Currently, EAL init in secondary processes will attach all fbarrays
in the memconfig to have access to the primary process's page tables.
However, fbarrays corresponding to external memory segments should
not be attached at initialization, because this will happen as part
of `rte_extmem_attach` [1] or `rte_malloc_heap_memory_attach` [2] calls.
1: https://doc.dpdk.org/api/rte__memory_8h.html#a2796da68de6825f8edf53759f8e4d230
2: https://doc.dpdk.org/api/rte__malloc_8h.html#af6360dea35bdf162feeb2b62cf149fd3
Fixes: ff3619d624 ("malloc: allow attaching to external memory chunks")
Cc: stable@dpdk.org
Suggested-by: Anatoly Burakov <anatoly.burakov@intel.com>
Signed-off-by: Deepak Khandelwal <deepak.khandelwal@intel.com>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
All OS implementations provide the same main loop.
Introduce helpers (shared for Linux and FreeBSD) to handle synchronisation
between main and threads and factorize the rest as common code.
Thread id are now logged as string in a common format across OS.
Note:
- this change also fixes Windows EAL: worker threads cpu affinity was
incorrectly reported in log.
- libabigail flags this change as breaking ABI in clang builds:
1 function with some indirect sub-type change:
[C] 'function int rte_eal_remote_launch(int (void*)*, void*, unsigned
int)' at eal_common_launch.c:35:1 has some indirect sub-type
changes:
parameter 1 of type 'int (void*)*' changed:
in pointed to type 'function type int (void*)' at rte_launch.h:31:1:
entity changed from 'function type int (void*)' to 'typedef
lcore_function_t' at rte_launch.h:31:1
type size hasn't changed
This is being investigated on libabigail side.
For now, we don't have much choice but to waive reports on this symbol.
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Morten Brørup <mb@smartsharesystems.com>
Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
So far, a worker thread has been using its thread_id to discover which
lcore has been assigned to it.
On the other hand, as noted by Tyler, the pthread API does not strictly
guarantee that a new thread won't start running eal_thread_loop before
pthread_create writes to &lcore_config[xx].thread_id.
Though all OS implementations supported in DPDK (recently) ensure this
property, it is more robust to have the main thread directly pass
the worker thread lcore.
Signed-off-by: David Marchand <david.marchand@redhat.com>
The ret value in rte_dev_event_monitor_stop stands for whether the
monitor has been successfully closed, and should not bind with
rte_intr_callback_unregister, so once it goes to the right exit point of
rte_dev_event_monitor, the ret value should be set to 0.
Also, the refmonitor count has been carefully evaluated, the value
change from 1 to 0, so there is no potential memory leak failure.
Fixes: 1fef6ced07 ("eal/linux: allow multiple starts of event monitor")
Cc: stable@dpdk.org
Signed-off-by: Wenxuan Wu <wenxuanx.wu@intel.com>
'recv()' fills the 'buf', later 'strlcpy()' used to copy from this buffer.
But as coverity warns 'recv()' doesn't guarantee that 'buf' is
null-terminated, but 'strlcpy()' requires it.
Enlarge 'buf' size to 'EAL_UEV_MSG_LEN + 1' and ensure the last one can
be set to 0 when received buffer size is EAL_UEV_MSG_LEN.
CID 375864: Memory - illegal accesses (STRING_NULL)
Passing unterminated string "buf" to "dev_uev_parse", which expects
a null-terminated string.
Coverity issue: 375864
Fixes: 0d0f478d04 ("eal/linux: add uevent parse and process")
Cc: stable@dpdk.org
Signed-off-by: Steve Yang <stevex.yang@intel.com>
Acked-by: Ferruh Yigit <ferruh.yigit@intel.com>
Some public header files were missing 'extern "C"' C++ guards,
and couldn't be used by C++ applications. Add the missing guards.
Fixes: af75078fec ("first public release")
Fixes: 7f3aa08639 ("eal: introduce bit operations API")
Fixes: 166a743c53 ("compat: add infrastructure to support symbol versioning")
Fixes: 8f40ee0734 ("eal/x86: get hypervisor name")
Fixes: 75583b0d1e ("eal: add keep alive monitoring")
Fixes: 88701645c9 ("eal: move interrupt type out of igb_uio")
Fixes: f04519d809 ("lib: add missing include dependencies")
Fixes: f58880682c ("trace: implement register API")
Fixes: 428eb983f5 ("eal: add OS specific header file")
Cc: stable@dpdk.org
Signed-off-by: Brian Dooley <brian.dooley@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Tyler Retzlaff <roretzla@linux.microsoft.com>
Functions like free, rte_free, and rte_mempool_free
already handle NULL pointer so the checks here are not necessary.
Remove redundant NULL pointer checks before free functions
found by nullfree.cocci
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
The mp action resources in malloc should be cleaned up via
rte_eal_cleanup.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
When rte_eal_cleanup is called, hotplug should unregister the
resources associated with the multi-process server.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
When rte_eal_cleanup is called the rte_mp_action for VFIO
should be freed.
Fixes: edf73dd330 ("ipc: handle unsupported IPC in action register")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
When application calls rte_eal_cleanup on shutdown,
the DPDK log should be closed and cleaned up.
This helps reduce false reports from tools like ASAN
and valgrind that track memory leaks.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Both Linux and FreeBSD have same code for creating runtime
directory and reading sysfs files. Put them in the new lib/eal/unix
subdirectory.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Systemd.exec supports configuring the runtime directory of a service
via RuntimeDirectory=. This creates the directory with the necessary
permissions which actual service may not have if running in container.
The change to DPDK is to look for the environment RUNTIME_DIRECTORY
first and use that in preference to the fallback alternatives.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Morten Brørup <mb@smartsharesystems.com>
The size argument to eal_set_runtime_dir is useless and was
being used incorrectly in strlcpy. It worked only because
all callers passed PATH_MAX which is same as sizeof the destination
runtime_dir.
Note: this is an internal API so no user exposed change.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: Morten Brørup <mb@smartsharesystems.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Linux EAL ensured that mapped hugepages are clean
by always mapping from newly created files:
existing hugepage backing files were always removed.
In this case, the kernel clears the page to prevent data leaks,
because the mapped memory may contain leftover data
from the previous process that was using this memory.
Clearing takes the bulk of the time spent in mmap(2),
increasing EAL initialization time.
Introduce a mode to keep existing files and reuse them
in order to speed up initial memory allocation in EAL.
Hugepages mapped from such files may contain data
left by the previous process that used this memory,
so RTE_MEMSEG_FLAG_DIRTY is set for their segments.
If multiple hugepages are mapped from the same file:
1. When fallocate(2) is used, all memory mapped from this file
is considered dirty, because it is unknown
which parts of the file are holes.
2. When ftruncate(3) is used, memory mapped from this file
is considered dirty unless the file is extended
to create a new mapping, which implies clean memory.
Signed-off-by: Dmitry Kozlyuk <dkozlyuk@nvidia.com>
Reviewed-by: Anatoly Burakov <anatoly.burakov@intel.com>
In preparation to extend --huge-unlink option semantics
refactor how it is stored in the internal configuration.
It makes future changes more isolated.
Signed-off-by: Dmitry Kozlyuk <dkozlyuk@nvidia.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
While debugging running DPDK service in a container, it is
useful to see which file creation failed. Don't hide this
failure with DEBUG.
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
We should call read() on RTE_INTR_HANDLE_VFIO_REQ event
to confirm that event.
Fixes: 0eb8a1c4c7 ("vfio: add request notifier interrupt")
Cc: stable@dpdk.org
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
This patch fixes coverity issue by adding a check for negative event fd
value.
Coverity issue: 373711, 373694
Fixes: c2bd9367e1 ("lib: remove direct access to interrupt handle")
Signed-off-by: Harman Kalra <hkalra@marvell.com>
Acked-by: David Marchand <david.marchand@redhat.com>
Currently, VFIO support for Linux is compiled unconditionally, and
supported kernel versions start with 4.4, so VFIO is assumed to always
be enabled. There is no way of disabling VFIO support at compile time
anyway, so just drop the "VFIO not available" fallback code altogether.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Acked-by: Chenbo Xia <chenbo.xia@intel.com>
Since its introduction in 2018, the SIGBUS handler was never registered,
and all related functions were unused.
A SIGBUS can be received by the application when accessing to hugepages
even if mmap() was successful, This happens especially when running
inside containers when there is not enough hugepages. In this case, we
need to recover. A similar scheme can be found in eal_memory.c.
Fixes: 582bed1e1d ("mem: support mapping hugepages at runtime")
Cc: stable@dpdk.org
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Acked-by: David Marchand <david.marchand@redhat.com>
The device event interrupt handler was always freed.
Bugzilla ID: 845
Fixes: c2bd9367e1 ("lib: remove direct access to interrupt handle")
Signed-off-by: David Marchand <david.marchand@redhat.com>
Tested-by: Yan Xia <yanx.xia@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Caught with ASan:
==9727==ERROR: AddressSanitizer: stack-buffer-overflow on address
0x7f0daa2fc0d0 at pc 0x7f0daeefacb2 bp 0x7f0daa2fadd0 sp 0x7f0daa2fa578
READ of size 1 at 0x7f0daa2fc0d0 thread T1
#0 0x7f0daeefacb1 (/lib64/libasan.so.5+0xbacb1)
#1 0x115eba1 in dev_uev_parse ../lib/eal/linux/eal_dev.c:167
#2 0x115f281 in dev_uev_handler ../lib/eal/linux/eal_dev.c:248
#3 0x1169b91 in eal_intr_process_interrupts
../lib/eal/linux/eal_interrupts.c:1026
#4 0x116a3a2 in eal_intr_handle_interrupts
../lib/eal/linux/eal_interrupts.c:1100
#5 0x116a7f0 in eal_intr_thread_main
../lib/eal/linux/eal_interrupts.c:1172
#6 0x112640a in ctrl_thread_init
../lib/eal/common/eal_common_thread.c:202
#7 0x7f0dade27159 in start_thread (/lib64/libpthread.so.0+0x8159)
#8 0x7f0dadb58f72 in clone (/lib64/libc.so.6+0xfcf72)
Address 0x7f0daa2fc0d0 is located in stack of thread T1 at offset 4192
in frame
#0 0x115f0c9 in dev_uev_handler ../lib/eal/linux/eal_dev.c:226
This frame has 2 object(s):
[32, 48) 'uevent'
[96, 4192) 'buf' <== Memory access at offset 4192 overflows this
variable
HINT: this may be a false positive if your program uses some custom
stack unwind mechanism or swapcontext
(longjmp and C++ exceptions *are* supported)
Thread T1 created by T0 here:
#0 0x7f0daee92ea3 in __interceptor_pthread_create
(/lib64/libasan.so.5+0x52ea3)
#1 0x1126542 in rte_ctrl_thread_create
../lib/eal/common/eal_common_thread.c:228
#2 0x116a8b5 in rte_eal_intr_init
../lib/eal/linux/eal_interrupts.c:1200
#3 0x1159dd1 in rte_eal_init ../lib/eal/linux/eal.c:1044
#4 0x7a22f8 in main ../app/test-pmd/testpmd.c:4105
#5 0x7f0dada7f802 in __libc_start_main (/lib64/libc.so.6+0x23802)
Bugzilla ID: 792
Fixes: 0d0f478d04 ("eal/linux: add uevent parse and process")
Cc: stable@dpdk.org
Signed-off-by: David Marchand <david.marchand@redhat.com>
Tested-by: Yan Xia <yanx.xia@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
clang-13 rightfully complains that the total_mem variable in
eal_parse_socket_arg is set but not used, since the final
accumulated total_mem result isn't used anywhere.
So just remove the total_mem variable.
Fixes: 0a703f0f36 ("eal/linux: fix parsing zero socket memory and limits")
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
Partial unmap support was introduced in commit c13ca4e81c
("vfio: fix DMA mapping granularity for IOVA as VA"), and with it
was added a check that dereferenced the IOMMU type to determine whether
partial ummapping is supported for currently configured IOMMU type. In
certain circumstances (such as when VFIO is supported, but no devices
were bound to the VFIO driver), the IOMMU type pointer can be NULL.
However, dereferencing of IOMMU type was guarded by access to the user
maps list - that is, we were always checking the user map list first,
and then, if we found a memory region that encloses the one we're trying
to unmap, we would have performed the IOMMU type check.
This ensured that the IOMMU type check will not cause any NULL pointer
dereferences, because in order for an IOMMU type check to have been
performed, there necessarily must have been at least one memory region
that was previously mapped successfully, and that implies having a
defined IOMMU type.
When commit 56259f7fc0 ("vfio: allow partially unmapping adjacent
memory") was introduced, the IOMMU type check was moved to
before we were traversing the user mem maps list, thereby introducing a
potential NULL dereference, because the IOMMU type access was no longer
guarded by the user mem maps list traversal.
Fix the issue by moving the IOMMU type check to after the user mem maps
traversal, thereby ensuring that by the time the check happens, the
IOMMU type is always valid.
Fixes: 56259f7fc0 ("vfio: allow partially unmapping adjacent memory")
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
Tested-by: Xuan Ding <xuan.ding@intel.com>
Removing direct access to interrupt handle structure fields,
rather use respective get set APIs for the same.
Making changes to all the libraries access the interrupt handle fields.
Signed-off-by: Harman Kalra <hkalra@marvell.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>
Tested-by: Raslan Darawsheh <rasland@nvidia.com>
Removing direct access to interrupt handle structure fields,
rather use respective get set APIs for the same.
Making changes to all the libraries access the interrupt handle fields.
Implementing alarm cleanup routine, where the memory allocated
for interrupt instance can be freed.
Signed-off-by: Harman Kalra <hkalra@marvell.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>
Tested-by: Raslan Darawsheh <rasland@nvidia.com>
Making changes to the interrupt framework to use interrupt handle
APIs to get/set any field.
Signed-off-by: Harman Kalra <hkalra@marvell.com>
Signed-off-by: David Marchand <david.marchand@redhat.com>
Tested-by: Raslan Darawsheh <rasland@nvidia.com>
Ensure that the memory operations before the call to
rte_eal_remote_launch are visible to the worker thread.
Use the function pointer to execute in worker thread
as the guard variable.
Ensure that the memory operations in worker thread, that happen
before it returns the status of the assigned function, are
visible to the main thread. Use the variable containing the
lcore's state as the guard variable.
Signed-off-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Reviewed-by: Ola Liljedahl <ola.liljedahl@arm.com>
Reviewed-by: Feifei Wang <feifei.wang2@arm.com>
FINISHED state seems to be used to indicate that the worker's update
of the 'state' is not visible to other threads. There seems to be no
requirement to have such a state.
Since the FINISHED state is removed, the API rte_eal_wait_lcore
is updated to always return the status of the last function that
ran in the worker core.
Signed-off-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Reviewed-by: Ola Liljedahl <ola.liljedahl@arm.com>
Reviewed-by: Feifei Wang <feifei.wang2@arm.com>
In the rte_eal_remote_launch function, the lcore function
pointer is checked for NULL. However, the pointer is never
reset to NULL. Reset the lcore function pointer and argument
after the worker has completed executing the lcore function.
Fixes: af75078fec ("first public release")
Cc: stable@dpdk.org
Signed-off-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Feifei Wang <feifei.wang2@arm.com>
Currently, if we map a memory area A, then map a separate memory area B
that by coincidence happens to be adjacent to A, current implementation
will merge these two segments into one, and if partial unmapping is not
supported, these segments will then be only allowed to be unmapped in
one go. In other words, given segments A and B that are adjacent, it
is currently not possible to map A, then map B, then unmap A.
Fix this by adding a notion of "chunk size", which will allow
subdividing segments into equally sized segments whenever we are dealing
with an IOMMU that does not support partial unmapping. With this change,
we will still be able to merge adjacent segments, but only if they are
of the same size. If we keep with our above example, adjacent segments A
and B will be stored as separate segments if they are of different
sizes.
Signed-off-by: Anatoly Burakov <anatoly.burakov@intel.com>
Signed-off-by: Xuan Ding <xuan.ding@intel.com>
Tested-by: Yvonne Yang <yvonnex.yang@intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Telemetry interface should be exposed for primary processes only, since
secondary processes will conflict on socket creation, and since all
data in secondary process is generally available to primary. For
example, all device stats for ethdevs, cryptodevs, etc. will all be
common across processes.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Ciara Power <ciara.power@intel.com>
Tested-by: Conor Walsh <conor.walsh@intel.com>
get_hugepage_dir() was implemented in such a way that a --huge-dir
option had to exactly match the mountpoint, but there's no reason for
this restriction: DPDK might not be the only user of hugepages, and
shouldn't assume it owns an entire mountpoint. For example, if I have
/dev/hugepages/myapp, and /dev/hugepages/dpdk, I should be able to
specify:
--huge-dir=/dev/hugepages/dpdk/
and have DPDK only use that sub-directory.
Fix the implementation to allow a sub-directory within a suitable
hugetlbfs mountpoint to be specified, preferring the closest match.
Signed-off-by: John Levon <john.levon@nutanix.com>
Acked-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
Currently there are some public headers that include 'sys/queue.h', which
is not POSIX, but usually provided by the Linux/BSD system library.
(Not in POSIX.1, POSIX.1-2001, or POSIX.1-2008. Present on the BSDs.)
The file is missing on Windows. During the Windows build, DPDK uses a
bundled copy, so building a DPDK library works fine. But when OVS or other
applications use DPDK as a library, because some DPDK public headers
include 'sys/queue.h', on Windows, it triggers an error due to no such
file.
One solution is to install the 'lib/eal/windows/include/sys/queue.h' into
Windows environment, such as [1]. However, this means DPDK exports the
functionalities of 'sys/queue.h' into the environment, which might cause
symbols, macros, headers clashing with other applications.
The patch fixes it by removing the "#include <sys/queue.h>" from
DPDK public headers, so programs including DPDK headers don't depend
on the system to provide 'sys/queue.h'. When these public headers use
macros such as TAILQ_xxx, we replace it by the ones with RTE_ prefix.
For Windows, we copy the definitions from <sys/queue.h> to rte_os.h
in Windows EAL. Note that these RTE_ macros are compatible with
<sys/queue.h>, both at the level of API (to use with <sys/queue.h>
macros in C files) and ABI (to avoid breaking it).
Additionally, the TAILQ_FOREACH_SAFE is not part of <sys/queue.h>,
the patch replaces it with RTE_TAILQ_FOREACH_SAFE.
[1] http://mails.dpdk.org/archives/dev/2021-August/216304.html
Suggested-by: Nick Connolly <nick.connolly@mayadata.io>
Suggested-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
Signed-off-by: William Tu <u9012063@gmail.com>
Acked-by: Dmitry Kozlyuk <dmitry.kozliuk@gmail.com>
Acked-by: Narcisa Vasile <navasile@linux.microsoft.com>
When multi-process is not wanted and DPDK is run with the "no-shconf"
flag, the telemetry library still needs a runtime directory to place the
unix socket for telemetry connections. Therefore, rather than not
creating the directory when this flag is set, we can change the code to
attempt the creation anyway, but not error out if it fails. If it
succeeds, then telemetry will be available, but if it fails, the rest of
DPDK will run without telemetry. This ensures that the "in-memory" flag
will allow DPDK to run even if the whole filesystem is read-only, for
example.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Morten Brørup <mb@smartsharesystems.com>
Reviewed-by: David Marchand <david.marchand@redhat.com>
There is no reason for the DPDK libraries to all have 'librte_' prefix on
the directory names. This prefix makes the directory names longer and also
makes it awkward to add features referring to individual libraries in the
build - should the lib names be specified with or without the prefix.
Therefore, we can just remove the library prefix and use the library's
unique name as the directory name, i.e. 'eal' rather than 'librte_eal'
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
