Change the doorbell setting so that the maximum value between the last and
current value is set. This is to avoid doorbells being lost.
Fixes: a7efd7773e31 ("qedr: Add support for PD,PKEY and CQ verbs") Link: https://lore.kernel.org/r/20200902165741.8355-3-michal.kalderon@marvell.com Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
rdma_for_each_block() makes assumptions about how the SGL is constructed
that don't work if the block size is below the page size used to to build
the SGL.
The rules for umem SGL construction require that the SG's all be PAGE_SIZE
aligned and we don't encode the actual byte offset of the VA range inside
the SGL using offset and length. So rdma_for_each_block() has no idea
where the actual starting/ending point is to compute the first/last block
boundary if the starting address should be within a SGL.
Fixing the SGL construction turns out to be really hard, and will be the
subject of other patches. For now block smaller pages.
Fixes: 4a35339958f1 ("RDMA/umem: Add API to find best driver supported page size in an MR") Link: https://lore.kernel.org/r/2-v2-270386b7e60b+28f4-umem_1_jgg@nvidia.com Reviewed-by: Leon Romanovsky <leonro@nvidia.com> Reviewed-by: Shiraz Saleem <shiraz.saleem@intel.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
It is possible for a single SGL to span an aligned boundary, eg if the SGL
is
61440 -> 90112
Then the length is 28672, which currently limits the block size to
32k. With a 32k page size the two covering blocks will be:
32768->65536 and 65536->98304
However, the correct answer is a 128K block size which will span the whole
28672 bytes in a single block.
Instead of limiting based on length figure out which high IOVA bits don't
change between the start and end addresses. That is the highest useful
page size.
Fixes: 4a35339958f1 ("RDMA/umem: Add API to find best driver supported page size in an MR") Link: https://lore.kernel.org/r/1-v2-270386b7e60b+28f4-umem_1_jgg@nvidia.com Reviewed-by: Leon Romanovsky <leonro@nvidia.com> Reviewed-by: Shiraz Saleem <shiraz.saleem@intel.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
Update XRCD destroy flow to allow command failure.
Fixes: 28ad5f65c314 ("RDMA: Move XRCD to be under ib_core responsibility") Link: https://lore.kernel.org/r/20200907120921.476363-8-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
Like any other verbs objects, CQ shouldn't fail during destroy, but
mlx5_ib didn't follow this contract with mixed IB verbs objects with
DEVX. Such mix causes to the situation where FW and kernel are fully
interdependent on the reference counting of each side.
Kernel verbs and drivers that don't have DEVX flows shouldn't fail.
Fixes: e39afe3d6dbd ("RDMA: Convert CQ allocations to be under core responsibility") Link: https://lore.kernel.org/r/20200907120921.476363-7-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
The ib_alloc_cq*() and ib_free_cq*() are solely kernel verbs to manage CQs
and doesn't need extra indirection just to call same functions with
constant parameter NULL as udata.
The rnbd_server module's communication manager (cm) initialization depends
on the registration of the "network namespace subsystem" of the RDMA CM
agent module. As such, when the kernel is configured to load the
rnbd_server and the RDMA cma module during initialization; and if the
rnbd_server module is initialized before RDMA cma module, a null ptr
dereference occurs during the RDMA bind operation.
All this happens cause the cm init is in the call chain of the module
init, which is not a preferred practice.
So remove the call to rdma_create_id() from the module init call chain.
Instead register rtrs-srv as an ib client, which makes sure that the
rdma_create_id() is called only when an ib device is added.
Fixes: 9cb837480424 ("RDMA/rtrs: server: main functionality") Link: https://lore.kernel.org/r/20200907103106.104530-1-haris.iqbal@cloud.ionos.com Reported-by: kernel test robot <rong.a.chen@intel.com> Signed-off-by: Md Haris Iqbal <haris.iqbal@cloud.ionos.com> Reviewed-by: Jack Wang <jinpu.wang@cloud.ionos.com> Reviewed-by: Leon Romanovsky <leonro@nvidia.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
Fix some off-by-one errors in xfs_rtalloc_query_range. The highest key
in the realtime bitmap is always one less than the number of rt extents,
which means that the key clamp at the start of the function is wrong.
The 4th argument to xfs_rtfind_forw is the highest rt extent that we
want to probe, which means that passing 1 less than the high key is
wrong. Finally, drop the rem variable that controls the loop because we
can compare the iteration point (rtstart) against the high key directly.
The sordid history of this function is that the original commit (fb3c3)
incorrectly passed (high_rec->ar_startblock - 1) as the 'limit' parameter
to xfs_rtfind_forw. This was wrong because the "high key" is supposed
to be the largest key for which the caller wants result rows, not the
key for the first row that could possibly be outside the range that the
caller wants to see.
A subsequent attempt (8ad56) to strengthen the parameter checking added
incorrect clamping of the parameters to the number of rt blocks in the
system (despite the bitmap functions all taking units of rt extents) to
avoid querying ranges past the end of rt bitmap file but failed to fix
the incorrect _rtfind_forw parameter. The original _rtfind_forw
parameter error then survived the conversion of the startblock and
blockcount fields to rt extents (a0e5c), and the most recent off-by-one
fix (a3a37) thought it was patching a problem when the end of the rt
volume is not in use, but none of these fixes actually solved the
original problem that the author was confused about the "limit" argument
to xfs_rtfind_forw.
Sadly, all four of these patches were written by this author and even
his own usage of this function and rt testing were inadequate to get
this fixed quickly.
Original-problem: fb3c3de2f65c ("xfs: add a couple of queries to iterate free extents in the rtbitmap") Not-fixed-by: 8ad560d2565e ("xfs: strengthen rtalloc query range checks") Not-fixed-by: a0e5c435babd ("xfs: fix xfs_rtalloc_rec units") Fixes: a3a374bf1889 ("xfs: fix off-by-one error in xfs_rtalloc_query_range") Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Chandan Babu R <chandanrlinux@gmail.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
"mount -o local_lock=posix..." was broken by the mount API conversion
due to the missing constant.
Fixes: e38bb238ed8c ("NFS: Convert mount option parsing to use functionality from fs_parser.h") Signed-off-by: Scott Mayhew <smayhew@redhat.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
Refactor xfs_getfsmap to improve its performance: instead of indirectly
calling a function that copies one record to userspace at a time, create
a shadow buffer in the kernel and copy the whole array once at the end.
On the author's computer, this reduces the runtime on his /home by ~20%.
This also eliminates a deadlock when running GETFSMAP against the
realtime device. The current code locks the rtbitmap to create
fsmappings and copies them into userspace, having not released the
rtbitmap lock. If the userspace buffer is an mmap of a sparse file that
itself resides on the realtime device, the write page fault will recurse
into the fs for allocation, which will deadlock on the rtbitmap lock.
Fixes: 4c934c7dd60c ("xfs: report realtime space information via the rtbitmap") Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Chandan Babu R <chandanrlinux@gmail.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
If userspace asked fsmap to count the number of entries, we cannot
return more than UINT_MAX entries because fmh_entries is u32.
Therefore, stop counting if we hit this limit or else we will waste time
to return truncated results.
Fixes: e89c041338ed ("xfs: implement the GETFSMAP ioctl") Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Reviewed-by: Chandan Babu R <chandanrlinux@gmail.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
If a bitmap needs to be allocated, and then by the time the thread
is scheduled to be run again all the indices which would satisfy the
allocation have been allocated then we would leak the allocation. Almost
impossible to hit in practice, but a trivial fix. Found by Coverity.
When ARC_SOC_HSDK is enabled and RESET_CONTROLLER is disabled, it results
in the following Kbuild warning:
WARNING: unmet direct dependencies detected for RESET_HSDK
Depends on [n]: RESET_CONTROLLER [=n] && HAS_IOMEM [=y] && (ARC_SOC_HSDK [=y] || COMPILE_TEST [=n])
Selected by [y]:
- ARC_SOC_HSDK [=y] && ISA_ARCV2 [=y]
The reason is that ARC_SOC_HSDK selects RESET_HSDK without depending on or
selecting RESET_CONTROLLER while RESET_HSDK is subordinate to
RESET_CONTROLLER.
Honor the kconfig menu hierarchy to remove kconfig dependency warnings.
The mere fact that the kernel has the MMC subsystem enabled (CONFIG_MMC
enabled) does not mean that the underlying hardware platform has the
SDHC hardware present. Within the ColdFire hardware defines that is
signified by MCFSDHC_BASE being defined with an address.
The platform data for the ColdFire parts is including the SDHC hardware
if CONFIG_MMC is enabled, instead of MCFSDHC_BASE. This means that if
you are compiling for a ColdFire target that does not support SDHC but
enable CONFIG_MMC you will fail to compile with errors like this:
arch/m68k/coldfire/device.c:565:12: error: ‘MCFSDHC_BASE’ undeclared here (not in a function)
.start = MCFSDHC_BASE,
^
arch/m68k/coldfire/device.c:566:25: error: ‘MCFSDHC_SIZE’ undeclared here (not in a function)
.end = MCFSDHC_BASE + MCFSDHC_SIZE - 1,
^
arch/m68k/coldfire/device.c:569:12: error: ‘MCF_IRQ_SDHC’ undeclared here (not in a function)
.start = MCF_IRQ_SDHC,
^
Make the SDHC platform support depend on MCFSDHC_BASE, that is only
include it if the specific ColdFire SoC has that hardware module.
Nathan popped up on #xfs and pointed out that we fail to handle
finobt btree blocks in xlog_recover_get_buf_lsn(). This means they
always fall through the entire magic number matching code to "recover
immediately". Whilst most of the time this is the correct behaviour,
occasionally it will be incorrect and could potentially overwrite
more recent metadata because we don't check the LSN in the on disk
metadata at all.
This bug has been present since the finobt was first introduced, and
is a potential cause of the occasional xfs_iget_check_free_state()
failures we see that indicate that the inode btree state does not
match the on disk inode state.
Fixes: aafc3c246529 ("xfs: support the XFS_BTNUM_FINOBT free inode btree type") Reported-by: Nathan Scott <nathans@redhat.com> Signed-off-by: Dave Chinner <dchinner@redhat.com> Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com> Reviewed-by: Brian Foster <bfoster@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
The L310_PREFETCH_CTRL register bits 28 and 29 to enable data and
instruction prefetch respectively can also be accessed via the
L2X0_AUX_CTRL register. They appear to be actually wired together in
hardware between the registers. Changing them in the prefetch
register only will get undone when restoring the aux control register
later on. For this reason, set these bits in both registers during
initialisation according to the devicetree property values.
We were failing that due to GTK2+ and then for the ZSTD test, which made
test-all.c, the fast path feature detection file to fail and thus
trigger building all of the feature tests, slowing down the test.
Eventually the ZSTD test would be built and would succeed, since it had
the needed -lzstd, avoiding:
$ cat /tmp/build/perf/feature/test-all.make.output
/usr/bin/ld: /tmp/ccRRJQ4u.o: in function `main_test_libzstd':
/home/acme/git/perf/tools/build/feature/test-libzstd.c:8: undefined reference to `ZSTD_createCStream'
/usr/bin/ld: /home/acme/git/perf/tools/build/feature/test-libzstd.c:9: undefined reference to `ZSTD_freeCStream'
collect2: error: ld returned 1 exit status
$
Fix it by adding -lzstd to the test-all target.
Now I need an entry to 'perf test' to make sure that
/tmp/build/perf/feature/test-all.make.output is empty...
Fixes: 3b1c5d9659718263 ("tools build: Implement libzstd feature check, LIBZSTD_DIR and NO_LIBZSTD defines") Reviewed-by: Alexei Budankov <alexey.budankov@linux.intel.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@kernel.org> Link: http://lore.kernel.org/lkml/20200904202611.GJ3753976@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
This is bitrotting, nobody is stepping up to work on it, and since we
treat warnings as errors, feature detection is failing in its main,
faster test (tools/build/feature/test-all.c) because of the GTK+2
infobar check.
So make this opt-in, at some point ditch this if nobody volunteers to
take care of this.
Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Ian Rogers <irogers@google.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
The signal handler in the alignment handler self test has the ability
to jump over the instruction that triggered the signal. It does this
by incrementing the PT_NIP in the user context by 4. If it were a
prefixed instruction this will mean that the suffix is then executed
which is incorrect. Instead check if the major opcode indicates a
prefixed instruction (e.g. it is 1) and if so increment PT_NIP by 8.
If ISA v3.1 is not available treat it as a word instruction even if
the major opcode is 1.
Fixes: 620a6473df36 ("selftests/powerpc: Add prefixed loads/stores to alignment_handler test") Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
[mpe: Fix 32-bit build, rename haveprefixes to prefixes_enabled] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200824131231.14008-1-jniethe5@gmail.com Signed-off-by: Sasha Levin <sashal@kernel.org>
At memory hot-remove time we can retrieve an LMB's nid from its
corresponding memory_block. There is no need to store the nid
in multiple locations.
Note that lmb_to_memblock() uses find_memory_block() to get the
corresponding memory_block. As find_memory_block() runs in sub-linear
time this approach is negligibly slower than what we do at present.
In exchange for this lookup at hot-remove time we no longer need to
call memory_add_physaddr_to_nid() during drmem_init() for each LMB.
On powerpc, memory_add_physaddr_to_nid() is a linear search, so this
spares us an O(n^2) initialization during boot.
On systems with many LMBs that initialization overhead is palpable and
disruptive. For example, on a box with 249854 LMBs we're seeing
drmem_init() take upwards of 30 seconds to complete:
With a patched kernel on the same machine we're no longer seeing the
soft lockup. drmem_init() now completes in negligible time, even when
the LMB count is large.
Fixes: b2d3b5ee66f2 ("powerpc/pseries: Track LMB nid instead of using device tree") Signed-off-by: Scott Cheloha <cheloha@linux.ibm.com> Reviewed-by: Nathan Lynch <nathanl@linux.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200811015115.63677-1-cheloha@linux.ibm.com Signed-off-by: Sasha Levin <sashal@kernel.org>
The drmem lmb list can have hundreds of thousands of entries, and
unfortunately lookups take the form of linear searches. As long as
this is the case, traversals have the potential to monopolize the CPU
and provoke lockup reports, workqueue stalls, and the like unless
they explicitly yield.
Rather than placing cond_resched() calls within various
for_each_drmem_lmb() loop blocks in the code, put it in the iteration
expression of the loop macro itself so users can't omit it.
Introduce a drmem_lmb_next() iteration helper function which calls
cond_resched() at a regular interval during array traversal. Each
iteration of the loop in DLPAR code paths can involve around ten RTAS
calls which can each take up to 250us, so this ensures the check is
performed at worst every few milliseconds.
Fixes: 6c6ea53725b3 ("powerpc/mm: Separate ibm, dynamic-memory data from DT format") Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com> Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20200813151131.2070161-1-nathanl@linux.ibm.com Signed-off-by: Sasha Levin <sashal@kernel.org>
The original function returns unsigned long and 0 on failure.
Fixes: 4a35339958f1 ("RDMA/umem: Add API to find best driver supported page size in an MR") Link: https://lore.kernel.org/r/0-v1-982a13cc5c6d+501ae-fix_best_pgsz_stub_jgg@nvidia.com Reviewed-by: Gal Pressman <galpress@amazon.com> Acked-by: Shiraz Saleem <shiraz.saleem@intel.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
It should be considered an illegal operation if the ULP attempts to modify
a QP from another state to the current hardware state. Otherwise, the ULP
can modify some fields of QPC at any time. For example, for a QP in state
of RTS, modify it from RTR to RTS can change the PSN, which is always not
as expected.
Fixes: 9a4435375cd1 ("IB/hns: Add driver files for hns RoCE driver") Link: https://lore.kernel.org/r/1598353674-24270-1-git-send-email-liweihang@huawei.com Signed-off-by: Lang Cheng <chenglang@huawei.com> Signed-off-by: Weihang Li <liweihang@huawei.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
Building lpddr2_nvm with clang can result in a giant stack usage
in one function:
drivers/mtd/lpddr/lpddr2_nvm.c:399:12: error: stack frame size of 1144 bytes in function 'lpddr2_nvm_probe' [-Werror,-Wframe-larger-than=]
The problem is that clang decides to build a copy of the mtd_info
structure on the stack and then do a memcpy() into the actual version. It
shouldn't really do it that way, but it's not strictly a bug either.
As a workaround, use a static const version of the structure to assign
most of the members upfront and then only set the few members that
require runtime knowledge at probe time.
All entry points to the rdma_cm from a ULP must be single threaded,
even this error unwinds. Add the missing locking.
Fixes: 7c11910783a1 ("RDMA/ucma: Put a lock around every call to the rdma_cm layer") Link: https://lore.kernel.org/r/20200818120526.702120-11-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
This value is locked under the file->mut, ensure it is held whenever
touching it.
The case in ucma_migrate_id() is a race, while in ucma_free_uctx() it is
already not possible for the write side to run, the movement is just for
clarity.
Fixes: 88314e4dda1e ("RDMA/cma: add support for rdma_migrate_id()") Link: https://lore.kernel.org/r/20200818120526.702120-10-leon@kernel.org Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@nvidia.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
Currently in the unlikely event that buf fails to be allocated it
is dereferenced a few times. Use the errexit flag to determine if
buf should be written to to avoid the null pointer dereferences.
Addresses-Coverity: ("Dereference after null check") Fixes: f518f154ecef ("refperf: Dynamically allocate experiment-summary output buffer") Signed-off-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
The conversion of rcu_fwds to dynamic allocation failed to actually
allocate the required structure. This commit therefore allocates it,
frees it, and updates rcu_fwds accordingly. While in the area, it
abstracts the cleanup actions into rcu_torture_fwd_prog_cleanup().
Fixes: 5155be9994e5 ("rcutorture: Dynamically allocate rcu_fwds structure") Reported-by: kernel test robot <rong.a.chen@intel.com> Signed-off-by: Paul E. McKenney <paulmck@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
On callback overload, it is necessary to quickly detect idle CPUs,
and rcu_gp_fqs_check_wake() checks for this condition. Unfortunately,
the code following the call to this function does not repeat this check,
which means that in reality no actual quiescent-state forcing, instead
only a couple of quick and pointless wakeups at the beginning of the
grace period.
This commit therefore adds a check for the RCU_GP_FLAG_OVLD flag in
the post-wakeup "if" statement in rcu_gp_fqs_loop().
Fixes: 1fca4d12f4637 ("rcu: Expedite first two FQS scans under callback-overload conditions") Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org> Signed-off-by: Neeraj Upadhyay <neeraju@codeaurora.org> Signed-off-by: Paul E. McKenney <paulmck@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
Both of_find_compatible_node() and of_find_node_by_type() will return
a refcounted node on success - thus for the success path the node must
be explicitly released with a of_node_put().
The call to of_find_compatible_node() returns a node pointer with
refcount incremented thus it must be explicitly decremented here
before returning.
Fixes: a489043f4626 ("powerpc/pseries: Implement arch_get_random_long() based on H_RANDOM") Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/1530522496-14816-1-git-send-email-hofrat@osadl.org Signed-off-by: Sasha Levin <sashal@kernel.org>
The mlx4 driver will proxy MAD packets through the PF driver. A VM or an
instantiated VF will send its MAD packets to the PF driver using
loop-back. The PF driver will be informed by an interrupt, but defer the
handling and polling of CQEs to a worker thread running on an ordered
work-queue.
Consider the following scenario: the VMs will in short proximity in time,
for example due to a network event, send many MAD packets to the PF
driver. Lets say there are K VMs, each sending N packets.
The interrupt from the first VM will start the worker thread, which will
poll N CQEs. A common case here is where the PF driver will multiplex the
packets received from the VMs out on the wire QP.
But before the wire QP has returned a send CQE and associated interrupt,
the other K - 1 VMs have sent their N packets as well.
The PF driver has to multiplex K * N packets out on the wire QP. But the
send-queue on the wire QP has a finite capacity.
So, in this scenario, if K * N is larger than the send-queue capacity of
the wire QP, we will get MAD packets dropped on the floor with this
dynamic debug message:
mlx4_ib_multiplex_mad: failed sending GSI to wire on behalf of slave 2 (-11)
and this despite the fact that the wire send-queue could have capacity,
but the PF driver isn't aware, because the wire send CQEs have not yet
been polled.
We can also have a similar scenario inbound, with a wire recv-queue larger
than the tunnel QP's send-queue. If many remote peers send MAD packets to
the very same VM, the tunnel send-queue destined to the VM could allegedly
be construed to be full by the PF driver.
This starvation is fixed by introducing separate work queues for the wire
QPs vs. the tunnel QPs.
With this fix, using a dual ported HCA, 8 VFs instantiated, we could run
cmtime on each of the 18 interfaces towards a similar configured peer,
each cmtime instance with 800 QPs (all in all 14400 QPs) without a single
CM packet getting lost.
Boardinfo was lost if I3C object for devices with boardinfo
available are not created or not added to the I3C device list
because of some failure e.g. SETDASA failed, retrieve info failed etc
This patch adds i3c_master_attach_boardinfo which scan boardinfo list
in the master object and 'attach' it to the I3C device object.
This test uses waking+wakeup_latency as an event name, which doesn't
make sense since it includes an operator. Illegal names are now
detected by the synthetic event command parsing, which causes this
test to fail. Change the name to 'waking_plus_wakeup_latency' to
prevent this.
Fix data race in prepend_path() with re-reading mnt->mnt_ns twice
without holding the lock.
is_mounted() does check for NULL, but is_anon_ns(mnt->mnt_ns) might
re-read the pointer again which could be NULL already, if in between
reads one of kern_unmount()/kern_unmount_array()/umount_tree() sets
mnt->mnt_ns to NULL.
This is seen in production with the following stack trace:
Currently __set_oom_adj loops through all processes in the system to keep
oom_score_adj and oom_score_adj_min in sync between processes sharing
their mm. This is done for any task with more that one mm_users, which
includes processes with multiple threads (sharing mm and signals).
However for such processes the loop is unnecessary because their signal
structure is shared as well.
Android updates oom_score_adj whenever a tasks changes its role
(background/foreground/...) or binds to/unbinds from a service, making it
more/less important. Such operation can happen frequently. We noticed
that updates to oom_score_adj became more expensive and after further
investigation found out that the patch mentioned in "Fixes" introduced a
regression. Using Pixel 4 with a typical Android workload, write time to
oom_score_adj increased from ~3.57us to ~362us. Moreover this regression
linearly depends on the number of multi-threaded processes running on the
system.
Mark the mm with a new MMF_MULTIPROCESS flag bit when task is created with
(CLONE_VM && !CLONE_THREAD && !CLONE_VFORK). Change __set_oom_adj to use
MMF_MULTIPROCESS instead of mm_users to decide whether oom_score_adj
update should be synchronized between multiple processes. To prevent
races between clone() and __set_oom_adj(), when oom_score_adj of the
process being cloned might be modified from userspace, we use
oom_adj_mutex. Its scope is changed to global.
The combination of (CLONE_VM && !CLONE_THREAD) is rarely used except for
the case of vfork(). To prevent performance regressions of vfork(), we
skip taking oom_adj_mutex and setting MMF_MULTIPROCESS when CLONE_VFORK is
specified. Clearing the MMF_MULTIPROCESS flag (when the last process
sharing the mm exits) is left out of this patch to keep it simple and
because it is believed that this threading model is rare. Should there
ever be a need for optimizing that case as well, it can be done by hooking
into the exit path, likely following the mm_update_next_owner pattern.
With the combination of (CLONE_VM && !CLONE_THREAD && !CLONE_VFORK) being
quite rare, the regression is gone after the change is applied.
[surenb@google.com: v3] Link: https://lkml.kernel.org/r/20200902012558.2335613-1-surenb@google.com Fixes: 44a70adec910 ("mm, oom_adj: make sure processes sharing mm have same view of oom_score_adj") Reported-by: Tim Murray <timmurray@google.com> Suggested-by: Michal Hocko <mhocko@kernel.org> Signed-off-by: Suren Baghdasaryan <surenb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Christian Brauner <christian.brauner@ubuntu.com> Acked-by: Michal Hocko <mhocko@suse.com> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Eugene Syromiatnikov <esyr@redhat.com> Cc: Christian Kellner <christian@kellner.me> Cc: Adrian Reber <areber@redhat.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: Aleksa Sarai <cyphar@cyphar.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Alexey Gladkov <gladkov.alexey@gmail.com> Cc: Michel Lespinasse <walken@google.com> Cc: Daniel Jordan <daniel.m.jordan@oracle.com> Cc: Andrei Vagin <avagin@gmail.com> Cc: Bernd Edlinger <bernd.edlinger@hotmail.de> Cc: John Johansen <john.johansen@canonical.com> Cc: Yafang Shao <laoar.shao@gmail.com> Link: https://lkml.kernel.org/r/20200824153036.3201505-1-surenb@google.com Debugged-by: Minchan Kim <minchan@kernel.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
Page P0 is allocated to the page cache. Page P1 is free.
Thread A Thread B Thread C
find_get_entry():
xas_load() returns P0
Removes P0 from page cache
P0 finds its buddy P1
alloc_pages(GFP_KERNEL, 1) returns P0
P0 has refcount 1
page_cache_get_speculative(P0)
P0 has refcount 2
__free_pages(P0)
P0 has refcount 1
put_page(P0)
P1 is not freed
Fix this by freeing all the pages in __free_pages() that won't be freed
by the call to put_page(). It's usually not a good idea to split a page,
but this is a very unlikely scenario.
Fixes: e286781d5f2e ("mm: speculative page references") Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Mike Rapoport <rppt@linux.ibm.com> Cc: Nick Piggin <npiggin@gmail.com> Cc: Hugh Dickins <hughd@google.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: https://lkml.kernel.org/r/20200926213919.26642-1-willy@infradead.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
Replace do_brk with do_brk_flags in comment of insert_vm_struct(), since
do_brk was removed in following commit.
Fixes: bb177a732c4369 ("mm: do not bug_on on incorrect length in __mm_populate()") Signed-off-by: Liao Pingfang <liao.pingfang@zte.com.cn> Signed-off-by: Yi Wang <wang.yi59@zte.com.cn> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Link: https://lkml.kernel.org/r/1600650778-43230-1-git-send-email-wang.yi59@zte.com.cn Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
The code in mc_handle_swap_pte() checks for non_swap_entry() and returns
NULL before checking is_device_private_entry() so device private pages are
never handled. Fix this by checking for non_swap_entry() after handling
device private swap PTEs.
I assume the memory cgroup accounting would be off somehow when moving
a process to another memory cgroup. Currently, the device private page
is charged like a normal anonymous page when allocated and is uncharged
when the page is freed so I think that path is OK.
Signed-off-by: Ralph Campbell <rcampbell@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Jerome Glisse <jglisse@redhat.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Ira Weiny <ira.weiny@intel.com> Link: https://lkml.kernel.org/r/20201009215952.2726-1-rcampbell@nvidia.com
xFixes: c733a82874a7 ("mm/memcontrol: support MEMORY_DEVICE_PRIVATE") Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
mem_cgroup_from_obj() checks the lowest bit of the page->mem_cgroup
pointer to determine if the page has an attached obj_cgroup vector instead
of a regular memcg pointer. If it's not set, it simple returns the
page->mem_cgroup value as a struct mem_cgroup pointer.
The commit 10befea91b61 ("mm: memcg/slab: use a single set of kmem_caches
for all allocations") changed the moment when this bit is set: if
previously it was set on the allocation of the slab page, now it can be
set well after, when the first accounted object is allocated on this page.
It opened a race: if page->mem_cgroup is set concurrently after the first
page_has_obj_cgroups(page) check, a pointer to the obj_cgroups array can
be returned as a memory cgroup pointer.
A simple check for page->mem_cgroup pointer for NULL before the
page_has_obj_cgroups() check fixes the race. Indeed, if the pointer is
not NULL, it's either a simple mem_cgroup pointer or a pointer to
obj_cgroup vector. The pointer can be asynchronously changed from NULL to
(obj_cgroup_vec | 0x1UL), but can't be changed from a valid memcg pointer
to objcg vector or back.
If the object passed to mem_cgroup_from_obj() is a slab object and
page->mem_cgroup is NULL, it means that the object is not accounted, so
the function must return NULL.
I've discovered the race looking at the code, so far I haven't seen it in
the wild.
Fixes: 10befea91b61 ("mm: memcg/slab: use a single set of kmem_caches for all allocations") Signed-off-by: Roman Gushchin <guro@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Shakeel Butt <shakeelb@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Vlastimil Babka <vbabka@suse.cz> Link: https://lkml.kernel.org/r/20200910022435.2773735-1-guro@fb.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
Dump vlan tag and proto for the usual vlan offload case if the
NF_LOG_MACDECODE flag is set on. Without this information the logging is
misleading as there is no reference to the VLAN header.
Fixes: 83e96d443b37 ("netfilter: log: split family specific code to nf_log_{ip,ip6,common}.c files") Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
Calling skb_orphan() is unnecessary in the strp rcv handler because the skb
is from a skb_clone() in __strp_recv. So it never has a destructor or a
sk assigned. Plus its confusing to read because it might hint to the reader
that the skb could have an sk assigned which is not true. Even if we did
have an sk assigned it would be cleaner to simply wait for the upcoming
kfree_skb().
Additionally, move the comment about strparser clone up so its closer to
the logic it is describing and add to it so that it is more complete.
fq qdisc requires tstamp to be cleared in forwarding path
Reported-by: Evgeny B <abt-admin@mail.ru> Link: https://bugzilla.kernel.org/show_bug.cgi?id=209427 Suggested-by: Eric Dumazet <eric.dumazet@gmail.com> Fixes: 8203e2d844d3 ("net: clear skb->tstamp in forwarding paths") Fixes: fb420d5d91c1 ("tcp/fq: move back to CLOCK_MONOTONIC") Fixes: 80b14dee2bea ("net: Add a new socket option for a future transmit time.") Signed-off-by: Julian Anastasov <ja@ssi.bg> Reviewed-by: Simon Horman <horms@verge.net.au> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
Fix follow warning:
Checking drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c...
[drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c:770]: (error) Invalid number
of character '{' when these macros are defined: ''.
Checking drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c: CONFIG_ACPI...
[drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c:770]: (error) Invalid number
of character '{' when these macros are defined: 'CONFIG_ACPI'.
......
Checking drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c: CONFIG_X86...
[drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c:770]: (error) Invalid number
of character '{' when these macros are defined: 'CONFIG_X86'.
Checking drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c: _X86_...
[drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c:770]: (error) Invalid number
of character '{' when these macros are defined: '_X86_'.
Checking drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c: __linux__...
[drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c:770]: (error) Invalid number
of character '{' when these macros are defined: '__linux__'.
Fixes: 97d798b276e9 ("drm/amdgpu: simplify ATIF backlight handling") Reported-by: Hulk Robot <hulkci@huawei.com> Signed-off-by: Ye Bin <yebin10@huawei.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
Amlogic SoC devices report the following errors frequently causing excessive
dmesg log spam and early log rotataion, although the errors appear to be
harmless as everything works fine:
[ 7.202702] panfrost ffe40000.gpu: error powering up gpu L2
[ 7.203760] panfrost ffe40000.gpu: error powering up gpu shader
ARM staff have advised increasing the timeout values to eliminate the errors
in most normal scenarios, and testing with several different G31/G52 devices
shows 20000 to be a reliable value.
Fixes: f3ba91228e8e ("drm/panfrost: Add initial panfrost driver") Suggested-by: Steven Price <steven.price@arm.com> Signed-off-by: Christian Hewitt <christianshewitt@gmail.com> Reviewed-by: Steven Price <steven.price@arm.com> Signed-off-by: Steven Price <steven.price@arm.com> Link: https://patchwork.freedesktop.org/patch/msgid/20201008141738.13560-1-christianshewitt@gmail.com Signed-off-by: Sasha Levin <sashal@kernel.org>
sdio.c:2403:3: warning: Attempt to free released memory
kfree(card->mpa_rx.buf);
^~~~~~~~~~~~~~~~~~~~~~~
When mwifiex_init_sdio() fails in its first call to
mwifiex_alloc_sdio_mpa_buffer, it falls back to calling it
again. If the second alloc of mpa_tx.buf fails, the error
handler will try to free the old, previously freed mpa_rx.buf.
Reviewing the code, it looks like a second double free would
happen with mwifiex_cleanup_sdio().
So set both pointers to NULL when they are freed.
Fixes: 5e6e3a92b9a4 ("wireless: mwifiex: initial commit for Marvell mwifiex driver") Signed-off-by: Tom Rix <trix@redhat.com> Reviewed-by: Brian Norris <briannorris@chromium.org> Signed-off-by: Kalle Valo <kvalo@codeaurora.org> Link: https://lore.kernel.org/r/20201004131931.29782-1-trix@redhat.com Signed-off-by: Sasha Levin <sashal@kernel.org>
It is unnecessary to force request-based DM to call into bio-based
dm_submit_bio (via indirect disk->fops->submit_bio) only to have it then
call blk_mq_submit_bio().
Fix this by establishing a request-based DM block_device_operations
(dm_rq_blk_dops, which doesn't have .submit_bio) and update
dm_setup_md_queue() to set md->disk->fops to it for
DM_TYPE_REQUEST_BASED.
Remove DM_TYPE_REQUEST_BASED conditional in dm_submit_bio and unexport
blk_mq_submit_bio.
Fixes: c62b37d96b6eb ("block: move ->make_request_fn to struct block_device_operations") Signed-off-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
Remove PSU EEPROM configuration for systems class equipped with
Mellanox chip Spectrume-2. Till now all the systems from this class
used few types of power units, all equipped with EEPROM device with
address space two bytes. Thus, all these devices have been handled by
EEPROM driver "24c32".
There is a new requirement is to support power unit replacement by "off
the shelf" device, matching electrical required parameters. Such device
could be equipped with different EEPROM type, which could be one byte
address space addressing or even could be not equipped with EEPROM.
In such case "24c32" will not work.
Fixes: 1bd42d94ccab ("platform/x86: mlx-platform: Add support for new 200G IB and Ethernet systems") Signed-off-by: Vadim Pasternak <vadimp@nvidia.com> Reviewed-by: Hans de Goede <hdegoede@redhat.com> Link: https://lore.kernel.org/r/20200923172053.26296-2-vadimp@nvidia.com Signed-off-by: Hans de Goede <hdegoede@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
Firmwares with API < 3.6 do not forward DELBA requests. Thus, when a
Block Ack session is restarted, the reordering buffer is not flushed and
the received sequence number is not contiguous. Therefore, mac80211
starts to wait some missing frames that it will never receive.
This patch disables the reordering buffer for old firmware. It is
harmless when the network is unencrypted. When the network is encrypted,
the non-contiguous frames will be thrown away by the TKIP/CCMP replay
protection. So, the user will observe some packet loss with UDP and
performance drop with TCP.
DA7219 uses I2S2 and I2S3 for input and output respectively. Commit 9e30251fb22e ("ASoC: mediatek: mt8183-da7219: support machine driver
with rt1015") introduces a bug that:
- If using I2S2 solely, MCLK to DA7219 is 256FS.
- If using I2S3 solely, MCLK to DA7219 is 128FS.
- If using I2S3 first and then I2S2, the MCLK changes from 128FS to
256FS. As a result, no sound output to the headset. Also no sound
input from the headset microphone.
Both I2S2 and I2S3 should set MCLK to 256FS. Fixes the wrong ops for
I2S3.
Fixes: 9e30251fb22e ("ASoC: mediatek: mt8183-da7219: support machine driver with rt1015") Signed-off-by: Tzung-Bi Shih <tzungbi@google.com> Link: https://lore.kernel.org/r/20201006101252.1890385-1-tzungbi@google.com Signed-off-by: Mark Brown <broonie@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
synth_field_size() returns either a positive size or an error (zero or
a negative value). However, the existing code assumes the only error
value is 0. It doesn't handle negative error codes, as it assigns
directly to field->size (a size_t; unsigned), thereby interpreting the
error code as a valid size instead.
Do the test before assignment to field->size.
[ axelrasmussen@google.com: changelog addition, first paragraph above ]
Link: https://lkml.kernel.org/r/9b6946d9776b2eeb43227678158196de1c3c6e1d.1601848695.git.zanussi@kernel.org Fixes: 4b147936fa50 (tracing: Add support for 'synthetic' events) Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org> Tested-by: Axel Rasmussen <axelrasmussen@google.com> Signed-off-by: Tom Zanussi <zanussi@kernel.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
This fixes commit 0107635e15ac
("staging: qlge: replace pr_err with netdev_err") which introduced an
build breakage of missing `struct ql_adapter *qdev` for some functions
and a warning of type mismatch with dumping enabled, i.e.,
$ make CFLAGS_MODULE="-DQL_ALL_DUMP -DQL_OB_DUMP -DQL_CB_DUMP \
-DQL_IB_DUMP -DQL_REG_DUMP -DQL_DEV_DUMP" M=drivers/staging/qlge
qlge_dbg.c: In function ‘ql_dump_ob_mac_rsp’:
qlge_dbg.c:2051:13: error: ‘qdev’ undeclared (first use in this function); did you mean ‘cdev’?
2051 | netdev_err(qdev->ndev, "%s\n", __func__);
| ^~~~
qlge_dbg.c: In function ‘ql_dump_routing_entries’:
qlge_dbg.c:1435:10: warning: format ‘%s’ expects argument of type ‘char *’, but argument 3 has type ‘int’ [-Wformat=]
1435 | "%s: Routing Mask %d = 0x%.08x\n",
| ~^
| |
| char *
| %d
1436 | i, value);
| ~
| |
| int
qlge_dbg.c:1435:37: warning: format ‘%x’ expects a matching ‘unsigned int’ argument [-Wformat=]
1435 | "%s: Routing Mask %d = 0x%.08x\n",
| ~~~~^
| |
| unsigned int
Note that now ql_dump_rx_ring/ql_dump_tx_ring won't check if the passed
parameter is a null pointer.
Fixes: 0107635e15ac ("staging: qlge: replace pr_err with netdev_err") Reported-by: Benjamin Poirier <benjamin.poirier@gmail.com> Suggested-by: Benjamin Poirier <benjamin.poirier@gmail.com> Reviewed-by: Benjamin Poirier <benjamin.poirier@gmail.com> Signed-off-by: Coiby Xu <coiby.xu@gmail.com> Link: https://lore.kernel.org/r/20201002235941.77062-1-coiby.xu@gmail.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
dma_alloc_coherent() is called with a fixed SZ_2M size, but frees happen
with IOAT_CHUNK_SIZE. Recently, IOAT_CHUNK_SIZE was reduced to 512M but
the allocation did not change. To fix, change to using the
IOAT_CHUNK_SIZE define.
This was caught with the upcoming patchset for converting Intel platforms to the
dma-iommu implementation. It has a warning when the unmapped size differs from
the mapped size.
The be_fill_queue() function can only fail when "eq_vaddress" is NULL and
since it's non-NULL here that means the function call can't fail. But
imagine if it could, then in that situation we would want to store the
"paddr" so that dma memory can be released.
Link: https://lore.kernel.org/r/20200928091300.GD377727@mwanda Fixes: bfead3b2cb46 ("[SCSI] be2iscsi: Adding msix and mcc_rings V3") Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
Corrects drivers/target/target_core_user.c:688:6: warning: 'page' may be
used uninitialized.
Link: https://lore.kernel.org/r/20200924001920.43594-1-john.p.donnelly@oracle.com Fixes: 3c58f737231e ("scsi: target: tcmu: Optimize use of flush_dcache_page") Cc: Mike Christie <michael.christie@oracle.com> Acked-by: Mike Christie <michael.christie@oracle.com> Signed-off-by: John Donnelly <john.p.donnelly@oracle.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by: Sasha Levin <sashal@kernel.org>
In DDMA mode if INTR OUT transfers mps not multiple of 4 then single packet
corresponds to single descriptor.
Descriptor limit set to mps and desc chain limit set to mps *
MAX_DMA_DESC_NUM_GENERIC. On that descriptors complete, to calculate
transfer size should be considered correction value for each descriptor.
In start request function, if "continue" is true then dma buffer address
should be incremmented by offset for all type of transfers, not only for
Control DATA_OUT transfers.
Fixes: cf77b5fb9b394 ("usb: dwc2: gadget: Transfer length limit checking for DDMA") Fixes: e02f9aa6119e0 ("usb: dwc2: gadget: EP 0 specific DDMA programming") Fixes: aa3e8bc81311e ("usb: dwc2: gadget: DDMA transfer start and complete") Signed-off-by: Minas Harutyunyan <hminas@synopsys.com> Signed-off-by: Felipe Balbi <balbi@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
When dumping wiphy information, we try to split the data into
many submessages, but for old userspace we still support the
old mode where this doesn't happen.
However, in this case we were not resetting our state correctly
and dumping multiple messages for each wiphy, which would have
broken such older userspace.
This was broken pretty much immediately afterwards because it
only worked in the original commit where non-split dumps didn't
have any more data than split dumps...
When OCXL is enabled and HOTPLUG_PCI is disabled, it results in the
following Kbuild warning:
WARNING: unmet direct dependencies detected for HOTPLUG_PCI_POWERNV
Depends on [n]: PCI [=y] && HOTPLUG_PCI [=n] && PPC_POWERNV [=y] && EEH [=y]
Selected by [y]:
- OCXL [=y] && PPC_POWERNV [=y] && PCI [=y] && EEH [=y]
The reason is that OCXL selects HOTPLUG_PCI_POWERNV without depending on
or selecting HOTPLUG_PCI while HOTPLUG_PCI_POWERNV is subordinate to
HOTPLUG_PCI.
HOTPLUG_PCI_POWERNV is a visible symbol with a set of dependencies.
Selecting it will lead to overlooking its other dependencies as well.
Let OCXL depend on HOTPLUG_PCI_POWERNV instead to avoid Kbuild issues.
The u_ether driver has a qmult setting that multiplies the
transmit queue length (which by default is 2).
The intent is that it should be enabled at high/super speed, but
because the code does not explicitly check for USB_SUPER_PLUS,
it is disabled at that speed.
Fix this by ensuring that the queue multiplier is enabled for any
wired link at high speed or above. Using >= for USB_SPEED_*
constants seems correct because it is what the gadget_is_xxxspeed
functions do.
The queue multiplier substantially helps performance at higher
speeds. On a direct SuperSpeed Plus link to a Linux laptop,
iperf3 single TCP stream:
Before (qmult=1): 1.3 Gbps
After (qmult=5): 3.2 Gbps
Fixes: 04617db7aa68 ("usb: gadget: add SS descriptors to Ethernet gadget") Reviewed-by: Maciej Żenczykowski <maze@google.com> Signed-off-by: Lorenzo Colitti <lorenzo@google.com> Signed-off-by: Felipe Balbi <balbi@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
The commit aba3a8d01d62 ("usb: gadget: u_serial: add suspend resume
callbacks") set/cleared the suspended flag in USB bus suspend/resume
only. But, when a USB cable is disconnected in the suspend, since some
controllers will not detect USB bus resume, the suspended flag is not
cleared. After that, user cannot send any data. To fix the issue,
clears the suspended flag in the gserial_disconnect().
Currently, SuperSpeed NCM gadgets report a speed of 851 Mbps
in USB_CDC_NOTIFY_SPEED_CHANGE. But the calculation appears to
assume 16 packets per microframe, and USB 3 and above no longer
use microframes.
Maximum speed is actually much higher. On a direct connection,
theoretical throughput is at most 3.86 Gbps for gen1x1 and
9.36 Gbps for gen2x1, and I have seen gadget->host iperf
throughput of >2 Gbps for gen1x1 and >4 Gbps for gen2x1.
Unfortunately the ConnectionSpeedChange defined in the CDC spec
only uses 32-bit values, so we can't report accurate numbers for
10Gbps and above. So, report 3.75Gbps for SuperSpeed (which is
roughly maximum theoretical performance) and 4.25Gbps for
SuperSpeed Plus (which is close to the maximum that we can report
in a 32-bit unsigned integer).
Currently if group-id and command-id values are zero we
trigger and collect every RX frame,
this is not the right behavior and zero value
should be handled like any other filter.
A call to wm_adsp_write_ctl() could cause a kernel crash if it
does not retrieve a valid kcontrol from snd_soc_card_get_kcontrol().
This can happen due to a missing control name prefix. Then,
snd_ctl_notify() crashes when it tries to use the id field.
Modified wm_adsp_write_ctl() to incorporate the name_prefix (if applicable)
such that it is able to retrieve a valid id field from the kcontrol
once the platform has booted.
Fixes: eb65ccdb0836 ("ASoC: wm_adsp: Expose mixer control API") Signed-off-by: Adam Brickman <Adam.Brickman@cirrus.com> Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com> Link: https://lore.kernel.org/r/20201001152425.8590-1-ckeepax@opensource.cirrus.com Signed-off-by: Mark Brown <broonie@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
The logic of this function was accidentally broken by a checkpatch
inspired cleanup. I've modified the code to restore the original
behavior and also make checkpatch happy.
If a DM device was suspended when bios were issued to it, those bios
would be deferred using queue_io(). Once the DM device was resumed
dm_process_bio() could be called by dm_wq_work() for original bio that
still needs splitting. dm_process_bio()'s check for current->bio_list
(meaning call chain is within ->submit_bio) as a prerequisite for
calling blk_queue_split() for "abnormal IO" would result in
dm_process_bio() never imposing corresponding queue_limits
(e.g. discard_granularity, discard_max_bytes, etc).
Fix this by always having dm_wq_work() resubmit deferred bios using
submit_bio_noacct().
Side-effect is blk_queue_split() is always called for "abnormal IO" from
->submit_bio, be it from application thread or dm_wq_work() workqueue,
so proper bio splitting and depth-first bio submission is performed.
For sake of clarity, remove current->bio_list check before call to
blk_queue_split().
Also, remove dm_wq_work()'s use of dm_{get,put}_live_table() -- no
longer needed since IO will be reissued in terms of ->submit_bio.
And rename bio variable from 'c' to 'bio'.
The name allocated for the regmap_config structure is freed
pretty early, right after the registration of the MMIO region.
Unfortunately, that doesn't follow the life cycle that debugfs
expects, as it can access the name field long after the free
has occurred.
Move the free on the error path, and keep it forever otherwise.
Fixes: e15d7f2b81d2 ("mfd: syscon: Use a unique name with regmap_config") Signed-off-by: Marc Zyngier <maz@kernel.org> Signed-off-by: Lee Jones <lee.jones@linaro.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
The best way to fix this is to eliminate the CPU0
port->mutex/work-completion scenario. So we suggest to register and
unregister the clock-notifier during the DW APB UART port probe/remove
procedures, instead of doing that at the points of the port
startup/shutdown.
It is erroneous to update the TTY port baud rate if it hasn't been
initialized yet, because in that case the TTY struct isn't set. So there
is no termios structure to get and re-calculate the baud if the current
baud can't be reached. Let's skip the baud rate update then until the port
is fully initialized.
Note the update UART clock method still sets the uartclk member with a new
ref clock value even if the port is turned off. The new UART ref clock
rate will be used later on the port starting up procedure.
Fixes: 868f3ee6e452 ("serial: 8250: Add 8250 port clock update method") Tested-by: Hans de Goede <hdegoede@redhat.com> Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru> Link: https://lore.kernel.org/r/20200923161950.6237-3-Sergey.Semin@baikalelectronics.ru Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
It has been a mistake to add the MCR register RTS/DTS fields setting in
the generic method of the UART reference clock update. There is no point
in asserting these lines at that procedure. Just discard the
serial8250_out_MCR() mathod invocation from there then.
Fixes: 868f3ee6e452 ("serial: 8250: Add 8250 port clock update method") Tested-by: Hans de Goede <hdegoede@redhat.com> Signed-off-by: Serge Semin <Sergey.Semin@baikalelectronics.ru> Link: https://lore.kernel.org/r/20200923161950.6237-2-Sergey.Semin@baikalelectronics.ru Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
It appears that almost traditionally the H variants have some deviations
in the register offsets in comparison to LP ones. This is the case for
Intel Tiger Lake as well. Fix register offsets for TGL-H variant.
Fixes: 653d96455e1e ("pinctrl: tigerlake: Add support for Tiger Lake-H") Reported-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com> Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com> Link: https://lore.kernel.org/r/20200929110306.40852-1-andriy.shevchenko@linux.intel.com Signed-off-by: Linus Walleij <linus.walleij@linaro.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
Chasing the callers of enic_dev_wait() revealed the gems of enic_reset()
and enic_tx_hang_reset() which are both invoked through work queues in
order to be able to call rtnl_lock(). So far so good.
After locking rtnl both functions acquire enic::enic_api_lock which
serializes against the (ab)use from infiniband. This is where the
trainwreck starts.
enic::enic_api_lock is a spin_lock() which implicitly disables preemption,
but both functions invoke a ton of functions under that lock which can
sleep. The BUG_ON(in_interrupt()) does not trigger in that case because it
can't detect the preempt disabled condition.
This clearly has never been tested with any of the mandatory debug options
for 7+ years, which would have caught that for sure.
Cure it by adding a enic_api_busy member to struct enic, which is modified
and evaluated with enic::enic_api_lock held.
If enic_api_devcmd_proxy_by_index() observes enic::enic_api_busy as true,
it drops enic::enic_api_lock and busy waits for enic::enic_api_busy to
become false.
It would be smarter to wait for a completion of that busy period, but
enic_api_devcmd_proxy_by_index() is called with other spin locks held which
obviously can't sleep.
Remove the BUG_ON(in_interrupt()) check as well because it's incomplete and
with proper debugging enabled the problem would have been caught from the
debug checks in schedule_timeout().
Fixes: 0b038566c0ea ("drivers/net: enic: Add an interface for USNIC to interact with firmware") Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Sasha Levin <sashal@kernel.org>
When the ADC is runtime suspended and starting a conversion, the stm32-adc
driver calls pm_runtime_get_sync() that gets cascaded to the parent
(e.g. runtime resume of stm32-adc-core driver). This also kicks the
autosuspend delay (e.g. 2s) of the parent.
Once the ADC is active, calling pm_runtime_get_sync() again (upon a new
capture) won't kick the autosuspend delay for the parent (stm32-adc-core
driver) as already active.
Currently, this makes the stm32-adc-core driver go in suspend state
every 2s when doing slow polling. As an example, doing a capture, e.g.
cat in_voltageY_raw at a 0.2s rate, the auto suspend delay for the parent
isn't refreshed. Once it expires, the parent immediately falls into
runtime suspended state, in between two captures, as soon as the child
driver falls into runtime suspend state:
- e.g. after 2s, + child calls pm_runtime_put_autosuspend() + 100ms
autosuspend delay of the child.
- stm32-adc-core switches off regulators, clocks and so on.
- They get switched on back again 100ms later in this example (at 2.2s).
So, use runtime_idle() callback in stm32-adc-core driver to call
pm_runtime_mark_last_busy() for the parent driver (stm32-adc-core),
to avoid this.
if of_find_device_by_node() succeed, qcom_iommu_of_xlate() doesn't have
a corresponding put_device(). Thus add put_device() to fix the exception
handling for this function implementation.
Fixes: 0ae349a0f33f ("iommu/qcom: Add qcom_iommu") Acked-by: Rob Clark <robdclark@gmail.com> Signed-off-by: Yu Kuai <yukuai3@huawei.com> Link: https://lore.kernel.org/r/20200929014037.2436663-1-yukuai3@huawei.com Signed-off-by: Will Deacon <will@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
The Aspeed pinconf data structures are split into 'conf' and 'map'
types, where the 'conf' struct defines which register and bitfield to
manipulate, while the 'map' struct defines what value to write to
the register and bitfield.
Both structs have a mask member, and the wrong mask was being used to
tell the regmap which bits to update.
A todo is to look at whether we can remove the mask from the 'map'
struct.
Fixes: 5f52c853847f ("pinctrl: aspeed: Use masks to describe pinconf bitfields") Signed-off-by: Andrew Jeffery <andrew@aj.id.au> Reviewed-by: Joel Stanley <joel@jms.id.au> Cc: Johnny Huang <johnny_huang@aspeedtech.com> Link: https://lore.kernel.org/r/20200910025631.2996342-3-andrew@aj.id.au Signed-off-by: Linus Walleij <linus.walleij@linaro.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
Currently if an unsupported iftype is detected the error return path
does not free the cmd_skb leading to a resource leak. Fix this by
free'ing cmd_skb.
Addresses-Coverity: ("Resource leak") Fixes: 805b28c05c8e ("qtnfmac: prepare for AP_VLAN interface type support") Signed-off-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: Kalle Valo <kvalo@codeaurora.org> Link: https://lore.kernel.org/r/20200925132224.21638-1-colin.king@canonical.com Signed-off-by: Sasha Levin <sashal@kernel.org>
The test_overhead prog_test included an fmod_ret program that attached to
__set_task_comm() in the kernel. However, this function was never listed as
allowed for return modification, so this only worked because of the
verifier skipping tests when a trampoline already existed for the attach
point. Now that the verifier checks have been fixed, remove fmod_ret from
the test so it works again.
Fixes: 4eaf0b5c5e04 ("selftest/bpf: Fmod_ret prog and implement test_overhead as part of bench") Acked-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
From the checks and commit messages for modify_return, it seems it was
never the intention that it should be possible to attach a tracing program
with expected_attach_type == BPF_MODIFY_RETURN to another BPF program.
However, check_attach_modify_return() will only look at the function name,
so if the target function starts with "security_", the attach will be
allowed even for bpf2bpf attachment.
Fix this oversight by also blocking the modification if a target program is
supplied.
Set up the speed according to crq->query_phys_parms.rsp.speed.
Fix IBMVNIC_10GBPS typo.
Fixes: f8d6ae0d27ec ("ibmvnic: Report actual backing device speed and duplex values") Signed-off-by: Lijun Pan <ljp@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Sasha Levin <sashal@kernel.org>
In commit f188b5e76aae ("coresight: etm4x: Save/restore state
across CPU low power states"), mistakenly TRCVMIDCCTLR1 register
value was saved in trcvmidcctlr0 state variable which is used to
store TRCVMIDCCTLR0 register value in etm4x_cpu_save() and then
same value is written back to both TRCVMIDCCTLR0 and TRCVMIDCCTLR1
in etm4x_cpu_restore(). There is already a trcvmidcctlr1 state
variable available for TRCVMIDCCTLR1, so use it.
Fixes: f188b5e76aae ("coresight: etm4x: Save/restore state across CPU low power states") Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com> Signed-off-by: Sai Prakash Ranjan <saiprakash.ranjan@codeaurora.org> Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org> Link: https://lore.kernel.org/r/20200928163513.70169-26-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
During module unload, a coresight driver module will call back into
the CTI driver to remove any links between the two devices.
The current code has 2 issues:-
1) in the CTI driver the matching code is matching to the wrong device
so misses all the links.
2) The callback is called too late in the unload process resulting in a
crash.
CTI code to remove sysfs link to other devices on shutdown, incorrectly
tries to remove a single ended link when these are all double ended. This
implementation leaves elements in the link info structure undefined which
results in a crash in recent tests for driver module unload.
This patch corrects the link removal code.
Fixes: 73274abb6557 ("coresight: cti: Add in sysfs links to other coresight devices") Reported-by: Tingwei Zhang <tingwei@codeaurora.org> Signed-off-by: Mike Leach <mike.leach@linaro.org> Signed-off-by: Mathieu Poirier <mathieu.poirier@linaro.org> Link: https://lore.kernel.org/r/20200928163513.70169-18-mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Sasha Levin <sashal@kernel.org>
When coresight_build_path() fails on all the cpus, etm_setup_aux
calls etm_free_aux() to free allocated event_data.
WARN_ON(cpumask_empty(mask) will be triggered since cpu mask is empty.
Check event_data->snk_config is not NULL first to avoid this
warning.
projects / users / dwmw2 / linux.git / log