| Age | Commit message (Collapse) | Author |
|---|
|
We've been seeing hard-to-trigger psi crashes when running inside VM
instances:
divide error: 0000 [#1] SMP PTI
Modules linked in: [...]
CPU: 0 PID: 212 Comm: kworker/0:2 Not tainted 4.16.18-119_fbk9_3817_gfe944c98d695 #119
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 0.0.0 02/06/2015
Workqueue: events psi_clock
RIP: 0010:psi_update_stats+0x270/0x490
RSP: 0018:ffffc90001117e10 EFLAGS: 00010246
RAX: 0000000000000000 RBX: 0000000000000000 RCX: ffff8800a35a13f8
RDX: 0000000000000000 RSI: ffff8800a35a1340 RDI: 0000000000000000
RBP: 0000000000000658 R08: ffff8800a35a1470 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 00000000000f8502
FS: 0000000000000000(0000) GS:ffff88023fc00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fbe370fa000 CR3: 00000000b1e3a000 CR4: 00000000000006f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
psi_clock+0x12/0x50
process_one_work+0x1e0/0x390
worker_thread+0x2b/0x3c0
? rescuer_thread+0x330/0x330
kthread+0x113/0x130
? kthread_create_worker_on_cpu+0x40/0x40
? SyS_exit_group+0x10/0x10
ret_from_fork+0x35/0x40
Code: 48 0f 47 c7 48 01 c2 45 85 e4 48 89 16 0f 85 e6 00 00 00 4c 8b 49 10 4c 8b 51 08 49 69 d9 f2 07 00 00 48 6b c0 64 4c 8b 29 31 d2 <48> f7 f7 49 69 d5 8d 06 00 00 48 89 c5 4c 69 f0 00 98 0b 00 48
The Code-line points to `period` being 0 inside update_stats(), and we
divide by that when calculating that period's pressure percentage.
The elapsed period should never be 0. The reason this can happen is due
to an off-by-one in the idle time / missing period calculation combined
with a coarse sched_clock() in the virtual machine.
The target time for aggregation is advanced into the future on a fixed
grid to prevent clock drift. So when an aggregation runs after some idle
period, we can not just set it to "now + psi_period", but have to
calculate the downtime and advance the target time relative to itself.
However, if the aggregator was disabled exactly one psi_period (ns), we
drop one idle period in the calculation due to a > when we should do >=.
In that case, next_update will be advanced from 'now - psi_period' to
'now' when it should be moved to 'now + psi_period'. The run finishes
with last_update == next_update == sched_clock().
With hardware clocks, this exact nanosecond match isn't likely in the
first place; but if it does happen, the clock will still have moved on and
the period non-zero by the time the worker runs. A pointlessly short
period, but besides the extra work, no harm no foul. However, a slow
sched_clock() like we have on VMs might not have advanced either by the
time the worker runs again. And when we calculate the elapsed period, the
result, our pressure divisor, will be 0. Ouch.
Fix this by correctly handling the situation when the elapsed time between
aggregation runs is precisely two periods, and advance the expiration
timestamp correctly to period into the future.
Link: http://lkml.kernel.org/r/20190214193157.15788-1-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reported-by: Łukasz Siudut <lsiudut@fb.com
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
qeueue/queue
Signed-off-by: Liu Song <liu.song11@zte.com.cn>
Signed-off-by: Tejun Heo <tj@kernel.org>
|
|
The first version of this method was missing the check for
`ret == PATH_MAX`; then such a check was added, but it didn't call kfree()
on error, so there was still a small memory leak in the error case.
Fix it by using strndup_user() instead of open-coding it.
Link: http://lkml.kernel.org/r/20190220165443.152385-1-jannh@google.com
Cc: Ingo Molnar <mingo@kernel.org>
Cc: stable@vger.kernel.org
Fixes: 0eadcc7a7bc0 ("perf/core: Fix perf_uprobe_init()")
Reviewed-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
Merge hch's big DMA rework series. This is in a topic branch in case he
wants to merge it to minimise conflicts.
|
|
|
|
The default irq domain allows legacy code to create irqdomain
mappings without having to track the domain it is allocating
from. Setting the default domain is a one shot, fire and forget
operation, and no effort was made to be able to retrieve this
information at a later point in time.
Newer irqdomain APIs (the hierarchical stuff) relies on both
the irqchip code to track the irqdomain it is allocating from,
as well as some form of firmware abstraction to easily identify
which piece of HW maps to which irq domain (DT, ACPI).
For systems without such firmware (or legacy platform that are
getting dragged into the 21st century), things are a bit harder.
For these cases (and these cases only!), let's provide a way
to retrieve the default domain, allowing the use of the v2 API
without having to resort to platform-specific hacks.
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
|
|
When thread1 called printk() which did not end with '\n', and then thread2
called printk() which ends with '\n' before thread1 calls pr_cont(), the
partial content saved into "struct cont" is flushed by thread2 despite the
partial content was generated by thread1. This leads to confusing output
as if the partial content was generated by thread2. Fix this problem by
passing correct caller information to log_store().
Before:
[ T8533] abcdefghijklm
[ T8533] ABCDEFGHIJKLMNOPQRSTUVWXYZ
[ T8532] nopqrstuvwxyz
[ T8532] abcdefghijklmnopqrstuvwxyz
[ T8533] abcdefghijklm
[ T8533] ABCDEFGHIJKLMNOPQRSTUVWXYZ
[ T8532] nopqrstuvwxyz
After:
[ T8507] abcdefghijklm
[ T8508] ABCDEFGHIJKLMNOPQRSTUVWXYZ
[ T8507] nopqrstuvwxyz
[ T8507] abcdefghijklmnopqrstuvwxyz
[ T8507] abcdefghijklm
[ T8508] ABCDEFGHIJKLMNOPQRSTUVWXYZ
[ T8507] nopqrstuvwxyz
Link: http://lkml.kernel.org/r/1550314773-8607-1-git-send-email-penguin-kernel@I-love.SAKURA.ne.jp
To: Dmitry Vyukov <dvyukov@google.com>
To: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
To: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
[pmladek: broke 80-column rule where it made more harm than good]
Signed-off-by: Petr Mladek <pmladek@suse.com>
|
|
There is a spelling mistake in the mini-howto help text. Fix it.
Link: http://lkml.kernel.org/r/20190217223222.16479-1-colin.king@canonical.com
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
Before setting tr->cond_snapshot, it must be NULL before it can be updated.
It can go to NULL when a trace event hist trigger is created or removed, and
can only be modified under the max_lock spin lock. But because it can only
be set to something other than NULL under both the max_lock spin lock as
well as the trace_types_lock, we can perform the check if it is not NULL
only under the trace_types_lock and fail out without having to grab the
max_lock spin lock.
This is very subtle, and deserves a comment.
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
Add a 'trace(synthetic_event_name, params)' alternative to
synthetic_event_name(params).
Currently, the syntax used for generating synthetic events is to
invoke synthetic_event_name(params) i.e. use the synthetic event name
as a function call.
Users requested a new form that more explicitly shows that the
synthetic event is in effect being traced. In this version, a new
'trace()' keyword is used, and the synthetic event name is passed in
as the first argument.
In addition, for the sake of consistency with other actions, change
the documention to emphasize the trace() form over the function-call
form, which remains documented as equivalent.
Link: http://lkml.kernel.org/r/d082773e50232a001480cf837679a1e01c1a2eb7.1550100284.git.tom.zanussi@linux.intel.com
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
Add support for a hist:onchange($var) handler, similar to the onmax()
handler but triggering whenever there's any change in $var, not just a
max.
Link: http://lkml.kernel.org/r/dfbc7e4ada242603e9ec3f049b5ad076a07dfd03.1550100284.git.tom.zanussi@linux.intel.com
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
Add support for hist:handlerXXX($var).snapshot(), which will take a
snapshot of the current trace buffer whenever handlerXXX is hit.
As a first user, this also adds snapshot() action support for the
onmax() handler i.e. hist:onmax($var).snapshot().
Also, the hist trigger key printing is moved into a separate function
so the snapshot() action can print a histogram key outside the
histogram display - add and use hist_trigger_print_key() for that
purpose.
Link: http://lkml.kernel.org/r/2f1a952c0dcd8aca8702ce81269581a692396d45.1550100284.git.tom.zanussi@linux.intel.com
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
Currently, tracing snapshots are context-free - they capture the ring
buffer contents at the time the tracing_snapshot() function was
invoked, and nothing else. Additionally, they're always taken
unconditionally - the calling code can decide whether or not to take a
snapshot, but the data used to make that decision is kept separately
from the snapshot itself.
This change adds the ability to associate with each trace instance
some user data, along with an 'update' function that can use that data
to determine whether or not to actually take a snapshot. The update
function can then update that data along with any other state (as part
of the data presumably), if warranted.
Because snapshots are 'global' per-instance, only one user can enable
and use a conditional snapshot for any given trace instance. To
enable a conditional snapshot (see details in the function and data
structure comments), the user calls tracing_snapshot_cond_enable().
Similarly, to disable a conditional snapshot and free it up for other
users, tracing_snapshot_cond_disable() should be called.
To actually initiate a conditional snapshot, tracing_snapshot_cond()
should be called. tracing_snapshot_cond() will invoke the update()
callback, allowing the user to decide whether or not to actually take
the snapshot and update the user-defined data associated with the
snapshot. If the callback returns 'true', tracing_snapshot_cond()
will then actually take the snapshot and return.
This scheme allows for flexibility in snapshot implementations - for
example, by implementing slightly different update() callbacks,
snapshots can be taken in situations where the user is only interested
in taking a snapshot when a new maximum in hit versus when a value
changes in any way at all. Future patches will demonstrate both
cases.
Link: http://lkml.kernel.org/r/1bea07828d5fd6864a585f83b1eed47ce097eb45.1550100284.git.tom.zanussi@linux.intel.com
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
The action refactor code allowed actions and handlers to be separated,
but the existing onmax handler and save action code is still not
flexible enough to handle arbitrary coupling. This change generalizes
them and in the process makes additional handlers and actions easier
to implement.
The onmax action can be broken up and thought of as two separate
components - a variable to be tracked (the parameter given to the
onmax($var_to_track) function) and an invisible variable created to
save the ongoing result of doing something with that variable, such as
saving the max value of that variable so far seen.
Separating it out like this and renaming it appropriately allows us to
use the same code for similar tracking functions such as
onchange($var_to_track), which would just track the last value seen
rather than the max seen so far, which is useful in some situations.
Additionally, because different handlers and actions may want to save
and access data differently e.g. save and retrieve tracking values as
local variables vs something more global, save_val() and get_val()
interface functions are introduced and max-specific implementations
are used instead.
The same goes for the code that checks whether a maximum has been hit
- a generic check_val() interface and max-checking implementation is
used instead, which allows future patches to make use of he same code
using their own implemetations of similar functionality.
Link: http://lkml.kernel.org/r/980ea73dd8e3f36db3d646f99652f8fed42b77d4.1550100284.git.tom.zanussi@linux.intel.com
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
Currently, the onmatch action data binds the onmatch action to data
related to synthetic event generation. Since we want to allow the
onmatch handler to potentially invoke a different action, and because
we expect other handlers to generate synthetic events, we need to
separate the data related to these two functions.
Also rename the onmatch data to something more descriptive, and create
and use common action data destroy function.
Link: http://lkml.kernel.org/r/b9abbf9aae69fe3920cdc8ddbcaad544dd258d78.1550100284.git.tom.zanussi@linux.intel.com
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
The hist trigger action code currently implements two essentially
hard-coded pairs of 'actions' - onmax(), which tracks a variable and
saves some event fields when a max is hit, and onmatch(), which is
hard-coded to generate a synthetic event.
These hardcoded pairs (track max/save fields and detect match/generate
synthetic event) should really be decoupled into separate components
that can then be arbitrarily combined. The first component of each
pair (track max/detect match) is called a 'handler' in the new code,
while the second component (save fields/generate synthetic event) is
called an 'action' in this scheme.
This change refactors the action code to reflect this split by adding
two handlers, HANDLER_ONMATCH and HANDLER_ONMAX, along with two
actions, ACTION_SAVE and ACTION_TRACE.
The new code combines them to produce the existing ONMATCH/TRACE and
ONMAX/SAVE functionality, but doesn't implement the other combinations
now possible. Future patches will expand these to further useful
cases, such as ONMAX/TRACE, as well as add additional handlers and
actions such as ONCHANGE and SNAPSHOT.
Also, add abbreviated documentation for handlers and actions to
README.
Link: http://lkml.kernel.org/r/98bfdd48c1b4ff29fc5766442f99f5bc3c34b76b.1550100284.git.tom.zanussi@linux.intel.com
Signed-off-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
Commit d716ff71dd12 ("tracing: Remove taking of trace_types_lock in
pipe files") use the current tracer instead of the copy in
tracing_open_pipe(), but it forget to remove the freeing sentence in
the error path.
There's an error path that can call kfree(iter->trace) after the iter->trace
was assigned to tr->current_trace, which would be bad to free.
Link: http://lkml.kernel.org/r/1550060946-45984-1-git-send-email-yi.zhang@huawei.com
Cc: stable@vger.kernel.org
Fixes: d716ff71dd12 ("tracing: Remove taking of trace_types_lock in pipe files")
Signed-off-by: zhangyi (F) <yi.zhang@huawei.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
All users of dma_declare_coherent want their allocations to be
exclusive, so default to exclusive allocations.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
This API is not used anywhere, so remove it.
Signed-off-by: Christoph Hellwig <hch@lst.de>
|
|
This is where all the related code already lives.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
This API is primarily used through DT entries, but two architectures
and two drivers call it directly. So instead of selecting the config
symbol for random architectures pull it in implicitly for the actual
users. Also rename the Kconfig option to describe the feature better.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Paul Burton <paul.burton@mips.com> # MIPS
Acked-by: Lee Jones <lee.jones@linaro.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux into devel
gpio: updates for v5.1 - part 2
- gpio-mockup updates improving the user-space testing interface and
adding line state tracking for correct edge interrupts
- interrupt simulator patch exposing the irq type configuration to
users
|
|
Two easily resolvable overlapping change conflicts, one in
TCP and one in the eBPF verifier.
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Pull networking fixes from David Miller:
1) Fix suspend and resume in mt76x0u USB driver, from Stanislaw
Gruszka.
2) Missing memory barriers in xsk, from Magnus Karlsson.
3) rhashtable fixes in mac80211 from Herbert Xu.
4) 32-bit MIPS eBPF JIT fixes from Paul Burton.
5) Fix for_each_netdev_feature() on big endian, from Hauke Mehrtens.
6) GSO validation fixes from Willem de Bruijn.
7) Endianness fix for dwmac4 timestamp handling, from Alexandre Torgue.
8) More strict checks in tcp_v4_err(), from Eric Dumazet.
9) af_alg_release should NULL out the sk after the sock_put(), from Mao
Wenan.
10) Missing unlock in mac80211 mesh error path, from Wei Yongjun.
11) Missing device put in hns driver, from Salil Mehta.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (44 commits)
sky2: Increase D3 delay again
vhost: correctly check the return value of translate_desc() in log_used()
net: netcp: Fix ethss driver probe issue
net: hns: Fixes the missing put_device in positive leg for roce reset
net: stmmac: Fix a race in EEE enable callback
qed: Fix iWARP syn packet mac address validation.
qed: Fix iWARP buffer size provided for syn packet processing.
r8152: Add support for MAC address pass through on RTL8153-BD
mac80211: mesh: fix missing unlock on error in table_path_del()
net/mlx4_en: fix spelling mistake: "quiting" -> "quitting"
net: crypto set sk to NULL when af_alg_release.
net: Do not allocate page fragments that are not skb aligned
mm: Use fixed constant in page_frag_alloc instead of size + 1
tcp: tcp_v4_err() should be more careful
tcp: clear icsk_backoff in tcp_write_queue_purge()
net: mv643xx_eth: disable clk on error path in mv643xx_eth_shared_probe()
qmi_wwan: apply SET_DTR quirk to Sierra WP7607
net: stmmac: handle endianness in dwmac4_get_timestamp
doc: Mention MSG_ZEROCOPY implementation for UDP
mlxsw: __mlxsw_sp_port_headroom_set(): Fix a use of local variable
...
|
|
Introduce cant_sleep() macro for annotation of functions that
cannot sleep.
Use it in BPF_PROG_RUN to catch execution of BPF programs in
preemptable context.
Suggested-by: Jann Horn <jannh@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
|
|
Implement the irq_set_type() callback and call irqd_set_trigger_type()
internally so that users interested in the configured trigger type can
later retrieve it using irqd_get_trigger_type(). We only support edge
trigger types.
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
|
|
This is a remnant of commit 5f155f27cb7f ("mm, cpuset: always use
seqlock when changing task's nodemask").
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace
Pull tracing fixes from Steven Rostedt:
"Two more tracing fixes
- Have kprobes not use copy_from_user() to access kernel addresses,
because kprobes can legitimately poke at bad kernel memory, which
will fault. Copy from user code should never fault in kernel space.
Using probe_mem_read() can handle kernel address space faulting.
- Put back the entries counter in the tracing output that was
accidentally removed"
* tag 'trace-v5.0-rc4-3' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
tracing: Fix number of entries in trace header
kprobe: Do not use uaccess functions to access kernel memory that can fault
|
|
The only user left is powerpc, but even there the generic dma-direct
version works just as well, given that we guarantee that the swiotlb
buffer must always be addressable.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Christian Zigotzky <chzigotzky@xenosoft.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
Instead of letting the architecture supply all of dma_set_mask just
give it an additional hook selected by Kconfig.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Christian Zigotzky <chzigotzky@xenosoft.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
The ppc_md and pci_controller_ops methods are unused now and can be
removed. The dma_nommu implementation is generic to the generic one
except for using max_pfn instead of calling into the memblock API,
and all other dma_map_ops instances implement a method of their own.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Christian Zigotzky <chzigotzky@xenosoft.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
If there is no ZONE_DMA32 we might need GFP_DMA to be able to
allocate memory that satisfies a 32-bit DMA mask.
Reported-by: Christian Zigotzky <chzigotzky@xenosoft.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Christian Zigotzky <chzigotzky@xenosoft.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
Now that the NVME driver is converted over to the calc_set() callback, the
workarounds of the original set support can be removed.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bjorn Helgaas <helgaas@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: linux-nvme@lists.infradead.org
Cc: linux-pci@vger.kernel.org
Cc: Keith Busch <keith.busch@intel.com>
Cc: Sumit Saxena <sumit.saxena@broadcom.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Shivasharan Srikanteshwara <shivasharan.srikanteshwara@broadcom.com>
Link: https://lkml.kernel.org/r/20190216172228.689834224@linutronix.de
|
|
The interrupt affinity spreading mechanism supports to spread out
affinities for one or more interrupt sets. A interrupt set contains one or
more interrupts. Each set is mapped to a specific functionality of a
device, e.g. general I/O queues and read I/O queus of multiqueue block
devices.
The number of interrupts per set is defined by the driver. It depends on
the total number of available interrupts for the device, which is
determined by the PCI capabilites and the availability of underlying CPU
resources, and the number of queues which the device provides and the
driver wants to instantiate.
The driver passes initial configuration for the interrupt allocation via a
pointer to struct irq_affinity.
Right now the allocation mechanism is complex as it requires to have a loop
in the driver to determine the maximum number of interrupts which are
provided by the PCI capabilities and the underlying CPU resources. This
loop would have to be replicated in every driver which wants to utilize
this mechanism. That's unwanted code duplication and error prone.
In order to move this into generic facilities it is required to have a
mechanism, which allows the recalculation of the interrupt sets and their
size, in the core code. As the core code does not have any knowledge about the
underlying device, a driver specific callback is required in struct
irq_affinity, which can be invoked by the core code. The callback gets the
number of available interupts as an argument, so the driver can calculate the
corresponding number and size of interrupt sets.
At the moment the struct irq_affinity pointer which is handed in from the
driver and passed through to several core functions is marked 'const', but for
the callback to be able to modify the data in the struct it's required to
remove the 'const' qualifier.
Add the optional callback to struct irq_affinity, which allows drivers to
recalculate the number and size of interrupt sets and remove the 'const'
qualifier.
For simple invocations, which do not supply a callback, a default callback
is installed, which just sets nr_sets to 1 and transfers the number of
spreadable vectors to the set_size array at index 0.
This is for now guarded by a check for nr_sets != 0 to keep the NVME driver
working until it is converted to the callback mechanism.
To make sure that the driver configuration is correct under all circumstances
the callback is invoked even when there are no interrupts for queues left,
i.e. the pre/post requirements already exhaust the numner of available
interrupts.
At the PCI layer irq_create_affinity_masks() has to be invoked even for the
case where the legacy interrupt is used. That ensures that the callback is
invoked and the device driver can adjust to that situation.
[ tglx: Fixed the simple case (no sets required). Moved the sanity check
for nr_sets after the invocation of the callback so it catches
broken drivers. Fixed the kernel doc comments for struct
irq_affinity and de-'This patch'-ed the changelog ]
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bjorn Helgaas <helgaas@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: linux-nvme@lists.infradead.org
Cc: linux-pci@vger.kernel.org
Cc: Keith Busch <keith.busch@intel.com>
Cc: Sumit Saxena <sumit.saxena@broadcom.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Shivasharan Srikanteshwara <shivasharan.srikanteshwara@broadcom.com>
Link: https://lkml.kernel.org/r/20190216172228.512444498@linutronix.de
|
|
The interrupt affinity spreading mechanism supports to spread out
affinities for one or more interrupt sets. A interrupt set contains one
or more interrupts. Each set is mapped to a specific functionality of a
device, e.g. general I/O queues and read I/O queus of multiqueue block
devices.
The number of interrupts per set is defined by the driver. It depends on
the total number of available interrupts for the device, which is
determined by the PCI capabilites and the availability of underlying CPU
resources, and the number of queues which the device provides and the
driver wants to instantiate.
The driver passes initial configuration for the interrupt allocation via
a pointer to struct irq_affinity.
Right now the allocation mechanism is complex as it requires to have a
loop in the driver to determine the maximum number of interrupts which
are provided by the PCI capabilities and the underlying CPU resources.
This loop would have to be replicated in every driver which wants to
utilize this mechanism. That's unwanted code duplication and error
prone.
In order to move this into generic facilities it is required to have a
mechanism, which allows the recalculation of the interrupt sets and
their size, in the core code. As the core code does not have any
knowledge about the underlying device, a driver specific callback will
be added to struct affinity_desc, which will be invoked by the core
code. The callback will get the number of available interupts as an
argument, so the driver can calculate the corresponding number and size
of interrupt sets.
To support this, two modifications for the handling of struct irq_affinity
are required:
1) The (optional) interrupt sets size information is contained in a
separate array of integers and struct irq_affinity contains a
pointer to it.
This is cumbersome and as the maximum number of interrupt sets is small,
there is no reason to have separate storage. Moving the size array into
struct affinity_desc avoids indirections and makes the code simpler.
2) At the moment the struct irq_affinity pointer which is handed in from
the driver and passed through to several core functions is marked
'const'.
With the upcoming callback to recalculate the number and size of
interrupt sets, it's necessary to remove the 'const'
qualifier. Otherwise the callback would not be able to update the data.
Implement #1 and store the interrupt sets size in 'struct irq_affinity'.
No functional change.
[ tglx: Fixed the memcpy() size so it won't copy beyond the size of the
source. Fixed the kernel doc comments for struct irq_affinity and
de-'This patch'-ed the changelog ]
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bjorn Helgaas <helgaas@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: linux-nvme@lists.infradead.org
Cc: linux-pci@vger.kernel.org
Cc: Keith Busch <keith.busch@intel.com>
Cc: Sumit Saxena <sumit.saxena@broadcom.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Shivasharan Srikanteshwara <shivasharan.srikanteshwara@broadcom.com>
Link: https://lkml.kernel.org/r/20190216172228.423723127@linutronix.de
|
|
All information and calculations in the interrupt affinity spreading code
is strictly unsigned int. Though the code uses int all over the place.
Convert it over to unsigned int.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bjorn Helgaas <helgaas@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: linux-nvme@lists.infradead.org
Cc: linux-pci@vger.kernel.org
Cc: Keith Busch <keith.busch@intel.com>
Cc: Sumit Saxena <sumit.saxena@broadcom.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Shivasharan Srikanteshwara <shivasharan.srikanteshwara@broadcom.com>
Link: https://lkml.kernel.org/r/20190216172228.336424556@linutronix.de
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux into devel
gpio updates for v5.1
- support for a new variant of pca953x
- documentation fix from Wolfram
- some tegra186 name changes
- two minor fixes for madera and altera-a10sr
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf fixes from Ingo Molnar:
"Two fixes on the kernel side: fix an over-eager condition that failed
larger perf ring-buffer sizes, plus fix crashes in the Intel BTS code
for a corner case, found by fuzzing"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/core: Fix impossible ring-buffer sizes warning
perf/x86: Add check_period PMU callback
|
|
Alexei Starovoitov says:
====================
pull-request: bpf-next 2019-02-16
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) numerous libbpf API improvements, from Andrii, Andrey, Yonghong.
2) test all bpf progs in alu32 mode, from Jiong.
3) skb->sk access and bpf_sk_fullsock(), bpf_tcp_sock() helpers, from Martin.
4) support for IP encap in lwt bpf progs, from Peter.
5) remove XDP_QUERY_XSK_UMEM dead code, from Jan.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Alexei Starovoitov says:
====================
pull-request: bpf 2019-02-16
The following pull-request contains BPF updates for your *net* tree.
The main changes are:
1) fix lockdep false positive in bpf_get_stackid(), from Alexei.
2) several AF_XDP fixes, from Bjorn, Magnus, Davidlohr.
3) fix narrow load from struct bpf_sock, from Martin.
4) mips JIT fixes, from Paul.
5) gso handling fix in bpf helpers, from Willem.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
There is no need to have the 'struct dentry *d_swiotlb_usage' variable
static since new value always be assigned before use it.
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
|
|
The netfilter conflicts were rather simple overlapping
changes.
However, the cls_tcindex.c stuff was a bit more complex.
On the 'net' side, Cong is fixing several races and memory
leaks. Whilst on the 'net-next' side we have Vlad adding
the rtnl-ness support.
What I've decided to do, in order to resolve this, is revert the
conversion over to using a workqueue that Cong did, bringing us back
to pure RCU. I did it this way because I believe that either Cong's
races don't apply with have Vlad did things, or Cong will have to
implement the race fix slightly differently.
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
cgroup_rstat_cpu_pop_updated() is used to traverse the updated cgroups
on flush. While it was only visiting updated ones in the subtree, it
was visiting @root unconditionally. We can easily check whether @root
is updated or not by looking at its ->updated_next just as with the
cgroups in the subtree.
* Remove the unnecessary cgroup_parent() test. The system root cgroup
is never updated and thus its ->updated_next is always NULL. No
need to test whether cgroup_parent() exists in addition to
->updated_next.
* Terminate traverse if ->updated_next is NULL. This can only happen
for subtree @root and there's no reason to visit it if it's not
marked updated.
This reduces cpu consumption when reading a lot of rstat backed files.
In a micro benchmark reading stat from ~1600 cgroups, the sys time was
lowered by >40%.
Signed-off-by: Tejun Heo <tj@kernel.org>
|
|
atomic_t variables are currently used to implement reference
counters with the following properties:
- counter is initialized to 1 using atomic_set()
- a resource is freed upon counter reaching zero
- once counter reaches zero, its further
increments aren't allowed
- counter schema uses basic atomic operations
(set, inc, inc_not_zero, dec_and_test, etc.)
Such atomic variables should be converted to a newly provided
refcount_t type and API that prevents accidental counter overflows
and underflows. This is important since overflows and underflows
can lead to use-after-free situation and be exploitable.
The variable uprobe.ref is used as pure reference counter.
Convert it to refcount_t and fix up the operations.
**Important note for maintainers:
Some functions from refcount_t API defined in lib/refcount.c
have different memory ordering guarantees than their atomic
counterparts.
The full comparison can be seen in
https://lkml.org/lkml/2017/11/15/57 and it is hopefully soon
in state to be merged to the documentation tree.
Normally the differences should not matter since refcount_t provides
enough guarantees to satisfy the refcounting use cases, but in
some rare cases it might matter.
Please double check that you don't have some undocumented
memory guarantees for this variable usage.
For the uprobe.ref it might make a difference
in following places:
- put_uprobe(): decrement in refcount_dec_and_test() only
provides RELEASE ordering and control dependency on success
vs. fully ordered atomic counterpart
Link: http://lkml.kernel.org/r/1547637627-29526-1-git-send-email-elena.reshetova@intel.com
Suggested-by: Kees Cook <keescook@chromium.org>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: David Windsor <dwindsor@gmail.com>
Reviewed-by: Hans Liljestrand <ishkamiel@gmail.com>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
Enabling of large number of functions by echoing in a large subset of the
functions in available_filter_functions can take a very long time. The
process requires testing all functions registered by the function tracer
(which is in the 10s of thousands), and doing a kallsyms lookup to convert
the ip address into a name, then comparing that name with the string passed
in.
When a function causes the function tracer to crash the system, a binary
bisect of the available_filter_functions can be done to find the culprit.
But this requires passing in half of the functions in
available_filter_functions over and over again, which makes it basically a
O(n^2) operation. With 40,000 functions, that ends up bing 1,600,000,000
opertions! And enabling this can take over 20 minutes.
As a quick speed up, if a number is passed into one of the filter files,
instead of doing a search, it just enables the function at the corresponding
line of the available_filter_functions file. That is:
# echo 50 > set_ftrace_filter
# cat set_ftrace_filter
x86_pmu_commit_txn
# head -50 available_filter_functions | tail -1
x86_pmu_commit_txn
This allows setting of half the available_filter_functions to take place in
less than a second!
# time seq 20000 > set_ftrace_filter
real 0m0.042s
user 0m0.005s
sys 0m0.015s
# wc -l set_ftrace_filter
20000 set_ftrace_filter
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
The following commit
441dae8f2f29 ("tracing: Add support for display of tgid in trace output")
removed the call to print_event_info() from print_func_help_header_irq()
which results in the ftrace header not reporting the number of entries
written in the buffer. As this wasn't the original intent of the patch,
re-introduce the call to print_event_info() to restore the orginal
behaviour.
Link: http://lkml.kernel.org/r/20190214152950.4179-1-quentin.perret@arm.com
Acked-by: Joel Fernandes <joelaf@google.com>
Cc: stable@vger.kernel.org
Fixes: 441dae8f2f29 ("tracing: Add support for display of tgid in trace output")
Signed-off-by: Quentin Perret <quentin.perret@arm.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
The userspace can ask kprobe to intercept strings at any memory address,
including invalid kernel address. In this case, fetch_store_strlen()
would crash since it uses general usercopy function, and user access
functions are no longer allowed to access kernel memory.
For example, we can crash the kernel by doing something as below:
$ sudo kprobe 'p:do_sys_open +0(+0(%si)):string'
[ 103.620391] BUG: GPF in non-whitelisted uaccess (non-canonical address?)
[ 103.622104] general protection fault: 0000 [#1] SMP PTI
[ 103.623424] CPU: 10 PID: 1046 Comm: cat Not tainted 5.0.0-rc3-00130-gd73aba1-dirty #96
[ 103.625321] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.0-2-g628b2e6-dirty-20190104_103505-linux 04/01/2014
[ 103.628284] RIP: 0010:process_fetch_insn+0x1ab/0x4b0
[ 103.629518] Code: 10 83 80 28 2e 00 00 01 31 d2 31 ff 48 8b 74 24 28 eb 0c 81 fa ff 0f 00 00 7f 1c 85 c0 75 18 66 66 90 0f ae e8 48 63
ca 89 f8 <8a> 0c 31 66 66 90 83 c2 01 84 c9 75 dc 89 54 24 34 89 44 24 28 48
[ 103.634032] RSP: 0018:ffff88845eb37ce0 EFLAGS: 00010246
[ 103.635312] RAX: 0000000000000000 RBX: ffff888456c4e5a8 RCX: 0000000000000000
[ 103.637057] RDX: 0000000000000000 RSI: 2e646c2f6374652f RDI: 0000000000000000
[ 103.638795] RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
[ 103.640556] R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000000
[ 103.642297] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000
[ 103.644040] FS: 0000000000000000(0000) GS:ffff88846f000000(0000) knlGS:0000000000000000
[ 103.646019] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 103.647436] CR2: 00007ffc79758038 CR3: 0000000463360006 CR4: 0000000000020ee0
[ 103.649147] Call Trace:
[ 103.649781] ? sched_clock_cpu+0xc/0xa0
[ 103.650747] ? do_sys_open+0x5/0x220
[ 103.651635] kprobe_trace_func+0x303/0x380
[ 103.652645] ? do_sys_open+0x5/0x220
[ 103.653528] kprobe_dispatcher+0x45/0x50
[ 103.654682] ? do_sys_open+0x1/0x220
[ 103.655875] kprobe_ftrace_handler+0x90/0xf0
[ 103.657282] ftrace_ops_assist_func+0x54/0xf0
[ 103.658564] ? __call_rcu+0x1dc/0x280
[ 103.659482] 0xffffffffc00000bf
[ 103.660384] ? __ia32_sys_open+0x20/0x20
[ 103.661682] ? do_sys_open+0x1/0x220
[ 103.662863] do_sys_open+0x5/0x220
[ 103.663988] do_syscall_64+0x60/0x210
[ 103.665201] entry_SYSCALL_64_after_hwframe+0x49/0xbe
[ 103.666862] RIP: 0033:0x7fc22fadccdd
[ 103.668034] Code: 48 89 54 24 e0 41 83 e2 40 75 32 89 f0 25 00 00 41 00 3d 00 00 41 00 74 24 89 f2 b8 01 01 00 00 48 89 fe bf 9c ff ff
ff 0f 05 <48> 3d 00 f0 ff ff 77 33 f3 c3 66 0f 1f 84 00 00 00 00 00 48 8d 44
[ 103.674029] RSP: 002b:00007ffc7972c3a8 EFLAGS: 00000287 ORIG_RAX: 0000000000000101
[ 103.676512] RAX: ffffffffffffffda RBX: 0000562f86147a21 RCX: 00007fc22fadccdd
[ 103.678853] RDX: 0000000000080000 RSI: 00007fc22fae1428 RDI: 00000000ffffff9c
[ 103.681151] RBP: ffffffffffffffff R08: 0000000000000000 R09: 0000000000000000
[ 103.683489] R10: 0000000000000000 R11: 0000000000000287 R12: 00007fc22fce90a8
[ 103.685774] R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000000
[ 103.688056] Modules linked in:
[ 103.689131] ---[ end trace 43792035c28984a1 ]---
This can be fixed by using probe_mem_read() instead, as it can handle faulting
kernel memory addresses, which kprobes can legitimately do.
Link: http://lkml.kernel.org/r/20190125151051.7381-1-changbin.du@gmail.com
Cc: stable@vger.kernel.org
Fixes: 9da3f2b7405 ("x86/fault: BUG() when uaccess helpers fault on kernel addresses")
Signed-off-by: Changbin Du <changbin.du@gmail.com>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace
Pull signal fix from Eric Biederman:
"Just a single patch that restores PTRACE_EVENT_EXIT functionality that
was accidentally broken by last weeks fixes"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
signal: Restore the stop PTRACE_EVENT_EXIT
|
|
Pick up upstream changes to avoid conflicts for pending patches.
|
|
ready_percpu_nmi() was the previous name of prepare_percpu_nmi(). Update
request_percpu_nmi() comment with the correct function name.
Signed-off-by: Julien Thierry <julien.thierry@arm.com>
Reported-by: Li Wei <liwei391@huawei.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
|
