| Age | Commit message (Collapse) | Author |
|---|
|
The addition of random_get_entropy_fallback() provides access to
whichever time source has the highest frequency, which is useful for
gathering entropy on platforms without available cycle counters. It's
not necessarily as good as being able to quickly access a cycle counter
that the CPU has, but it's still something, even when it falls back to
being jiffies-based.
In the event that a given arch does not define get_cycles(), falling
back to the get_cycles() default implementation that returns 0 is really
not the best we can do. Instead, at least calling
random_get_entropy_fallback() would be preferable, because that always
needs to return _something_, even falling back to jiffies eventually.
It's not as though random_get_entropy_fallback() is super high precision
or guaranteed to be entropic, but basically anything that's not zero all
the time is better than returning zero all the time.
Finally, since random_get_entropy_fallback() is used during extremely
early boot when randomizing freelists in mm_init(), it can be called
before timekeeping has been initialized. In that case there really is
nothing we can do; jiffies hasn't even started ticking yet. So just give
up and return 0.
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Theodore Ts'o <tytso@mit.edu>
|
|
Earlier the PREEMPT_RT patch had a PREEMPT_RT_FULL and PREEMPT_RT_BASE
Kconfig option. The latter was a subset of the functionality that was
enabled with PREEMPT_RT_FULL and was mainly useful for debugging.
During the merging efforts the two Kconfig options were abandoned in the
v5.4.3-rt1 release and since then there is only PREEMPT_RT which enables
the full features set (as PREEMPT_RT_FULL did in earlier releases).
Replace the PREEMPT_RT_FULL reference with PREEMPT_RT.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: André Almeida <andrealmeid@igalia.com>
Link: https://lore.kernel.org/r/YnvWUvq1vpqCfCU7@linutronix.de
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup
Pull cgroup fix from Tejun Heo:
"Waiman's fix for a cgroup2 cpuset bug where it could miss nodes which
were hot-added"
* 'for-5.18-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
cgroup/cpuset: Remove cpus_allowed/mems_allowed setup in cpuset_init_smp()
|
|
Hardware core level testing features require near simultaneous execution
of WRMSR instructions on all threads of a core to initiate a test.
Provide a customized cut down version of stop_machine_cpuslocked() that
just operates on the threads of a single core.
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20220506225410.1652287-4-tony.luck@intel.com
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
|
|
Commit fa2c3254d7cf (sched/tracing: Don't re-read p->state when emitting
sched_switch event, 2022-01-20) added a new prev_state argument to the
sched_switch tracepoint, before the prev task_struct pointer.
This reordering of arguments broke BPF programs that use the raw
tracepoint (e.g. tp_btf programs). The type of the second argument has
changed and existing programs that assume a task_struct* argument
(e.g. for bpf_task_storage access) will now fail to verify.
If we instead append the new argument to the end, all existing programs
would continue to work and can conditionally extract the prev_state
argument on supported kernel versions.
Fixes: fa2c3254d7cf (sched/tracing: Don't re-read p->state when emitting sched_switch event, 2022-01-20)
Signed-off-by: Delyan Kratunov <delyank@fb.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lkml.kernel.org/r/c8a6930dfdd58a4a5755fc01732675472979732b.camel@fb.com
|
|
exp.2022.05.11a: Expedited-grace-period latency-reduction updates.
|
|
Enabling CONFIG_RCU_BOOST did not reduce RCU expedited grace-period
latency because its workqueues run at SCHED_OTHER, and thus can be
delayed by normal processes. This commit avoids these delays by moving
the expedited GP work items to a real-time-priority kthread_worker.
This option is controlled by CONFIG_RCU_EXP_KTHREAD and disabled by
default on PREEMPT_RT=y kernels which disable expedited grace periods
after boot by unconditionally setting rcupdate.rcu_normal_after_boot=1.
The results were evaluated on arm64 Android devices (6GB ram) running
5.10 kernel, and capturing trace data in critical user-level code.
The table below shows the resulting order-of-magnitude improvements
in synchronize_rcu_expedited() latency:
------------------------------------------------------------------------
| | workqueues | kthread_worker | Diff |
------------------------------------------------------------------------
| Count | 725 | 688 | |
------------------------------------------------------------------------
| Min Duration (ns) | 326 | 447 | 37.12% |
------------------------------------------------------------------------
| Q1 (ns) | 39,428 | 38,971 | -1.16% |
------------------------------------------------------------------------
| Q2 - Median (ns) | 98,225 | 69,743 | -29.00% |
------------------------------------------------------------------------
| Q3 (ns) | 342,122 | 126,638 | -62.98% |
------------------------------------------------------------------------
| Max Duration (ns) | 372,766,967 | 2,329,671 | -99.38% |
------------------------------------------------------------------------
| Avg Duration (ns) | 2,746,353 | 151,242 | -94.49% |
------------------------------------------------------------------------
| Standard Deviation (ns) | 19,327,765 | 294,408 | |
------------------------------------------------------------------------
The below table show the range of maximums/minimums for
synchronize_rcu_expedited() latency from all experiments:
------------------------------------------------------------------------
| | workqueues | kthread_worker | Diff |
------------------------------------------------------------------------
| Total No. of Experiments | 25 | 23 | |
------------------------------------------------------------------------
| Largest Maximum (ns) | 372,766,967 | 2,329,671 | -99.38% |
------------------------------------------------------------------------
| Smallest Maximum (ns) | 38,819 | 86,954 | 124.00% |
------------------------------------------------------------------------
| Range of Maximums (ns) | 372,728,148 | 2,242,717 | |
------------------------------------------------------------------------
| Largest Minimum (ns) | 88,623 | 27,588 | -68.87% |
------------------------------------------------------------------------
| Smallest Minimum (ns) | 326 | 447 | 37.12% |
------------------------------------------------------------------------
| Range of Minimums (ns) | 88,297 | 27,141 | |
------------------------------------------------------------------------
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Reported-by: Tim Murray <timmurray@google.com>
Reported-by: Wei Wang <wvw@google.com>
Tested-by: Kyle Lin <kylelin@google.com>
Tested-by: Chunwei Lu <chunweilu@google.com>
Tested-by: Lulu Wang <luluw@google.com>
Signed-off-by: Kalesh Singh <kaleshsingh@google.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
|
|
Currently both expedited and regular grace period stall warnings use
a single timeout value that with units of seconds. However, recent
Android use cases problem require a sub-100-millisecond expedited RCU CPU
stall warning. Given that expedited RCU grace periods normally complete
in far less than a single millisecond, especially for small systems,
this is not unreasonable.
Therefore introduce the CONFIG_RCU_EXP_CPU_STALL_TIMEOUT kernel
configuration that defaults to 20 msec on Android and remains the same
as that of the non-expedited stall warnings otherwise. It also can be
changed in run-time via: /sys/.../parameters/rcu_exp_cpu_stall_timeout.
[ paulmck: Default of zero to use CONFIG_RCU_STALL_TIMEOUT. ]
Signed-off-by: Uladzislau Rezki <uladzislau.rezki@sony.com>
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
|
|
In commit e458716a92b57 ("PM: EM: Mark inefficiencies in CPUFreq"),
cpufreq_cpu_get() is called without a cpufreq_cpu_put(), permanently
increasing the reference counts of the policy struct.
Decrement the reference count once the policy struct is not used
anymore.
Fixes: e458716a92b57 ("PM: EM: Mark inefficiencies in CPUFreq")
Tested-by: Cristian Marussi <cristian.marussi@arm.com>
Signed-off-by: Pierre Gondois <pierre.gondois@arm.com>
Reviewed-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
|
|
The change to call update_rq_clock() before activate_task()
commit 840d719604b0 ("sched/deadline: Update rq_clock of later_rq
when pushing a task") is no longer needed since commit f4904815f97a
("sched/deadline: Fix double accounting of rq/running bw in push & pull")
removed the add_running_bw() before the activate_task().
So we remove some comments that are no longer needed and update
rq clock in activate_task().
Signed-off-by: Hao Jia <jiahao.os@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Reviewed-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Link: https://lore.kernel.org/r/20220430085843.62939-3-jiahao.os@bytedance.com
|
|
When we use raw_spin_rq_lock() to acquire the rq lock and have to
update the rq clock while holding the lock, the kernel may issue
a WARN_DOUBLE_CLOCK warning.
Since we directly use raw_spin_rq_lock() to acquire rq lock instead of
rq_lock(), there is no corresponding change to rq->clock_update_flags.
In particular, we have obtained the rq lock of other CPUs, the
rq->clock_update_flags of this CPU may be RQCF_UPDATED at this time, and
then calling update_rq_clock() will trigger the WARN_DOUBLE_CLOCK warning.
So we need to clear RQCF_UPDATED of rq->clock_update_flags to avoid
the WARN_DOUBLE_CLOCK warning.
For the sched_rt_period_timer() and migrate_task_rq_dl() cases
we simply replace raw_spin_rq_lock()/raw_spin_rq_unlock() with
rq_lock()/rq_unlock().
For the {pull,push}_{rt,dl}_task() cases, we add the
double_rq_clock_clear_update() function to clear RQCF_UPDATED of
rq->clock_update_flags, and call double_rq_clock_clear_update()
before double_lock_balance()/double_rq_lock() returns to avoid the
WARN_DOUBLE_CLOCK warning.
Some call trace reports:
Call Trace 1:
<IRQ>
sched_rt_period_timer+0x10f/0x3a0
? enqueue_top_rt_rq+0x110/0x110
__hrtimer_run_queues+0x1a9/0x490
hrtimer_interrupt+0x10b/0x240
__sysvec_apic_timer_interrupt+0x8a/0x250
sysvec_apic_timer_interrupt+0x9a/0xd0
</IRQ>
<TASK>
asm_sysvec_apic_timer_interrupt+0x12/0x20
Call Trace 2:
<TASK>
activate_task+0x8b/0x110
push_rt_task.part.108+0x241/0x2c0
push_rt_tasks+0x15/0x30
finish_task_switch+0xaa/0x2e0
? __switch_to+0x134/0x420
__schedule+0x343/0x8e0
? hrtimer_start_range_ns+0x101/0x340
schedule+0x4e/0xb0
do_nanosleep+0x8e/0x160
hrtimer_nanosleep+0x89/0x120
? hrtimer_init_sleeper+0x90/0x90
__x64_sys_nanosleep+0x96/0xd0
do_syscall_64+0x34/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xae
Call Trace 3:
<TASK>
deactivate_task+0x93/0xe0
pull_rt_task+0x33e/0x400
balance_rt+0x7e/0x90
__schedule+0x62f/0x8e0
do_task_dead+0x3f/0x50
do_exit+0x7b8/0xbb0
do_group_exit+0x2d/0x90
get_signal+0x9df/0x9e0
? preempt_count_add+0x56/0xa0
? __remove_hrtimer+0x35/0x70
arch_do_signal_or_restart+0x36/0x720
? nanosleep_copyout+0x39/0x50
? do_nanosleep+0x131/0x160
? audit_filter_inodes+0xf5/0x120
exit_to_user_mode_prepare+0x10f/0x1e0
syscall_exit_to_user_mode+0x17/0x30
do_syscall_64+0x40/0x90
entry_SYSCALL_64_after_hwframe+0x44/0xae
Call Trace 4:
update_rq_clock+0x128/0x1a0
migrate_task_rq_dl+0xec/0x310
set_task_cpu+0x84/0x1e4
try_to_wake_up+0x1d8/0x5c0
wake_up_process+0x1c/0x30
hrtimer_wakeup+0x24/0x3c
__hrtimer_run_queues+0x114/0x270
hrtimer_interrupt+0xe8/0x244
arch_timer_handler_phys+0x30/0x50
handle_percpu_devid_irq+0x88/0x140
generic_handle_domain_irq+0x40/0x60
gic_handle_irq+0x48/0xe0
call_on_irq_stack+0x2c/0x60
do_interrupt_handler+0x80/0x84
Steps to reproduce:
1. Enable CONFIG_SCHED_DEBUG when compiling the kernel
2. echo 1 > /sys/kernel/debug/clear_warn_once
echo "WARN_DOUBLE_CLOCK" > /sys/kernel/debug/sched/features
echo "NO_RT_PUSH_IPI" > /sys/kernel/debug/sched/features
3. Run some rt/dl tasks that periodically work and sleep, e.g.
Create 2*n rt or dl (90% running) tasks via rt-app (on a system
with n CPUs), and Dietmar Eggemann reports Call Trace 4 when running
on PREEMPT_RT kernel.
Signed-off-by: Hao Jia <jiahao.os@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lore.kernel.org/r/20220430085843.62939-2-jiahao.os@bytedance.com
|
|
Obtain the new INTEL_FAM6 stuff required.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
|
|
Queued rwlock was originally named "queue rwlock" which wasn't quite
grammatically correct. However there are still some "queue rwlock"
references in the code. Change those to "queued rwlock" for consistency.
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20220510192134.434753-1-longman@redhat.com
|
|
Since commit 0953fb263714 ("irq: remove handle_domain_{irq,nmi}()"),
generic_handle_domain_irq() warns if called outside hardirq context, even
though the function calls down to handle_irq_desc(), which warns about the
same, but conditionally on handle_enforce_irqctx().
The newly added warning is a false positive if the interrupt originates
from any other irqchip than x86 APIC or ARM GIC/GICv3. Those are the only
ones for which handle_enforce_irqctx() returns true. Per commit
c16816acd086 ("genirq: Add protection against unsafe usage of
generic_handle_irq()"):
"In general calling generic_handle_irq() with interrupts disabled from non
interrupt context is harmless. For some interrupt controllers like the
x86 trainwrecks this is outright dangerous as it might corrupt state if
an interrupt affinity change is pending."
Examples for interrupt chips where the warning is a false positive are
USB-attached GPIO controllers such as drivers/gpio/gpio-dln2.c:
USB gadgets are incapable of directly signaling an interrupt because they
cannot initiate a bus transaction by themselves. All communication on
the bus is initiated by the host controller, which polls a gadget's
Interrupt Endpoint in regular intervals. If an interrupt is pending,
that information is passed up the stack in softirq context, from which a
hardirq is synthesized via generic_handle_domain_irq().
Remove the warning to eliminate such false positives.
Fixes: 0953fb263714 ("irq: remove handle_domain_{irq,nmi}()")
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Jakub Kicinski <kuba@kernel.org>
CC: Linus Walleij <linus.walleij@linaro.org>
Cc: Bartosz Golaszewski <brgl@bgdev.pl>
Cc: Octavian Purdila <octavian.purdila@nxp.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20220505113207.487861b2@kernel.org
Link: https://lore.kernel.org/r/20220506203242.GA1855@wunner.de
Link: https://lore.kernel.org/r/c3caf60bfa78e5fdbdf483096b7174da65d1813a.1652168866.git.lukas@wunner.de
|
|
With all implementations of aops->readpage converted to aops->read_folio,
we can stop checking whether it's set and remove the member from aops.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
|
|
Change all the callers of ->readpage to call ->read_folio in preference,
if it exists. This is a transitional duplication, and will be removed
by the end of the series.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
|
|
arch_check_user_regs() is used at the moment to verify that struct pt_regs
contains valid values when entering the kernel from userspace. s390 needs
a place in the generic entry code to modify a cpu data structure when
switching from userspace to kernel mode. As arch_check_user_regs() is
exactly this, rename it to arch_enter_from_user_mode().
When entering the kernel from userspace, arch_check_user_regs() is
used to verify that struct pt_regs contains valid values. Note that
the NMI codepath doesn't call this function. s390 needs a place in the
generic entry code to modify a cpu data structure when switching from
userspace to kernel mode. As arch_check_user_regs() is exactly this,
rename it to arch_enter_from_user_mode().
Signed-off-by: Sven Schnelle <svens@linux.ibm.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andy Lutomirski <luto@kernel.org>
Link: https://lore.kernel.org/r/20220504062351.2954280-2-tmricht@linux.ibm.com
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull timer fix from Thomas Gleixner:
"A fix and an email address update:
- Mark the NMI safe time accessors notrace to prevent tracer
recursion when they are selected as trace clocks.
- John Stultz has a new email address"
* tag 'timers-urgent-2022-05-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
timekeeping: Mark NMI safe time accessors as notrace
MAINTAINERS: Update email address for John Stultz
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull irq fix from Thomas Gleixner:
"A fix for the threaded interrupt core.
A quick sequence of request/free_irq() can result in a hang because
the interrupt thread did not reach the thread function and got stopped
in the kthread core already. That leaves a state active counter
arround which makes a invocation of synchronized_irq() on that
interrupt hang forever.
Ensure that the thread reached the thread function in request_irq() to
prevent that"
* tag 'irq-urgent-2022-05-08' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
genirq: Synchronize interrupt thread startup
|
|
The stackleak_erase() code dynamically handles being on a task stack or
another stack. In most cases, this is a fixed property of the caller,
which the caller is aware of, as an architecture might always return
using the task stack, or might always return using a trampoline stack.
This patch adds stackleak_erase_on_task_stack() and
stackleak_erase_off_task_stack() functions which callers can use to
avoid on_thread_stack() check and associated redundant work when the
calling stack is known. The existing stackleak_erase() is retained as a
safe default.
There should be no functional change as a result of this patch.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Popov <alex.popov@linux.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220427173128.2603085-13-mark.rutland@arm.com
|
|
Currently we over-estimate the region of stack which must be erased.
To determine the region to be erased, we scan downwards for a contiguous
block of poison values (or the low bound of the stack). There are a few
minor problems with this today:
* When we find a block of poison values, we include this block within
the region to erase.
As this is included within the region to erase, this causes us to
redundantly overwrite 'STACKLEAK_SEARCH_DEPTH' (128) bytes with
poison.
* As the loop condition checks 'poison_count <= depth', it will run an
additional iteration after finding the contiguous block of poison,
decrementing 'erase_low' once more than necessary.
As this is included within the region to erase, this causes us to
redundantly overwrite an additional unsigned long with poison.
* As we always decrement 'erase_low' after checking an element on the
stack, we always include the element below this within the region to
erase.
As this is included within the region to erase, this causes us to
redundantly overwrite an additional unsigned long with poison.
Note that this is not a functional problem. As the loop condition
checks 'erase_low > task_stack_low', we'll never clobber the
STACK_END_MAGIC. As we always decrement 'erase_low' after this, we'll
never fail to erase the element immediately above the STACK_END_MAGIC.
In total, this can cause us to erase `128 + 2 * sizeof(unsigned long)`
bytes more than necessary, which is unfortunate.
This patch reworks the logic to find the address immediately above the
poisoned region, by finding the lowest non-poisoned address. This is
factored into a stackleak_find_top_of_poison() helper both for clarity
and so that this can be shared with the LKDTM test in subsequent
patches.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Popov <alex.popov@linux.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220427173128.2603085-8-mark.rutland@arm.com
|
|
Prior to returning to userspace, we reset current->lowest_stack to a
reasonable high bound. Currently we do this by subtracting the arbitrary
value `THREAD_SIZE/64` from the top of the stack, for reasons lost to
history.
Looking at configurations today:
* On i386 where THREAD_SIZE is 8K, the bound will be 128 bytes. The
pt_regs at the top of the stack is 68 bytes (with 0 to 16 bytes of
padding above), and so this covers an additional portion of 44 to 60
bytes.
* On x86_64 where THREAD_SIZE is at least 16K (up to 32K with KASAN) the
bound will be at least 256 bytes (up to 512 with KASAN). The pt_regs
at the top of the stack is 168 bytes, and so this cover an additional
88 bytes of stack (up to 344 with KASAN).
* On arm64 where THREAD_SIZE is at least 16K (up to 64K with 64K pages
and VMAP_STACK), the bound will be at least 256 bytes (up to 1024 with
KASAN). The pt_regs at the top of the stack is 336 bytes, so this can
fall within the pt_regs, or can cover an additional 688 bytes of
stack.
Clearly the `THREAD_SIZE/64` value doesn't make much sense -- in the
worst case, this will cause more than 600 bytes of stack to be erased
for every syscall, even if actual stack usage were substantially
smaller.
This patches makes this slightly less nonsensical by consistently
resetting current->lowest_stack to the base of the task pt_regs. For
clarity and for consistency with the handling of the low bound, the
generation of the high bound is split into a helper with commentary
explaining why.
Since the pt_regs at the top of the stack will be clobbered upon the
next exception entry, we don't need to poison these at exception exit.
By using task_pt_regs() as the high stack boundary instead of
current_top_of_stack() we avoid some redundant poisoning, and the
compiler can share the address generation between the poisoning and
resetting of `current->lowest_stack`, making the generated code more
optimal.
It's not clear to me whether the existing `THREAD_SIZE/64` offset was a
dodgy heuristic to skip the pt_regs, or whether it was attempting to
minimize the number of times stackleak_check_stack() would have to
update `current->lowest_stack` when stack usage was shallow at the cost
of unconditionally poisoning a small portion of the stack for every exit
to userspace.
For now I've simply removed the offset, and if we need/want to minimize
updates for shallow stack usage it should be easy to add a better
heuristic atop, with appropriate commentary so we know what's going on.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Popov <alex.popov@linux.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220427173128.2603085-7-mark.rutland@arm.com
|
|
The logic within __stackleak_erase() can be a little hard to follow, as
`boundary` switches from being the low bound to the high bound mid way
through the function, and `kstack_ptr` is used to represent the start of
the region to erase while `boundary` represents the end of the region to
erase.
Make this a little clearer by consistently using clearer variable names.
The `boundary` variable is removed, the bounds of the region to erase
are described by `erase_low` and `erase_high`, and bounds of the task
stack are described by `task_stack_low` and `task_stack_high`.
As the same time, remove the comment above the variables, since it is
unclear whether it's intended as rationale, a complaint, or a TODO, and
is more confusing than helpful.
There should be no functional change as a result of this patch.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Popov <alex.popov@linux.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220427173128.2603085-6-mark.rutland@arm.com
|
|
In stackleak_task_init(), stackleak_track_stack(), and
__stackleak_erase(), we open-code skipping the STACK_END_MAGIC at the
bottom of the stack. Each case is implemented slightly differently, and
only the __stackleak_erase() case is commented.
In stackleak_task_init() and stackleak_track_stack() we unconditionally
add sizeof(unsigned long) to the lowest stack address. In
stackleak_task_init() we use end_of_stack() for this, and in
stackleak_track_stack() we use task_stack_page(). In __stackleak_erase()
we handle this by detecting if `kstack_ptr` has hit the stack end
boundary, and if so, conditionally moving it above the magic.
This patch adds a new stackleak_task_low_bound() helper which is used in
all three cases, which unconditionally adds sizeof(unsigned long) to the
lowest address on the task stack, with commentary as to why. This uses
end_of_stack() as stackleak_task_init() did prior to this patch, as this
is consistent with the code in kernel/fork.c which initializes the
STACK_END_MAGIC value.
In __stackleak_erase() we no longer need to check whether we've spilled
into the STACK_END_MAGIC value, as stackleak_track_stack() ensures that
`current->lowest_stack` stops immediately above this, and similarly the
poison scan will stop immediately above this.
For stackleak_task_init() and stackleak_track_stack() this results in no
change to code generation. For __stackleak_erase() the generated
assembly is slightly simpler and shorter.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Popov <alex.popov@linux.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220427173128.2603085-5-mark.rutland@arm.com
|
|
In __stackleak_erase() we check that the `erase_low` value derived from
`current->lowest_stack` is above the lowest legitimate stack pointer
value, but this is already enforced by stackleak_track_stack() when
recording the lowest stack value.
Remove the redundant check.
There should be no functional change as a result of this patch.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Popov <alex.popov@linux.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220427173128.2603085-4-mark.rutland@arm.com
|
|
In stackleak_erase() we check skip_erasing() after accessing some fields
from current. As generating the address of current uses asm which
hazards with the static branch asm, this work is always performed, even
when the static branch is patched to jump to the return at the end of the
function.
This patch avoids this redundant work by moving the skip_erasing() check
earlier.
To avoid complicating initialization within stackleak_erase(), the body
of the function is split out into a __stackleak_erase() helper, with the
check left in a wrapper function. The __stackleak_erase() helper is
marked __always_inline to ensure that this is inlined into
stackleak_erase() and not instrumented.
Before this patch, on x86-64 w/ GCC 11.1.0 the start of the function is:
<stackleak_erase>:
65 48 8b 04 25 00 00 mov %gs:0x0,%rax
00 00
48 8b 48 20 mov 0x20(%rax),%rcx
48 8b 80 98 0a 00 00 mov 0xa98(%rax),%rax
66 90 xchg %ax,%ax <------------ static branch
48 89 c2 mov %rax,%rdx
48 29 ca sub %rcx,%rdx
48 81 fa ff 3f 00 00 cmp $0x3fff,%rdx
After this patch, on x86-64 w/ GCC 11.1.0 the start of the function is:
<stackleak_erase>:
0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) <--- static branch
65 48 8b 04 25 00 00 mov %gs:0x0,%rax
00 00
48 8b 48 20 mov 0x20(%rax),%rcx
48 8b 80 98 0a 00 00 mov 0xa98(%rax),%rax
48 89 c2 mov %rax,%rdx
48 29 ca sub %rcx,%rdx
48 81 fa ff 3f 00 00 cmp $0x3fff,%rdx
Before this patch, on arm64 w/ GCC 11.1.0 the start of the function is:
<stackleak_erase>:
d503245f bti c
d5384100 mrs x0, sp_el0
f9401003 ldr x3, [x0, #32]
f9451000 ldr x0, [x0, #2592]
d503201f nop <------------------------------- static branch
d503233f paciasp
cb030002 sub x2, x0, x3
d287ffe1 mov x1, #0x3fff
eb01005f cmp x2, x1
After this patch, on arm64 w/ GCC 11.1.0 the start of the function is:
<stackleak_erase>:
d503245f bti c
d503201f nop <------------------------------- static branch
d503233f paciasp
d5384100 mrs x0, sp_el0
f9401003 ldr x3, [x0, #32]
d287ffe1 mov x1, #0x3fff
f9451000 ldr x0, [x0, #2592]
cb030002 sub x2, x0, x3
eb01005f cmp x2, x1
While this may not be a huge win on its own, moving the static branch
will permit further optimization of the body of the function in
subsequent patches.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Popov <alex.popov@linux.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220427173128.2603085-3-mark.rutland@arm.com
|
|
In preparation for Clang supporting randstruct, reorganize the Kconfigs,
move the attribute macros, and generalize the feature to be named
CONFIG_RANDSTRUCT for on/off, CONFIG_RANDSTRUCT_FULL for the full
randomization mode, and CONFIG_RANDSTRUCT_PERFORMANCE for the cache-line
sized mode.
Cc: linux-hardening@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220503205503.3054173-4-keescook@chromium.org
|
|
According to the current crashkernel=Y,low support in other ARCHes, it's
an optional command-line option. When it doesn't exist, kernel will try
to allocate minimum required memory below 4G automatically.
However, __parse_crashkernel() returns '-EINVAL' for all error cases. It
can't distinguish the nonexistent option from invalid option.
Change __parse_crashkernel() to return '-ENOENT' for the nonexistent option
case. With this change, crashkernel,low memory will take the default
value if crashkernel=,low is not specified; while crashkernel reservation
will fail and bail out if an invalid option is specified.
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Acked-by: Baoquan He <bhe@redhat.com>
Link: https://lore.kernel.org/r/20220506114402.365-2-thunder.leizhen@huawei.com
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
|
|
The original intent of the 'console' tracepoint per the commit 95100358491a
("printk/tracing: Add console output tracing") had been to "[...] record
any printk messages into the trace, regardless of the current console
loglevel. This can help correlate (existing) printk debugging with other
tracing."
Petr points out [1] that calling trace_console_rcuidle() in
call_console_driver() had been the wrong thing for a while, because
"printk() always used console_trylock() and the message was flushed to
the console only when the trylock succeeded. And it was always deferred
in NMI or when printed via printk_deferred()."
With the commit 09c5ba0aa2fc ("printk: add kthread console printers"),
things only got worse, and calls to call_console_driver() no longer
happen with typical printk() calls but always appear deferred [2].
As such, the tracepoint can no longer serve its purpose to clearly
correlate printk() calls and other tracing, as well as breaks usecases
that expect every printk() call to result in a callback of the console
tracepoint. Notably, the KFENCE and KCSAN test suites, which want to
capture console output and assume a printk() immediately gives us a
callback to the console tracepoint.
Fix the console tracepoint by moving it into printk_sprint() [3].
One notable difference is that by moving tracing into printk_sprint(),
the 'text' will no longer include the "header" (loglevel and timestamp),
but only the raw message. Arguably this is less of a problem now that
the console tracepoint happens on the printk() call and isn't delayed.
Link: https://lore.kernel.org/all/Ym+WqKStCg%2FEHfh3@alley/ [1]
Link: https://lore.kernel.org/all/CA+G9fYu2kS0wR4WqMRsj2rePKV9XLgOU1PiXnMvpT+Z=c2ucHA@mail.gmail.com/ [2]
Link: https://lore.kernel.org/all/87fslup9dx.fsf@jogness.linutronix.de/ [3]
Reported-by: Linux Kernel Functional Testing <lkft@linaro.org>
Signed-off-by: Marco Elver <elver@google.com>
Cc: John Ogness <john.ogness@linutronix.de>
Cc: Petr Mladek <pmladek@suse.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Acked-by: John Ogness <john.ogness@linutronix.de>
Acked-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20220503073844.4148944-1-elver@google.com
|
|
- sched/core is on a pretty old -rc1 base - refresh it to include recent fixes.
- this also allows up to resolve a (trivial) .mailmap conflict
Conflicts:
.mailmap
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
There are 3 places where the cpu and node masks of the top cpuset can
be initialized in the order they are executed:
1) start_kernel -> cpuset_init()
2) start_kernel -> cgroup_init() -> cpuset_bind()
3) kernel_init_freeable() -> do_basic_setup() -> cpuset_init_smp()
The first cpuset_init() call just sets all the bits in the masks.
The second cpuset_bind() call sets cpus_allowed and mems_allowed to the
default v2 values. The third cpuset_init_smp() call sets them back to
v1 values.
For systems with cgroup v2 setup, cpuset_bind() is called once. As a
result, cpu and memory node hot add may fail to update the cpu and node
masks of the top cpuset to include the newly added cpu or node in a
cgroup v2 environment.
For systems with cgroup v1 setup, cpuset_bind() is called again by
rebind_subsystem() when the v1 cpuset filesystem is mounted as shown
in the dmesg log below with an instrumented kernel.
[ 2.609781] cpuset_bind() called - v2 = 1
[ 3.079473] cpuset_init_smp() called
[ 7.103710] cpuset_bind() called - v2 = 0
smp_init() is called after the first two init functions. So we don't
have a complete list of active cpus and memory nodes until later in
cpuset_init_smp() which is the right time to set up effective_cpus
and effective_mems.
To fix this cgroup v2 mask setup problem, the potentially incorrect
cpus_allowed & mems_allowed setting in cpuset_init_smp() are removed.
For cgroup v2 systems, the initial cpuset_bind() call will set the masks
correctly. For cgroup v1 systems, the second call to cpuset_bind()
will do the right setup.
cc: stable@vger.kernel.org
Signed-off-by: Waiman Long <longman@redhat.com>
Tested-by: Feng Tang <feng.tang@intel.com>
Reviewed-by: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
|
|
A kernel hang can be observed when running setserial in a loop on a kernel
with force threaded interrupts. The sequence of events is:
setserial
open("/dev/ttyXXX")
request_irq()
do_stuff()
-> serial interrupt
-> wake(irq_thread)
desc->threads_active++;
close()
free_irq()
kthread_stop(irq_thread)
synchronize_irq() <- hangs because desc->threads_active != 0
The thread is created in request_irq() and woken up, but does not get on a
CPU to reach the actual thread function, which would handle the pending
wake-up. kthread_stop() sets the should stop condition which makes the
thread immediately exit, which in turn leaves the stale threads_active
count around.
This problem was introduced with commit 519cc8652b3a, which addressed a
interrupt sharing issue in the PCIe code.
Before that commit free_irq() invoked synchronize_irq(), which waits for
the hard interrupt handler and also for associated threads to complete.
To address the PCIe issue synchronize_irq() was replaced with
__synchronize_hardirq(), which only waits for the hard interrupt handler to
complete, but not for threaded handlers.
This was done under the assumption, that the interrupt thread already
reached the thread function and waits for a wake-up, which is guaranteed to
be handled before acting on the stop condition. The problematic case, that
the thread would not reach the thread function, was obviously overlooked.
Make sure that the interrupt thread is really started and reaches
thread_fn() before returning from __setup_irq().
This utilizes the existing wait queue in the interrupt descriptor. The
wait queue is unused for non-shared interrupts. For shared interrupts the
usage might cause a spurious wake-up of a waiter in synchronize_irq() or the
completion of a threaded handler might cause a spurious wake-up of the
waiter for the ready flag. Both are harmless and have no functional impact.
[ tglx: Amended changelog ]
Fixes: 519cc8652b3a ("genirq: Synchronize only with single thread on free_irq()")
Signed-off-by: Thomas Pfaff <tpfaff@pcs.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/552fe7b4-9224-b183-bb87-a8f36d335690@pcs.com
|
|
This introduces a per-filter flag (SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV)
that makes it so that when notifications are received by the supervisor the
notifying process will transition to wait killable semantics. Although wait
killable isn't a set of semantics formally exposed to userspace, the
concept is searchable. If the notifying process is signaled prior to the
notification being received by the userspace agent, it will be handled as
normal.
One quirk about how this is handled is that the notifying process
only switches to TASK_KILLABLE if it receives a wakeup from either
an addfd or a signal. This is to avoid an unnecessary wakeup of
the notifying task.
The reasons behind switching into wait_killable only after userspace
receives the notification are:
* Avoiding unncessary work - Often, workloads will perform work that they
may abort (request racing comes to mind). This allows for syscalls to be
aborted safely prior to the notification being received by the
supervisor. In this, the supervisor doesn't end up doing work that the
workload does not want to complete anyways.
* Avoiding side effects - We don't want the syscall to be interruptible
once the supervisor starts doing work because it may not be trivial
to reverse the operation. For example, unmounting a file system may
take a long time, and it's hard to rollback, or treat that as
reentrant.
* Avoid breaking runtimes - Various runtimes do not GC when they are
during a syscall (or while running native code that subsequently
calls a syscall). If many notifications are blocked, and not picked
up by the supervisor, this can get the application into a bad state.
Signed-off-by: Sargun Dhillon <sargun@sargun.me>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220503080958.20220-2-sargun@sargun.me
|
|
'rcu-tasks.2022.04.11b', 'srcu.2022.05.03a', 'torture.2022.04.11b', 'torture-tasks.2022.04.20a' and 'torturescript.2022.04.20a' into HEAD
docs.2022.04.20a: Documentation updates.
fixes.2022.04.20a: Miscellaneous fixes.
nocb.2022.04.11b: Callback-offloading updates.
rcu-tasks.2022.04.11b: RCU-tasks updates.
srcu.2022.05.03a: Put SRCU on a memory diet.
torture.2022.04.11b: Torture-test updates.
torture-tasks.2022.04.20a: Avoid torture testing changing RCU configuration.
torturescript.2022.04.20a: Torture-test scripting updates.
|
|
Commit 9c7ef4c30f12 ("srcu: Make Tree SRCU able to operate without
snp_node array") initializes the local variable sdp differently depending
on the srcu's state in srcu_gp_start(). Either way, this initialization
overwrites the value used when sdp is defined.
This commit therefore drops this pointless definition-time initialization.
Although there is no functional change, compiler code generation may
be affected.
Signed-off-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
|
|
If an SRCU reader blocks while a synchronize_srcu_expedited() waits for
that same reader, then that grace period will spawn an endless series of
workqueue handlers, consuming a full CPU. This quickly gets pointless
because consuming more CPU isn't going to make that reader get done
faster, especially if it is blocked waiting for an external event.
This commit therefore spawns at most one pair of back-to-back workqueue
handlers per expedited grace period phase, instead inserting increasing
delays as that grace period phase grows older, but capped at 10 jiffies.
In any case, if there have been at least 100 back-to-back workqueue
handlers within a single jiffy, regardless of grace period or grace-period
phase, then a one-jiffy delay is inserted.
[ paulmck: Apply feedback from kernel test robot. ]
Cc: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Reported-by: Song Liu <song@kernel.org>
Tested-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
|
|
This commit increases the sensitivity of contention detection by adding
checks to the acquisition of the srcu_data structure's lock on the
call_srcu() code path.
Co-developed-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Signed-off-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
|
|
This commit adds a srcutree.convert_to_big option of zero that causes
SRCU to decide at boot whether to wait for contention (small systems) or
immediately expand to large (large systems). A new srcutree.big_cpu_lim
(defaulting to 128) defines how many CPUs constitute a large system.
Co-developed-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Signed-off-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
|
|
kthread_blkcg is only used by the built-in blk-cgroup code.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20220420042723.1010598-16-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
All callers of bio_blkcg actually want the CSS, so replace it with an
interface that does return the CSS. This now allows to move
struct blkcg_gq to block/blk-cgroup.h instead of exposing it in a
public header.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20220420042723.1010598-10-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
Pass the cgroup_subsys_state instead of a the blkg so that blktrace
doesn't need to poke into blk-cgroup internals, and give the name a
blk prefix as the current name is way too generic for a public
interface.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20220420042723.1010598-9-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
|
|
Use flat rather than nested indentation for chained else/if clauses as
per coding-style.rst:
if (x == y) {
..
} else if (x > y) {
...
} else {
....
}
This also improves readability.
Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <jstultz@google.com>
Link: https://lore.kernel.org/r/alpine.DEB.2.21.2204240148220.9383@angie.orcam.me.uk
|
|
The kernel uses kHz as the unit for clock rates reported between 1MHz
(inclusive) and 4MHz (exclusive), e.g.:
sched_clock: 64 bits at 1000kHz, resolution 1000ns, wraps every 2199023255500ns
This reduces the amount of data lost due to rounding, but hasn't been
replicated for the kHz range when support was added for proper reporting of
sub-kHz clock rates. Take the same approach for rates between 1kHz
(inclusive) and 4kHz (exclusive), which makes it consistent.
Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/alpine.DEB.2.21.2204240106380.9383@angie.orcam.me.uk
|
|
The frequency reported for clock sources are rounded down, which gives
misleading figures, e.g.:
I/O ASIC clock frequency 24999480Hz
sched_clock: 32 bits at 24MHz, resolution 40ns, wraps every 85901132779ns
MIPS counter frequency 59998512Hz
sched_clock: 32 bits at 59MHz, resolution 16ns, wraps every 35792281591ns
Rounding to nearest is more adequate:
I/O ASIC clock frequency 24999664Hz
sched_clock: 32 bits at 25MHz, resolution 40ns, wraps every 85900499947ns
MIPS counter frequency 59999728Hz
sched_clock: 32 bits at 60MHz, resolution 16ns, wraps every 35791556599ns
Signed-off-by: Maciej W. Rozycki <macro@orcam.me.uk>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <jstultz@google.com>
Link: https://lore.kernel.org/r/alpine.DEB.2.21.2204240055590.9383@angie.orcam.me.uk
|
|
pm_runtime_resume_and_get() achieves the same and simplifies the code.
[ tglx: Simplify it further by presetting retval ]
Reported-by: Zeal Robot <zealci@zte.com.cn>
Signed-off-by: Minghao Chi <chi.minghao@zte.com.cn>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20220418110716.2559453-1-chi.minghao@zte.com.cn
|
|
Provide a inline function which replaces the copy & pasta.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220415091921.072296632@linutronix.de
|
|
Accessing timekeeper::offset_boot in ktime_get_boot_fast_ns() is an
intended data race as the reader side cannot synchronize with a writer and
there is no space in struct tk_read_base of the NMI safe timekeeper.
Mark it so.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20220415091920.956045162@linutronix.de
|
|
The PASID is being freed too early. It needs to stay around until after
device drivers that might be using it have had a chance to clear it out
of the hardware.
The relevant refcounts are:
mmget() /mmput() refcount the mm's address space
mmgrab()/mmdrop() refcount the mm itself
The PASID is currently tied to the life of the mm's address space and freed
in __mmput(). This makes logical sense because the PASID can't be used
once the address space is gone.
But, this misses an important point: even after the address space is gone,
the PASID will still be programmed into a device. Device drivers might,
for instance, still need to flush operations that are outstanding and need
to use that PASID. They do this at file->release() time.
Device drivers call the IOMMU driver to hold a reference on the mm itself
and drop it at file->release() time. But, the IOMMU driver holds a
reference on the mm itself, not the address space. The address space (and
the PASID) is long gone by the time the driver tries to clean up. This is
effectively a use-after-free bug on the PASID.
To fix this, move the PASID free operation from __mmput() to __mmdrop().
This ensures that the IOMMU driver's existing mmgrab() keeps the PASID
allocated until it drops its mm reference.
Fixes: 701fac40384f ("iommu/sva: Assign a PASID to mm on PASID allocation and free it on mm exit")
Reported-by: Zhangfei Gao <zhangfei.gao@foxmail.com>
Suggested-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Suggested-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Zhangfei Gao <zhangfei.gao@foxmail.com>
Reviewed-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
Link: https://lore.kernel.org/r/20220428180041.806809-1-fenghua.yu@intel.com
|
|
flush_smp_call_function_queue() invokes do_softirq() which is not available
on PREEMPT_RT. flush_smp_call_function_queue() is invoked from the idle
task and the migration task with preemption or interrupts disabled.
So RT kernels cannot process soft interrupts in that context as that has to
acquire 'sleeping spinlocks' which is not possible with preemption or
interrupts disabled and forbidden from the idle task anyway.
The currently known SMP function call which raises a soft interrupt is in
the block layer, but this functionality is not enabled on RT kernels due to
latency and performance reasons.
RT could wake up ksoftirqd unconditionally, but this wants to be avoided if
there were soft interrupts pending already when this is invoked in the
context of the migration task. The migration task might have preempted a
threaded interrupt handler which raised a soft interrupt, but did not reach
the local_bh_enable() to process it. The "running" ksoftirqd might prevent
the handling in the interrupt thread context which is causing latency
issues.
Add a new function which handles this case explicitely for RT and falls
back to do_softirq() on !RT kernels. In the RT case this warns when one of
the flushed SMP function calls raised a soft interrupt so this can be
investigated.
[ tglx: Moved the RT part out of SMP code ]
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/YgKgL6aPj8aBES6G@linutronix.de
Link: https://lore.kernel.org/r/20220413133024.356509586@linutronix.de
|
|
This is invoked from the stopper thread too, which is definitely not idle.
Rename it to flush_smp_call_function_queue() and fixup the callers.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220413133024.305001096@linutronix.de
|
