Different subsystems may call cgroup_rstat_updated() within the same
cgroup, resulting in a tree of pending updates from multiple subsystems.
When one of these subsystems is flushed via cgroup_rstat_flushed(), all
other subsystems with pending updates on the tree will also be flushed.
Change the paradigm of having a single rstat tree for all subsystems to
having separate trees for each subsystem. This separation allows for
subsystems to perform flushes without the side effects of other subsystems.
As an example, flushing the cpu stats will no longer cause the memory stats
to be flushed and vice versa.
In order to achieve subsystem-specific trees, change the tree node type
from cgroup to cgroup_subsys_state pointer. Then remove those pointers from
the cgroup and instead place them on the css. Finally, change update/flush
functions to make use of the different node type (css). These changes allow
a specific subsystem to be associated with an update or flush. Separate
rstat trees will now exist for each unique subsystem.
Since updating/flushing will now be done at the subsystem level, there is
no longer a need to keep track of updated css nodes at the cgroup level.
The list management of these nodes done within the cgroup (rstat_css_list
and related) has been removed accordingly.
Conditional guards for checking validity of a given css were placed within
css_rstat_updated/flush() to prevent undefined behavior occuring from kfunc
usage in bpf programs. Guards were also placed within css_rstat_init/exit()
in order to help consolidate calls to them. At call sites for all four
functions, the existing guards were removed.
Signed-off-by: JP Kobryn <inwardvessel@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Adjust the implementation of css_is_cgroup() so that it compares the given
css to cgroup::self. Rename the function to css_is_self() in order to
reflect that. Change the existing css->ss NULL check to a warning in the
true branch. Finally, adjust call sites to use the new function name.
Signed-off-by: JP Kobryn <inwardvessel@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
An early init subsystem that attempts to make use of rstat can lead to
failures during early boot. The reason for this is the timing in which the
css's of the root cgroup have css_online() invoked on them. At the point of
this call, there is a stated assumption that a cgroup has "successfully
completed all allocations" [0]. An example of a subsystem that relies on
the previously mentioned assumption [0] is the memory subsystem. Within its
implementation of css_online(), work is queued to asynchronously begin
flushing via rstat. In the early init path for a given subsystem, having
rstat enabled leads to this sequence:
cgroup_init_early()
for_each_subsys(ss, ssid)
if (ss->early_init)
cgroup_init_subsys(ss, true)
cgroup_init_subsys(ss, early_init)
css = ss->css_alloc(...)
init_and_link_css(css, ss, ...)
...
online_css(css)
online_css(css)
ss = css->ss
ss->css_online(css)
Continuing to use the memory subsystem as an example, the issue with this
sequence is that css_rstat_init() has not been called yet. This means there
is now a race between the pending async work to flush rstat and the call to
css_rstat_init(). So a flush can occur within the given cgroup while the
rstat fields are not initialized.
Since we are in the early init phase, the rstat fields cannot be
initialized because they require per-cpu allocations. So it's not possible
to have css_rstat_init() called early enough (before online_css()). This
patch treats the combination of early init and rstat the same as as other
invalid conditions.
[0] Documentation/admin-guide/cgroup-v1/cgroups.rst (section: css_online)
Signed-off-by: JP Kobryn <inwardvessel@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Throughout the verifier's logic, there are multiple checks for
inconsistent states that should never happen and would indicate a
verifier bug. These bugs are typically logged in the verifier logs and
sometimes preceded by a WARN_ONCE.
This patch reworks these checks to consistently emit a verifier log AND
a warning when CONFIG_DEBUG_KERNEL is enabled. The consistent use of
WARN_ONCE should help fuzzers (ex. syzkaller) expose any situation
where they are actually able to reach one of those buggy verifier
states.
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Paul Chaignon <paul.chaignon@gmail.com>
Link: https://lore.kernel.org/r/aCs1nYvNNMq8dAWP@mail.gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
A recent patch that addressed a UAF introduced a reference count leak:
the parallel_data refcount is incremented unconditionally, regardless
of the return value of queue_work(). If the work item is already queued,
the incremented refcount is never decremented.
Fix this by checking the return value of queue_work() and decrementing
the refcount when necessary.
Resolves:
Unreferenced object 0xffff9d9f421e3d80 (size 192):
comm "cryptomgr_probe", pid 157, jiffies 4294694003
hex dump (first 32 bytes):
80 8b cf 41 9f 9d ff ff b8 97 e0 89 ff ff ff ff ...A............
d0 97 e0 89 ff ff ff ff 19 00 00 00 1f 88 23 00 ..............#.
backtrace (crc 838fb36):
__kmalloc_cache_noprof+0x284/0x320
padata_alloc_pd+0x20/0x1e0
padata_alloc_shell+0x3b/0xa0
0xffffffffc040a54d
cryptomgr_probe+0x43/0xc0
kthread+0xf6/0x1f0
ret_from_fork+0x2f/0x50
ret_from_fork_asm+0x1a/0x30
Fixes: dd7d37ccf6 ("padata: avoid UAF for reorder_work")
Cc: <stable@vger.kernel.org>
Signed-off-by: Dominik Grzegorzek <dominik.grzegorzek@oracle.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Section .static_call_sites holds data structures that need to be sorted and
processed only at module load time. This initial processing happens in
static_call_add_module(), which is invoked as a callback to the
MODULE_STATE_COMING notification from prepare_coming_module().
The section is never modified afterwards. Make it therefore read-only after
module initialization to avoid any (non-)accidental modifications.
Reviewed-by: Sami Tolvanen <samitolvanen@google.com>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Link: https://lore.kernel.org/r/20250306131430.7016-4-petr.pavlu@suse.com
Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Pull hotfixes from Andrew Morton:
"Nine singleton hotfixes, all MM. Four are cc:stable"
* tag 'mm-hotfixes-stable-2025-05-17-09-41' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
mm: userfaultfd: correct dirty flags set for both present and swap pte
zsmalloc: don't underflow size calculation in zs_obj_write()
mm/page_alloc: fix race condition in unaccepted memory handling
mm/page_alloc: ensure try_alloc_pages() plays well with unaccepted memory
MAINTAINERS: add mm GUP section
mm/codetag: move tag retrieval back upfront in __free_pages()
mm/memory: fix mapcount / refcount sanity check for mTHP reuse
kernel/fork: only call untrack_pfn_clear() on VMAs duplicated for fork()
mm: hugetlb: fix incorrect fallback for subpool
`pr_cont()` unfortunately does not work here, as other parts of the
Linux kernel log between the two log lines:
[18445.295056] r8152-cfgselector 4-1.1.3: USB disconnect, device number 5
[18445.295112] OOM killer enabled.
[18445.295115] Restarting tasks ...
[18445.295185] usb 3-1: USB disconnect, device number 2
[18445.295193] usb 3-1.1: USB disconnect, device number 3
[18445.296262] usb 3-1.5: USB disconnect, device number 4
[18445.297017] done.
[18445.297029] random: crng reseeded on system resumption
`pr_cont()` also uses the default log level, normally warning, if the
corresponding log line is interrupted.
Therefore, replace the `pr_cont()`, and explicitly log it as a separate
line with log level info:
Restarting tasks: Starting
[…]
Restarting tasks: Done
Signed-off-by: Paul Menzel <pmenzel@molgen.mpg.de>
Link: https://patch.msgid.link/20250511174648.950430-1-pmenzel@molgen.mpg.de
[ rjw: Rebase on top of an earlier analogous change ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Creating an irq domain that serves as an MSI parent requires
a substantial amount of esoteric boiler-plate code, some of
which is often provided twice (such as the bus token).
To make things a bit simpler for the unsuspecting MSI tinkerer,
provide a helper that does it for them, and serves as documentation
of what needs to be provided.
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250513172819.2216709-3-maz@kernel.org
irqdomain.c's kernel-doc exists, but is not plugged into Documentation/
yet.
Before plugging it in, fix it first: irq_domain_get_irq_data() and
irq_domain_set_info() were documented twice. Identically, by both
definitions for CONFIG_IRQ_DOMAIN_HIERARCHY and !CONFIG_IRQ_DOMAIN_HIERARCHY.
Therefore, switch the second kernel-doc into an ordinary comment -- change
"/**" to simple "/*". This avoids sphinx's: WARNING: Duplicate C
declaration
Next, in commit b7b377332b ("irqdomain: Fix the kernel-doc and plug it
into Documentation"), irqdomain.h's (header) kernel-doc was added into
core-api/genericirq.rst. But given the amount of irqdomain functions and
structures, move all these to core-api/irq/irq-domain.rst now.
Finally, add these newly fixed irqdomain.c's (source) docs there as
well.
Signed-off-by: Jiri Slaby (SUSE) <jirislaby@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250319092951.37667-58-jirislaby@kernel.org
Most irq_domain_add_*() functions are unused now, so drop them. The
remaining ones are moved to the deprecated section and will be removed
during the merge window after the patches in various trees have been
merged.
Note: The Chinese docs are touched but unfinished. I cannot parse those.
[ tglx: Remove the leftover in irq-domain.rst and handle merge logistics ]
Signed-off-by: Jiri Slaby (SUSE) <jirislaby@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250319092951.37667-41-jirislaby@kernel.org
All uses of of_node_to_fwnode() in non-irqdomain code were changed to
"officially" defined of_fwnode_handle(). Therefore, the former can be
dropped along with the last uses in the irqdomain code.
Due to merge logistics the inline cannot be dropped immediately. Move it to
a deprecated section, which will be removed during the merge window.
[ tglx: Handle merge logistics ]
Signed-off-by: Jiri Slaby (SUSE) <jirislaby@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250319092951.37667-12-jirislaby@kernel.org
Currently, the ->gpwrap is not tested (at all per my testing) due to the
requirement of a large delta between a CPU's rdp->gp_seq and its node's
rnp->gpseq.
This results in no testing of ->gpwrap being set. This patch by default
adds 5 minutes of testing with ->gpwrap forced by lowering the delta
between rdp->gp_seq and rnp->gp_seq to just 8 GPs. All of this is
configurable, including the active time for the setting and a full
testing cycle.
By default, the first 25 minutes of a test will have the _default_
behavior there is right now (ULONG_MAX / 4) delta. Then for 5 minutes,
we switch to a smaller delta causing 1-2 wraps in 5 minutes. I believe
this is reasonable since we at least add a little bit of testing for
usecases where ->gpwrap is set.
[ Apply fix for Dan Carpenter's bug report on init path cleanup. ]
[ Apply kernel doc warning fix from Akira Yokosawa. ]
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
The rcu_torture_reader() and rcu_torture_fwd_prog_cr() functions
run CPU-bound for extended periods of time (tens or even
hundreds of milliseconds), so they invoke tick_dep_set_task() and
tick_dep_clear_task() to ensure that the scheduling-clock tick helps
move grace periods forward.
So why doesn't rcu_torture_fwd_prog_nr() also invoke tick_dep_set_task()
and tick_dep_clear_task()? Because the point of this function is to test
RCU's ability to (eventually) force grace periods forward even when the
tick has been disabled during long CPU-bound kernel execution.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
For built with CONFIG_PROVE_RCU=y and CONFIG_PREEMPT_RT=y kernels,
Disable BH does not change the SOFTIRQ corresponding bits in
preempt_count(), but change current->softirq_disable_cnt, this
resulted in the following splat:
WARNING: suspicious RCU usage
kernel/rcu/tree_plugin.h:36 Unsafe read of RCU_NOCB offloaded state!
stack backtrace:
CPU: 0 UID: 0 PID: 22 Comm: rcuc/0
Call Trace:
[ 0.407907] <TASK>
[ 0.407910] dump_stack_lvl+0xbb/0xd0
[ 0.407917] dump_stack+0x14/0x20
[ 0.407920] lockdep_rcu_suspicious+0x133/0x210
[ 0.407932] rcu_rdp_is_offloaded+0x1c3/0x270
[ 0.407939] rcu_core+0x471/0x900
[ 0.407942] ? lockdep_hardirqs_on+0xd5/0x160
[ 0.407954] rcu_cpu_kthread+0x25f/0x870
[ 0.407959] ? __pfx_rcu_cpu_kthread+0x10/0x10
[ 0.407966] smpboot_thread_fn+0x34c/0xa50
[ 0.407970] ? trace_preempt_on+0x54/0x120
[ 0.407977] ? __pfx_smpboot_thread_fn+0x10/0x10
[ 0.407982] kthread+0x40e/0x840
[ 0.407990] ? __pfx_kthread+0x10/0x10
[ 0.407994] ? rt_spin_unlock+0x4e/0xb0
[ 0.407997] ? rt_spin_unlock+0x4e/0xb0
[ 0.408000] ? __pfx_kthread+0x10/0x10
[ 0.408006] ? __pfx_kthread+0x10/0x10
[ 0.408011] ret_from_fork+0x40/0x70
[ 0.408013] ? __pfx_kthread+0x10/0x10
[ 0.408018] ret_from_fork_asm+0x1a/0x30
[ 0.408042] </TASK>
Currently, triggering an rdp offloaded state change need the
corresponding rdp's CPU goes offline, and at this time the rcuc
kthreads has already in parking state. this means the corresponding
rcuc kthreads can safely read offloaded state of rdp while it's
corresponding cpu is online.
This commit therefore add softirq_count() check for
Preempt-RT kernels.
Suggested-by: Joel Fernandes <joelagnelf@nvidia.com>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Zqiang <qiang.zhang1211@gmail.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
perf always allocates contiguous AUX pages based on aux_watermark.
However, this contiguous allocation doesn't benefit all PMUs. For
instance, ARM SPE and TRBE operate with virtual pages, and Coresight
ETR allocates a separate buffer. For these PMUs, allocating contiguous
AUX pages unnecessarily exacerbates memory fragmentation. This
fragmentation can prevent their use on long-running devices.
This patch modifies the perf driver to be memory-friendly by default,
by allocating non-contiguous AUX pages. For PMUs requiring contiguous
pages (Intel BTS and some Intel PT), the existing
PERF_PMU_CAP_AUX_NO_SG capability can be used. For PMUs that don't
require but can benefit from contiguous pages (some Intel PT), a new
capability, PERF_PMU_CAP_AUX_PREFER_LARGE, is added to maintain their
existing behavior.
Signed-off-by: Yabin Cui <yabinc@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: James Clark <james.clark@linaro.org>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20250508232642.148767-1-yabinc@google.com
Affinity-managed interrupts can be shut down and restarted during CPU
hotunplug/plug. Thereby the interrupt may be left in an unexpected state.
Specifically:
1. Interrupt is affine to CPU N
2. disable_irq() -> depth is 1
3. CPU N goes offline
4. irq_shutdown() -> depth is set to 1 (again)
5. CPU N goes online
6. irq_startup() -> depth is set to 0 (BUG! driver expects that the interrupt
still disabled)
7. enable_irq() -> depth underflow / unbalanced enable_irq() warning
This is only a problem for managed interrupts and CPU hotplug, all other
cases like request()/free()/request() truly needs to reset a possibly stale
disable depth value.
Provide a startup function, which takes the disable depth into account, and
invoked it for the managed interrupts in the CPU hotplug path.
This requires to change irq_shutdown() to do a depth increment instead of
setting it to 1, which allows to retain the disable depth, but is harmless
for the other code paths using irq_startup(), which will still reset the
disable depth unconditionally to keep the original correct behaviour.
A kunit tests will be added separately to cover some of these aspects.
[ tglx: Massaged changelog ]
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250514201353.3481400-2-briannorris@chromium.org
Pull Kbuild fixes from Masahiro Yamada:
- Add proper pahole version dependency to CONFIG_GENDWARFKSYMS to avoid
module loading errors
- Fix UAPI header tests for the OpenRISC architecture
- Add dependency on the libdw package in Debian and RPM packages
- Disable -Wdefault-const-init-unsafe warnings on Clang
- Make "make clean ARCH=um" also clean the arch/x86/ directory
- Revert the use of -fmacro-prefix-map=, which causes issues with
debugger usability
* tag 'kbuild-fixes-v6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild:
kbuild: fix typos "module.builtin" to "modules.builtin"
Revert "kbuild, rust: use -fremap-path-prefix to make paths relative"
Revert "kbuild: make all file references relative to source root"
kbuild: fix dependency on sorttable
init: remove unused CONFIG_CC_CAN_LINK_STATIC
um: let 'make clean' properly clean underlying SUBARCH as well
kbuild: Disable -Wdefault-const-init-unsafe
kbuild: rpm-pkg: Add (elfutils-devel or libdw-devel) to BuildRequires
kbuild: deb-pkg: Add libdw-dev:native to Build-Depends-Arch
usr/include: openrisc: don't HDRTEST bpf_perf_event.h
kbuild: Require pahole <v1.28 or >v1.29 with GENDWARFKSYMS on X86
There is currently some confusion in the s390x JIT regarding whether
orig_call can be NULL and what that means. Originally the NULL value
was used to distinguish the struct_ops case, but this was superseded by
BPF_TRAMP_F_INDIRECT (see commit 0c970ed2f8 ("s390/bpf: Fix indirect
trampoline generation").
The remaining reason to have this check is that NULL can actually be
passed to the arch_bpf_trampoline_size() call - but not to the
respective arch_prepare_bpf_trampoline()! call - by
bpf_struct_ops_prepare_trampoline().
Remove this asymmetry by passing stub_func to both functions, so that
JITs may rely on orig_call never being NULL.
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Acked-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20250512221911.61314-2-iii@linux.ibm.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Pull tracing fixes from Steven Rostedt:
- Fix sample code that uses trace_array_printk()
The sample code for in kernel use of trace_array (that creates an
instance for use within the kernel) and shows how to use
trace_array_printk() that writes into the created instance, used
trace_printk_init_buffers(). But that function is used to initialize
normal trace_printk() and produces the NOTICE banner which is not
needed for use of trace_array_printk(). The function to initialize
that is trace_array_init_printk() that takes the created trace array
instance as a parameter.
Update the sample code to reflect the proper usage.
- Fix preemption count output for stacktrace event
The tracing buffer shows the preempt count level when an event
executes. Because writing the event itself disables preemption, this
needs to be accounted for when recording. The stacktrace event did
not account for this so the output of the stacktrace event showed
preemption was disabled while the event that triggered the stacktrace
shows preemption is enabled and this leads to confusion. Account for
preemption being disabled for the stacktrace event.
The same happened for stack traces triggered by function tracer.
- Fix persistent ring buffer when trace_pipe is used
The ring buffer swaps the reader page with the next page to read from
the write buffer when trace_pipe is used. If there's only a page of
data in the ring buffer, this swap will cause the "commit" pointer
(last data written) to be on the reader page. If more data is written
to the buffer, it is added to the reader page until it falls off back
into the write buffer.
If the system reboots and the commit pointer is still on the reader
page, even if new data was written, the persistent buffer validator
will miss finding the commit pointer because it only checks the write
buffer and does not check the reader page. This causes the validator
to fail the validation and clear the buffer, where the new data is
lost.
There was a check for this, but it checked the "head pointer", which
was incorrect, because the "head pointer" always stays on the write
buffer and is the next page to swap out for the reader page. Fix the
logic to catch this case and allow the user to still read the data
after reboot.
* tag 'trace-v6.15-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
ring-buffer: Fix persistent buffer when commit page is the reader page
ftrace: Fix preemption accounting for stacktrace filter command
ftrace: Fix preemption accounting for stacktrace trigger command
tracing: samples: Initialize trace_array_printk() with the correct function
The ring buffer is made up of sub buffers (sometimes called pages as they
are by default PAGE_SIZE). It has the following "pages":
"tail page" - this is the page that the next write will write to
"head page" - this is the page that the reader will swap the reader page with.
"reader page" - This belongs to the reader, where it will swap the head
page from the ring buffer so that the reader does not
race with the writer.
The writer may end up on the "reader page" if the ring buffer hasn't
written more than one page, where the "tail page" and the "head page" are
the same.
The persistent ring buffer has meta data that points to where these pages
exist so on reboot it can re-create the pointers to the cpu_buffer
descriptor. But when the commit page is on the reader page, the logic is
incorrect.
The check to see if the commit page is on the reader page checked if the
head page was the reader page, which would never happen, as the head page
is always in the ring buffer. The correct check would be to test if the
commit page is on the reader page. If that's the case, then it can exit
out early as the commit page is only on the reader page when there's only
one page of data in the buffer. There's no reason to iterate the ring
buffer pages to find the "commit page" as it is already found.
To trigger this bug:
# echo 1 > /sys/kernel/tracing/instances/boot_mapped/events/syscalls/sys_enter_fchownat/enable
# touch /tmp/x
# chown sshd /tmp/x
# reboot
On boot up, the dmesg will have:
Ring buffer meta [0] is from previous boot!
Ring buffer meta [1] is from previous boot!
Ring buffer meta [2] is from previous boot!
Ring buffer meta [3] is from previous boot!
Ring buffer meta [4] commit page not found
Ring buffer meta [5] is from previous boot!
Ring buffer meta [6] is from previous boot!
Ring buffer meta [7] is from previous boot!
Where the buffer on CPU 4 had a "commit page not found" error and that
buffer is cleared and reset causing the output to be empty and the data lost.
When it works correctly, it has:
# cat /sys/kernel/tracing/instances/boot_mapped/trace_pipe
<...>-1137 [004] ..... 998.205323: sys_enter_fchownat: __syscall_nr=0x104 (260) dfd=0xffffff9c (4294967196) filename=(0xffffc90000a0002c) user=0x3e8 (1000) group=0xffffffff (4294967295) flag=0x0 (0
Cc: stable@vger.kernel.org
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20250513115032.3e0b97f7@gandalf.local.home
Fixes: 5f3b6e839f ("ring-buffer: Validate boot range memory events")
Reported-by: Tasos Sahanidis <tasos@tasossah.com>
Tested-by: Tasos Sahanidis <tasos@tasossah.com>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
When using the stacktrace trigger command to trace syscalls, the
preemption count was consistently reported as 1 when the system call
event itself had 0 (".").
For example:
root@ubuntu22-vm:/sys/kernel/tracing/events/syscalls/sys_enter_read
$ echo stacktrace > trigger
$ echo 1 > enable
sshd-416 [002] ..... 232.864910: sys_read(fd: a, buf: 556b1f3221d0, count: 8000)
sshd-416 [002] ...1. 232.864913: <stack trace>
=> ftrace_syscall_enter
=> syscall_trace_enter
=> do_syscall_64
=> entry_SYSCALL_64_after_hwframe
The root cause is that the trace framework disables preemption in __DO_TRACE before
invoking the trigger callback.
Use the tracing_gen_ctx_dec() that will accommodate for the increase of
the preemption count in __DO_TRACE when calling the callback. The result
is the accurate reporting of:
sshd-410 [004] ..... 210.117660: sys_read(fd: 4, buf: 559b725ba130, count: 40000)
sshd-410 [004] ..... 210.117662: <stack trace>
=> ftrace_syscall_enter
=> syscall_trace_enter
=> do_syscall_64
=> entry_SYSCALL_64_after_hwframe
Cc: stable@vger.kernel.org
Fixes: ce33c845b0 ("tracing: Dump stacktrace trigger to the corresponding instance")
Link: https://lore.kernel.org/20250512094246.1167956-1-dolinux.peng@gmail.com
Signed-off-by: pengdonglin <dolinux.peng@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Naked scx_root dereferences are being used as temporary markers to indicate
that they need to be updated to point to the right scheduler instance.
Explain the situation.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Andrea Righi <arighi@nvidia.com>
In preparation of hierarchical scheduling support, add @sch to scx_exit()
and friends:
- scx_exit/error() updated to take explicit @sch instead of assuming
scx_root.
- scx_kf_exit/error() added. These are to be used from kfuncs, don't take
@sch and internally determine the scx_sched instance to abort. Currently,
it's always scx_root but once multiple scheduler support is in place, it
will be the scx_sched instance that invoked the kfunc. This simplifies
many callsites and defers scx_sched lookup until error is triggered.
- @sch is propagated to ops_cpu_valid() and ops_sanitize_err(). The CPU
validity conditions in ops_cpu_valid() are factored into __cpu_valid() to
implement kf_cpu_valid() which is the counterpart to scx_kf_exit/error().
- All users are converted. Most conversions are straightforward.
check_rq_for_timeouts() and scx_softlockup() are updated to use explicit
rcu_dereference*(scx_root) for safety as they may execute asynchronous to
the exit path. scx_tick() is also updated to use rcu_dereference(). While
not strictly necessary due to the preceding scx_enabled() test and IRQ
disabled context, this removes the subtlety at no noticeable cost.
No behavior changes intended.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
__scx_exit() is the base exit implementation and there are three wrappers on
top of it - scx_exit(), __scx_error() and scx_error(). This is more
confusing than helpful especially given that there are only a couple users
of scx_exit() and __scx_error(). To simplify the situation:
- Make __scx_exit() take va_list and rename it to scx_vexit(). This is to
ease implementing more complex extensions on top.
- Make scx_exit() a varargs wrapper around __scx_exit(). scx_exit() now
takes both @kind and @exit_code.
- Convert existing scx_exit() and __scx_error() users to use the new
scx_exit().
- scx_error() remains unchanged.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
In preparation of hierarchical scheduling support, make SCX_CALL_OP*() take
explicit @sch instead of assuming scx_root. As scx_root is still the only
scheduler instance, this patch doesn't make any functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
- Always cache scx_root into local variable sch before using.
- Don't use scx_root if cached sch is available.
- Wrap !sch test with unlikely().
- Pass @scx into scx_cgroup_init/exit().
No behavior changes intended.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
The current device MSI infrastructure is subtly broken, as it will issue an
.msi_prepare() callback into the MSI controller driver every time it needs
to allocate an MSI. That's pretty wrong, as the contract (or unwarranted
assumption, depending who you ask) between the MSI controller and the core
code is that .msi_prepare() is called exactly once per device.
This leads to some subtle breakage in some MSI controller drivers, as it
gives the impression that there are multiple endpoints sharing a bus
identifier (RID in PCI parlance, DID for GICv3+). It implies that whatever
allocation the ITS driver (for example) has done on behalf of these devices
cannot be undone, as there is no way to track the shared state. This is
particularly bad for wire-MSI devices, for which .msi_prepare() is called
for each input line.
To address this issue, move the call to .msi_prepare() to take place at the
point of irq domain allocation, which is the only place that makes
sense. The msi_alloc_info_t structure is made part of the
msi_domain_template, so that its life-cycle is that of the domain as well.
Finally, the msi_info::alloc_data field is made to point at this allocation
tracking structure, ensuring that it is carried around the block.
This is all pretty straightforward, except for the non-device-MSI
leftovers, which still have to call .msi_prepare() at the old spot. One
day...
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250513163144.2215824-4-maz@kernel.org
The ITS driver currently nukes the structure representing an endpoint
device translating via an ITS on freeing the last LPI allocated for it.
That's an unfortunate state of affair, as it is pretty common for a driver
to allocate a single MSI, do something clever, teardown this MSI, and
reallocate a whole bunch of them. The NVME driver does exactly that,
amongst others.
What happens in that case is that the core code is accidentaly issuing
another .msi_prepare() call, even if it shouldn't. This luckily cancels
the above behaviour and hides the problem.
In order to fix the core code, start by implementing the new
.msi_teardown() callback. Nothing calls it yet, so a side effect is that
the its_dev structure will not be freed and that the DID will stay
mapped. Not a big deal, and this will be solved in following patches.
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250513163144.2215824-3-maz@kernel.org
While the MSI ops do have a .msi_prepare() callback that is responsible for
setting up the relevant (usually per-device) allocation, there is no
callback reversing this setup.
For this purpose, add .msi_teardown() callback.
In order to avoid breaking the ITS driver that suffers from related issues,
do not call the callback just yet.
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250513163144.2215824-2-maz@kernel.org
Commit 8589e325ba ("genirq/manage: Rework irq_set_irq_wake()") updated
the irq_set_irq_wake() to use the new guards for locking the interrupt
descriptor.
However, in doing so it inadvertently changed irq_set_irq_wake() such that
the 'chip_bus_lock' is no longer acquired. This has caused system suspend
tests to fail on some Tegra platforms.
Fix this by correcting the guard used in irq_set_irq_wake() to ensure the
'chip_bus_lock' is held.
Fixes: 8589e325ba ("genirq/manage: Rework irq_set_irq_wake()")
Signed-off-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250514095041.1109783-1-jonathanh@nvidia.com
Instead of hardcoding the list of kfuncs that need prog->aux passed to
them with a combination of fixup_kfunc_call adjustment + __ign suffix,
combine both in __prog suffix, which ignores the argument passed in, and
fixes it up to the prog->aux. This allows kfuncs to have the prog->aux
passed into them without having to touch the verifier.
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20250513142812.1021591-1-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
