The functions get_online_cpus() and put_online_cpus() have been
deprecated during the CPU hotplug rework. They map directly to
cpus_read_lock() and cpus_read_unlock().
Replace deprecated CPU-hotplug functions with the official version.
The behavior remains unchanged.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20210803141621.780504-33-bigeasy@linutronix.de
The functions get_online_cpus() and put_online_cpus() have been
deprecated during the CPU hotplug rework. They map directly to
cpus_read_lock() and cpus_read_unlock().
Replace deprecated CPU-hotplug functions with the official version.
The behavior remains unchanged.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20210803141621.780504-26-bigeasy@linutronix.de
Fix kernel-doc warnings in kernel/bpf/core.c (found by scripts/kernel-doc
and W=1 builds). That is, correct a function name in a comment and add
return descriptions for 2 functions.
Fixes these kernel-doc warnings:
kernel/bpf/core.c:1372: warning: expecting prototype for __bpf_prog_run(). Prototype was for ___bpf_prog_run() instead
kernel/bpf/core.c:1372: warning: No description found for return value of '___bpf_prog_run'
kernel/bpf/core.c:1883: warning: No description found for return value of 'bpf_prog_select_runtime'
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210809215229.7556-1-rdunlap@infradead.org
By adding the pidfd_create() declaration to linux/pid.h, we
effectively expose this function to the rest of the kernel. In order
to avoid any unintended behavior, or set false expectations upon this
function, ensure that constraints are forced upon each of the passed
parameters. This includes the checking of whether the passed struct
pid is a thread-group leader as pidfd creation is currently limited to
such pid types.
Link: https://lore.kernel.org/r/2e9b91c2d529d52a003b8b86c45f866153be9eb5.1628398044.git.repnop@google.com
Signed-off-by: Matthew Bobrowski <repnop@google.com>
Acked-by: Christian Brauner <christian.brauner@ubuntu.com>
Signed-off-by: Jan Kara <jack@suse.cz>
X86 IO/APIC and MSI interrupts (when used without interrupts remapping)
require that the affinity setup on startup is done before the interrupt is
enabled for the first time as the non-remapped operation mode cannot safely
migrate enabled interrupts from arbitrary contexts. Provide a new irq chip
flag which allows affected hardware to request this.
This has to be opt-in because there have been reports in the past that some
interrupt chips cannot handle affinity setting before startup.
Fixes: 1840475676 ("genirq: Expose default irq affinity mask (take 3)")
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20210729222542.779791738@linutronix.de
Commit b910eaaaa4 ("bpf: Fix NULL pointer dereference in bpf_get_local_storage()
helper") fixed a bug for bpf_get_local_storage() helper so different tasks
won't mess up with each other's percpu local storage.
The percpu data contains 8 slots so it can hold up to 8 contexts (same or
different tasks), for 8 different program runs, at the same time. This in
general is sufficient. But our internal testing showed the following warning
multiple times:
[...]
warning: WARNING: CPU: 13 PID: 41661 at include/linux/bpf-cgroup.h:193
__cgroup_bpf_run_filter_sock_ops+0x13e/0x180
RIP: 0010:__cgroup_bpf_run_filter_sock_ops+0x13e/0x180
<IRQ>
tcp_call_bpf.constprop.99+0x93/0xc0
tcp_conn_request+0x41e/0xa50
? tcp_rcv_state_process+0x203/0xe00
tcp_rcv_state_process+0x203/0xe00
? sk_filter_trim_cap+0xbc/0x210
? tcp_v6_inbound_md5_hash.constprop.41+0x44/0x160
tcp_v6_do_rcv+0x181/0x3e0
tcp_v6_rcv+0xc65/0xcb0
ip6_protocol_deliver_rcu+0xbd/0x450
ip6_input_finish+0x11/0x20
ip6_input+0xb5/0xc0
ip6_sublist_rcv_finish+0x37/0x50
ip6_sublist_rcv+0x1dc/0x270
ipv6_list_rcv+0x113/0x140
__netif_receive_skb_list_core+0x1a0/0x210
netif_receive_skb_list_internal+0x186/0x2a0
gro_normal_list.part.170+0x19/0x40
napi_complete_done+0x65/0x150
mlx5e_napi_poll+0x1ae/0x680
__napi_poll+0x25/0x120
net_rx_action+0x11e/0x280
__do_softirq+0xbb/0x271
irq_exit_rcu+0x97/0xa0
common_interrupt+0x7f/0xa0
</IRQ>
asm_common_interrupt+0x1e/0x40
RIP: 0010:bpf_prog_1835a9241238291a_tw_egress+0x5/0xbac
? __cgroup_bpf_run_filter_skb+0x378/0x4e0
? do_softirq+0x34/0x70
? ip6_finish_output2+0x266/0x590
? ip6_finish_output+0x66/0xa0
? ip6_output+0x6c/0x130
? ip6_xmit+0x279/0x550
? ip6_dst_check+0x61/0xd0
[...]
Using drgn [0] to dump the percpu buffer contents showed that on this CPU
slot 0 is still available, but slots 1-7 are occupied and those tasks in
slots 1-7 mostly don't exist any more. So we might have issues in
bpf_cgroup_storage_unset().
Further debugging confirmed that there is a bug in bpf_cgroup_storage_unset().
Currently, it tries to unset "current" slot with searching from the start.
So the following sequence is possible:
1. A task is running and claims slot 0
2. Running BPF program is done, and it checked slot 0 has the "task"
and ready to reset it to NULL (not yet).
3. An interrupt happens, another BPF program runs and it claims slot 1
with the *same* task.
4. The unset() in interrupt context releases slot 0 since it matches "task".
5. Interrupt is done, the task in process context reset slot 0.
At the end, slot 1 is not reset and the same process can continue to occupy
slots 2-7 and finally, when the above step 1-5 is repeated again, step 3 BPF
program won't be able to claim an empty slot and a warning will be issued.
To fix the issue, for unset() function, we should traverse from the last slot
to the first. This way, the above issue can be avoided.
The same reverse traversal should also be done in bpf_get_local_storage() helper
itself. Otherwise, incorrect local storage may be returned to BPF program.
[0] https://github.com/osandov/drgn
Fixes: b910eaaaa4 ("bpf: Fix NULL pointer dereference in bpf_get_local_storage() helper")
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210810010413.1976277-1-yhs@fb.com
Back then, commit 96ae522795 ("bpf: Add bpf_probe_write_user BPF helper
to be called in tracers") added the bpf_probe_write_user() helper in order
to allow to override user space memory. Its original goal was to have a
facility to "debug, divert, and manipulate execution of semi-cooperative
processes" under CAP_SYS_ADMIN. Write to kernel was explicitly disallowed
since it would otherwise tamper with its integrity.
One use case was shown in cf9b1199de ("samples/bpf: Add test/example of
using bpf_probe_write_user bpf helper") where the program DNATs traffic
at the time of connect(2) syscall, meaning, it rewrites the arguments to
a syscall while they're still in userspace, and before the syscall has a
chance to copy the argument into kernel space. These days we have better
mechanisms in BPF for achieving the same (e.g. for load-balancers), but
without having to write to userspace memory.
Of course the bpf_probe_write_user() helper can also be used to abuse
many other things for both good or bad purpose. Outside of BPF, there is
a similar mechanism for ptrace(2) such as PTRACE_PEEK{TEXT,DATA} and
PTRACE_POKE{TEXT,DATA}, but would likely require some more effort.
Commit 96ae522795 explicitly dedicated the helper for experimentation
purpose only. Thus, move the helper's availability behind a newly added
LOCKDOWN_BPF_WRITE_USER lockdown knob so that the helper is disabled under
the "integrity" mode. More fine-grained control can be implemented also
from LSM side with this change.
Fixes: 96ae522795 ("bpf: Add bpf_probe_write_user BPF helper to be called in tracers")
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Pull cgroup fix from Tejun Heo:
"One commit to fix a possible A-A deadlock around u64_stats_sync on
32bit machines caused by updating it without disabling IRQ when it may
be read from IRQ context"
* 'for-5.14-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
cgroup: rstat: fix A-A deadlock on 32bit around u64_stats_sync
The functions get_online_cpus() and put_online_cpus() have been
deprecated during the CPU hotplug rework. They map directly to
cpus_read_lock() and cpus_read_unlock().
Replace deprecated CPU-hotplug functions with the official version.
The behavior remains unchanged.
Cc: Zefan Li <lizefan.x@bytedance.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: cgroups@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Tejun Heo <tj@kernel.org>
The cpuset fields that manage partition root state do not strictly
follow the cpuset locking rule that update to cpuset has to be done
with both the callback_lock and cpuset_mutex held. This is now fixed
by making sure that the locking rule is upheld.
Fixes: 3881b86128 ("cpuset: Add an error state to cpuset.sched.partition")
Fixes: 4b842da276 ("cpuset: Make CPU hotplug work with partition")
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The functions get_online_cpus() and put_online_cpus() have been
deprecated during the CPU hotplug rework. They map directly to
cpus_read_lock() and cpus_read_unlock().
Replace deprecated CPU-hotplug functions with the official version.
The behavior remains unchanged.
Cc: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Tejun Heo <tj@kernel.org>
Replace ida_simple_get() with ida_alloc() and ida_simple_remove() with
ida_free(), the latter is more concise and intuitive.
In addition, if ida_alloc() fails, NULL is returned directly. This
eliminates unnecessary initialization of two local variables and an 'if'
judgment.
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Rename LOCKDOWN_BPF_READ into LOCKDOWN_BPF_READ_KERNEL so we have naming
more consistent with a LOCKDOWN_BPF_WRITE_USER option that we are adding.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Now that all the .map_sg operations have been converted to returning
proper error codes, drop the code to handle a zero return value,
add a warning if a zero is returned.
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
The .map_sg() op now expects an error code instead of zero on failure.
The only errno to return is -EINVAL in the case when DMA is not
supported.
Signed-off-by: Martin Oliveira <martin.oliveira@eideticom.com>
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Now that the map_sg() op expects error codes instead of return zero on
error, convert dma_direct_map_sg() to return an error code. Per the
documentation for dma_map_sgtable(), -EIO is returned due to an
DMA_MAPPING_ERROR with unknown cause.
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Allow dma_map_sgtable() to pass errors from the map_sg() ops. This
will be required for returning appropriate error codes when mapping
P2PDMA memory.
Introduce __dma_map_sg_attrs() which will return the raw error code
from the map_sg operation (whether it be negative or zero). Then add a
dma_map_sg_attrs() wrapper to convert any negative errors to zero to
satisfy the existing calling convention.
dma_map_sgtable() defines three error codes that .map_sg implementations
are allowed to return: -EINVAL, -ENOMEM and -EIO. The latter of which
is a generic return for cases that are passing DMA_MAPPING_ERROR
through.
dma_map_sgtable() will convert a zero error return for old map_sg() ops
into a -EIO return and return any negative errors as reported.
This allows map_sg implementations to start returning multiple
negative error codes. Legacy map_sg implementations can continue
to return zero until they are all converted.
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Due to link order, dma_debug_init is called before debugfs has a chance
to initialize (via debugfs_init which also happens in the core initcall
stage), so the directories for dma-debug are never created.
Decouple dma_debug_fs_init from dma_debug_init and defer its init until
core_initcall_sync (after debugfs has been initialized) while letting
dma-debug initialization occur as soon as possible to catch any early
mappings, as suggested in [1].
[1] https://lore.kernel.org/linux-iommu/YIgGa6yF%2Fadg8OSN@kroah.com/
Fixes: 15b28bbcd5 ("dma-debug: move initialization to common code")
Signed-off-by: Anthony Iliopoulos <ailiop@suse.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
There is already a memory_intersects() helper in sections.h,
use memory_intersects() directly instead of private overlap().
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Pull timer fix from Thomas Gleixner:
"A single timer fix:
- Prevent a memory ordering issue in the timer expiry code which
makes it possible to observe falsely that the callback has been
executed already while that's not the case, which violates the
guarantee of del_timer_sync()"
* tag 'timers-urgent-2021-08-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
timers: Move clearing of base::timer_running under base:: Lock
Pull scheduler fix from Thomas Gleixner:
"A single scheduler fix:
- Prevent a double enqueue caused by rt_effective_prio() being
invoked twice in __sched_setscheduler()"
* tag 'sched-urgent-2021-08-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/rt: Fix double enqueue caused by rt_effective_prio
Pull perf fixes from Thomas Gleixner:
"A set of perf fixes:
- Correct the permission checks for perf event which send SIGTRAP to
a different process and clean up that code to be more readable.
- Prevent an out of bound MSR access in the x86 perf code which
happened due to an incomplete limiting to the actually available
hardware counters.
- Prevent access to the AMD64_EVENTSEL_HOSTONLY bit when running
inside a guest.
- Handle small core counter re-enabling correctly by issuing an ACK
right before reenabling it to prevent a stale PEBS record being
kept around"
* tag 'perf-urgent-2021-08-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86/intel: Apply mid ACK for small core
perf/x86/amd: Don't touch the AMD64_EVENTSEL_HOSTONLY bit inside the guest
perf/x86: Fix out of bound MSR access
perf: Refactor permissions check into perf_check_permission()
perf: Fix required permissions if sigtrap is requested
Daniel Borkmann says:
====================
pull-request: bpf 2021-08-07
The following pull-request contains BPF updates for your *net* tree.
We've added 4 non-merge commits during the last 9 day(s) which contain
a total of 4 files changed, 8 insertions(+), 7 deletions(-).
The main changes are:
1) Fix integer overflow in htab's lookup + delete batch op, from Tatsuhiko Yasumatsu.
2) Fix invalid fd 0 close in libbpf if BTF parsing failed, from Daniel Xu.
3) Fix libbpf feature probe for BPF_PROG_TYPE_CGROUP_SOCKOPT, from Robin Gögge.
4) Fix minor libbpf doc warning regarding code-block language, from Randy Dunlap.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
In __htab_map_lookup_and_delete_batch(), hash buckets are iterated
over to count the number of elements in each bucket (bucket_size).
If bucket_size is large enough, the multiplication to calculate
kvmalloc() size could overflow, resulting in out-of-bounds write
as reported by KASAN:
[...]
[ 104.986052] BUG: KASAN: vmalloc-out-of-bounds in __htab_map_lookup_and_delete_batch+0x5ce/0xb60
[ 104.986489] Write of size 4194224 at addr ffffc9010503be70 by task crash/112
[ 104.986889]
[ 104.987193] CPU: 0 PID: 112 Comm: crash Not tainted 5.14.0-rc4 #13
[ 104.987552] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014
[ 104.988104] Call Trace:
[ 104.988410] dump_stack_lvl+0x34/0x44
[ 104.988706] print_address_description.constprop.0+0x21/0x140
[ 104.988991] ? __htab_map_lookup_and_delete_batch+0x5ce/0xb60
[ 104.989327] ? __htab_map_lookup_and_delete_batch+0x5ce/0xb60
[ 104.989622] kasan_report.cold+0x7f/0x11b
[ 104.989881] ? __htab_map_lookup_and_delete_batch+0x5ce/0xb60
[ 104.990239] kasan_check_range+0x17c/0x1e0
[ 104.990467] memcpy+0x39/0x60
[ 104.990670] __htab_map_lookup_and_delete_batch+0x5ce/0xb60
[ 104.990982] ? __wake_up_common+0x4d/0x230
[ 104.991256] ? htab_of_map_free+0x130/0x130
[ 104.991541] bpf_map_do_batch+0x1fb/0x220
[...]
In hashtable, if the elements' keys have the same jhash() value, the
elements will be put into the same bucket. By putting a lot of elements
into a single bucket, the value of bucket_size can be increased to
trigger the integer overflow.
Triggering the overflow is possible for both callers with CAP_SYS_ADMIN
and callers without CAP_SYS_ADMIN.
It will be trivial for a caller with CAP_SYS_ADMIN to intentionally
reach this overflow by enabling BPF_F_ZERO_SEED. As this flag will set
the random seed passed to jhash() to 0, it will be easy for the caller
to prepare keys which will be hashed into the same value, and thus put
all the elements into the same bucket.
If the caller does not have CAP_SYS_ADMIN, BPF_F_ZERO_SEED cannot be
used. However, it will be still technically possible to trigger the
overflow, by guessing the random seed value passed to jhash() (32bit)
and repeating the attempt to trigger the overflow. In this case,
the probability to trigger the overflow will be low and will take
a very long time.
Fix the integer overflow by calling kvmalloc_array() instead of
kvmalloc() to allocate memory.
Fixes: 057996380a ("bpf: Add batch ops to all htab bpf map")
Signed-off-by: Tatsuhiko Yasumatsu <th.yasumatsu@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210806150419.109658-1-th.yasumatsu@gmail.com
The WARN_ON_ONCE() invocation within the CONFIG_PREEMPT=y version of
rcu_note_context_switch() triggers when there is a voluntary context
switch in an RCU read-side critical section, but there is quite a gap
between the output of that WARN_ON_ONCE() and this RCU-usage error.
This commit therefore converts the WARN_ON_ONCE() to a WARN_ONCE()
that explicitly describes the problem in its message.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
There are a few remaining locations in kernel/rcu that still use
"&per_cpu()". This commit replaces them with "per_cpu_ptr(&)", and does
not introduce any functional change.
Reviewed-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Reviewed-by: Neeraj Upadhyay <neeraju@codeaurora.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Liu Song <liu.song11@zte.com.cn>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Within rcu_gp_fqs_loop(), the "ret" local variable is set to the
return value from swait_event_idle_timeout_exclusive(), but "ret" is
unconditionally overwritten later in the code. This commit therefore
removes this useless assignment.
Signed-off-by: Liu Song <liu.song11@zte.com.cn>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit marks the accesses in tree_stall.h so as to both avoid
undesirable compiler optimizations and to keep KCSAN focused on the
accesses of the core algorithm.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The kbuild test project found an oversized stack frame in rcu_gp_kthread()
for some kernel configurations. This oversizing was due to a very large
amount of inlining, which is unnecessary due to the fact that this code
executes infrequently. This commit therefore marks rcu_gp_init() and
rcu_gp_fqs_loop noinline_for_stack to conserve stack space.
Reported-by: kernel test robot <lkp@intel.com>
Tested-by: Rong Chen <rong.a.chen@intel.com>
[ paulmck: noinline_for_stack per Nathan Chancellor. ]
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Accesses to ->qsmask are normally protected by ->lock, but there is an
exception in the diagnostic code in rcu_check_boost_fail(). This commit
therefore applies data_race() to this access to avoid KCSAN complaining
about the C-language writes protected by ->lock.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
This commit marks some interrupt-induced read-side data races in
__srcu_read_lock(), __srcu_read_unlock(), and srcu_torture_stats_print().
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Systems with low-bandwidth consoles can have very large printk()
latencies, and on such systems it makes no sense to have the next RCU CPU
stall warning message start output before the prior message completed.
This commit therefore sets the time of the next stall only after the
prints have completed. While printing, the time of the next stall
message is set to ULONG_MAX/2 jiffies into the future.
Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
rcu_cpu_stall_reset() is one of the functions virtual CPUs
execute during VM resume in order to handle jiffies skew
that can trigger false positive stall warnings. Paul has
pointed out that this approach is problematic because
rcu_cpu_stall_reset() disables RCU grace period stall-detection
virtually forever, while in fact it can just restart the
stall-detection timeout.
Suggested-by: "Paul E. McKenney" <paulmck@kernel.org>
Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Signed-off-by: Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The soft watchdog timer function checks if a virtual machine
was suspended and hence what looks like a lockup in fact
is a false positive.
This is what kvm_check_and_clear_guest_paused() does: it
tests guest PVCLOCK_GUEST_STOPPED (which is set by the host)
and if it's set then we need to touch all watchdogs and bail
out.
Watchdog timer function runs from IRQ, so PVCLOCK_GUEST_STOPPED
check works fine.
There is, however, one more watchdog that runs from IRQ, so
watchdog timer fn races with it, and that watchdog is not aware
of PVCLOCK_GUEST_STOPPED - RCU stall detector.
apic_timer_interrupt()
smp_apic_timer_interrupt()
hrtimer_interrupt()
__hrtimer_run_queues()
tick_sched_timer()
tick_sched_handle()
update_process_times()
rcu_sched_clock_irq()
This triggers RCU stalls on our devices during VM resume.
If tick_sched_handle()->rcu_sched_clock_irq() runs on a VCPU
before watchdog_timer_fn()->kvm_check_and_clear_guest_paused()
then there is nothing on this VCPU that touches watchdogs and
RCU reads stale gp stall timestamp and new jiffies value, which
makes it think that RCU has stalled.
Make RCU stall watchdog aware of PVCLOCK_GUEST_STOPPED and
don't report RCU stalls when we resume the VM.
Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Signed-off-by: Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
KCSAN flags accesses to ->rcu_read_lock_nesting as data races, but
in the past, the overhead of marked accesses was excessive. However,
that was long ago, and much has changed since then, both in terms of
hardware and of compilers. Here is data taken on an eight-core laptop
using Intel(R) Core(TM) i9-10885H CPU @ 2.40GHz with a kernel built
using gcc version 9.3.0, with all data in nanoseconds.
Unmarked accesses (status quo), measured by three refscale runs:
Minimum reader duration: 3.286 2.851 3.395
Median reader duration: 3.698 3.531 3.4695
Maximum reader duration: 4.481 5.215 5.157
Marked accesses, also measured by three refscale runs:
Minimum reader duration: 3.501 3.677 3.580
Median reader duration: 4.053 3.723 3.895
Maximum reader duration: 7.307 4.999 5.511
This focused microbenhmark shows only sub-nanosecond differences which
are unlikely to be visible at the system level. This commit therefore
marks data-racing accesses to ->rcu_read_lock_nesting.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Accesses to the rcu_data structure's ->dynticks field have always been
fully ordered because it was not possible to prove that weaker ordering
was safe. However, with the removal of the rcu_eqs_special_set() function
and the advent of the Linux-kernel memory model, it is now easy to show
that two of the four original full memory barriers can be weakened to
acquire and release operations. The remaining pair must remain full
memory barriers. This change makes the memory ordering requirements
more evident, and it might well also speed up the to-idle and from-idle
fastpaths on some architectures.
The following litmus test, adapted from one supplied off-list by Frederic
Weisbecker, models the RCU grace-period kthread detecting an idle CPU
that is concurrently transitioning to non-idle:
C dynticks-from-idle
{
DYNTICKS=0; (* Initially idle. *)
}
P0(int *X, int *DYNTICKS)
{
int dynticks;
int x;
// Idle.
dynticks = READ_ONCE(*DYNTICKS);
smp_store_release(DYNTICKS, dynticks + 1);
smp_mb();
// Now non-idle
x = READ_ONCE(*X);
}
P1(int *X, int *DYNTICKS)
{
int dynticks;
WRITE_ONCE(*X, 1);
smp_mb();
dynticks = smp_load_acquire(DYNTICKS);
}
exists (1:dynticks=0 /\ 0:x=1)
Running "herd7 -conf linux-kernel.cfg dynticks-from-idle.litmus" verifies
this transition, namely, showing that if the RCU grace-period kthread (P1)
sees another CPU as idle (P0), then any memory access prior to the start
of the grace period (P1's write to X) will be seen by any RCU read-side
critical section following the to-non-idle transition (P0's read from X).
This is a straightforward use of full memory barriers to force ordering
in a store-buffering (SB) litmus test.
The following litmus test, also adapted from the one supplied off-list
by Frederic Weisbecker, models the RCU grace-period kthread detecting
a non-idle CPU that is concurrently transitioning to idle:
C dynticks-into-idle
{
DYNTICKS=1; (* Initially non-idle. *)
}
P0(int *X, int *DYNTICKS)
{
int dynticks;
// Non-idle.
WRITE_ONCE(*X, 1);
dynticks = READ_ONCE(*DYNTICKS);
smp_store_release(DYNTICKS, dynticks + 1);
smp_mb();
// Now idle.
}
P1(int *X, int *DYNTICKS)
{
int x;
int dynticks;
smp_mb();
dynticks = smp_load_acquire(DYNTICKS);
x = READ_ONCE(*X);
}
exists (1:dynticks=2 /\ 1:x=0)
Running "herd7 -conf linux-kernel.cfg dynticks-into-idle.litmus" verifies
this transition, namely, showing that if the RCU grace-period kthread
(P1) sees another CPU as newly idle (P0), then any pre-idle memory access
(P0's write to X) will be seen by any code following the grace period
(P1's read from X). This is a simple release-acquire pair forcing
ordering in a message-passing (MP) litmus test.
Of course, if the grace-period kthread detects the CPU as non-idle,
it will refrain from reporting a quiescent state on behalf of that CPU,
so there are no ordering requirements from the grace-period kthread in
that case. However, other subsystems call rcu_is_idle_cpu() to check
for CPUs being non-idle from an RCU perspective. That case is also
verified by the above litmus tests with the proviso that the sense of
the low-order bit of the DYNTICKS counter be inverted.
Unfortunately, on x86 smp_mb() is as expensive as a cache-local atomic
increment. This commit therefore weakens only the read from ->dynticks.
However, the updates are abstracted into a rcu_dynticks_inc() function
to ease any future changes that might be needed.
[ paulmck: Apply Linus Torvalds feedback. ]
Link: https://lore.kernel.org/lkml/20210721202127.2129660-4-paulmck@kernel.org/
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
If rcu_print_task_stall() is invoked on an rcu_node structure that does
not contain any tasks blocking the current grace period, it takes an
early exit that fails to release that rcu_node structure's lock. This
results in a self-deadlock, which is detected by lockdep.
To reproduce this bug:
tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration 3 --trust-make --configs "TREE03" --kconfig "CONFIG_PROVE_LOCKING=y" --bootargs "rcutorture.stall_cpu=30 rcutorture.stall_cpu_block=1 rcutorture.fwd_progress=0 rcutorture.test_boost=0"
This will also result in other complaints, including RCU's scheduler
hook complaining about blocking rather than preemption and an rcutorture
writer stall.
Only a partial RCU CPU stall warning message will be printed because of
the self-deadlock.
This commit therefore releases the lock on the rcu_print_task_stall()
function's early exit path.
Fixes: c583bcb8f5 ("rcu: Don't invoke try_invoke_on_locked_down_task() with irqs disabled")
Tested-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Yanfei Xu <yanfei.xu@windriver.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
The for loop in rcu_print_task_stall() always omits ts[0], which points
to the first task blocking the stalled grace period. This in turn fails
to count this first task, which means that ndetected will be equal to
zero when all CPUs have passed through their quiescent states and only
one task is blocking the stalled grace period. This zero value for
ndetected will in turn result in an incorrect "All QSes seen" message:
rcu: INFO: rcu_preempt detected stalls on CPUs/tasks:
rcu: Tasks blocked on level-1 rcu_node (CPUs 12-23):
(detected by 15, t=6504 jiffies, g=164777, q=9011209)
rcu: All QSes seen, last rcu_preempt kthread activity 1 (4295252379-4295252378), jiffies_till_next_fqs=1, root ->qsmask 0x2
BUG: sleeping function called from invalid context at include/linux/uaccess.h:156
in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 70613, name: msgstress04
INFO: lockdep is turned off.
Preemption disabled at:
[<ffff8000104031a4>] create_object.isra.0+0x204/0x4b0
CPU: 15 PID: 70613 Comm: msgstress04 Kdump: loaded Not tainted
5.12.2-yoctodev-standard #1
Hardware name: Marvell OcteonTX CN96XX board (DT)
Call trace:
dump_backtrace+0x0/0x2cc
show_stack+0x24/0x30
dump_stack+0x110/0x188
___might_sleep+0x214/0x2d0
__might_sleep+0x7c/0xe0
This commit therefore fixes the loop to include ts[0].
Fixes: c583bcb8f5 ("rcu: Don't invoke try_invoke_on_locked_down_task() with irqs disabled")
Tested-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Yanfei Xu <yanfei.xu@windriver.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Pull tracing fixes from Steven Rostedt:
"Fix tracepoint race between static_call and callback data
As callbacks to a tracepoint are paired with the data that is passed
in when the callback is registered to the tracepoint, it must have
that data passed to the callback when the tracepoint is triggered,
else bad things will happen. To keep the two together, they are both
assigned to a tracepoint structure and added to an array. The
tracepoint call site will dereference the structure (via RCU) and call
the callback in that structure along with the data in that structure.
This keeps the callback and data tightly coupled.
Because of the overhead that retpolines have on tracepoint callbacks,
if there's only one callback attached to a tracepoint (a common case),
then it is called via a static call (code modified to do a direct call
instead of an indirect call). But to implement this, the data had to
be decoupled from the callback, as now the callback is implemented via
a direct call from the static call and not an indirect call from the
dereferenced structure.
Note, the static call only calls a callback used when there's a single
callback attached to the tracepoint. If more than one callback is
attached to the same tracepoint, then the static call will call an
iterator function that goes back to dereferencing the structure
keeping the callback and its data tightly coupled again.
Issues can arise when going from 0 callbacks to one, as the static
call is assigned to the callback, and it must take care that the data
passed to it is loaded before the static call calls the callback.
Going from 1 to 2 callbacks is not an issue, as long as the static
call is updated to the iterator before the tracepoint structure array
is updated via RCU. Going from 2 to more or back down to 2 is not an
issue as the iterator can handle all theses cases. But going from 2 to
1, care must be taken as the static call is now calling a callback and
the data that is loaded must be the data for that callback.
Care was taken to ensure the callback and data would be in-sync, but
after a bug was reported, it became clear that not enough was done to
make sure that was the case. These changes address this.
The first change is to compare the old and new data instead of the old
and new callback, as it's the data that can corrupt the callback, even
if the callback is the same (something getting freed).
The next change is to convert these transitions into states, to make
it easier to know when a synchronization is needed, and to perform
those synchronizations. The problem with this patch is that it slows
down disabling all events from under a second, to making it take over
10 seconds to do the same work. But that is addressed in the final
patch.
The final patch uses the RCU state functions to keep track of the RCU
state between the transitions, and only needs to perform the
synchronization if an RCU synchronization hasn't been done already.
This brings the performance of disabling all events back to its
original value. That's because no synchronization is required between
disabling tracepoints but is required when enabling a tracepoint after
its been disabled. If an RCU synchronization happens after the
tracepoint is disabled, and before it is re-enabled, there's no need
to do the synchronization again.
Both the second and third patch have subtle complexities that they are
separated into two patches. But because the second patch causes such a
regression in performance, the third patch adds a "Fixes" tag to the
second patch, such that the two must be backported together and not
just the second patch"
* tag 'trace-v5.14-rc4-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace:
tracepoint: Use rcu get state and cond sync for static call updates
tracepoint: Fix static call function vs data state mismatch
tracepoint: static call: Compare data on transition from 2->1 callees
State transitions from 1->0->1 and N->2->1 callbacks require RCU
synchronization. Rather than performing the RCU synchronization every
time the state change occurs, which is quite slow when many tracepoints
are registered in batch, instead keep a snapshot of the RCU state on the
most recent transitions which belong to a chain, and conditionally wait
for a grace period on the last transition of the chain if one g.p. has
not elapsed since the last snapshot.
This applies to both RCU and SRCU.
This brings the performance regression caused by commit 231264d692
("Fix: tracepoint: static call function vs data state mismatch") back to
what it was originally.
Before this commit:
# trace-cmd start -e all
# time trace-cmd start -p nop
real 0m10.593s
user 0m0.017s
sys 0m0.259s
After this commit:
# trace-cmd start -e all
# time trace-cmd start -p nop
real 0m0.878s
user 0m0.000s
sys 0m0.103s
Link: https://lkml.kernel.org/r/20210805192954.30688-1-mathieu.desnoyers@efficios.com
Link: https://lore.kernel.org/io-uring/4ebea8f0-58c9-e571-fd30-0ce4f6f09c70@samba.org/
Cc: stable@vger.kernel.org
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Stefan Metzmacher <metze@samba.org>
Fixes: 231264d692 ("Fix: tracepoint: static call function vs data state mismatch")
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
The Energy Model (EM) provides useful information about device power in
each performance state to other subsystems like: Energy Aware Scheduler
(EAS). The energy calculation in EAS does arithmetic operation based on
the EM em_cpu_energy(). Current implementation of that function uses
em_perf_state::cost as a pre-computed cost coefficient equal to:
cost = power * max_frequency / frequency.
The 'power' is expressed in milli-Watts (or in abstract scale).
There are corner cases when the EAS energy calculation for two Performance
Domains (PDs) return the same value. The EAS compares these values to
choose smaller one. It might happen that this values are equal due to
rounding error. In such scenario, we need better resolution, e.g. 1000
times better. To provide this possibility increase the resolution in the
em_perf_state::cost for 64-bit architectures. The cost of increasing
resolution on 32-bit is pretty high (64-bit division) and is not justified
since there are no new 32bit big.LITTLE EAS systems expected which would
benefit from this higher resolution.
This patch allows to avoid the rounding to milli-Watt errors, which might
occur in EAS energy estimation for each PD. The rounding error is common
for small tasks which have small utilization value.
There are two places in the code where it makes a difference:
1. In the find_energy_efficient_cpu() where we are searching for
best_delta. We might suffer there when two PDs return the same result,
like in the example below.
Scenario:
Low utilized system e.g. ~200 sum_util for PD0 and ~220 for PD1. There
are quite a few small tasks ~10-15 util. These tasks would suffer for
the rounding error. These utilization values are typical when running games
on Android. One of our partners has reported 5..10mA less battery drain
when running with increased resolution.
Some details:
We have two PDs: PD0 (big) and PD1 (little)
Let's compare w/o patch set ('old') and w/ patch set ('new')
We are comparing energy w/ task and w/o task placed in the PDs
a) 'old' w/o patch set, PD0
task_util = 13
cost = 480
sum_util_w/o_task = 215
sum_util_w_task = 228
scale_cpu = 1024
energy_w/o_task = 480 * 215 / 1024 = 100.78 => 100
energy_w_task = 480 * 228 / 1024 = 106.87 => 106
energy_diff = 106 - 100 = 6
(this is equal to 'old' PD1's energy_diff in 'c)')
b) 'new' w/ patch set, PD0
task_util = 13
cost = 480 * 1000 = 480000
sum_util_w/o_task = 215
sum_util_w_task = 228
energy_w/o_task = 480000 * 215 / 1024 = 100781
energy_w_task = 480000 * 228 / 1024 = 106875
energy_diff = 106875 - 100781 = 6094
(this is not equal to 'new' PD1's energy_diff in 'd)')
c) 'old' w/o patch set, PD1
task_util = 13
cost = 160
sum_util_w/o_task = 283
sum_util_w_task = 293
scale_cpu = 355
energy_w/o_task = 160 * 283 / 355 = 127.55 => 127
energy_w_task = 160 * 296 / 355 = 133.41 => 133
energy_diff = 133 - 127 = 6
(this is equal to 'old' PD0's energy_diff in 'a)')
d) 'new' w/ patch set, PD1
task_util = 13
cost = 160 * 1000 = 160000
sum_util_w/o_task = 283
sum_util_w_task = 293
scale_cpu = 355
energy_w/o_task = 160000 * 283 / 355 = 127549
energy_w_task = 160000 * 296 / 355 = 133408
energy_diff = 133408 - 127549 = 5859
(this is not equal to 'new' PD0's energy_diff in 'b)')
2. Difference in the 6% energy margin filter at the end of
find_energy_efficient_cpu(). With this patch the margin comparison also
has better resolution, so it's possible to have better task placement
thanks to that.
Fixes: 27871f7a8a ("PM: Introduce an Energy Model management framework")
Reported-by: CCJ Yeh <CCj.Yeh@mediatek.com>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
