ case 8:
+ __builtin_memmove(dst, src, 8);
+ break;
+ default:
+ memmove(dst, src, n);
+ }
+}
