The bpf_remove_insns() function returns WARN_ON_ONCE(error), where
error is a result of bpf_adj_branches(), and thus should be always 0
However, if for any reason it is not 0, then it will be converted to
boolean by WARN_ON_ONCE and returned to user space as 1, not an actual
error value. Fix this by returning the original err after the WARN check.
Signed-off-by: Anton Protopopov <aspsk@isovalent.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20241210114245.836164-1-aspsk@isovalent.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
When processing calls to global sub-programs, verifier decides whether
to invalidate all packet pointers in current state depending on the
changes_pkt_data property of the global sub-program.
Because of this, an extension program replacing a global sub-program
must be compatible with changes_pkt_data property of the sub-program
being replaced.
This commit:
- adds changes_pkt_data flag to struct bpf_prog_aux:
- this flag is set in check_cfg() for main sub-program;
- in jit_subprogs() for other sub-programs;
- modifies bpf_check_attach_btf_id() to check changes_pkt_data flag;
- moves call to check_attach_btf_id() after the call to check_cfg(),
because it needs changes_pkt_data flag to be set:
bpf_check:
... ...
- check_attach_btf_id resolve_pseudo_ldimm64
resolve_pseudo_ldimm64 --> bpf_prog_is_offloaded
bpf_prog_is_offloaded check_cfg
check_cfg + check_attach_btf_id
... ...
The following fields are set by check_attach_btf_id():
- env->ops
- prog->aux->attach_btf_trace
- prog->aux->attach_func_name
- prog->aux->attach_func_proto
- prog->aux->dst_trampoline
- prog->aux->mod
- prog->aux->saved_dst_attach_type
- prog->aux->saved_dst_prog_type
- prog->expected_attach_type
Neither of these fields are used by resolve_pseudo_ldimm64() or
bpf_prog_offload_verifier_prep() (for netronome and netdevsim
drivers), so the reordering is safe.
Suggested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20241210041100.1898468-6-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
When processing calls to certain helpers, verifier invalidates all
packet pointers in a current state. For example, consider the
following program:
__attribute__((__noinline__))
long skb_pull_data(struct __sk_buff *sk, __u32 len)
{
return bpf_skb_pull_data(sk, len);
}
SEC("tc")
int test_invalidate_checks(struct __sk_buff *sk)
{
int *p = (void *)(long)sk->data;
if ((void *)(p + 1) > (void *)(long)sk->data_end) return TCX_DROP;
skb_pull_data(sk, 0);
*p = 42;
return TCX_PASS;
}
After a call to bpf_skb_pull_data() the pointer 'p' can't be used
safely. See function filter.c:bpf_helper_changes_pkt_data() for a list
of such helpers.
At the moment verifier invalidates packet pointers when processing
helper function calls, and does not traverse global sub-programs when
processing calls to global sub-programs. This means that calls to
helpers done from global sub-programs do not invalidate pointers in
the caller state. E.g. the program above is unsafe, but is not
rejected by verifier.
This commit fixes the omission by computing field
bpf_subprog_info->changes_pkt_data for each sub-program before main
verification pass.
changes_pkt_data should be set if:
- subprogram calls helper for which bpf_helper_changes_pkt_data
returns true;
- subprogram calls a global function,
for which bpf_subprog_info->changes_pkt_data should be set.
The verifier.c:check_cfg() pass is modified to compute this
information. The commit relies on depth first instruction traversal
done by check_cfg() and absence of recursive function calls:
- check_cfg() would eventually visit every call to subprogram S in a
state when S is fully explored;
- when S is fully explored:
- every direct helper call within S is explored
(and thus changes_pkt_data is set if needed);
- every call to subprogram S1 called by S was visited with S1 fully
explored (and thus S inherits changes_pkt_data from S1).
The downside of such approach is that dead code elimination is not
taken into account: if a helper call inside global function is dead
because of current configuration, verifier would conservatively assume
that the call occurs for the purpose of the changes_pkt_data
computation.
Reported-by: Nick Zavaritsky <mejedi@gmail.com>
Closes: https://lore.kernel.org/bpf/0498CA22-5779-4767-9C0C-A9515CEA711F@gmail.com/
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20241210041100.1898468-4-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Use BPF helper number instead of function pointer in
bpf_helper_changes_pkt_data(). This would simplify usage of this
function in verifier.c:check_cfg() (in a follow-up patch),
where only helper number is easily available and there is no real need
to lookup helper proto.
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20241210041100.1898468-3-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Syzbot reported [1] crash that happens for following tracing scenario:
- create tracepoint perf event with attr.inherit=1, attach it to the
process and set bpf program to it
- attached process forks -> chid creates inherited event
the new child event shares the parent's bpf program and tp_event
(hence prog_array) which is global for tracepoint
- exit both process and its child -> release both events
- first perf_event_detach_bpf_prog call will release tp_event->prog_array
and second perf_event_detach_bpf_prog will crash, because
tp_event->prog_array is NULL
The fix makes sure the perf_event_detach_bpf_prog checks prog_array
is valid before it tries to remove the bpf program from it.
[1] https://lore.kernel.org/bpf/Z1MR6dCIKajNS6nU@krava/T/#m91dbf0688221ec7a7fc95e896a7ef9ff93b0b8ad
Fixes: 0ee288e69d ("bpf,perf: Fix perf_event_detach_bpf_prog error handling")
Reported-by: syzbot+2e0d2840414ce817aaac@syzkaller.appspotmail.com
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20241208142507.1207698-1-jolsa@kernel.org
Uprobes always use bpf_prog_run_array_uprobe() under tasks-trace-RCU
protection. But it is possible to attach a non-sleepable BPF program to a
uprobe, and non-sleepable BPF programs are freed via normal RCU (see
__bpf_prog_put_noref()). This leads to UAF of the bpf_prog because a normal
RCU grace period does not imply a tasks-trace-RCU grace period.
Fix it by explicitly waiting for a tasks-trace-RCU grace period after
removing the attachment of a bpf_prog to a perf_event.
Fixes: 8c7dcb84e3 ("bpf: implement sleepable uprobes by chaining gps")
Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Suggested-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/bpf/20241210-bpf-fix-actual-uprobe-uaf-v1-1-19439849dd44@google.com
Pull scheduler fixes from Borislav Petkov:
- Remove wrong enqueueing of a task for a later wakeup when a task
blocks on a RT mutex
- Do not setup a new deadline entity on a boosted task as that has
happened already
- Update preempt= kernel command line param
- Prevent needless softirqd wakeups in the idle task's context
- Detect the case where the idle load balancer CPU becomes busy and
avoid unnecessary load balancing invocation
- Remove an unnecessary load balancing need_resched() call in
nohz_csd_func()
- Allow for raising of SCHED_SOFTIRQ softirq type on RT but retain the
warning to catch any other cases
- Remove a wrong warning when a cpuset update makes the task affinity
no longer a subset of the cpuset
* tag 'sched_urgent_for_v6.13_rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
locking: rtmutex: Fix wake_q logic in task_blocks_on_rt_mutex
sched/deadline: Fix warning in migrate_enable for boosted tasks
sched/core: Update kernel boot parameters for LAZY preempt.
sched/core: Prevent wakeup of ksoftirqd during idle load balance
sched/fair: Check idle_cpu() before need_resched() to detect ilb CPU turning busy
sched/core: Remove the unnecessary need_resched() check in nohz_csd_func()
softirq: Allow raising SCHED_SOFTIRQ from SMP-call-function on RT kernel
sched: fix warning in sched_setaffinity
sched/deadline: Fix replenish_dl_new_period dl_server condition
The powerpc user access code is special, and unlike other architectures
distinguishes between user access for reading and writing.
And commit 43a43faf53 ("futex: improve user space accesses") messed
that up. It went undetected elsewhere, but caused ppc32 to fail early
during boot, because the user access had been started with
user_read_access_begin(), but then finished off with just a plain
"user_access_end()".
Note that the address-masking user access helpers don't even have that
read-vs-write distinction, so if powerpc ever wants to do address
masking tricks, we'll have to do some extra work for it.
[ Make sure to also do it for the EFAULT case, as pointed out by
Christophe Leroy ]
Reported-by: Andreas Schwab <schwab@linux-m68k.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Link: https://lore.kernel.org/all/87bjxl6b0i.fsf@igel.home/
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull irq fixes from Borislav Petkov:
- Fix a /proc/interrupts formatting regression
- Have the BCM2836 interrupt controller enter power management states
properly
- Other fixlets
* tag 'irq_urgent_for_v6.13_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
irqchip/stm32mp-exti: CONFIG_STM32MP_EXTI should not default to y when compile-testing
genirq/proc: Add missing space separator back
irqchip/bcm2836: Enable SKIP_SET_WAKE and MASK_ON_SUSPEND
irqchip/gic-v3: Fix irq_complete_ack() comment
Pull timer fix from Borislav Petkov:
- Handle the case where clocksources with small counter width can,
in conjunction with overly long idle sleeps, falsely trigger the
negative motion detection of clocksources
* tag 'timers_urgent_for_v6.13_rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
clocksource: Make negative motion detection more robust
Pull misc fixes from Andrew Morton:
"24 hotfixes. 17 are cc:stable. 15 are MM and 9 are non-MM.
The usual bunch of singletons - please see the relevant changelogs for
details"
* tag 'mm-hotfixes-stable-2024-12-07-22-39' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (24 commits)
iio: magnetometer: yas530: use signed integer type for clamp limits
sched/numa: fix memory leak due to the overwritten vma->numab_state
mm/damon: fix order of arguments in damos_before_apply tracepoint
lib: stackinit: hide never-taken branch from compiler
mm/filemap: don't call folio_test_locked() without a reference in next_uptodate_folio()
scatterlist: fix incorrect func name in kernel-doc
mm: correct typo in MMAP_STATE() macro
mm: respect mmap hint address when aligning for THP
mm: memcg: declare do_memsw_account inline
mm/codetag: swap tags when migrate pages
ocfs2: update seq_file index in ocfs2_dlm_seq_next
stackdepot: fix stack_depot_save_flags() in NMI context
mm: open-code page_folio() in dump_page()
mm: open-code PageTail in folio_flags() and const_folio_flags()
mm: fix vrealloc()'s KASAN poisoning logic
Revert "readahead: properly shorten readahead when falling back to do_page_cache_ra()"
selftests/damon: add _damon_sysfs.py to TEST_FILES
selftest: hugetlb_dio: fix test naming
ocfs2: free inode when ocfs2_get_init_inode() fails
nilfs2: fix potential out-of-bounds memory access in nilfs_find_entry()
...
Pull bpf fixes from Daniel Borkmann::
- Fix several issues for BPF LPM trie map which were found by syzbot
and during addition of new test cases (Hou Tao)
- Fix a missing process_iter_arg register type check in the BPF
verifier (Kumar Kartikeya Dwivedi, Tao Lyu)
- Fix several correctness gaps in the BPF verifier when interacting
with the BPF stack without CAP_PERFMON (Kumar Kartikeya Dwivedi,
Eduard Zingerman, Tao Lyu)
- Fix OOB BPF map writes when deleting elements for the case of xsk map
as well as devmap (Maciej Fijalkowski)
- Fix xsk sockets to always clear DMA mapping information when
unmapping the pool (Larysa Zaremba)
- Fix sk_mem_uncharge logic in tcp_bpf_sendmsg to only uncharge after
sent bytes have been finalized (Zijian Zhang)
- Fix BPF sockmap with vsocks which was missing a queue check in poll
and sockmap cleanup on close (Michal Luczaj)
- Fix tools infra to override makefile ARCH variable if defined but
empty, which addresses cross-building tools. (Björn Töpel)
- Fix two resolve_btfids build warnings on unresolved bpf_lsm symbols
(Thomas Weißschuh)
- Fix a NULL pointer dereference in bpftool (Amir Mohammadi)
- Fix BPF selftests to check for CONFIG_PREEMPTION instead of
CONFIG_PREEMPT (Sebastian Andrzej Siewior)
* tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf: (31 commits)
selftests/bpf: Add more test cases for LPM trie
selftests/bpf: Move test_lpm_map.c to map_tests
bpf: Use raw_spinlock_t for LPM trie
bpf: Switch to bpf mem allocator for LPM trie
bpf: Fix exact match conditions in trie_get_next_key()
bpf: Handle in-place update for full LPM trie correctly
bpf: Handle BPF_EXIST and BPF_NOEXIST for LPM trie
bpf: Remove unnecessary kfree(im_node) in lpm_trie_update_elem
bpf: Remove unnecessary check when updating LPM trie
selftests/bpf: Add test for narrow spill into 64-bit spilled scalar
selftests/bpf: Add test for reading from STACK_INVALID slots
selftests/bpf: Introduce __caps_unpriv annotation for tests
bpf: Fix narrow scalar spill onto 64-bit spilled scalar slots
bpf: Don't mark STACK_INVALID as STACK_MISC in mark_stack_slot_misc
samples/bpf: Remove unnecessary -I flags from libbpf EXTRA_CFLAGS
bpf: Zero index arg error string for dynptr and iter
selftests/bpf: Add tests for iter arg check
bpf: Ensure reg is PTR_TO_STACK in process_iter_arg
tools: Override makefile ARCH variable if defined, but empty
selftests/bpf: Add apply_bytes test to test_txmsg_redir_wait_sndmem in test_sockmap
...
After switching from kmalloc() to the bpf memory allocator, there will be
no blocking operation during the update of LPM trie. Therefore, change
trie->lock from spinlock_t to raw_spinlock_t to make LPM trie usable in
atomic context, even on RT kernels.
The max value of prefixlen is 2048. Therefore, update or deletion
operations will find the target after at most 2048 comparisons.
Constructing a test case which updates an element after 2048 comparisons
under a 8 CPU VM, and the average time and the maximal time for such
update operation is about 210us and 900us.
Signed-off-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20241206110622.1161752-8-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Multiple syzbot warnings have been reported. These warnings are mainly
about the lock order between trie->lock and kmalloc()'s internal lock.
See report [1] as an example:
======================================================
WARNING: possible circular locking dependency detected
6.10.0-rc7-syzkaller-00003-g4376e966ecb7 #0 Not tainted
------------------------------------------------------
syz.3.2069/15008 is trying to acquire lock:
ffff88801544e6d8 (&n->list_lock){-.-.}-{2:2}, at: get_partial_node ...
but task is already holding lock:
ffff88802dcc89f8 (&trie->lock){-.-.}-{2:2}, at: trie_update_elem ...
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #1 (&trie->lock){-.-.}-{2:2}:
__raw_spin_lock_irqsave
_raw_spin_lock_irqsave+0x3a/0x60
trie_delete_elem+0xb0/0x820
___bpf_prog_run+0x3e51/0xabd0
__bpf_prog_run32+0xc1/0x100
bpf_dispatcher_nop_func
......
bpf_trace_run2+0x231/0x590
__bpf_trace_contention_end+0xca/0x110
trace_contention_end.constprop.0+0xea/0x170
__pv_queued_spin_lock_slowpath+0x28e/0xcc0
pv_queued_spin_lock_slowpath
queued_spin_lock_slowpath
queued_spin_lock
do_raw_spin_lock+0x210/0x2c0
__raw_spin_lock_irqsave
_raw_spin_lock_irqsave+0x42/0x60
__put_partials+0xc3/0x170
qlink_free
qlist_free_all+0x4e/0x140
kasan_quarantine_reduce+0x192/0x1e0
__kasan_slab_alloc+0x69/0x90
kasan_slab_alloc
slab_post_alloc_hook
slab_alloc_node
kmem_cache_alloc_node_noprof+0x153/0x310
__alloc_skb+0x2b1/0x380
......
-> #0 (&n->list_lock){-.-.}-{2:2}:
check_prev_add
check_prevs_add
validate_chain
__lock_acquire+0x2478/0x3b30
lock_acquire
lock_acquire+0x1b1/0x560
__raw_spin_lock_irqsave
_raw_spin_lock_irqsave+0x3a/0x60
get_partial_node.part.0+0x20/0x350
get_partial_node
get_partial
___slab_alloc+0x65b/0x1870
__slab_alloc.constprop.0+0x56/0xb0
__slab_alloc_node
slab_alloc_node
__do_kmalloc_node
__kmalloc_node_noprof+0x35c/0x440
kmalloc_node_noprof
bpf_map_kmalloc_node+0x98/0x4a0
lpm_trie_node_alloc
trie_update_elem+0x1ef/0xe00
bpf_map_update_value+0x2c1/0x6c0
map_update_elem+0x623/0x910
__sys_bpf+0x90c/0x49a0
...
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(&trie->lock);
lock(&n->list_lock);
lock(&trie->lock);
lock(&n->list_lock);
*** DEADLOCK ***
[1]: https://syzkaller.appspot.com/bug?extid=9045c0a3d5a7f1b119f7
A bpf program attached to trace_contention_end() triggers after
acquiring &n->list_lock. The program invokes trie_delete_elem(), which
then acquires trie->lock. However, it is possible that another
process is invoking trie_update_elem(). trie_update_elem() will acquire
trie->lock first, then invoke kmalloc_node(). kmalloc_node() may invoke
get_partial_node() and try to acquire &n->list_lock (not necessarily the
same lock object). Therefore, lockdep warns about the circular locking
dependency.
Invoking kmalloc() before acquiring trie->lock could fix the warning.
However, since BPF programs call be invoked from any context (e.g.,
through kprobe/tracepoint/fentry), there may still be lock ordering
problems for internal locks in kmalloc() or trie->lock itself.
To eliminate these potential lock ordering problems with kmalloc()'s
internal locks, replacing kmalloc()/kfree()/kfree_rcu() with equivalent
BPF memory allocator APIs that can be invoked in any context. The lock
ordering problems with trie->lock (e.g., reentrance) will be handled
separately.
Three aspects of this change require explanation:
1. Intermediate and leaf nodes are allocated from the same allocator.
Since the value size of LPM trie is usually small, using a single
alocator reduces the memory overhead of the BPF memory allocator.
2. Leaf nodes are allocated before disabling IRQs. This handles cases
where leaf_size is large (e.g., > 4KB - 8) and updates require
intermediate node allocation. If leaf nodes were allocated in
IRQ-disabled region, the free objects in BPF memory allocator would not
be refilled timely and the intermediate node allocation may fail.
3. Paired migrate_{disable|enable}() calls for node alloc and free. The
BPF memory allocator uses per-CPU struct internally, these paired calls
are necessary to guarantee correctness.
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20241206110622.1161752-7-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
trie_get_next_key() uses node->prefixlen == key->prefixlen to identify
an exact match, However, it is incorrect because when the target key
doesn't fully match the found node (e.g., node->prefixlen != matchlen),
these two nodes may also have the same prefixlen. It will return
expected result when the passed key exist in the trie. However when a
recently-deleted key or nonexistent key is passed to
trie_get_next_key(), it may skip keys and return incorrect result.
Fix it by using node->prefixlen == matchlen to identify exact matches.
When the condition is true after the search, it also implies
node->prefixlen equals key->prefixlen, otherwise, the search would
return NULL instead.
Fixes: b471f2f1de ("bpf: implement MAP_GET_NEXT_KEY command for LPM_TRIE map")
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20241206110622.1161752-6-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
When a LPM trie is full, in-place updates of existing elements
incorrectly return -ENOSPC.
Fix this by deferring the check of trie->n_entries. For new insertions,
n_entries must not exceed max_entries. However, in-place updates are
allowed even when the trie is full.
Fixes: b95a5c4db0 ("bpf: add a longest prefix match trie map implementation")
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20241206110622.1161752-5-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
When "node->prefixlen == matchlen" is true, it means that the node is
fully matched. If "node->prefixlen == key->prefixlen" is false, it means
the prefix length of key is greater than the prefix length of node,
otherwise, matchlen will not be equal with node->prefixlen. However, it
also implies that the prefix length of node must be less than
max_prefixlen.
Therefore, "node->prefixlen == trie->max_prefixlen" will always be false
when the check of "node->prefixlen == key->prefixlen" returns false.
Remove this unnecessary comparison.
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20241206110622.1161752-2-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
[Problem Description]
When running the hackbench program of LTP, the following memory leak is
reported by kmemleak.
# /opt/ltp/testcases/bin/hackbench 20 thread 1000
Running with 20*40 (== 800) tasks.
# dmesg | grep kmemleak
...
kmemleak: 480 new suspected memory leaks (see /sys/kernel/debug/kmemleak)
kmemleak: 665 new suspected memory leaks (see /sys/kernel/debug/kmemleak)
# cat /sys/kernel/debug/kmemleak
unreferenced object 0xffff888cd8ca2c40 (size 64):
comm "hackbench", pid 17142, jiffies 4299780315
hex dump (first 32 bytes):
ac 74 49 00 01 00 00 00 4c 84 49 00 01 00 00 00 .tI.....L.I.....
00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
backtrace (crc bff18fd4):
[<ffffffff81419a89>] __kmalloc_cache_noprof+0x2f9/0x3f0
[<ffffffff8113f715>] task_numa_work+0x725/0xa00
[<ffffffff8110f878>] task_work_run+0x58/0x90
[<ffffffff81ddd9f8>] syscall_exit_to_user_mode+0x1c8/0x1e0
[<ffffffff81dd78d5>] do_syscall_64+0x85/0x150
[<ffffffff81e0012b>] entry_SYSCALL_64_after_hwframe+0x76/0x7e
...
This issue can be consistently reproduced on three different servers:
* a 448-core server
* a 256-core server
* a 192-core server
[Root Cause]
Since multiple threads are created by the hackbench program (along with
the command argument 'thread'), a shared vma might be accessed by two or
more cores simultaneously. When two or more cores observe that
vma->numab_state is NULL at the same time, vma->numab_state will be
overwritten.
Although current code ensures that only one thread scans the VMAs in a
single 'numa_scan_period', there might be a chance for another thread
to enter in the next 'numa_scan_period' while we have not gotten till
numab_state allocation [1].
Note that the command `/opt/ltp/testcases/bin/hackbench 50 process 1000`
cannot the reproduce the issue. It is verified with 200+ test runs.
[Solution]
Use the cmpxchg atomic operation to ensure that only one thread executes
the vma->numab_state assignment.
[1] https://lore.kernel.org/lkml/1794be3c-358c-4cdc-a43d-a1f841d91ef7@amd.com/
Link: https://lkml.kernel.org/r/20241113102146.2384-1-ahuang12@lenovo.com
Fixes: ef6a22b70f ("sched/numa: apply the scan delay to every new vma")
Signed-off-by: Adrian Huang <ahuang12@lenovo.com>
Reported-by: Jiwei Sun <sunjw10@lenovo.com>
Reviewed-by: Raghavendra K T <raghavendra.kt@amd.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Ben Segall <bsegall@google.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Pull audit build problem workaround from Paul Moore:
"A minor audit patch that shuffles some code slightly to workaround a
GCC bug affecting a number of people.
The GCC folks have been able to reproduce the problem and are
discussing solutions (see the bug report link in the commit), but
since the workaround is trivial let's do that in the kernel so we can
unblock people who are hitting this"
* tag 'audit-pr-20241205' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit:
audit: workaround a GCC bug triggered by task comm changes
Pull tracing fixes from Steven Rostedt:
- Fix trace histogram sort function cmp_entries_dup()
The sort function cmp_entries_dup() returns either 1 or 0, and not -1
if parameter "a" is less than "b" by memcmp().
- Fix archs that call trace_hardirqs_off() without RCU watching
Both x86 and arm64 no longer call any tracepoints with RCU not
watching. It was assumed that it was safe to get rid of
trace_*_rcuidle() version of the tracepoint calls. This was needed to
get rid of the SRCU protection and be able to implement features like
faultable traceponits and add rust tracepoints.
Unfortunately, there were a few architectures that still relied on
that logic. There's only one file that has tracepoints that are
called without RCU watching. Add macro logic around the tracepoints
for architectures that do not have CONFIG_ARCH_WANTS_NO_INSTR defined
will check if the code is in the idle path (the only place RCU isn't
watching), and enable RCU around calling the tracepoint, but only do
it if the tracepoint is enabled.
* tag 'trace-v6.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
tracing: Fix archs that still call tracepoints without RCU watching
tracing: Fix cmp_entries_dup() to respect sort() comparison rules
Guenter reported boot stalls on a emulated ARM 32-bit platform, which has a
24-bit wide clocksource.
It turns out that the calculated maximal idle time, which limits idle
sleeps to prevent clocksource wrap arounds, is close to the point where the
negative motion detection triggers.
max_idle_ns: 597268854 ns
negative motion tripping point: 671088640 ns
If the idle wakeup is delayed beyond that point, the clocksource
advances far enough to trigger the negative motion detection. This
prevents the clock to advance and in the worst case the system stalls
completely if the consecutive sleeps based on the stale clock are
delayed as well.
Cure this by calculating a more robust cut-off value for negative motion,
which covers 87.5% of the actual clocksource counter width. Compare the
delta against this value to catch negative motion. This is specifically for
clock sources with a small counter width as their wrap around time is close
to the half counter width. For clock sources with wide counters this is not
a problem because the maximum idle time is far from the half counter width
due to the math overflow protection constraints.
For the case at hand this results in a tripping point of 1174405120ns.
Note, that this cannot prevent issues when the delay exceeds the 87.5%
margin, but that's not different from the previous unchecked version which
allowed arbitrary time jumps.
Systems with small counter width are prone to invalid results, but this
problem is unlikely to be seen on real hardware. If such a system
completely stalls for more than half a second, then there are other more
urgent problems than the counter wrapping around.
Fixes: c163e40af9 ("timekeeping: Always check for negative motion")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/all/8734j5ul4x.ffs@tglx
Closes: https://lore.kernel.org/all/387b120b-d68a-45e8-b6ab-768cd95d11c2@roeck-us.net
Tracepoints require having RCU "watching" as it uses RCU to do updates to
the tracepoints. There are some cases that would call a tracepoint when
RCU was not "watching". This was usually in the idle path where RCU has
"shutdown". For the few locations that had tracepoints without RCU
watching, there was an trace_*_rcuidle() variant that could be used. This
used SRCU for protection.
There are tracepoints that trace when interrupts and preemption are
enabled and disabled. In some architectures, these tracepoints are called
in a path where RCU is not watching. When x86 and arm64 removed these
locations, it was incorrectly assumed that it would be safe to remove the
trace_*_rcuidle() variant and also remove the SRCU logic, as it made the
code more complex and harder to implement new tracepoint features (like
faultable tracepoints and tracepoints in rust).
Instead of bringing back the trace_*_rcuidle(), as it will not be trivial
to do as new code has already been added depending on its removal, add a
workaround to the one file that still requires it (trace_preemptirq.c). If
the architecture does not define CONFIG_ARCH_WANTS_NO_INSTR, then check if
the code is in the idle path, and if so, call ct_irq_enter/exit() which
will enable RCU around the tracepoint.
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/20241204100414.4d3e06d0@gandalf.local.home
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Fixes: 48bcda6848 ("tracing: Remove definition of trace_*_rcuidle()")
Closes: https://lore.kernel.org/all/bddb02de-957a-4df5-8e77-829f55728ea2@roeck-us.net/
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Tested-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
When CAP_PERFMON and CAP_SYS_ADMIN (allow_ptr_leaks) are disabled, the
verifier aims to reject partial overwrite on an 8-byte stack slot that
contains a spilled pointer.
However, in such a scenario, it rejects all partial stack overwrites as
long as the targeted stack slot is a spilled register, because it does
not check if the stack slot is a spilled pointer.
Incomplete checks will result in the rejection of valid programs, which
spill narrower scalar values onto scalar slots, as shown below.
0: R1=ctx() R10=fp0
; asm volatile ( @ repro.bpf.c:679
0: (7a) *(u64 *)(r10 -8) = 1 ; R10=fp0 fp-8_w=1
1: (62) *(u32 *)(r10 -8) = 1
attempt to corrupt spilled pointer on stack
processed 2 insns (limit 1000000) max_states_per_insn 0 total_states 0 peak_states 0 mark_read 0.
Fix this by expanding the check to not consider spilled scalar registers
when rejecting the write into the stack.
Previous discussion on this patch is at link [0].
[0]: https://lore.kernel.org/bpf/20240403202409.2615469-1-tao.lyu@epfl.ch
Fixes: ab125ed3ec ("bpf: fix check for attempt to corrupt spilled pointer")
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Tao Lyu <tao.lyu@epfl.ch>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20241204044757.1483141-3-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Inside mark_stack_slot_misc, we should not upgrade STACK_INVALID to
STACK_MISC when allow_ptr_leaks is false, since invalid contents
shouldn't be read unless the program has the relevant capabilities.
The relaxation only makes sense when env->allow_ptr_leaks is true.
However, such conversion in privileged mode becomes unnecessary, as
invalid slots can be read without being upgraded to STACK_MISC.
Currently, the condition is inverted (i.e. checking for true instead of
false), simply remove it to restore correct behavior.
Fixes: eaf18febd6 ("bpf: preserve STACK_ZERO slots on partial reg spills")
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Reported-by: Tao Lyu <tao.lyu@epfl.ch>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20241204044757.1483141-2-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
The cmp_entries_dup() function used as the comparator for sort()
violated the symmetry and transitivity properties required by the
sorting algorithm. Specifically, it returned 1 whenever memcmp() was
non-zero, which broke the following expectations:
* Symmetry: If x < y, then y > x.
* Transitivity: If x < y and y < z, then x < z.
These violations could lead to incorrect sorting and failure to
correctly identify duplicate elements.
Fix the issue by directly returning the result of memcmp(), which
adheres to the required comparison properties.
Cc: stable@vger.kernel.org
Fixes: 08d43a5fa0 ("tracing: Add lock-free tracing_map")
Link: https://lore.kernel.org/20241203202228.1274403-1-visitorckw@gmail.com
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Andrii spotted that process_dynptr_func's rejection of incorrect
argument register type will print an error string where argument numbers
are not zero-indexed, unlike elsewhere in the verifier. Fix this by
subtracting 1 from regno. The same scenario exists for iterator
messages. Fix selftest error strings that match on the exact argument
number while we're at it to ensure clean bisection.
Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20241203002235.3776418-1-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Currently, KF_ARG_PTR_TO_ITER handling missed checking the reg->type and
ensuring it is PTR_TO_STACK. Instead of enforcing this in the caller of
process_iter_arg, move the check into it instead so that all callers
will gain the check by default. This is similar to process_dynptr_func.
An existing selftest in verifier_bits_iter.c fails due to this change,
but it's because it was passing a NULL pointer into iter_next helper and
getting an error further down the checks, but probably meant to pass an
uninitialized iterator on the stack (as is done in the subsequent test
below it). We will gain coverage for non-PTR_TO_STACK arguments in later
patches hence just change the declaration to zero-ed stack object.
Fixes: 06accc8779 ("bpf: add support for open-coded iterator loops")
Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Tao Lyu <tao.lyu@epfl.ch>
[ Kartikeya: move check into process_iter_arg, rewrite commit log ]
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20241203000238.3602922-2-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Anders had bisected a crash using PREEMPT_RT with linux-next and
isolated it down to commit 894d1b3db4 ("locking/mutex: Remove
wakeups from under mutex::wait_lock"), where it seemed the
wake_q structure was somehow getting corrupted causing a null
pointer traversal.
I was able to easily repoduce this with PREEMPT_RT and managed
to isolate down that through various call stacks we were
actually calling wake_up_q() twice on the same wake_q.
I found that in the problematic commit, I had added the
wake_up_q() call in task_blocks_on_rt_mutex() around
__ww_mutex_add_waiter(), following a similar pattern in
__mutex_lock_common().
However, its just wrong. We haven't dropped the lock->wait_lock,
so its contrary to the point of the original patch. And it
didn't match the __mutex_lock_common() logic of re-initializing
the wake_q after calling it midway in the stack.
Looking at it now, the wake_up_q() call is incorrect and should
just be removed. So drop the erronious logic I had added.
Fixes: 894d1b3db4 ("locking/mutex: Remove wakeups from under mutex::wait_lock")
Closes: https://lore.kernel.org/lkml/6afb936f-17c7-43fa-90e0-b9e780866097@app.fastmail.com/
Reported-by: Anders Roxell <anders.roxell@linaro.org>
Reported-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: John Stultz <jstultz@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Tested-by: Anders Roxell <anders.roxell@linaro.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lore.kernel.org/r/20241114190051.552665-1-jstultz@google.com
When running the following command:
while true; do
stress-ng --cyclic 30 --timeout 30s --minimize --quiet
done
a warning is eventually triggered:
WARNING: CPU: 43 PID: 2848 at kernel/sched/deadline.c:794
setup_new_dl_entity+0x13e/0x180
...
Call Trace:
<TASK>
? show_trace_log_lvl+0x1c4/0x2df
? enqueue_dl_entity+0x631/0x6e0
? setup_new_dl_entity+0x13e/0x180
? __warn+0x7e/0xd0
? report_bug+0x11a/0x1a0
? handle_bug+0x3c/0x70
? exc_invalid_op+0x14/0x70
? asm_exc_invalid_op+0x16/0x20
enqueue_dl_entity+0x631/0x6e0
enqueue_task_dl+0x7d/0x120
__do_set_cpus_allowed+0xe3/0x280
__set_cpus_allowed_ptr_locked+0x140/0x1d0
__set_cpus_allowed_ptr+0x54/0xa0
migrate_enable+0x7e/0x150
rt_spin_unlock+0x1c/0x90
group_send_sig_info+0xf7/0x1a0
? kill_pid_info+0x1f/0x1d0
kill_pid_info+0x78/0x1d0
kill_proc_info+0x5b/0x110
__x64_sys_kill+0x93/0xc0
do_syscall_64+0x5c/0xf0
entry_SYSCALL_64_after_hwframe+0x6e/0x76
RIP: 0033:0x7f0dab31f92b
This warning occurs because set_cpus_allowed dequeues and enqueues tasks
with the ENQUEUE_RESTORE flag set. If the task is boosted, the warning
is triggered. A boosted task already had its parameters set by
rt_mutex_setprio, and a new call to setup_new_dl_entity is unnecessary,
hence the WARN_ON call.
Check if we are requeueing a boosted task and avoid calling
setup_new_dl_entity if that's the case.
Fixes: 295d6d5e37 ("sched/deadline: Fix switching to -deadline")
Signed-off-by: Wander Lairson Costa <wander@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/r/20240724142253.27145-2-wander@redhat.com
Scheduler raises a SCHED_SOFTIRQ to trigger a load balancing event on
from the IPI handler on the idle CPU. If the SMP function is invoked
from an idle CPU via flush_smp_call_function_queue() then the HARD-IRQ
flag is not set and raise_softirq_irqoff() needlessly wakes ksoftirqd
because soft interrupts are handled before ksoftirqd get on the CPU.
Adding a trace_printk() in nohz_csd_func() at the spot of raising
SCHED_SOFTIRQ and enabling trace events for sched_switch, sched_wakeup,
and softirq_entry (for SCHED_SOFTIRQ vector alone) helps observing the
current behavior:
<idle>-0 [000] dN.1.: nohz_csd_func: Raising SCHED_SOFTIRQ from nohz_csd_func
<idle>-0 [000] dN.4.: sched_wakeup: comm=ksoftirqd/0 pid=16 prio=120 target_cpu=000
<idle>-0 [000] .Ns1.: softirq_entry: vec=7 [action=SCHED]
<idle>-0 [000] .Ns1.: softirq_exit: vec=7 [action=SCHED]
<idle>-0 [000] d..2.: sched_switch: prev_comm=swapper/0 prev_pid=0 prev_prio=120 prev_state=R ==> next_comm=ksoftirqd/0 next_pid=16 next_prio=120
ksoftirqd/0-16 [000] d..2.: sched_switch: prev_comm=ksoftirqd/0 prev_pid=16 prev_prio=120 prev_state=S ==> next_comm=swapper/0 next_pid=0 next_prio=120
...
Use __raise_softirq_irqoff() to raise the softirq. The SMP function call
is always invoked on the requested CPU in an interrupt handler. It is
guaranteed that soft interrupts are handled at the end.
Following are the observations with the changes when enabling the same
set of events:
<idle>-0 [000] dN.1.: nohz_csd_func: Raising SCHED_SOFTIRQ for nohz_idle_balance
<idle>-0 [000] dN.1.: softirq_raise: vec=7 [action=SCHED]
<idle>-0 [000] .Ns1.: softirq_entry: vec=7 [action=SCHED]
No unnecessary ksoftirqd wakeups are seen from idle task's context to
service the softirq.
Fixes: b2a02fc43a ("smp: Optimize send_call_function_single_ipi()")
Closes: https://lore.kernel.org/lkml/fcf823f-195e-6c9a-eac3-25f870cb35ac@inria.fr/ [1]
Reported-by: Julia Lawall <julia.lawall@inria.fr>
Suggested-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lore.kernel.org/r/20241119054432.6405-5-kprateek.nayak@amd.com
Commit b2a02fc43a ("smp: Optimize send_call_function_single_ipi()")
optimizes IPIs to idle CPUs in TIF_POLLING_NRFLAG mode by setting the
TIF_NEED_RESCHED flag in idle task's thread info and relying on
flush_smp_call_function_queue() in idle exit path to run the
call-function. A softirq raised by the call-function is handled shortly
after in do_softirq_post_smp_call_flush() but the TIF_NEED_RESCHED flag
remains set and is only cleared later when schedule_idle() calls
__schedule().
need_resched() check in _nohz_idle_balance() exists to bail out of load
balancing if another task has woken up on the CPU currently in-charge of
idle load balancing which is being processed in SCHED_SOFTIRQ context.
Since the optimization mentioned above overloads the interpretation of
TIF_NEED_RESCHED, check for idle_cpu() before going with the existing
need_resched() check which can catch a genuine task wakeup on an idle
CPU processing SCHED_SOFTIRQ from do_softirq_post_smp_call_flush(), as
well as the case where ksoftirqd needs to be preempted as a result of
new task wakeup or slice expiry.
In case of PREEMPT_RT or threadirqs, although the idle load balancing
may be inhibited in some cases on the ilb CPU, the fact that ksoftirqd
is the only fair task going back to sleep will trigger a newidle balance
on the CPU which will alleviate some imbalance if it exists if idle
balance fails to do so.
Fixes: b2a02fc43a ("smp: Optimize send_call_function_single_ipi()")
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241119054432.6405-4-kprateek.nayak@amd.com
The need_resched() check currently in nohz_csd_func() can be tracked
to have been added in scheduler_ipi() back in 2011 via commit
ca38062e57 ("sched: Use resched IPI to kick off the nohz idle balance")
Since then, it has travelled quite a bit but it seems like an idle_cpu()
check currently is sufficient to detect the need to bail out from an
idle load balancing. To justify this removal, consider all the following
case where an idle load balancing could race with a task wakeup:
o Since commit f3dd3f6745 ("sched: Remove the limitation of WF_ON_CPU
on wakelist if wakee cpu is idle") a target perceived to be idle
(target_rq->nr_running == 0) will return true for
ttwu_queue_cond(target) which will offload the task wakeup to the idle
target via an IPI.
In all such cases target_rq->ttwu_pending will be set to 1 before
queuing the wake function.
If an idle load balance races here, following scenarios are possible:
- The CPU is not in TIF_POLLING_NRFLAG mode in which case an actual
IPI is sent to the CPU to wake it out of idle. If the
nohz_csd_func() queues before sched_ttwu_pending(), the idle load
balance will bail out since idle_cpu(target) returns 0 since
target_rq->ttwu_pending is 1. If the nohz_csd_func() is queued after
sched_ttwu_pending() it should see rq->nr_running to be non-zero and
bail out of idle load balancing.
- The CPU is in TIF_POLLING_NRFLAG mode and instead of an actual IPI,
the sender will simply set TIF_NEED_RESCHED for the target to put it
out of idle and flush_smp_call_function_queue() in do_idle() will
execute the call function. Depending on the ordering of the queuing
of nohz_csd_func() and sched_ttwu_pending(), the idle_cpu() check in
nohz_csd_func() should either see target_rq->ttwu_pending = 1 or
target_rq->nr_running to be non-zero if there is a genuine task
wakeup racing with the idle load balance kick.
o The waker CPU perceives the target CPU to be busy
(targer_rq->nr_running != 0) but the CPU is in fact going idle and due
to a series of unfortunate events, the system reaches a case where the
waker CPU decides to perform the wakeup by itself in ttwu_queue() on
the target CPU but target is concurrently selected for idle load
balance (XXX: Can this happen? I'm not sure, but we'll consider the
mother of all coincidences to estimate the worst case scenario).
ttwu_do_activate() calls enqueue_task() which would increment
"rq->nr_running" post which it calls wakeup_preempt() which is
responsible for setting TIF_NEED_RESCHED (via a resched IPI or by
setting TIF_NEED_RESCHED on a TIF_POLLING_NRFLAG idle CPU) The key
thing to note in this case is that rq->nr_running is already non-zero
in case of a wakeup before TIF_NEED_RESCHED is set which would
lead to idle_cpu() check returning false.
In all cases, it seems that need_resched() check is unnecessary when
checking for idle_cpu() first since an impending wakeup racing with idle
load balancer will either set the "rq->ttwu_pending" or indicate a newly
woken task via "rq->nr_running".
Chasing the reason why this check might have existed in the first place,
I came across Peter's suggestion on the fist iteration of Suresh's
patch from 2011 [1] where the condition to raise the SCHED_SOFTIRQ was:
sched_ttwu_do_pending(list);
if (unlikely((rq->idle == current) &&
rq->nohz_balance_kick &&
!need_resched()))
raise_softirq_irqoff(SCHED_SOFTIRQ);
Since the condition to raise the SCHED_SOFIRQ was preceded by
sched_ttwu_do_pending() (which is equivalent of sched_ttwu_pending()) in
the current upstream kernel, the need_resched() check was necessary to
catch a newly queued task. Peter suggested modifying it to:
if (idle_cpu() && rq->nohz_balance_kick && !need_resched())
raise_softirq_irqoff(SCHED_SOFTIRQ);
where idle_cpu() seems to have replaced "rq->idle == current" check.
Even back then, the idle_cpu() check would have been sufficient to catch
a new task being enqueued. Since commit b2a02fc43a ("smp: Optimize
send_call_function_single_ipi()") overloads the interpretation of
TIF_NEED_RESCHED for TIF_POLLING_NRFLAG idling, remove the
need_resched() check in nohz_csd_func() to raise SCHED_SOFTIRQ based
on Peter's suggestion.
Fixes: b2a02fc43a ("smp: Optimize send_call_function_single_ipi()")
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241119054432.6405-3-kprateek.nayak@amd.com
do_softirq_post_smp_call_flush() on PREEMPT_RT kernels carries a
WARN_ON_ONCE() for any SOFTIRQ being raised from an SMP-call-function.
Since do_softirq_post_smp_call_flush() is called with preempt disabled,
raising a SOFTIRQ during flush_smp_call_function_queue() can lead to
longer preempt disabled sections.
Since commit b2a02fc43a ("smp: Optimize
send_call_function_single_ipi()") IPIs to an idle CPU in
TIF_POLLING_NRFLAG mode can be optimized out by instead setting
TIF_NEED_RESCHED bit in idle task's thread_info and relying on the
flush_smp_call_function_queue() in the idle-exit path to run the
SMP-call-function.
To trigger an idle load balancing, the scheduler queues
nohz_csd_function() responsible for triggering an idle load balancing on
a target nohz idle CPU and sends an IPI. Only now, this IPI is optimized
out and the SMP-call-function is executed from
flush_smp_call_function_queue() in do_idle() which can raise a
SCHED_SOFTIRQ to trigger the balancing.
So far, this went undetected since, the need_resched() check in
nohz_csd_function() would make it bail out of idle load balancing early
as the idle thread does not clear TIF_POLLING_NRFLAG before calling
flush_smp_call_function_queue(). The need_resched() check was added with
the intent to catch a new task wakeup, however, it has recently
discovered to be unnecessary and will be removed in the subsequent
commit after which nohz_csd_function() can raise a SCHED_SOFTIRQ from
flush_smp_call_function_queue() to trigger an idle load balance on an
idle target in TIF_POLLING_NRFLAG mode.
nohz_csd_function() bails out early if "idle_cpu()" check for the
target CPU, and does not lock the target CPU's rq until the very end,
once it has found tasks to run on the CPU and will not inhibit the
wakeup of, or running of a newly woken up higher priority task. Account
for this and prevent a WARN_ON_ONCE() when SCHED_SOFTIRQ is raised from
flush_smp_call_function_queue().
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20241119054432.6405-2-kprateek.nayak@amd.com
Commit 8f9ea86fdf added some logic to sched_setaffinity that included
a WARN when a per-task affinity assignment races with a cpuset update.
Specifically, we can have a race where a cpuset update results in the
task affinity no longer being a subset of the cpuset. That's fine; we
have a fallback to instead use the cpuset mask. However, we have a WARN
set up that will trigger if the cpuset mask has no overlap at all with
the requested task affinity. This shouldn't be a warning condition; its
trivial to create this condition.
Reproduced the warning by the following setup:
- $PID inside a cpuset cgroup
- another thread repeatedly switching the cpuset cpus from 1-2 to just 1
- another thread repeatedly setting the $PID affinity (via taskset) to 2
Fixes: 8f9ea86fdf ("sched: Always preserve the user requested cpumask")
Signed-off-by: Josh Don <joshdon@google.com>
Acked-and-tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Waiman Long <longman@redhat.com>
Tested-by: Madadi Vineeth Reddy <vineethr@linux.ibm.com>
Link: https://lkml.kernel.org/r/20241111182738.1832953-1-joshdon@google.com
Pull timer fixes from Borislav Petkov:
- Fix a case where posix timers with a thread-group-wide target would
miss signals if some of the group's threads are exiting
- Fix a hang caused by ndelay() calling the wrong delay function
__udelay()
- Fix a wrong offset calculation in adjtimex(2) when using ADJ_MICRO
(microsecond resolution) and a negative offset
* tag 'timers_urgent_for_v6.13_rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
posix-timers: Target group sigqueue to current task only if not exiting
delay: Fix ndelay() spuriously treated as udelay()
ntp: Remove invalid cast in time offset math
Pull dma-mapping fix from Christoph Hellwig:
- fix physical address calculation for struct dma_debug_entry (Fedor
Pchelkin)
* tag 'dma-mapping-6.13-2024-11-30' of git://git.infradead.org/users/hch/dma-mapping:
dma-debug: fix physical address calculation for struct dma_debug_entry
Pull driver core updates from Greg KH:
"Here is a small set of driver core changes for 6.13-rc1.
Nothing major for this merge cycle, except for the two simple merge
conflicts are here just to make life interesting.
Included in here are:
- sysfs core changes and preparations for more sysfs api cleanups
that can come through all driver trees after -rc1 is out
- fw_devlink fixes based on many reports and debugging sessions
- list_for_each_reverse() removal, no one was using it!
- last-minute seq_printf() format string bug found and fixed in many
drivers all at once.
- minor bugfixes and changes full details in the shortlog"
* tag 'driver-core-6.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (35 commits)
Fix a potential abuse of seq_printf() format string in drivers
cpu: Remove spurious NULL in attribute_group definition
s390/con3215: Remove spurious NULL in attribute_group definition
perf: arm-ni: Remove spurious NULL in attribute_group definition
driver core: Constify bin_attribute definitions
sysfs: attribute_group: allow registration of const bin_attribute
firmware_loader: Fix possible resource leak in fw_log_firmware_info()
drivers: core: fw_devlink: Fix excess parameter description in docstring
driver core: class: Correct WARN() message in APIs class_(for_each|find)_device()
cacheinfo: Use of_property_present() for non-boolean properties
cdx: Fix cdx_mmap_resource() after constifying attr in ->mmap()
drivers: core: fw_devlink: Make the error message a bit more useful
phy: tegra: xusb: Set fwnode for xusb port devices
drm: display: Set fwnode for aux bus devices
driver core: fw_devlink: Stop trying to optimize cycle detection logic
driver core: Constify attribute arguments of binary attributes
sysfs: bin_attribute: add const read/write callback variants
sysfs: implement all BIN_ATTR_* macros in terms of __BIN_ATTR()
sysfs: treewide: constify attribute callback of bin_attribute::llseek()
sysfs: treewide: constify attribute callback of bin_attribute::mmap()
...
A sigqueue belonging to a posix timer, which target is not a specific
thread but a whole thread group, is preferrably targeted to the current
task if it is part of that thread group.
However nothing prevents a posix timer event from queueing such a
sigqueue from a reaped yet running task. The interruptible code space
between exit_notify() and the final call to schedule() is enough for
posix_timer_fn() hrtimer to fire.
If that happens while the current task is part of the thread group
target, it is proposed to handle it but since its sighand pointer may
have been cleared already, the sigqueue is dropped even if there are
other tasks running within the group that could handle it.
As a result posix timers with thread group wide target may miss signals
when some of their threads are exiting.
Fix this with verifying that the current task hasn't been through
exit_notify() before proposing it as a preferred target so as to ensure
that its sighand is still here and stable.
complete_signal() might still reconsider the choice and find a better
target within the group if current has passed retarget_shared_pending()
already.
Fixes: bcb7ee7902 ("posix-timers: Prefer delivery of signals to the current thread")
Reported-by: Anthony Mallet <anthony.mallet@laas.fr>
Suggested-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Oleg Nesterov <oleg@redhat.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/all/20241122234811.60455-1-frederic@kernel.org
Closes: https://lore.kernel.org/all/26411.57288.238690.681680@gargle.gargle.HOWL
Pull more tracing updates from Steven Rostedt:
- Add trace flag for NEED_RESCHED_LAZY
Now that NEED_RESCHED_LAZY is upstream, add it to the status bits of
the common_flags. This will now show when the NEED_RESCHED_LAZY flag
is set that is used for debugging latency issues in the kernel via a
trace.
- Remove leftover "__idx" variable when SRCU was removed from the
tracepoint code
- Add rcu_tasks_trace guard
To add a guard() around the tracepoint code, a rcu_tasks_trace guard
needs to be created first.
- Remove __DO_TRACE() macro and just call __DO_TRACE_CALL() directly
The DO_TRACE() macro has conditional locking depending on what was
passed into the macro parameters. As the guts of the macro has been
moved to __DO_TRACE_CALL() to handle static call logic, there's no
reason to keep the __DO_TRACE() macro around.
It is better to just do the locking in place without the conditionals
and call __DO_TRACE_CALL() from those locations. The "cond" passed in
can also be moved out of that macro. This simplifies the code.
- Remove the "cond" from the system call tracepoint macros
The "cond" variable was added to allow some tracepoints to check a
condition within the static_branch (jump/nop) logic. The system calls
do not need this. Removing it simplifies the code.
- Replace scoped_guard() with just guard() in the tracepoint logic
guard() works just as well as scoped_guard() in the tracepoint logic
and the scoped_guard() causes some issues.
* tag 'trace-v6.13-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
tracing: Use guard() rather than scoped_guard()
tracing: Remove cond argument from __DECLARE_TRACE_SYSCALL
tracing: Remove conditional locking from __DO_TRACE()
rcupdate_trace: Define rcu_tasks_trace lock guard
tracing: Remove __idx variable from __DO_TRACE
tracing: Move it_func[0] comment to the relevant context
tracing: Record task flag NEED_RESCHED_LAZY.
