When --no-huge mode is used, the memory is currently allocated with
mmap(NULL, ...). This is fine in most cases, but can fail in cases
where DPDK is run on a machine with an IOMMU that is of more limited
address width than that of a VA, because we're not specifying the
address hint for mmap() call.
Fix it by preallocating VA space before mapping it.
Cc: stable@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Tested-by: David Marchand <david.marchand@redhat.com>
Tested-by: Jun W Zhou <junx.w.zhou@intel.com>
Currently, when we are creating DMA mappings for memory that's
either external or is backed by hugepages in IOVA as PA mode, we
assume that each page is necessarily discontiguous. This may not
actually be the case, especially for external memory, where the
user is able to create their own IOVA table and make it
contiguous. This is a problem because VFIO has a limited number
of DMA mappings, and it does not appear to concatenate them and
treats each mapping as separate, even when they cover adjacent
areas.
Fix this so that we always map contiguous memory in a single
chunk, as opposed to mapping each segment separately.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Ray Kinsella <ray.kinsella@intel.com>
Added an API to check if current execution is in interrupt
context. This will be helpful to handle nested interrupt cases.
Signed-off-by: Harman Kalra <hkalra@marvell.com>
Signed-off-by: Sunil Kumar Kori <skori@marvell.com>
Reviewed-by: Jerin Jacob <jerinj@marvell.com>
The loop to unwind existing mmaps was only unmapping the
first segment and the error paths after mmap() were not
doing munmap of the current segment.
Fixes: 66cc45e293ed ("mem: replace memseg with memseg lists")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
ppc64le failed when using large physical memory. I found problems in my two
commits in the past.
In commit e072d16f8920 ("vfio: fix expanding DMA area in ppc64le"), I added
a sanity check using a mapped address to resolve an issue around expanding
IOMMU window, but this was not enough, since memory allocation can return
memory anywhere dependent on memory fragmentation. DPDK may still skip DMA
mapping and attempts to unmap non-mapped DMA during expanding IOMMU window.
As a result, SPDK apps using large physical memory frequently failed to
proceed the communication with NVMe and/or went into an infinite loop.
The root cause of the bug was in a gap between memory segments managed by
DPDK and firmware-level DMA mapping. DPDK's memory segments don't contain
the state of DMA mapping, and so, the memesg_walk cannot determine if an
iterated memory segment is mapped or not. This resulted in incorrect DMA
maps and unmaps.
At this time, I added the code to avoid iterating non-mapped memory
segments during DMA mapping. The memseg_walk iterates over memory segments
marked as "used", and so, the code sets memory segments that will be
mapped or unmapped as "free" transiently.
The commit db90b4969e2e ("vfio: retry creating sPAPR DMA window") allows
retring different page levels and sizes to create DMA window. However, this
allows page sizes different from hugepage sizes. This inconsistency caused
failures at the time of DMA mapping after the window creation. This patch
fixes to retry only different page levels.
Fixes: e072d16f8920 ("vfio: fix expanding DMA area in ppc64le")
Fixes: db90b4969e2e ("vfio: retry creating sPAPR DMA window")
Cc: stable@dpdk.org
Signed-off-by: Takeshi Yoshimura <tyos@jp.ibm.com>
Reviewed-by: David Christensen <drc@linux.vnet.ibm.com>
The header linux/version.h isn't included when CONFIG_RTE_EAL_VFIO
is explicitly disabled. LINUX_VERSION_CODE and KERNEL_VERSION are
therefore undefined, causing the build failure:
lib/librte_eal/linux/eal/eal.c: In function ‘rte_eal_init’:
lib/librte_eal/linux/eal/eal.c:1076:32: error: "LINUX_VERSION_CODE" is
not defined, evaluates to 0 [-Werror=undef]
Fixes: a0dede62a537 ("eal/linux: remove KNI restriction on IOVA")
Cc: stable@dpdk.org
Signed-off-by: Ali Alnubani <alialnu@mellanox.com>
Previous fix gives hiccups to gcc on RHEL 7.6:
== Build lib/librte_eal/linux/eal
CC eal_interrupts.o
...lib/librte_eal/linux/eal/eal_interrupts.c: In function
‘eal_intr_thread_main’:
...lib/librte_eal/linux/eal/eal_interrupts.c:1048:9: error: missing
initializer for field ‘events’ of ‘struct epoll_event’
[-Werror=missing-field-initializers]
struct epoll_event ev = { };
^
In file included from ...lib/librte_eal/linux/eal/eal_interrupts.c:15:0:
/usr/include/sys/epoll.h:89:12: note: ‘events’ declared here
uint32_t events; /* Epoll events */
^
...lib/librte_eal/linux/eal/eal_interrupts.c: At top level:
cc1: error: unrecognized command line option
"-Wno-address-of-packed-member" [-Werror]
cc1: all warnings being treated as errors
Fixes: e0ab8020ac2a ("eal/linux: fix uninitialized data valgrind warning")
Cc: stable@dpdk.org
Reported-by: Andrew Rybchenko <arybchenko@solarflare.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>
Valgrind reports that eal interrupt thread is calling epoll_ctl
with uninitialized data.
This is a false positive, because the kernel is not going to care about
the unused bits in the union but trivial to fix by initializing it.
Fixes: af75078fece3 ("first public release")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: David Marchand <david.marchand@redhat.com>
The 'get_user_pages_remote()' API is updated in kernel 4.10.0 [1],
but the check added as > 4.9.0,
this logic is broken for kernels 4.9.x, because they justify
> 4.9.0 check but have the old API.
Fixing the check as >= 4.10.0
[1]
commit 5b56d49fc31d ("mm: add locked parameter to get_user_pages_remote()")
Fixes: d965af9e8ae1 ("kni: increase kernel version requirement for VA")
Reported-by: Andrew Rybchenko <arybchenko@solarflare.com>
Suggested-by: David Marchand <david.marchand@redhat.com>
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Tested-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
A build error reported related to the selected 'get_user_pages_remote()'
kernel API:
.../kernel/linux/kni/kni_dev.h:113:8:
error: too few arguments to function ‘get_user_pages_remote’
ret = get_user_pages_remote(tsk, tsk->mm, iova, 1
^~~~~~~~~~~~~~~~~~~~~
Currently there are three versions of the 'get_user_pages_remote()'
supported, based on kernel version < 4.9, = 4.9, > 4.9.
These version based checks are not working fine with the distro kernels
which is the cause of reported build error. The error reported by the
kernel version 4.8, but it is using API defined in > 4.9.
To be able to take control of this, and possible more, related build
error, increasing the minimum supported kernel version for iova=va with
KNI to kernel version 4.9.
This leaves us with single version of the kernel API and more manageable.
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
Since the library versioning for both stable and experimental ABI's is
now managed globally, the LIBABIVER and version variables no longer
serve any useful purpose, and can be removed.
The replacement in Makefiles was done using the following regex:
^(#.*\n)?LIBABIVER\s*:=\s*\d+\n(\s*\n)?
(LIBABIVER := numbers, optionally preceded by a comment and optionally
succeeded by an empty line)
The replacement for meson files was done using the following regex:
^(#.*\n)?version\s*=\s*\d+\n(\s*\n)?
(version = numbers, optionally preceded by a comment and optionally
succeeded by an empty line)
[David]: those variables are manually removed for the files:
- drivers/common/qat/Makefile
- lib/librte_eal/meson.build
[David]: the LIBABIVER is restored for the external ethtool example
library.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
Fix these as they are user visible. Found with codespell.
Fixes: bacaa2754017 ("eal: add channel for multi-process communication")
Fixes: f05e26051c15 ("eal: add IPC asynchronous request")
Fixes: 0cbce3a167f1 ("vfio: skip DMA map failure if already mapped")
Fixes: 445c6528b55f ("power: common interface for guest and host")
Fixes: e6c6dc0f96c8 ("power: add p-state driver compatibility")
Fixes: 8f972312b8f4 ("vhost: support vhost-user")
Cc: stable@dpdk.org
Signed-off-by: Kevin Traynor <ktraynor@redhat.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
The name in rte_kni_device_info is passed to the kernel, which allows
interface names with at most 16 bytes (IFNAMSIZ). rte_kni_alloc with a
longer name currently trigger a kernel BUG in alloc_netdev_mqs in
net/core/dev.c. Reduce RTE_KNI_NAMESIZE to prevent this situation.
Signed-off-by: Michael Pfeiffer <michael.pfeiffer@tu-ilmenau.de>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
Now that KNI supports VA (with kernel versions starting 4.6.0), we can
accept IOVA as VA, but KNI must be configured for this.
Pass iova_mode when creating KNI netdevs.
So far, IOVA detection policy forced IOVA as PA when KNI is loaded,
whatever the buses IOVA requirements were.
We can now use IOVA as VA, but this comes with a cost in KNI.
When no constraint is expressed by the buses, keep the current behavior
of choosing PA.
Note: this change supposes that dpdk is built on the same kernel than
the target system kernel; no objection has been expressed on this topic.
Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>
Reviewed-by: Jerin Jacob <jerinj@marvell.com>
Patch adds support for kernel module to work in IOVA = VA mode by
providing address translation routines to convert userspace VA to
kernel VA.
KNI performance using PA is not changed by this patch.
But comparing KNI using PA to KNI using VA, the latter will have lower
performance due to the cost of the added translation.
This translation is implemented only with kernel versions starting 4.6.0.
Signed-off-by: Vamsi Attunuru <vattunuru@marvell.com>
Signed-off-by: Kiran Kumar K <kirankumark@marvell.com>
Reviewed-by: Jerin Jacob <jerinj@marvell.com>
Currently, externally created heaps are supposed to be automatically
mapped for VFIO DMA by EAL, however they only do so if, at the time of
heap creation, VFIO is initialized and has at least one device
available. If no devices are available at the time of heap creation (or
if devices were available, but were since hot-unplugged, thus dropping
all VFIO container mappings), then VFIO mapping code would have skipped
over externally allocated heaps.
The fix is two-fold. First, we allow externally allocated memory
segments to be marked as "heap" segments. This allows us to distinguish
between external memory segments that were created via heap API, from
those that were created via rte_extmem_register() API.
Then, we fix the VFIO code to only skip non-heap external segments.
Also, since external heaps are not guaranteed to have valid IOVA
addresses, we will skip those which have invalid IOVA addresses as well.
Fixes: 0f526d674f8e ("malloc: separate creating memseg list and malloc heap")
Cc: stable@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Tested-by: Rajesh Ravi <rajesh.ravi@broadcom.com>
Acked-by: David Marchand <david.marchand@redhat.com>
The rte_vfio_dma_map/unmap API's have been marked as deprecated in
release 19.05. Remove them.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: David Marchand <david.marchand@redhat.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
When requesting DMA mapping to default container, we are meant to
supply the RTE_VFIO_DEFAULT_CONTAINER_FD value, however this is
not handled correctly by get_vfio_cfg_by_container_fd(), because
it only looks at actual fd values and does not check for this
special case.
Fix it to return default container if the fd requested is the
special RTE_VFIO_DEFAULT_CONTAINER_FD value.
Fixes: 4106d89a18f8 ("vfio: allow DMA map to the default container")
Cc: stable@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
Acked-by: Shahaf Shuler <shahafs@mellanox.com>
Starting with kernel version 4.10, there are new min/max MTU values in
net_device structure, which are set to ETH_MIN_MTU and ETH_DATA_LEN by
default. We should be able to change these values to allow MTU more than
1500 to be set on KNI.
Signed-off-by: Igor Ryzhov <iryzhov@nfware.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
This code belongs to the lcore API, move the prototype to the right
header, then factorize the code into the common code.
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
The internal structure of lcore_config does not need to be part of
visible API/ABI. Make it private to EAL.
Rearrange the structure so it takes less memory (and cache footprint).
Since we change the ABI, bump the library version.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Currently, mem config will be mapped without using the virtual
area reservation infrastructure, which means it will be mapped
at an arbitrary location. This may cause failures to map the
shared config in secondary process due to things like PCI
whitelist arguments allocating memory in a space where the
primary has allocated the shared mem config.
Fix this by using virtual area reservation to reserve space for
the mem config, thereby avoiding the problem and reserving the
shared config (hopefully) far away from any normal memory
allocations.
Cc: stable@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Not all OS's follow Linux's memory layout, which may lead to
problems following the suggested common address hint absent
of a base-virtaddr flag. Make this address hint OS-specific.
Cc: stable@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Moving RTE_CPU* definitions from the common code to the Linux and
FreeBSD rte_os.h file to avoid #ifdef clutter.
Signed-off-by: Pallavi Kadam <pallavi.kadam@intel.com>
Signed-off-by: Antara Ganesh Kolar <antara.ganesh.kolar@intel.com>
Reviewed-by: Ranjit Menon <ranjit.menon@intel.com>
Reviewed-by: Jerin Jacob <jerinj@marvell.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>
We are using '--base-virtaddr' in a few places. We have a define for that,
so use it instead.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
According to our docs, only Linuxapp supports base-virtaddr option.
That is, strictly speaking, not true because most of the things
that are attempting to respect base-virtaddr are in common files,
so FreeBSD already *mostly* supports this option in practice.
This commit fixes the remaining bits to explicitly support
base-virtaddr option, and moves the arg parsing from EAL to common
options parsing code. Documentation is also updated to reflect
that all platforms now support base-virtaddr.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
An ifdef present in eal_memory.c references "RTE_ARCH_PPC64" when
it should actually use "RTE_ARCH_PPC_64". Simple testing revealed
that both the PPC_64 and non-PPC_64 versions of the code involved
work, but the PPC_64 version of the code is retained to be
consistent with other instances in the same file where mmapped
memory is accessed in reverse order on Power platforms.
Fixes: 66cc45e293ed ("mem: replace memseg with memseg lists")
Cc: stable@dpdk.org
Signed-off-by: David Christensen <drc@linux.vnet.ibm.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
This code was added 7+ years ago in
commit fb022b85bae4 ("timer: check TSC reliability")
presumably when variant TSCs were still somewhat common.
But this code doesn't do anything except print a warning,
and the warning doesn't give any kind of advice to the user,
so let's just remove it.
While the warning has no functional meaning, the /proc/cpuinfo
parsing consumes a non-trivial amount of time which is especially
noticeable in secondary processes.
On my test system, it consumes 21ms out of the 66ms total execution
time for rte_eal_init() in a secondary process.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
This patch adds support to allow users enable/disable allmulticast mode for
kni interface.
This requirement comes from bugzilla 312, more details can refer to:
https://bugs.dpdk.org/show_bug.cgi?id=312
Bugzilla ID: 312
Signed-off-by: Xiaolong Ye <xiaolong.ye@intel.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
Have rte_eal_config_reattach clean up the mapped address which is a valid
address but not the one intended.
Coverity issue: 343439
Fixes: 4e8854ae89fa ("eal: do not panic on shared memory init")
Fixes: b149a7064261 ("eal/freebsd: add config reattach in secondary process")
Cc: stable@dpdk.org
Signed-off-by: Arnon Warshavsky <arnon@qwilt.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
The code checks both rte_mp_request_sync() return code and that the number
of messages in the reply equals 1. If rte_mp_request_sync() succeeds but
there was more than one message, those messages would get leaked.
Found via code review by Anatoly Burakov of patches that used the vhost
code as a template for using rte_mp_request_sync().
Fixes: 83a73c5fef66 ("vfio: use generic multi-process channel")
Cc: stable@dpdk.org
Reported-by: Anatoly Burakov <anatoly.burakov@intel.com>
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Restrict this header inclusion to its real users.
Fixes: 028669bc9f0d ("eal: hide shared memory config")
Cc: stable@dpdk.org
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
When IOMMU is not available, /sys/kernel/iommu_groups will not be
populated. This is happening since at least 3.6 when VFIO support
was added. If the directory is empty, EAL should not pick IOVA as
VA as the default IOVA mode.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Tested-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Tested-by: Jerin Jacob <jerinj@marvell.com>
Reviewed-by: Jerin Jacob <jerinj@marvell.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
When using IOVA as VA mode, there is no need to map segments
page by page. This normally isn't a problem, but it becomes one
when attempting to use DPDK in no-huge mode, where VFIO subsystem
simply runs out of space to store mappings.
Fix this for x86 by triggering different callbacks based on whether
IOVA as VA mode is enabled.
Fixes: 73a639085938 ("vfio: allow to map other memory regions")
Cc: stable@dpdk.org
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Tested-by: Andrius Sirvys <andrius.sirvys@intel.com>
Add new ack interrupt API to avoid using
VFIO_IRQ_SET_ACTION_TRIGGER(rte_intr_enable()) for
acking interrupt purpose for VFIO based interrupt handlers.
This implementation is specific to Linux.
Using rte_intr_enable() for acking interrupt has below issues
* Time consuming to do for every interrupt received as it will
free_irq() followed by request_irq() and all other initializations
* A race condition because of a window between free_irq() and
request_irq() with packet reception still on and device still
enabled and would throw warning messages like below.
[158764.159833] do_IRQ: 9.34 No irq handler for vector
In this patch, rte_intr_ack() is a no-op for VFIO_MSIX/VFIO_MSI interrupts
as they are edge triggered and kernel would not mask the interrupt before
delivering the event to userspace and we don't need to ack.
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Tested-by: Shahed Shaikh <shshaikh@marvell.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>
This reverts commit 89aac60e0be9ed95a87b16e3595f102f9faaffb4.
"vfio: fix interrupts race condition"
The above mentioned commit moves the interrupt's eventfd setup
to probe time but only enables one interrupt for all types of
interrupt handles i.e VFIO_MSI, VFIO_LEGACY, VFIO_MSIX, UIO.
It works fine with default case but breaks below cases specifically
for MSIX based interrupt handles.
* Applications like l3fwd-power that request rxq interrupts
while ethdev setup.
* Drivers that need > 1 MSIx interrupts to be configured for
functionality to work.
VFIO PCI for MSIx expects all the possible vectors to be setup up
when using VFIO_IRQ_SET_ACTION_TRIGGER so that they can be
allocated from kernel pci subsystem. Only way to increase the number
of vectors later is first free all by using VFIO_IRQ_SET_DATA_NONE
with action trigger and then enable new vector count.
Above commit changes the behavior of rte_intr_[enable|disable] to
only mask and unmask unlike earlier behavior and thereby
breaking above two scenarios.
Fixes: 89aac60e0be9 ("vfio: fix interrupts race condition")
Cc: stable@dpdk.org
Signed-off-by: Nithin Dabilpuram <ndabilpuram@marvell.com>
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Tested-by: Stephen Hemminger <stephen@networkplumber.org>
Tested-by: Shahed Shaikh <shshaikh@marvell.com>
Tested-by: Lei Yao <lei.a.yao@intel.com>
Acked-by: David Marchand <david.marchand@redhat.com>
When bus layer reports the preferred mode as RTE_IOVA_DC then
select the RTE_IOVA_VA mode:
- All drivers work in RTE_IOVA_VA mode, irrespective of physical
address availability.
- By default, a mempool asks for IOVA-contiguous memory using
RTE_MEMZONE_IOVA_CONTIG. This is slow in RTE_IOVA_PA mode and it
may affect the application boot time.
Signed-off-by: Jerin Jacob <jerinj@marvell.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>
In ppc64le, expanding DMA areas always fail because we cannot remove
a DMA window. As a result, we cannot allocate more than one memseg in
ppc64le. This is because vfio_spapr_dma_mem_map() doesn't unmap all
the mapped DMA before removing the window. This patch fixes this
incorrect behavior.
I also fixed the order of ioctl for unregister and unmap. The ioctl
for unregister sometimes report device busy errors due to the
existence of mapped area.
Signed-off-by: Takeshi Yoshimura <tyos@jp.ibm.com>
Acked-by: David Christensen <drc@linux.vnet.ibm.com>
va2pa depends on the physical address and virtual address offset of
current mbuf. It may get the wrong physical address of next mbuf which
allocated in another hugepage segment.
In rte_mempool_populate_default(), trying to allocate whole block of
contiguous memory could be failed. Then, it would reserve memory in
several memzones that have different physical address and virtual address
offsets. The rte_mempool_populate_default() is used by
rte_pktmbuf_pool_create().
Fixes: 8451269e6d7b ("kni: remove continuous memory restriction")
Cc: stable@dpdk.org
Signed-off-by: Yangchao Zhou <zhouyates@gmail.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
The commit db90b4969e2e ("vfio: retry creating sPAPR DMA window")
introduced a build breakage on old Linux. Linux <4.2 does not define ddw in
struct vfio_iommu_spapr_tce_info. Without ddw, we cannot change window size
and so should give up the creation. I just exculuded the retrying code if
ddw is not supported.
Fixes: db90b4969e2e ("vfio: retry creating sPAPR DMA window")
Signed-off-by: Takeshi Yoshimura <tyos@jp.ibm.com>
Tested-by: Anatoly Burakov <anatoly.burakov@intel.com>
Populating the eventfd in rte_intr_enable in each request to vfio
triggers a reconfiguration of the interrupt handler on the kernel side.
The problem is that rte_intr_enable is often used to re-enable masked
interrupts from drivers interrupt handlers.
This reconfiguration leaves a window during which a device could send
an interrupt and then the kernel logs this (unsolicited from the kernel
point of view) interrupt:
[158764.159833] do_IRQ: 9.34 No irq handler for vector
VFIO api makes it possible to set the fd at setup time.
Make use of this and then we only need to ask for masking/unmasking
legacy interrupts and we have nothing to do for MSI/MSIX.
"rxtx" interrupts are left untouched but are most likely subject to the
same issue.
Reported-at: https://bugzilla.redhat.com/show_bug.cgi?id=1654824
Fixes: 5c782b3928b8 ("vfio: interrupts")
Cc: stable@dpdk.org
Signed-off-by: David Marchand <david.marchand@redhat.com>
Tested-by: Shahed Shaikh <shshaikh@marvell.com>
sPAPR allows only page_shift from VFIO_IOMMU_SPAPR_TCE_GET_INFO ioctl.
However, Linux 4.17 or before returns incorrect page_shift for Power9.
I added the code for retrying creation of sPAPR DMA window.
Signed-off-by: Takeshi Yoshimura <tyos@jp.ibm.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Currently, nothing stops DPDK to attempt to run primary and
secondary processes while having different versions. This
can lead to all sorts of weird behavior and makes it harder
to maintain compatibility without breaking ABI every once
in a while.
Fix it by explicitly disallowing running different DPDK
versions as primary and secondary processes.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: David Marchand <david.marchand@redhat.com>
Currently, each EAL will update internal/shared config in their
own way at init, resulting in needless duplication of code and
OS-dependent behavior. Move the functions to a common file and
add missing FreeBSD steps.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: David Marchand <david.marchand@redhat.com>
Currently, mcfg completion function exists in two independent
implementations doing the same thing, which is bug prone.
Unify the two functions and move them into one place.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: David Marchand <david.marchand@redhat.com>
Currently, the function to wait until config completion is
static inline for no reason. Move its implementation to
an EAL common file.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: David Marchand <david.marchand@redhat.com>
Now that everything that has ever accessed the shared memory
config is doing so through the public API's, we can make it
internal. Since we're removing quite a few headers from
rte_eal_memconfig.h, we need to add them back in places
where this header is used.
This bumps the ABI, so also change all build files and make
update documentation.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: David Marchand <david.marchand@redhat.com>
Currently, the memory hotplug is locked automatically by all
memory-related _walk() functions, but sometimes locking the
memory subsystem outside of them is needed. There is no
public API to do that, so it creates a dependency on shared
memory config to be public. Fix this by introducing a new
API to lock/unlock the memory hotplug subsystem.
Create a new common file for all things mem config, and a
new API namespace rte_mcfg_*, and search-and-replace all
usages of the locks with the new API.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: David Marchand <david.marchand@redhat.com>
Currently, if the bus selects IOVA as PA, the memory init can fail when
lacking access to physical addresses.
This can be quite hard for normal users to understand what is wrong
since this is the default behavior.
Catch this situation earlier in eal init by validating physical addresses
availability, or select IOVA when no clear preferrence had been expressed.
The bus code is changed so that it reports when it does not care about
the IOVA mode and let the eal init decide.
In Linux implementation, rework rte_eal_using_phys_addrs() so that it can
be called earlier but still avoid a circular dependency with
rte_mem_virt2phys().
In FreeBSD implementation, rte_eal_using_phys_addrs() always returns
false, so the detection part is left as is.
If librte_kni is compiled in and the KNI kmod is loaded,
- if the buses requested VA, force to PA if physical addresses are
available as it was done before,
- else, keep iova as VA, KNI init will fail later.
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
We had some inconsistencies between functions prototypes and actual
definitions.
Let's avoid this by only adding the experimental tag to the prototypes.
Tests with gcc and clang show it is enough.
git grep -l __rte_experimental |grep \.c$ |while read file; do
sed -i -e '/^__rte_experimental$/d' $file;
sed -i -e 's/ *__rte_experimental//' $file;
sed -i -e 's/__rte_experimental *//' $file;
done
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
