Pull cgroup fix from Tejun Heo:
"Fix an old and subtle bug in the migration path.
css_sets are used to track tasks and migrations are tasks moving from
a group of css_sets to another group of css_sets. The migration path
pins all source and destination css_sets in the prep stage.
Unfortunately, it was overloading the same list_head entry to track
sources and destinations, which got confused for migrations which are
partially identity leading to use-after-frees.
Fixed by using dedicated list_heads for tracking sources and
destinations"
* tag 'cgroup-for-5.19-rc6-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
cgroup: Use separate src/dst nodes when preloading css_sets for migration
Currently, an unsigned kernel could be kexec'ed when IMA arch specific
policy is configured unless lockdown is enabled. Enforce kernel
signature verification check in the kexec_file_load syscall when IMA
arch specific policy is configured.
Fixes: 99d5cadfde ("kexec_file: split KEXEC_VERIFY_SIG into KEXEC_SIG and KEXEC_SIG_FORCE")
Reported-and-suggested-by: Mimi Zohar <zohar@linux.ibm.com>
Signed-off-by: Coiby Xu <coxu@redhat.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
A sysctl variable is accessed concurrently, and there is always a chance
of data-race. So, all readers and writers need some basic protection to
avoid load/store-tearing.
This patch changes proc_dointvec_ms_jiffies() to use READ_ONCE() and
WRITE_ONCE() internally to fix data-races on the sysctl side. For now,
proc_dointvec_ms_jiffies() itself is tolerant to a data-race, but we still
need to add annotations on the other subsystem's side.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A sysctl variable is accessed concurrently, and there is always a chance
of data-race. So, all readers and writers need some basic protection to
avoid load/store-tearing.
This patch changes proc_dou8vec_minmax() to use READ_ONCE() and
WRITE_ONCE() internally to fix data-races on the sysctl side. For now,
proc_dou8vec_minmax() itself is tolerant to a data-race, but we still
need to add annotations on the other subsystem's side.
Fixes: cb94441306 ("sysctl: add proc_dou8vec_minmax()")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With CONFIG_PREEMPT_RT, it is possible to hit a deadlock between two
normal priority tasks (SCHED_OTHER, nice level zero):
INFO: task kworker/u8:0:8 blocked for more than 491 seconds.
Not tainted 5.15.49-rt46 #1
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:kworker/u8:0 state:D stack: 0 pid: 8 ppid: 2 flags:0x00000000
Workqueue: writeback wb_workfn (flush-7:0)
[<c08a3a10>] (__schedule) from [<c08a3d84>] (schedule+0xdc/0x134)
[<c08a3d84>] (schedule) from [<c08a65a0>] (rt_mutex_slowlock_block.constprop.0+0xb8/0x174)
[<c08a65a0>] (rt_mutex_slowlock_block.constprop.0) from [<c08a6708>]
+(rt_mutex_slowlock.constprop.0+0xac/0x174)
[<c08a6708>] (rt_mutex_slowlock.constprop.0) from [<c0374d60>] (fat_write_inode+0x34/0x54)
[<c0374d60>] (fat_write_inode) from [<c0297304>] (__writeback_single_inode+0x354/0x3ec)
[<c0297304>] (__writeback_single_inode) from [<c0297998>] (writeback_sb_inodes+0x250/0x45c)
[<c0297998>] (writeback_sb_inodes) from [<c0297c20>] (__writeback_inodes_wb+0x7c/0xb8)
[<c0297c20>] (__writeback_inodes_wb) from [<c0297f24>] (wb_writeback+0x2c8/0x2e4)
[<c0297f24>] (wb_writeback) from [<c0298c40>] (wb_workfn+0x1a4/0x3e4)
[<c0298c40>] (wb_workfn) from [<c0138ab8>] (process_one_work+0x1fc/0x32c)
[<c0138ab8>] (process_one_work) from [<c0139120>] (worker_thread+0x22c/0x2d8)
[<c0139120>] (worker_thread) from [<c013e6e0>] (kthread+0x16c/0x178)
[<c013e6e0>] (kthread) from [<c01000fc>] (ret_from_fork+0x14/0x38)
Exception stack(0xc10e3fb0 to 0xc10e3ff8)
3fa0: 00000000 00000000 00000000 00000000
3fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
3fe0: 00000000 00000000 00000000 00000000 00000013 00000000
INFO: task tar:2083 blocked for more than 491 seconds.
Not tainted 5.15.49-rt46 #1
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:tar state:D stack: 0 pid: 2083 ppid: 2082 flags:0x00000000
[<c08a3a10>] (__schedule) from [<c08a3d84>] (schedule+0xdc/0x134)
[<c08a3d84>] (schedule) from [<c08a41b0>] (io_schedule+0x14/0x24)
[<c08a41b0>] (io_schedule) from [<c08a455c>] (bit_wait_io+0xc/0x30)
[<c08a455c>] (bit_wait_io) from [<c08a441c>] (__wait_on_bit_lock+0x54/0xa8)
[<c08a441c>] (__wait_on_bit_lock) from [<c08a44f4>] (out_of_line_wait_on_bit_lock+0x84/0xb0)
[<c08a44f4>] (out_of_line_wait_on_bit_lock) from [<c0371fb0>] (fat_mirror_bhs+0xa0/0x144)
[<c0371fb0>] (fat_mirror_bhs) from [<c0372a68>] (fat_alloc_clusters+0x138/0x2a4)
[<c0372a68>] (fat_alloc_clusters) from [<c0370b14>] (fat_alloc_new_dir+0x34/0x250)
[<c0370b14>] (fat_alloc_new_dir) from [<c03787c0>] (vfat_mkdir+0x58/0x148)
[<c03787c0>] (vfat_mkdir) from [<c0277b60>] (vfs_mkdir+0x68/0x98)
[<c0277b60>] (vfs_mkdir) from [<c027b484>] (do_mkdirat+0xb0/0xec)
[<c027b484>] (do_mkdirat) from [<c0100060>] (ret_fast_syscall+0x0/0x1c)
Exception stack(0xc2e1bfa8 to 0xc2e1bff0)
bfa0: 01ee42f0 01ee4208 01ee42f0 000041ed 00000000 00004000
bfc0: 01ee42f0 01ee4208 00000000 00000027 01ee4302 00000004 000dcb00 01ee4190
bfe0: 000dc368 bed11924 0006d4b0 b6ebddfc
Here the kworker is waiting on msdos_sb_info::s_lock which is held by
tar which is in turn waiting for a buffer which is locked waiting to be
flushed, but this operation is plugged in the kworker.
The lock is a normal struct mutex, so tsk_is_pi_blocked() will always
return false on !RT and thus the behaviour changes for RT.
It seems that the intent here is to skip blk_flush_plug() in the case
where a non-preemptible lock (such as a spinlock) has been converted to
a rtmutex on RT, which is the case covered by the SM_RTLOCK_WAIT
schedule flag. But sched_submit_work() is only called from schedule()
which is never called in this scenario, so the check can simply be
deleted.
Looking at the history of the -rt patchset, in fact this change was
present from v5.9.1-rt20 until being dropped in v5.13-rt1 as it was part
of a larger patch [1] most of which was replaced by commit b4bfa3fcfe
("sched/core: Rework the __schedule() preempt argument").
As described in [1]:
The schedule process must distinguish between blocking on a regular
sleeping lock (rwsem and mutex) and a RT-only sleeping lock (spinlock
and rwlock):
- rwsem and mutex must flush block requests (blk_schedule_flush_plug())
even if blocked on a lock. This can not deadlock because this also
happens for non-RT.
There should be a warning if the scheduling point is within a RCU read
section.
- spinlock and rwlock must not flush block requests. This will deadlock
if the callback attempts to acquire a lock which is already acquired.
Similarly to being preempted, there should be no warning if the
scheduling point is within a RCU read section.
and with the tsk_is_pi_blocked() in the scheduler path, we hit the first
issue.
[1] https://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git/tree/patches/0022-locking-rtmutex-Use-custom-scheduling-function-for-s.patch?h=linux-5.10.y-rt-patches
Signed-off-by: John Keeping <john@metanate.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lkml.kernel.org/r/20220708162702.1758865-1-john@metanate.com
The capacity of the CPU available for CFS tasks can be reduced because of
other activities running on the latter. In such case, it's worth trying to
move CFS tasks on a CPU with more available capacity.
The rework of the load balance has filtered the case when the CPU is
classified to be fully busy but its capacity is reduced.
Check if CPU's capacity is reduced while gathering load balance statistic
and classify it group_misfit_task instead of group_fully_busy so we can
try to move the load on another CPU.
Reported-by: David Chen <david.chen@nutanix.com>
Reported-by: Zhang Qiao <zhangqiao22@huawei.com>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: David Chen <david.chen@nutanix.com>
Tested-by: Zhang Qiao <zhangqiao22@huawei.com>
Link: https://lkml.kernel.org/r/20220708154401.21411-1-vincent.guittot@linaro.org
Yang Jihing reported a race between perf_event_set_output() and
perf_mmap_close():
CPU1 CPU2
perf_mmap_close(e2)
if (atomic_dec_and_test(&e2->rb->mmap_count)) // 1 - > 0
detach_rest = true
ioctl(e1, IOC_SET_OUTPUT, e2)
perf_event_set_output(e1, e2)
...
list_for_each_entry_rcu(e, &e2->rb->event_list, rb_entry)
ring_buffer_attach(e, NULL);
// e1 isn't yet added and
// therefore not detached
ring_buffer_attach(e1, e2->rb)
list_add_rcu(&e1->rb_entry,
&e2->rb->event_list)
After this; e1 is attached to an unmapped rb and a subsequent
perf_mmap() will loop forever more:
again:
mutex_lock(&e->mmap_mutex);
if (event->rb) {
...
if (!atomic_inc_not_zero(&e->rb->mmap_count)) {
...
mutex_unlock(&e->mmap_mutex);
goto again;
}
}
The loop in perf_mmap_close() holds e2->mmap_mutex, while the attach
in perf_event_set_output() holds e1->mmap_mutex. As such there is no
serialization to avoid this race.
Change perf_event_set_output() to take both e1->mmap_mutex and
e2->mmap_mutex to alleviate that problem. Additionally, have the loop
in perf_mmap() detach the rb directly, this avoids having to wait for
the concurrent perf_mmap_close() to get around to doing it to make
progress.
Fixes: 9bb5d40cd9 ("perf: Fix mmap() accounting hole")
Reported-by: Yang Jihong <yangjihong1@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Yang Jihong <yangjihong1@huawei.com>
Link: https://lkml.kernel.org/r/YsQ3jm2GR38SW7uD@worktop.programming.kicks-ass.net
Pull tracing fixes from Steven Rostedt:
"Fixes and minor clean ups for tracing:
- Fix memory leak by reverting what was thought to be a double free.
A static tool had gave a false positive that a double free was
possible in the error path, but it was actually a different
location that confused the static analyzer (and those of us that
reviewed it).
- Move use of static buffers by ftrace_dump() to a location that can
be used by kgdb's ftdump(), as it needs it for the same reasons.
- Clarify in the Kconfig description that function tracing has
negligible impact on x86, but may have a bit bigger impact on other
architectures.
- Remove unnecessary extra semicolon in trace event.
- Make a local variable static that is used in the fprobes sample
- Use KSYM_NAME_LEN for length of function in kprobe sample and get
rid of unneeded macro for the same purpose"
* tag 'trace-v5.19-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
samples: Use KSYM_NAME_LEN for kprobes
fprobe/samples: Make sample_probe static
blk-iocost: tracing: atomic64_read(&ioc->vtime_rate) is assigned an extra semicolon
ftrace: Be more specific about arch impact when function tracer is enabled
tracing: Fix sleeping while atomic in kdb ftdump
tracing/histograms: Fix memory leak problem
It was brought up that on ARMv7, that because the FUNCTION_TRACER does not
use nops to keep function tracing disabled because of the use of a link
register, it does have some performance impact.
The start of functions when -pg is used to compile the kernel is:
push {lr}
bl 8010e7c0 <__gnu_mcount_nc>
When function tracing is tuned off, it becomes:
push {lr}
add sp, sp, #4
Which just puts the stack back to its normal location. But these two
instructions at the start of every function does incur some overhead.
Be more honest in the Kconfig FUNCTION_TRACER description and specify that
the overhead being in the noise was x86 specific, but other architectures
may vary.
Link: https://lore.kernel.org/all/20220705105416.GE5208@pengutronix.de/
Link: https://lkml.kernel.org/r/20220706161231.085a83da@gandalf.local.home
Reported-by: Sascha Hauer <sha@pengutronix.de>
Acked-by: Sascha Hauer <s.hauer@pengutronix.de>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
If you drop into kdb and type "ftdump" you'll get a sleeping while
atomic warning from memory allocation in trace_find_next_entry().
This appears to have been caused by commit ff895103a8 ("tracing:
Save off entry when peeking at next entry"), which added the
allocation in that path. The problematic commit was already fixed by
commit 8e99cf91b9 ("tracing: Do not allocate buffer in
trace_find_next_entry() in atomic") but that fix missed the kdb case.
The fix here is easy: just move the assignment of the static buffer to
the place where it should have been to begin with:
trace_init_global_iter(). That function is called in two places, once
is right before the assignment of the static buffer added by the
previous fix and once is in kdb.
Note that it appears that there's a second static buffer that we need
to assign that was added in commit efbbdaa22b ("tracing: Show real
address for trace event arguments"), so we'll move that too.
Link: https://lkml.kernel.org/r/20220708170919.1.I75844e5038d9425add2ad853a608cb44bb39df40@changeid
Fixes: ff895103a8 ("tracing: Save off entry when peeking at next entry")
Fixes: efbbdaa22b ("tracing: Show real address for trace event arguments")
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
This reverts commit 46bbe5c671.
As commit 46bbe5c671 ("tracing: fix double free") said, the
"double free" problem reported by clang static analyzer is:
> In parse_var_defs() if there is a problem allocating
> var_defs.expr, the earlier var_defs.name is freed.
> This free is duplicated by free_var_defs() which frees
> the rest of the list.
However, if there is a problem allocating N-th var_defs.expr:
+ in parse_var_defs(), the freed 'earlier var_defs.name' is
actually the N-th var_defs.name;
+ then in free_var_defs(), the names from 0th to (N-1)-th are freed;
IF ALLOCATING PROBLEM HAPPENED HERE!!! -+
\
|
0th 1th (N-1)-th N-th V
+-------------+-------------+-----+-------------+-----------
var_defs: | name | expr | name | expr | ... | name | expr | name | ///
+-------------+-------------+-----+-------------+-----------
These two frees don't act on same name, so there was no "double free"
problem before. Conversely, after that commit, we get a "memory leak"
problem because the above "N-th var_defs.name" is not freed.
If enable CONFIG_DEBUG_KMEMLEAK and inject a fault at where the N-th
var_defs.expr allocated, then execute on shell like:
$ echo 'hist:key=call_site:val=$v1,$v2:v1=bytes_req,v2=bytes_alloc' > \
/sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
Then kmemleak reports:
unreferenced object 0xffff8fb100ef3518 (size 8):
comm "bash", pid 196, jiffies 4295681690 (age 28.538s)
hex dump (first 8 bytes):
76 31 00 00 b1 8f ff ff v1......
backtrace:
[<0000000038fe4895>] kstrdup+0x2d/0x60
[<00000000c99c049a>] event_hist_trigger_parse+0x206f/0x20e0
[<00000000ae70d2cc>] trigger_process_regex+0xc0/0x110
[<0000000066737a4c>] event_trigger_write+0x75/0xd0
[<000000007341e40c>] vfs_write+0xbb/0x2a0
[<0000000087fde4c2>] ksys_write+0x59/0xd0
[<00000000581e9cdf>] do_syscall_64+0x3a/0x80
[<00000000cf3b065c>] entry_SYSCALL_64_after_hwframe+0x46/0xb0
Link: https://lkml.kernel.org/r/20220711014731.69520-1-zhengyejian1@huawei.com
Cc: stable@vger.kernel.org
Fixes: 46bbe5c671 ("tracing: fix double free")
Reported-by: Hulk Robot <hulkci@huawei.com>
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Reviewed-by: Tom Zanussi <tom.zanussi@linux.intel.com>
Signed-off-by: Zheng Yejian <zhengyejian1@huawei.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Pull module fixes from Luis Chamberlain:
"Although most of the move of code in in v5.19-rc1 should have not
introduced a regression patch review on one of the file changes
captured a checkpatch warning which advised to use strscpy() and it
caused a buffer overflow when an incorrect length is passed.
Another change which checkpatch complained about was an odd RCU usage,
but that was properly addressed in a separate patch to the move by
Aaron. That caused a regression with PREEMPT_RT=y due to an unbounded
latency.
This series fixes both and adjusts documentation which we forgot to do
for the move"
* tag 'modules-5.19-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux:
module: kallsyms: Ensure preemption in add_kallsyms() with PREEMPT_RT
doc: module: update file references
module: Fix "warning: variable 'exit' set but not used"
module: Fix selfAssignment cppcheck warning
modules: Fix corruption of /proc/kallsyms
The commit 08126db5ff ("module: kallsyms: Fix suspicious rcu usage")
under PREEMPT_RT=y, disabling preemption introduced an unbounded
latency since the loop is not fixed. This change caused a regression
since previously preemption was not disabled and we would dereference
RCU-protected pointers explicitly. That being said, these pointers
cannot change.
Before kallsyms-specific data is prepared/or set-up, we ensure that
the unformed module is known to be unique i.e. does not already exist
(see load_module()). Therefore, we can fix this by using the common and
more appropriate RCU flavour as this section of code can be safely
preempted.
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Fixes: 08126db5ff ("module: kallsyms: Fix suspicious rcu usage")
Signed-off-by: Aaron Tomlin <atomlin@redhat.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
As Chris explains, the comment above exit_itimers() is not correct,
we can race with proc_timers_seq_ops. Change exit_itimers() to clear
signal->posix_timers with ->siglock held.
Cc: <stable@vger.kernel.org>
Reported-by: chris@accessvector.net
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* irq/plic-masking:
: .
: SiFive PLIC optimisations from Samuel Holland:
:
: "This series removes the spinlocks and cpumask operations from the PLIC
: driver's hot path. As far as I know, using the priority to mask
: interrupts is an intended usage and will work on all existing
: implementations. [...]"
: .
irqchip/sifive-plic: Separate the enable and mask operations
irqchip/sifive-plic: Make better use of the effective affinity mask
PCI: hv: Take a const cpumask in hv_compose_msi_req_get_cpu()
genirq: Provide an IRQ affinity mask in non-SMP configs
genirq: Return a const cpumask from irq_data_get_affinity_mask
genirq: Add and use an irq_data_update_affinity helper
genirq: Refactor accessors to use irq_data_get_affinity_mask
genirq: Drop redundant irq_init_effective_affinity
genirq: GENERIC_IRQ_EFFECTIVE_AFF_MASK depends on SMP
genirq: GENERIC_IRQ_IPI depends on SMP
irqchip/mips-gic: Only register IPI domain when SMP is enabled
Signed-off-by: Marc Zyngier <maz@kernel.org>
CI reported the following splat while running the strace testsuite:
WARNING: CPU: 1 PID: 3570031 at kernel/ptrace.c:272 ptrace_check_attach+0x12e/0x178
CPU: 1 PID: 3570031 Comm: strace Tainted: G OE 5.19.0-20220624.rc3.git0.ee819a77d4e7.300.fc36.s390x #1
Hardware name: IBM 3906 M04 704 (z/VM 7.1.0)
Call Trace:
[<00000000ab4b645a>] ptrace_check_attach+0x132/0x178
([<00000000ab4b6450>] ptrace_check_attach+0x128/0x178)
[<00000000ab4b6cde>] __s390x_sys_ptrace+0x86/0x160
[<00000000ac03fcec>] __do_syscall+0x1d4/0x200
[<00000000ac04e312>] system_call+0x82/0xb0
Last Breaking-Event-Address:
[<00000000ab4ea3c8>] wait_task_inactive+0x98/0x190
This is because JOBCTL_TRACED is set, but the task is not in TASK_TRACED
state. Caused by ptrace_unfreeze_traced() which does:
task->jobctl &= ~TASK_TRACED
but it should be:
task->jobctl &= ~JOBCTL_TRACED
Fixes: 31cae1eaae ("sched,signal,ptrace: Rework TASK_TRACED, TASK_STOPPED state")
Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Tested-by: Alexander Gordeev <agordeev@linux.ibm.com>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Daniel Borkmann says:
====================
bpf 2022-07-08
We've added 3 non-merge commits during the last 2 day(s) which contain
a total of 7 files changed, 40 insertions(+), 24 deletions(-).
The main changes are:
1) Fix cBPF splat triggered by skb not having a mac header, from Eric Dumazet.
2) Fix spurious packet loss in generic XDP when pushing packets out (note
that native XDP is not affected by the issue), from Johan Almbladh.
3) Fix bpf_dynptr_{read,write}() helper signatures with flag argument before
its set in stone as UAPI, from Joanne Koong.
* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
bpf: Add flags arg to bpf_dynptr_read and bpf_dynptr_write APIs
bpf: Make sure mac_header was set before using it
xdp: Fix spurious packet loss in generic XDP TX path
====================
Link: https://lore.kernel.org/r/20220708213418.19626-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
A sysctl variable is accessed concurrently, and there is always a chance
of data-race. So, all readers and writers need some basic protection to
avoid load/store-tearing.
This patch changes proc_dointvec_jiffies() to use READ_ONCE() and
WRITE_ONCE() internally to fix data-races on the sysctl side. For now,
proc_dointvec_jiffies() itself is tolerant to a data-race, but we still
need to add annotations on the other subsystem's side.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A sysctl variable is accessed concurrently, and there is always a chance
of data-race. So, all readers and writers need some basic protection to
avoid load/store-tearing.
This patch changes proc_doulongvec_minmax() to use READ_ONCE() and
WRITE_ONCE() internally to fix data-races on the sysctl side. For now,
proc_doulongvec_minmax() itself is tolerant to a data-race, but we still
need to add annotations on the other subsystem's side.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A sysctl variable is accessed concurrently, and there is always a chance
of data-race. So, all readers and writers need some basic protection to
avoid load/store-tearing.
This patch changes proc_douintvec_minmax() to use READ_ONCE() and
WRITE_ONCE() internally to fix data-races on the sysctl side. For now,
proc_douintvec_minmax() itself is tolerant to a data-race, but we still
need to add annotations on the other subsystem's side.
Fixes: 61d9b56a89 ("sysctl: add unsigned int range support")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A sysctl variable is accessed concurrently, and there is always a chance
of data-race. So, all readers and writers need some basic protection to
avoid load/store-tearing.
This patch changes proc_dointvec_minmax() to use READ_ONCE() and
WRITE_ONCE() internally to fix data-races on the sysctl side. For now,
proc_dointvec_minmax() itself is tolerant to a data-race, but we still
need to add annotations on the other subsystem's side.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A sysctl variable is accessed concurrently, and there is always a chance
of data-race. So, all readers and writers need some basic protection to
avoid load/store-tearing.
This patch changes proc_douintvec() to use READ_ONCE() and WRITE_ONCE()
internally to fix data-races on the sysctl side. For now, proc_douintvec()
itself is tolerant to a data-race, but we still need to add annotations on
the other subsystem's side.
Fixes: e7d316a02f ("sysctl: handle error writing UINT_MAX to u32 fields")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
A sysctl variable is accessed concurrently, and there is always a chance
of data-race. So, all readers and writers need some basic protection to
avoid load/store-tearing.
This patch changes proc_dointvec() to use READ_ONCE() and WRITE_ONCE()
internally to fix data-races on the sysctl side. For now, proc_dointvec()
itself is tolerant to a data-race, but we still need to add annotations on
the other subsystem's side.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Commit 13bbbfbea7 ("bpf: Add bpf_dynptr_read and bpf_dynptr_write")
added the bpf_dynptr_write() and bpf_dynptr_read() APIs.
However, it will be needed for some dynptr types to pass in flags as
well (e.g. when writing to a skb, the user may like to invalidate the
hash or recompute the checksum).
This patch adds a "u64 flags" arg to the bpf_dynptr_read() and
bpf_dynptr_write() APIs before their UAPI signature freezes where
we then cannot change them anymore with a 5.19.x released kernel.
Fixes: 13bbbfbea7 ("bpf: Add bpf_dynptr_read and bpf_dynptr_write")
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20220706232547.4016651-1-joannelkoong@gmail.com
Pull networking fixes from Paolo Abeni:
"Including fixes from bpf, netfilter, can, and bluetooth.
Current release - regressions:
- bluetooth: fix deadlock on hci_power_on_sync
Previous releases - regressions:
- sched: act_police: allow 'continue' action offload
- eth: usbnet: fix memory leak in error case
- eth: ibmvnic: properly dispose of all skbs during a failover
Previous releases - always broken:
- bpf:
- fix insufficient bounds propagation from
adjust_scalar_min_max_vals
- clear page contiguity bit when unmapping pool
- netfilter: nft_set_pipapo: release elements in clone from
abort path
- mptcp: netlink: issue MP_PRIO signals from userspace PMs
- can:
- rcar_canfd: fix data transmission failed on R-Car V3U
- gs_usb: gs_usb_open/close(): fix memory leak
Misc:
- add Wenjia as SMC maintainer"
* tag 'net-5.19-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (57 commits)
wireguard: Kconfig: select CRYPTO_CHACHA_S390
crypto: s390 - do not depend on CRYPTO_HW for SIMD implementations
wireguard: selftests: use microvm on x86
wireguard: selftests: always call kernel makefile
wireguard: selftests: use virt machine on m68k
wireguard: selftests: set fake real time in init
r8169: fix accessing unset transport header
net: rose: fix UAF bug caused by rose_t0timer_expiry
usbnet: fix memory leak in error case
Revert "tls: rx: move counting TlsDecryptErrors for sync"
mptcp: update MIB_RMSUBFLOW in cmd_sf_destroy
mptcp: fix local endpoint accounting
selftests: mptcp: userspace PM support for MP_PRIO signals
mptcp: netlink: issue MP_PRIO signals from userspace PMs
mptcp: Acquire the subflow socket lock before modifying MP_PRIO flags
mptcp: Avoid acquiring PM lock for subflow priority changes
mptcp: fix locking in mptcp_nl_cmd_sf_destroy()
net/mlx5e: Fix matchall police parameters validation
net/sched: act_police: allow 'continue' action offload
net: lan966x: hardcode the number of external ports
...
These are indeed "should not happen" situations, but it turns out recent
changes made the 'task_is_stopped_or_trace()' case trigger (fix for that
exists, is pending more testing), and the BUG_ON() makes it
unnecessarily hard to actually debug for no good reason.
It's been that way for a long time, but let's make it clear: BUG_ON() is
not good for debugging, and should never be used in situations where you
could just say "this shouldn't happen, but we can continue".
Use WARN_ON_ONCE() instead to make sure it gets logged, and then just
continue running. Instead of making the system basically unusuable
because you crashed the machine while potentially holding some very core
locks (eg this function is commonly called while holding 'tasklist_lock'
for writing).
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Now that the irq_data_update_affinity helper exists, enforce its use
by returning a a const cpumask from irq_data_get_affinity_mask.
Since the previous commit already updated places that needed to call
irq_data_update_affinity, this commit updates the remaining code that
either did not modify the cpumask or immediately passed the modified
mask to irq_set_affinity.
Signed-off-by: Samuel Holland <samuel@sholland.org>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220701200056.46555-8-samuel@sholland.org
An IRQ's effective affinity can only be different from its configured
affinity if there are multiple CPUs. Make it clear that this option is
only meaningful when SMP is enabled. Most of the relevant code in
irqdesc.c is already hidden behind CONFIG_SMP anyway.
Signed-off-by: Samuel Holland <samuel@sholland.org>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20220701200056.46555-4-samuel@sholland.org
Use try_cmpxchg instead of cmpxchg (*ptr, old, new) != old in
set_nr_{and_not,if}_polling. x86 cmpxchg returns success in ZF flag,
so this change saves a compare after cmpxchg.
The definition of cmpxchg based fetch_or was changed in the
same way as atomic_fetch_##op definitions were changed
in e6790e4b5d.
Also declare these two functions as inline to ensure inlining. In the
case of set_nr_and_not_polling, the compiler (gcc) tries to outsmart
itself by constructing the boolean return value with logic operations
on the fetched value, and these extra operations enlarge the function
over the inlining threshold value.
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220629151552.6015-1-ubizjak@gmail.com
4feee7d126 previously added per-task forced idle accounting. This patch
extends this to also include cgroups.
rstat is used for cgroup accounting, except for the root, which uses
kcpustat in order to bypass the need for doing an rstat flush when
reading root stats.
Only cgroup v2 is supported. Similar to the task accounting, the cgroup
accounting requires that schedstats is enabled.
Signed-off-by: Josh Don <joshdon@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lkml.kernel.org/r/20220629211426.3329954-1-joshdon@google.com
Daniel Borkmann says:
====================
pull-request: bpf 2022-07-02
We've added 7 non-merge commits during the last 14 day(s) which contain
a total of 6 files changed, 193 insertions(+), 86 deletions(-).
The main changes are:
1) Fix clearing of page contiguity when unmapping XSK pool, from Ivan Malov.
2) Two verifier fixes around bounds data propagation, from Daniel Borkmann.
3) Fix fprobe sample module's parameter descriptions, from Masami Hiramatsu.
4) General BPF maintainer entry revamp to better scale patch reviews.
* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
bpf, selftests: Add verifier test case for jmp32's jeq/jne
bpf, selftests: Add verifier test case for imm=0,umin=0,umax=1 scalar
bpf: Fix insufficient bounds propagation from adjust_scalar_min_max_vals
bpf: Fix incorrect verifier simulation around jmp32's jeq/jne
xsk: Clear page contiguity bit when unmapping pool
bpf, docs: Better scale maintenance of BPF subsystem
fprobe, samples: Add module parameter descriptions
====================
Link: https://lore.kernel.org/r/20220701230121.10354-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When CONFIG_MODULE_UNLOAD is not selected, 'exit' is
set but never used.
It is not possible to replace the #ifdef CONFIG_MODULE_UNLOAD by
IS_ENABLED(CONFIG_MODULE_UNLOAD) because mod->exit doesn't exist
when CONFIG_MODULE_UNLOAD is not selected.
And because of the rcu_read_lock_sched() section it is not easy
to regroup everything in a single #ifdef. Let's regroup partially
and add missing #ifdef to completely opt out the use of
'exit' when CONFIG_MODULE_UNLOAD is not selected.
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
cppcheck reports the following warnings:
kernel/module/main.c:1455:26: warning: Redundant assignment of 'mod->core_layout.size' to itself. [selfAssignment]
mod->core_layout.size = strict_align(mod->core_layout.size);
^
kernel/module/main.c:1489:26: warning: Redundant assignment of 'mod->init_layout.size' to itself. [selfAssignment]
mod->init_layout.size = strict_align(mod->init_layout.size);
^
kernel/module/main.c:1493:26: warning: Redundant assignment of 'mod->init_layout.size' to itself. [selfAssignment]
mod->init_layout.size = strict_align(mod->init_layout.size);
^
kernel/module/main.c:1504:26: warning: Redundant assignment of 'mod->init_layout.size' to itself. [selfAssignment]
mod->init_layout.size = strict_align(mod->init_layout.size);
^
kernel/module/main.c:1459:26: warning: Redundant assignment of 'mod->data_layout.size' to itself. [selfAssignment]
mod->data_layout.size = strict_align(mod->data_layout.size);
^
kernel/module/main.c:1463:26: warning: Redundant assignment of 'mod->data_layout.size' to itself. [selfAssignment]
mod->data_layout.size = strict_align(mod->data_layout.size);
^
kernel/module/main.c:1467:26: warning: Redundant assignment of 'mod->data_layout.size' to itself. [selfAssignment]
mod->data_layout.size = strict_align(mod->data_layout.size);
^
This is due to strict_align() being a no-op when
CONFIG_STRICT_MODULE_RWX is not selected.
Transform strict_align() macro into an inline function. It will
allow type checking and avoid the selfAssignment warning.
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
The commit 91fb02f315 ("module: Move kallsyms support into a separate
file") changed from using strlcpy() to using strscpy() which created a
buffer overflow. That happened because:
1) an incorrect value was passed as the buffer length
2) strscpy() (unlike strlcpy()) may copy beyond the length of the
input string when copying word-by-word.
The assumption was that because it was already known that the strings
being copied would fit in the space available, it was not necessary
to correctly set the buffer length. strscpy() breaks that assumption
because although it will not touch bytes beyond the given buffer length
it may write bytes beyond the input string length when writing
word-by-word.
The result of the buffer overflow is to corrupt the symbol type
information that follows. e.g.
$ sudo cat -v /proc/kallsyms | grep '\^' | head
ffffffffc0615000 ^@ rfcomm_session_get [rfcomm]
ffffffffc061c060 ^@ session_list [rfcomm]
ffffffffc06150d0 ^@ rfcomm_send_frame [rfcomm]
ffffffffc0615130 ^@ rfcomm_make_uih [rfcomm]
ffffffffc07ed58d ^@ bnep_exit [bnep]
ffffffffc07ec000 ^@ bnep_rx_control [bnep]
ffffffffc07ec1a0 ^@ bnep_session [bnep]
ffffffffc07e7000 ^@ input_leds_event [input_leds]
ffffffffc07e9000 ^@ input_leds_handler [input_leds]
ffffffffc07e7010 ^@ input_leds_disconnect [input_leds]
Notably, the null bytes (represented above by ^@) can confuse tools.
Fix by correcting the buffer length.
Fixes: 91fb02f315 ("module: Move kallsyms support into a separate file")
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Kuee reported a corner case where the tnum becomes constant after the call
to __reg_bound_offset(), but the register's bounds are not, that is, its
min bounds are still not equal to the register's max bounds.
This in turn allows to leak pointers through turning a pointer register as
is into an unknown scalar via adjust_ptr_min_max_vals().
Before:
func#0 @0
0: R1=ctx(off=0,imm=0,umax=0,var_off=(0x0; 0x0)) R10=fp(off=0,imm=0,umax=0,var_off=(0x0; 0x0))
0: (b7) r0 = 1 ; R0_w=scalar(imm=1,umin=1,umax=1,var_off=(0x1; 0x0))
1: (b7) r3 = 0 ; R3_w=scalar(imm=0,umax=0,var_off=(0x0; 0x0))
2: (87) r3 = -r3 ; R3_w=scalar()
3: (87) r3 = -r3 ; R3_w=scalar()
4: (47) r3 |= 32767 ; R3_w=scalar(smin=-9223372036854743041,umin=32767,var_off=(0x7fff; 0xffffffffffff8000),s32_min=-2147450881)
5: (75) if r3 s>= 0x0 goto pc+1 ; R3_w=scalar(umin=9223372036854808575,var_off=(0x8000000000007fff; 0x7fffffffffff8000),s32_min=-2147450881,u32_min=32767)
6: (95) exit
from 5 to 7: R0=scalar(imm=1,umin=1,umax=1,var_off=(0x1; 0x0)) R1=ctx(off=0,imm=0,umax=0,var_off=(0x0; 0x0)) R3=scalar(umin=32767,umax=9223372036854775807,var_off=(0x7fff; 0x7fffffffffff8000),s32_min=-2147450881) R10=fp(off=0,imm=0,umax=0,var_off=(0x0; 0x0))
7: (d5) if r3 s<= 0x8000 goto pc+1 ; R3=scalar(umin=32769,umax=9223372036854775807,var_off=(0x7fff; 0x7fffffffffff8000),s32_min=-2147450881,u32_min=32767)
8: (95) exit
from 7 to 9: R0=scalar(imm=1,umin=1,umax=1,var_off=(0x1; 0x0)) R1=ctx(off=0,imm=0,umax=0,var_off=(0x0; 0x0)) R3=scalar(umin=32767,umax=32768,var_off=(0x7fff; 0x8000)) R10=fp(off=0,imm=0,umax=0,var_off=(0x0; 0x0))
9: (07) r3 += -32767 ; R3_w=scalar(imm=0,umax=1,var_off=(0x0; 0x0)) <--- [*]
10: (95) exit
What can be seen here is that R3=scalar(umin=32767,umax=32768,var_off=(0x7fff;
0x8000)) after the operation R3 += -32767 results in a 'malformed' constant, that
is, R3_w=scalar(imm=0,umax=1,var_off=(0x0; 0x0)). Intersecting with var_off has
not been done at that point via __update_reg_bounds(), which would have improved
the umax to be equal to umin.
Refactor the tnum <> min/max bounds information flow into a reg_bounds_sync()
helper and use it consistently everywhere. After the fix, bounds have been
corrected to R3_w=scalar(imm=0,umax=0,var_off=(0x0; 0x0)) and thus the register
is regarded as a 'proper' constant scalar of 0.
After:
func#0 @0
0: R1=ctx(off=0,imm=0,umax=0,var_off=(0x0; 0x0)) R10=fp(off=0,imm=0,umax=0,var_off=(0x0; 0x0))
0: (b7) r0 = 1 ; R0_w=scalar(imm=1,umin=1,umax=1,var_off=(0x1; 0x0))
1: (b7) r3 = 0 ; R3_w=scalar(imm=0,umax=0,var_off=(0x0; 0x0))
2: (87) r3 = -r3 ; R3_w=scalar()
3: (87) r3 = -r3 ; R3_w=scalar()
4: (47) r3 |= 32767 ; R3_w=scalar(smin=-9223372036854743041,umin=32767,var_off=(0x7fff; 0xffffffffffff8000),s32_min=-2147450881)
5: (75) if r3 s>= 0x0 goto pc+1 ; R3_w=scalar(umin=9223372036854808575,var_off=(0x8000000000007fff; 0x7fffffffffff8000),s32_min=-2147450881,u32_min=32767)
6: (95) exit
from 5 to 7: R0=scalar(imm=1,umin=1,umax=1,var_off=(0x1; 0x0)) R1=ctx(off=0,imm=0,umax=0,var_off=(0x0; 0x0)) R3=scalar(umin=32767,umax=9223372036854775807,var_off=(0x7fff; 0x7fffffffffff8000),s32_min=-2147450881) R10=fp(off=0,imm=0,umax=0,var_off=(0x0; 0x0))
7: (d5) if r3 s<= 0x8000 goto pc+1 ; R3=scalar(umin=32769,umax=9223372036854775807,var_off=(0x7fff; 0x7fffffffffff8000),s32_min=-2147450881,u32_min=32767)
8: (95) exit
from 7 to 9: R0=scalar(imm=1,umin=1,umax=1,var_off=(0x1; 0x0)) R1=ctx(off=0,imm=0,umax=0,var_off=(0x0; 0x0)) R3=scalar(umin=32767,umax=32768,var_off=(0x7fff; 0x8000)) R10=fp(off=0,imm=0,umax=0,var_off=(0x0; 0x0))
9: (07) r3 += -32767 ; R3_w=scalar(imm=0,umax=0,var_off=(0x0; 0x0)) <--- [*]
10: (95) exit
Fixes: b03c9f9fdc ("bpf/verifier: track signed and unsigned min/max values")
Reported-by: Kuee K1r0a <liulin063@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20220701124727.11153-2-daniel@iogearbox.net
Kuee reported a quirk in the jmp32's jeq/jne simulation, namely that the
register value does not match expectations for the fall-through path. For
example:
Before fix:
0: R1=ctx(off=0,imm=0) R10=fp0
0: (b7) r2 = 0 ; R2_w=P0
1: (b7) r6 = 563 ; R6_w=P563
2: (87) r2 = -r2 ; R2_w=Pscalar()
3: (87) r2 = -r2 ; R2_w=Pscalar()
4: (4c) w2 |= w6 ; R2_w=Pscalar(umin=563,umax=4294967295,var_off=(0x233; 0xfffffdcc),s32_min=-2147483085) R6_w=P563
5: (56) if w2 != 0x8 goto pc+1 ; R2_w=P571 <--- [*]
6: (95) exit
R0 !read_ok
After fix:
0: R1=ctx(off=0,imm=0) R10=fp0
0: (b7) r2 = 0 ; R2_w=P0
1: (b7) r6 = 563 ; R6_w=P563
2: (87) r2 = -r2 ; R2_w=Pscalar()
3: (87) r2 = -r2 ; R2_w=Pscalar()
4: (4c) w2 |= w6 ; R2_w=Pscalar(umin=563,umax=4294967295,var_off=(0x233; 0xfffffdcc),s32_min=-2147483085) R6_w=P563
5: (56) if w2 != 0x8 goto pc+1 ; R2_w=P8 <--- [*]
6: (95) exit
R0 !read_ok
As can be seen on line 5 for the branch fall-through path in R2 [*] is that
given condition w2 != 0x8 is false, verifier should conclude that r2 = 8 as
upper 32 bit are known to be zero. However, verifier incorrectly concludes
that r2 = 571 which is far off.
The problem is it only marks false{true}_reg as known in the switch for JE/NE
case, but at the end of the function, it uses {false,true}_{64,32}off to
update {false,true}_reg->var_off and they still hold the prior value of
{false,true}_reg->var_off before it got marked as known. The subsequent
__reg_combine_32_into_64() then propagates this old var_off and derives new
bounds. The information between min/max bounds on {false,true}_reg from
setting the register to known const combined with the {false,true}_reg->var_off
based on the old information then derives wrong register data.
Fix it by detangling the BPF_JEQ/BPF_JNE cases and updating relevant
{false,true}_{64,32}off tnums along with the register marking to known
constant.
Fixes: 3f50f132d8 ("bpf: Verifier, do explicit ALU32 bounds tracking")
Reported-by: Kuee K1r0a <liulin063@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20220701124727.11153-1-daniel@iogearbox.net
find_energy_efficient_cpu() integrates a margin to protect tasks from
bouncing back and forth from a CPU to another. This margin is set as being
6% of the total current energy estimated on the system. This however does
not work for two reasons:
1. The energy estimation is not a good absolute value:
compute_energy() used in feec() is a good estimation for task placement as
it allows to compare the energy with and without a task. The computed
delta will give a good overview of the cost for a certain task placement.
It, however, doesn't work as an absolute estimation for the total energy
of the system. First it adds the contribution to idle CPUs into the
energy, second it mixes util_avg with util_est values. util_avg contains
the near history for a CPU usage, it doesn't tell at all what the current
utilization is. A system that has been quite busy in the near past will
hold a very high energy and then a high margin preventing any task
migration to a lower capacity CPU, wasting energy. It even creates a
negative feedback loop: by holding the tasks on a less efficient CPU, the
margin contributes in keeping the energy high.
2. The margin handicaps small tasks:
On a system where the workload is composed mostly of small tasks (which is
often the case on Android), the overall energy will be high enough to
create a margin none of those tasks can cross. On a Pixel4, a small
utilization of 5% on all the CPUs creates a global estimated energy of 140
joules, as per the Energy Model declaration of that same device. This
means, after applying the 6% margin that any migration must save more than
8 joules to happen. No task with a utilization lower than 40 would then be
able to migrate away from the biggest CPU of the system.
The 6% of the overall system energy was brought by the following patch:
(eb92692b25 sched/fair: Speed-up energy-aware wake-ups)
It was previously 6% of the prev_cpu energy. Also, the following one
made this margin value conditional on the clusters where the task fits:
(8d4c97c105 sched/fair: Only compute base_energy_pd if necessary)
We could simply revert that margin change to what it was, but the original
version didn't have strong grounds neither and as demonstrated in (1.) the
estimated energy isn't a good absolute value. Instead, removing it
completely. It is indeed, made possible by recent changes that improved
energy estimation comparison fairness (sched/fair: Remove task_util from
effective utilization in feec()) (PM: EM: Increase energy calculation
precision) and task utilization stabilization (sched/fair: Decay task
util_avg during migration)
Without a margin, we could have feared bouncing between CPUs. But running
LISA's eas_behaviour test coverage on three different platforms (Hikey960,
RB-5 and DB-845) showed no issue.
Removing the energy margin enables more energy-optimized placements for a
more energy efficient system.
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lkml.kernel.org/r/20220621090414.433602-8-vdonnefort@google.com
The energy estimation in find_energy_efficient_cpu() (feec()) relies on
the computation of the effective utilization for each CPU of a perf domain
(PD). This effective utilization is then used as an estimation of the busy
time for this pd. The function effective_cpu_util() which gives this value,
scales the utilization relative to IRQ pressure on the CPU to take into
account that the IRQ time is hidden from the task clock. The IRQ scaling is
as follow:
effective_cpu_util = irq + (cpu_cap - irq)/cpu_cap * util
Where util is the sum of CFS/RT/DL utilization, cpu_cap the capacity of
the CPU and irq the IRQ avg time.
If now we take as an example a task placement which doesn't raise the OPP
on the candidate CPU, we can write the energy delta as:
delta = OPPcost/cpu_cap * (effective_cpu_util(cpu_util + task_util) -
effective_cpu_util(cpu_util))
= OPPcost/cpu_cap * (cpu_cap - irq)/cpu_cap * task_util
We end-up with an energy delta depending on the IRQ avg time, which is a
problem: first the time spent on IRQs by a CPU has no effect on the
additional energy that would be consumed by a task. Second, we don't want
to favour a CPU with a higher IRQ avg time value.
Nonetheless, we need to take the IRQ avg time into account. If a task
placement raises the PD's frequency, it will increase the energy cost for
the entire time where the CPU is busy. A solution is to only use
effective_cpu_util() with the CPU contribution part. The task contribution
is added separately and scaled according to prev_cpu's IRQ time.
No change for the FREQUENCY_UTIL component of the energy estimation. We
still want to get the actual frequency that would be selected after the
task placement.
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lkml.kernel.org/r/20220621090414.433602-7-vdonnefort@google.com
The Perf Domain (PD) cpumask (struct em_perf_domain.cpus) stays
invariant after Energy Model creation, i.e. it is not updated after
CPU hotplug operations.
That's why the PD mask is used in conjunction with the cpu_online_mask
(or Sched Domain cpumask). Thereby the cpu_online_mask is fetched
multiple times (in compute_energy()) during a run-queue selection
for a task.
cpu_online_mask may change during this time which can lead to wrong
energy calculations.
To be able to avoid this, use the select_rq_mask per-cpu cpumask to
create a cpumask out of PD cpumask and cpu_online_mask and pass it
through the function calls of the EAS run-queue selection path.
The PD cpumask for max_spare_cap_cpu/compute_prev_delta selection
(find_energy_efficient_cpu()) is now ANDed not only with the SD mask
but also with the cpu_online_mask. This is fine since this cpumask
has to be in syc with the one used for energy computation
(compute_energy()).
An exclusive cpuset setup with at least one asymmetric CPU capacity
island (hence the additional AND with the SD cpumask) is the obvious
exception here.
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lkml.kernel.org/r/20220621090414.433602-6-vdonnefort@google.com
On 21/06/2022 11:04, Vincent Donnefort wrote:
> From: Dietmar Eggemann <dietmar.eggemann@arm.com>
https://lkml.kernel.org/r/202206221253.ZVyGQvPX-lkp@intel.com discovered
that this patch doesn't build anymore (on tip sched/core or linux-next)
because of commit f5b2eeb499 ("sched/fair: Consider CPU affinity when
allowing NUMA imbalance in find_idlest_group()").
New version of [PATCH v11 4/7] sched/fair: Rename select_idle_mask to
select_rq_mask below.
-- >8 --
Decouple the name of the per-cpu cpumask select_idle_mask from its usage
in select_idle_[cpu/capacity]() of the CFS run-queue selection
(select_task_rq_fair()).
This is to support the reuse of this cpumask in the Energy Aware
Scheduling (EAS) path (find_energy_efficient_cpu()) of the CFS run-queue
selection.
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lkml.kernel.org/r/250691c7-0e2b-05ab-bedf-b245c11d9400@arm.com
effective_cpu_util() already has a `int cpu' parameter which allows to
retrieve the CPU capacity scale factor (or maximum CPU capacity) inside
this function via an arch_scale_cpu_capacity(cpu).
A lot of code calling effective_cpu_util() (or the shim
sched_cpu_util()) needs the maximum CPU capacity, i.e. it will call
arch_scale_cpu_capacity() already.
But not having to pass it into effective_cpu_util() will make the EAS
wake-up code easier, especially when the maximum CPU capacity reduced
by the thermal pressure is passed through the EAS wake-up functions.
Due to the asymmetric CPU capacity support of arm/arm64 architectures,
arch_scale_cpu_capacity(int cpu) is a per-CPU variable read access via
per_cpu(cpu_scale, cpu) on such a system.
On all other architectures it is a a compile-time constant
(SCHED_CAPACITY_SCALE).
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lkml.kernel.org/r/20220621090414.433602-4-vdonnefort@google.com
Before being migrated to a new CPU, a task sees its PELT values
synchronized with rq last_update_time. Once done, that same task will also
have its sched_avg last_update_time reset. This means the time between
the migration and the last clock update will not be accounted for in
util_avg and a discontinuity will appear. This issue is amplified by the
PELT clock scaling. It takes currently one tick after the CPU being idle
to let clock_pelt catching up clock_task.
This is especially problematic for asymmetric CPU capacity systems which
need stable util_avg signals for task placement and energy estimation.
Ideally, this problem would be solved by updating the runqueue clocks
before the migration. But that would require taking the runqueue lock
which is quite expensive [1]. Instead estimate the missing time and update
the task util_avg with that value.
To that end, we need sched_clock_cpu() but it is a costly function. Limit
the usage to the case where the source CPU is idle as we know this is when
the clock is having the biggest risk of being outdated.
See comment in migrate_se_pelt_lag() for more details about how the PELT
value is estimated. Notice though this estimation doesn't take into account
IRQ and Paravirt time.
[1] https://lkml.kernel.org/r/20190709115759.10451-1-chris.redpath@arm.com
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lkml.kernel.org/r/20220621090414.433602-3-vdonnefort@google.com
Introducing macro helpers u64_u32_{store,load}() to factorize lockless
accesses to u64 variables for 32-bits architectures.
Users are for now cfs_rq.min_vruntime and sched_avg.last_update_time. To
accommodate the later where the copy lies outside of the structure
(cfs_rq.last_udpate_time_copy instead of sched_avg.last_update_time_copy),
use the _copy() version of those helpers.
Those new helpers encapsulate smp_rmb() and smp_wmb() synchronization and
therefore, have a small penalty for 32-bits machines in set_task_rq_fair()
and init_cfs_rq().
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://lkml.kernel.org/r/20220621090414.433602-2-vdonnefort@google.com
