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>
Everything is now in place to use the Host IOMMU Device callbacks
to retrieve the page size mask usable with a given assigned device.
This new method brings the advantage to pass the info much earlier
to the virtual IOMMU and before the IOMMU MR gets enabled. So let's
remove the call to memory_region_iommu_set_page_size_mask in
vfio common.c and remove the single implementation of the IOMMU MR
callback in the virtio-iommu.c
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Since the host IOVA ranges are now passed through the
PCIIOMMUOps set_host_resv_regions and we have removed
the only implementation of iommu_set_iova_range() in
the virtio-iommu and the only call site in vfio/common,
let's retire the IOMMU MR API and its memory wrapper.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Instead of using a single global bounce buffer, give each AddressSpace
its own bounce buffer. The MapClient callback mechanism moves to
AddressSpace accordingly.
This is in preparation for generalizing bounce buffer handling further
to allow multiple bounce buffers, with a total allocation limit
configured per AddressSpace.
Reviewed-by: Peter Xu <peterx@redhat.com>
Tested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Mattias Nissler <mnissler@rivosinc.com>
Message-ID: <20240507094210.300566-2-mnissler@rivosinc.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
[PMD: Split patch, part 2/2]
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Propagate AddressSpace handler to following helpers:
- register_map_client()
- unregister_map_client()
- notify_map_clients[_locked]()
Rename them using 'address_space_' prefix instead of 'cpu_'.
The AddressSpace argument will be used in the next commit.
Reviewed-by: Peter Xu <peterx@redhat.com>
Tested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Mattias Nissler <mnissler@rivosinc.com>
Message-ID: <20240507094210.300566-2-mnissler@rivosinc.com>
[PMD: Split patch, part 1/2]
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
'NEED_CPU_H' guard target-specific code; it is defined by meson
altogether with the 'CONFIG_TARGET' definition. Rename NEED_CPU_H
as COMPILING_PER_TARGET to clarify its meaning.
Mechanical change running:
$ sed -i s/NEED_CPU_H/COMPILING_PER_TARGET/g $(git grep -l NEED_CPU_H)
then manually add a /* COMPILING_PER_TARGET */ comment
after the '#endif' when the block is large.
Inspired-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20240322161439.6448-4-philmd@linaro.org>
Migration pull for 9.1
- Het's new test cases for "channels"
- Het's fix for a typo for vsock parsing
- Cedric's VFIO error report series
- Cedric's one more patch for dirty-bitmap error reports
- Zhijian's rdma deprecation patch
- Yuan's zeropage optimization to fix double faults on anon mem
- Zhijian's COLO fix on a crash
# -----BEGIN PGP SIGNATURE-----
#
# iIgEABYKADAWIQS5GE3CDMRX2s990ak7X8zN86vXBgUCZig4HxIccGV0ZXJ4QHJl
# ZGhhdC5jb20ACgkQO1/MzfOr1wbQiwD/V5nSJzSuAG4Ra1Fjo+LRG2TT6qk8eNCi
# fIytehSw6cYA/0wqarxOF0tr7ikeyhtG3w4xFf44kk6KcPkoVSl1tqoL
# =pJmQ
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 23 Apr 2024 03:37:19 PM PDT
# gpg: using EDDSA key B9184DC20CC457DACF7DD1A93B5FCCCDF3ABD706
# gpg: issuer "peterx@redhat.com"
# gpg: Good signature from "Peter Xu <xzpeter@gmail.com>" [unknown]
# gpg: aka "Peter Xu <peterx@redhat.com>" [unknown]
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg: There is no indication that the signature belongs to the owner.
# Primary key fingerprint: B918 4DC2 0CC4 57DA CF7D D1A9 3B5F CCCD F3AB D706
* tag 'migration-20240423-pull-request' of https://gitlab.com/peterx/qemu: (26 commits)
migration/colo: Fix bdrv_graph_rdlock_main_loop: Assertion `!qemu_in_coroutine()' failed.
migration/multifd: solve zero page causing multiple page faults
migration: Add Error** argument to add_bitmaps_to_list()
migration: Modify ram_init_bitmaps() to report dirty tracking errors
migration: Add Error** argument to xbzrle_init()
migration: Add Error** argument to ram_state_init()
memory: Add Error** argument to the global_dirty_log routines
migration: Introduce ram_bitmaps_destroy()
memory: Add Error** argument to .log_global_start() handler
migration: Add Error** argument to .load_setup() handler
migration: Add Error** argument to .save_setup() handler
migration: Add Error** argument to qemu_savevm_state_setup()
migration: Add Error** argument to vmstate_save()
migration: Always report an error in ram_save_setup()
migration: Always report an error in block_save_setup()
vfio: Always report an error in vfio_save_setup()
s390/stattrib: Add Error** argument to set_migrationmode() handler
tests/qtest/migration: Fix typo for vsock in SocketAddress_to_str
tests/qtest/migration: Add negative tests to validate migration QAPIs
tests/qtest/migration: Add multifd_tcp_plain test using list of channels instead of uri
...
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Now that the log_global*() handlers take an Error** parameter and
return a bool, do the same for memory_global_dirty_log_start() and
memory_global_dirty_log_stop(). The error is reported in the callers
for now and it will be propagated in the call stack in the next
changes.
To be noted a functional change in ram_init_bitmaps(), if the dirty
pages logger fails to start, there is no need to synchronize the dirty
pages bitmaps. colo_incoming_start_dirty_log() could be modified in a
similar way.
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Anthony Perard <anthony.perard@citrix.com>
Cc: Paul Durrant <paul@xen.org>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hyman Huang <yong.huang@smartx.com>
Signed-off-by: Cédric Le Goater <clg@redhat.com>
Reviewed-by: Fabiano Rosas <farosas@suse.de>
Acked-by: Peter Xu <peterx@redhat.com>
Link: https://lore.kernel.org/r/20240320064911.545001-12-clg@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Add KVM guest_memfd support to RAMBlock so both normal hva based memory
and kvm guest memfd based private memory can be associated in one RAMBlock.
Introduce new flag RAM_GUEST_MEMFD. When it's set, it calls KVM ioctl to
create private guest_memfd during RAMBlock setup.
Allocating a new RAM_GUEST_MEMFD flag to instruct the setup of guest memfd
is more flexible and extensible than simply relying on the VM type because
in the future we may have the case that not all the memory of a VM need
guest memfd. As a benefit, it also avoid getting MachineState in memory
subsystem.
Note, RAM_GUEST_MEMFD is supposed to be set for memory backends of
confidential guests, such as TDX VM. How and when to set it for memory
backends will be implemented in the following patches.
Introduce memory_region_has_guest_memfd() to query if the MemoryRegion has
KVM guest_memfd allocated.
Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Message-ID: <20240320083945.991426-7-michael.roth@amd.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
