aboutsummaryrefslogtreecommitdiff
path: root/lib
AgeCommit message (Collapse)AuthorFilesLines
2022-11-22allow shadow memory offset per shadow ioeventfd (#703)Thanos Makatos2-8/+10
Signed-off-by: Thanos Makatos <thanos.makatos@nutanix.com> Reviewed-by: John Levon <john.levon@nutanix.com>
2022-11-16check spelling (#720)John Levon1-1/+1
Use misspell-fixer if available, and correct the small number of errors it found. Rather than trying to install into the CI, run it directly from a github action. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Swapnil Ingle <swapnil.ingle@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2022-10-05add some unlikely (#717)Thanos Makatos1-13/+16
Signed-off-by: Thanos Makatos <thanos.makatos@nutanix.com> Reviewed-by: John Levon <john.levon@nutanix.com>
2022-10-05only call debug_region_access if in debug mode (#716)Thanos Makatos1-1/+9
Signed-off-by: Thanos Makatos <thanos.makatos@nutanix.com> Reviewed-by: John Levon <john.levon@nutanix.com>
2022-10-05don't duplicate FD in get region info (#715)Thanos Makatos1-9/+3
This is out of spec. Signed-off-by: Thanos Makatos <thanos.makatos@nutanix.com> Reviewed-by: John Levon <john.levon@nutanix.com>
2022-10-04fix compilation for i386 and ppc64 (#709)Thanos Makatos10-63/+102
Signed-off-by: Thanos Makatos <thanos.makatos@nutanix.com> Reviewed-by: John Levon <john.levon@nutanix.com> Reported-by: Eduardo Lima <eblima@gmail.com>
2022-08-18make SGL error-checking DEBUG-only (#706)John Levon1-3/+11
As vfu_addr_to_sgl() and co are on the hot path, compile out these sanity checks for non-DEBUG builds. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Swapnil Ingle <swapnil.ingle@nutanix.com>
2022-08-18avoid vfu_log() in SGL hot path (#705)John Levon1-0/+10
Even though in non-debug, we don't actually log anything here, even assembling the arguments to vfu_log() has a performance impact. Hide them behind a DEBUG_SGL define - even in a DEBUG build, they are particularly noisy and low-value. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Swapnil Ingle <swapnil.ingle@nutanix.com>
2022-08-08delete socket on vfu_ctx_destroy (#702)Thanos Makatos2-5/+9
fixes #660 Signed-off-by: Thanos Makatos <thanos.makatos@nutanix.com> Reviewed-by: John Levon <john.levon@nutanix.com> Reviewed-by: Swapnil Ingle <swapnil.ingle@nutanix.com>
2022-07-04support for shadow ioeventfd (#698)Thanos Makatos2-3/+22
When an ioeventfd is written to, KVM discards the value since it has no memory to write it to, and simply kicks the eventfd. This a problem for devices such a NVMe controllers that need the value (e.g. doorbells on BAR0). This patch allows the vfio-user server to pass a file descriptor that can be mmap'ed and KVM can write the ioeventfd value to this _shadow_ memory instead of discarding it. This shadow memory is not exposed to the guest. Signed-off-by: Thanos Makatos <thanos.makatos@nutanix.com> Reviewed-by: John Levon <john.levon@nutanix.com> Change-Id: Iad849c94076ffa5988e034c8bf7ec312d01f095f
2022-06-09report function in quiesce_check_allowed() (#693)John Levon1-7/+10
Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Swapnil Ingle <swapnil.ingle@nutanix.com>
2022-06-07irq: inform device of IRQ mask & unmask via callback (#694)Jag Raman3-2/+44
Client masks or unmasks a device IRQ using the VFIO_USER_DEVICE_SET_IRQS message. Inform the device of such changes to the IRQ state. Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Reviewed-by: John Levon <john.levon@nutanix.com>
2022-05-30allow all LOG_* levels (#691)John Levon1-2/+1
While libvfio-user doesn't use them all, at least SPDK was expecting to be able to set LOG_NOTICE level, and silently failing. There's no reason we can't support any valid syslog level. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Swapnil Ingle <swapnil.ingle@nutanix.com>
2022-05-30allow concurrent dirty bitmap get (#677)John Levon3-15/+87
Use atomic operations to allow concurrent bitmap updates with VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP operations. Dirtying clients can race against each other, so we must use atomic or when marking dirty: we do this byte-by-byte. When reading the dirty bitmap, we must be careful to not race and lose any set bits within the same byte. If we miss an update, we'll catch it the next time around, presuming that before the final pass we'll have quiesced all I/O. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Raphael Norwitz <raphael.norwitz@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2022-05-27re-work SGL API (#675)John Levon3-52/+61
Harmonize and rename the vfu_*sg() APIs to better reflect their functionality: in our case, there is no mapping happening as part of these calls, they are merely housekeeping for range splitting, dirty tracking, and so on. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2022-05-27remove maps list from DMA controller (#674)John Levon2-42/+7
->maps existed so that if a consumer does vfu_map_sg() and then we are asked to enable dirty page tracking, we won't mark those pages as dirty, and will hence potentially lose data. Now that we require quiesce and the use of either vfu_unmap_sg() or vfu_sg_mark_dirty(), there's no need to have this list any more. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2022-05-27remove refcnt from region (#673)John Levon2-5/+0
The reference count is unused, and not atomically handled, remove it. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2022-05-27re-work SG dirty tracking (#672)John Levon2-8/+52
Move SG dirtying to vfu_unmap_sg(): as we don't want to track SGs ourselves, doing this in vfu_map_sg() is no longer the right place. Note that the lack of tracking implies that any SGs must be unmapped before the final stop and copy phase. To avoid the need for this, add vfu_mark_sg_dirty(): this allows a consumer to mark a region as dirty explicitly without needing to unmap it. Currently it's the same as vfu_unmap_sg(), but that's an implementation detail. Note this still marks current maps after a get operation; that will change subsequently. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2022-05-27require quiesce for VFIO_USER_DIRTY_PAGES (#671)John Levon1-0/+3
If we require a quiesce for these calls, we can be sure that it will not race with any usage of vfu_*_sg() calls, as a first step towards concurrency. This is not ideal for VFIO_IOMMU_DIRTY_PAGES_FLAG_GET_BITMAP, which can potentially be called multiple times during pre-copy phase, but that's something we can fix later. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2022-05-23libvfio-user.h: sync VFIO_DEVICE_STATE_XXXX definitions with upstream (#690)Jag Raman3-40/+40
Rename VFIO_DEVICE_STATE_XXXX defines as VFIO_DEVICE_STATE_V1_XXXX. Upstream renamed these variable to be of the XXXX_V1_XXXX format and switched an enum for VFIO_DEVICE_STATE_XXXX. Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Reviewed-by: John Levon <john.levon@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2022-05-12run scan-build in CI (#680)John Levon2-1/+5
Yet another static analyzer pass, this one is used by SPDK, and as it did detect some minor issues, it's worth running. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2022-05-09build: delete CMake build rulesDaniel P. Berrangé1-89/+0
Now that Meson is functional, support for building with CMake is removed so that there is only one build system to maintain. Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
2022-05-09build: introduce Meson build file rulesDaniel P. Berrangé1-0/+47
The Meson build system used by many other virt projects (QEMU, libvirt and others) is easier to understand & maintain rules for than cmake, guiding towards best practice. Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
2022-04-28lib: export dma_sg_size symbol in library (#664)Daniel Berrangé1-1/+1
The dma_sg_size() method is listed in libvfio-user.h but the symbol is marked private in the ELF library. Signed-off-by: Daniel P. Berrangé <berrange@redhat.com> Reviewed-by: John Levon <john.levon@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2022-04-21fix a small coverity complaint (#663)John Levon1-6/+0
The complaint was: 259 if (ret != 0) { >>> CID 392380: Possible Control flow issues (DEADCODE) >>> Execution cannot reach this statement: "free(tp);". 260 free(tp); 261 return ERROR_INT(ret); 262 } Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Swapnil Ingle <swapnil.ingle@nutanix.com>
2022-04-21support AFL++ fuzzing (#623)John Levon9-340/+1002
To support fuzzing with AFL++, add a "pipe" transport that reads from stdin and outputs to stdout: this is the most convenient way of doing fuzzing. Add some docs on how to run a fuzzing session. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Swapnil Ingle <swapnil.ingle@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2022-04-19use struct iovec for grouping buffer and length (#658)Thanos Makatos4-124/+118
This make it tidier and easier to pass to function the buffer and length, instead of passing the whole msg. Signed-off-by: Thanos Makatos <thanos.makatos@nutanix.com> Reviewed-by: John Levon <john.levon@nutanix.com>
2022-03-07check for allowed operations in quiesce state (#647)Thanos Makatos4-0/+60
Signed-off-by: Thanos Makatos <thanos.makatos@nutanix.com> Reviewed-by: John Levon <john.levon@nutanix.com>
2022-03-02improve region access debugging (#653)John Levon3-60/+49
Many region accesses of interest are of normal register sizes; sniff the region access size, and report the read/written value if possible. Clean up dump_buffer() now, as it's not of much use. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2022-02-25clarify when logging when device changes migration state (#649)Thanos Makatos1-1/+6
This makes reading logs easier. Signed-off-by: Thanos Makatos <thanos.makatos@nutanix.com> Reviewed-by: John Levon <john.levon@nutanix.com>
2022-02-24additional logging around dirty pages (#650)Thanos Makatos2-0/+30
Signed-off-by: Thanos Makatos <thanos.makatos@nutanix.com> Reviewed-by: John Levon <john.levon@nutanix.com>
2022-02-04ignore writes to RO MSI-X registers (#642)Thanos Makatos1-32/+19
Signed-off-by: Thanos Makatos <thanos.makatos@nutanix.com> Reviewed-by: John Levon <john.levon@nutanix.com>
2022-01-17small get_request_header() cleanup (#637)John Levon1-9/+2
LGTM.com reports "Comparison is always true because ret <= -1.", and it's indeed correct (but harmless). Clean this up. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2021-12-22fix coverity issues (#636)John Levon1-0/+1
Fix three remaining low priority coverity issues; they do not represent bugs. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Swapnil Ingle <swapnil.ingle@nutanix.com>
2021-12-09allow DMA funcs to be called in quiesced state (#635)Thanos Makatos1-2/+0
Signed-off-by: Thanos Makatos <thanos.makatos@nutanix.com> Reviewed-by: John Levon <john.levon@nutanix.com>
2021-12-01refactor process_request() (#633)John Levon2-177/+200
Instead of process_request() having a dual role, split into get_request() and handle_request(). Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2021-11-30introduce device quiesce callback (#609)Thanos Makatos8-100/+256
Signed-off-by: Thanos Makatos <thanos.makatos@nutanix.com> Reviewed-by: John Leon <john.levon@nutanix.com>
2021-11-24verify region is mapped before acquiring dirty bitmap (#627)John Levon1-0/+12
DMA regions not mapped by the server are not dirty tracked (the client must track changes via handling VFIO_USER_DMA_WRITE), but we weren't correctly enforcing this, which could segfault when ->dirty_bitmap was NULL. Found via AFL++. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2021-11-24check ->argsz for VFIO_USER_DIRTY_PAGES (#628)John Levon1-5/+12
We weren't checking for a too-large ->argsz for this command. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2021-11-24fix dma unmap validation (#626)John Levon1-40/+57
There were two issues with unmap request validation when the dirty bitmap flag was set: - we weren't checking ->argsz against the maximum transfer size, allowing a client to trigger unbounded allocations - we needed to check for overflow when calculating the requested message out size Found via AFL++. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2021-11-24is_valid_region_access(): account for wrap-around (#624)John Levon2-2/+9
AFL++ found this, though we already knew about it, so fix it by comparing against a saturating addition. This was the only instance of client-controlled potential overflow I noticed. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Swapnil Ingle <swapnil.ingle@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2021-11-12don't assert in dev_get_caps() (#621)John Levon1-5/+6
As clients control ->client_max_fds, we should return an error, not assert, if we can't represent a region's mmap_areas. Found via AFL++. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Swapnil Ingle <swapnil.ingle@nutanix.com>
2021-11-11Fix reply of VFIO_USER_DEVICE_GET_REGION_INFO (#619)Swapnil Ingle1-4/+8
* Fix reply of VFIO_USER_DEVICE_GET_REGION_INFO Set VFIO_REGION_INFO_FLAG_CAPS flag only if caps are part of the reply. Signed-off-by: Swapnil Ingle <swapnil.ingle@nutanix.com> Reviewed-by: John Levon <john.levon@nutanix.com>
2021-10-20fix coverity warnings (#611)John Levon1-1/+2
Fix a few coverity-identified issues. Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Swapnil Ingle <swapnil.ingle@nutanix.com>
2021-10-05make migration state callback optionally asynchronous (#608)Thanos Makatos3-14/+69
Some devices need the migration state callback to be asynchronous. The simplest way to implement this is to require from the callback to return -1 and set errno to EBUSY, not process any other new messages (vfu_ctx_run returns -1 and sets errno to EBUSY), and provide a way to the user to complete migration (vfu_migr_done). Signed-off-by: Thanos Makatos <thanos.makatos@nutanix.com> Reviewed-by: John Levon <john.levon@nutanix.com> Reviewed-by: Swapnil Ingle <swapnil.ingle@nutanix.com>
2021-09-28disable VFIO_USER_DEVICE_GET_REGION_IO_FDS on invalid region (#607)John Levon1-0/+5
If a region is not set up, asking for its iofds should fail with EINVAL. Co-authored-by: John Levon <john.levon@nutanix.com> Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2021-09-28fix issue with get_region_io_fds when fd = -1 (#606)John Levon1-5/+1
An unmappable region should still allow io fds, as they are orthogonal. Co-authored-by: John Levon <john.levon@nutanix.com> Signed-off-by: John Levon <john.levon@nutanix.com> Reviewed-by: Thanos Makatos <thanos.makatos@nutanix.com>
2021-09-08initial ioeventfd support (#601)JAKelly102-1/+193
Provide initial support for handling VFIO_USER_DEVICE_GET_REGION_IO_FDS, along with a new vfu_create_ioeventfd() API. Reviewed-by: John Levon <john.levon@nutanix.com>
2021-08-27Add support for VFIO_DMA_UNMAP_FLAG_ALL flag (#600)Swapnil Ingle1-1/+24
* Add support for VFIO_DMA_UNMAP_FLAG_ALL flag Signed-off-by: Swapnil Ingle <swapnil.ingle@nutanix.com> Reviewed-by: John Levon <john.levon@nutanix.com>
2021-08-26Fix err path of handle_dma_unmap() (#597)Swapnil Ingle1-5/+5
* initial dma_unmap test Signed-off-by: John Levon <john.levon@nutanix.com> Signed-off-by: Swapnil Ingle <swapnil.ingle@nutanix.com> * Fix err path of handle_dma_unmap() Set msg->out_size before successful return. Otherwise in case of error reply path we may endup setting iovecs[1].iov_len with invalid iovecs[1].iov_base in tran_sock_reply() Signed-off-by: Swapnil Ingle <swapnil.ingle@nutanix.com> Reviewed-by: John Levon <john.levon@nutanix.com>
generated by cgit v1.1 at 2025-09-20 19:54:48 +0000