syzkaller reported an issue:
WARNING: CPU: 3 PID: 217 at kernel/bpf/core.c:2357 __bpf_prog_ret0_warn+0xa/0x20 kernel/bpf/core.c:2357
Modules linked in:
CPU: 3 UID: 0 PID: 217 Comm: kworker/u32:6 Not tainted 6.15.0-rc4-syzkaller-00040-g8bac8898fe39
RIP: 0010:__bpf_prog_ret0_warn+0xa/0x20 kernel/bpf/core.c:2357
Call Trace:
<TASK>
bpf_dispatcher_nop_func include/linux/bpf.h:1316 [inline]
__bpf_prog_run include/linux/filter.h:718 [inline]
bpf_prog_run include/linux/filter.h:725 [inline]
cls_bpf_classify+0x74a/0x1110 net/sched/cls_bpf.c:105
...
When creating bpf program, 'fp->jit_requested' depends on bpf_jit_enable.
This issue is triggered because of CONFIG_BPF_JIT_ALWAYS_ON is not set
and bpf_jit_enable is set to 1, causing the arch to attempt JIT the prog,
but jit failed due to FAULT_INJECTION. As a result, incorrectly
treats the program as valid, when the program runs it calls
`__bpf_prog_ret0_warn` and triggers the WARN_ON_ONCE(1).
Reported-by: syzbot+0903f6d7f285e41cdf10@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/bpf/6816e34e.a70a0220.254cdc.002c.GAE@google.com
Fixes: fa9dd599b4 ("bpf: get rid of pure_initcall dependency to enable jits")
Signed-off-by: KaFai Wan <mannkafai@gmail.com>
Link: https://lore.kernel.org/r/20250526133358.2594176-1-mannkafai@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Marc Suñé (Isovalent, part of Cisco) reported an issue where an
uninitialized variable caused generating bpf prog binary code not
working as expected. The reproducer is in [1] where the flags
“-Wall -Werror” are enabled, but there is no warning as the compiler
takes advantage of uninitialized variable to do aggressive optimization.
The optimized code looks like below:
; {
0: bf 16 00 00 00 00 00 00 r6 = r1
; bpf_printk("Start");
1: 18 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r1 = 0x0 ll
0000000000000008: R_BPF_64_64 .rodata
3: b4 02 00 00 06 00 00 00 w2 = 0x6
4: 85 00 00 00 06 00 00 00 call 0x6
; DEFINE_FUNC_CTX_POINTER(data)
5: 61 61 4c 00 00 00 00 00 w1 = *(u32 *)(r6 + 0x4c)
; bpf_printk("pre ipv6_hdrlen_offset");
6: 18 01 00 00 06 00 00 00 00 00 00 00 00 00 00 00 r1 = 0x6 ll
0000000000000030: R_BPF_64_64 .rodata
8: b4 02 00 00 17 00 00 00 w2 = 0x17
9: 85 00 00 00 06 00 00 00 call 0x6
<END>
The verifier will report the following failure:
9: (85) call bpf_trace_printk#6
last insn is not an exit or jmp
The above verifier log does not give a clear hint about how to fix
the problem and user may take quite some time to figure out that
the issue is due to compiler taking advantage of uninitialized variable.
In llvm internals, uninitialized variable usage may generate
'unreachable' IR insn and these 'unreachable' IR insns may indicate
uninitialized variable impact on code optimization. So far, llvm
BPF backend ignores 'unreachable' IR hence the above code is generated.
With clang21 patch [2], those 'unreachable' IR insn are converted
to func __bpf_trap(). In order to maintain proper control flow
graph for bpf progs, [2] also adds an 'exit' insn after bpf_trap()
if __bpf_trap() is the last insn in the function. The new code looks like:
; {
0: bf 16 00 00 00 00 00 00 r6 = r1
; bpf_printk("Start");
1: 18 01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 r1 = 0x0 ll
0000000000000008: R_BPF_64_64 .rodata
3: b4 02 00 00 06 00 00 00 w2 = 0x6
4: 85 00 00 00 06 00 00 00 call 0x6
; DEFINE_FUNC_CTX_POINTER(data)
5: 61 61 4c 00 00 00 00 00 w1 = *(u32 *)(r6 + 0x4c)
; bpf_printk("pre ipv6_hdrlen_offset");
6: 18 01 00 00 06 00 00 00 00 00 00 00 00 00 00 00 r1 = 0x6 ll
0000000000000030: R_BPF_64_64 .rodata
8: b4 02 00 00 17 00 00 00 w2 = 0x17
9: 85 00 00 00 06 00 00 00 call 0x6
10: 85 10 00 00 ff ff ff ff call -0x1
0000000000000050: R_BPF_64_32 __bpf_trap
11: 95 00 00 00 00 00 00 00 exit
<END>
In kernel, a new kfunc __bpf_trap() is added. During insn
verification, any hit with __bpf_trap() will result in
verification failure. The kernel is able to provide better
log message for debugging.
With llvm patch [2] and without this patch (no __bpf_trap()
kfunc for existing kernel), e.g., for old kernels, the verifier
outputs
10: <invalid kfunc call>
kfunc '__bpf_trap' is referenced but wasn't resolved
Basically, kernel does not support __bpf_trap() kfunc.
This still didn't give clear signals about possible reason.
With llvm patch [2] and with this patch, the verifier outputs
10: (85) call __bpf_trap#74479
unexpected __bpf_trap() due to uninitialized variable?
It gives much better hints for verification failure.
[1] https://github.com/msune/clang_bpf/blob/main/Makefile#L3
[2] https://github.com/llvm/llvm-project/pull/131731
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20250523205326.1291640-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Currently, the verifier has both special_kfunc_set and special_kfunc_list.
When adding a new kfunc usage to the verifier, it is often confusing
about whether special_kfunc_set or special_kfunc_list or both should
add that kfunc. For example, some kfuncs, e.g., bpf_dynptr_from_skb,
bpf_dynptr_clone, bpf_wq_set_callback_impl, does not need to be
in special_kfunc_set.
To avoid potential future confusion, special_kfunc_set is deleted
and btf_id_set_contains(&special_kfunc_set, ...) is removed.
The code is refactored with a new func check_special_kfunc(),
which contains all codes covered by original branch
meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)
There is no functionality change.
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20250523205321.1291431-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This open coded iterator allows for more flexibility when creating BPF
programs. It can support output in formats other than text. With an open
coded iterator, a single BPF program can traverse multiple kernel data
structures (now including dmabufs), allowing for more efficient analysis
of kernel data compared to multiple reads from procfs, sysfs, or
multiple traditional BPF iterator invocations.
Signed-off-by: T.J. Mercier <tjmercier@google.com>
Acked-by: Christian König <christian.koenig@amd.com>
Acked-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20250522230429.941193-4-tjmercier@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This reverts commit 4a8f635a60.
Althought get_pid_task() internally already calls rcu_read_lock() and
rcu_read_unlock(), the find_vpid() was not.
The documentation for find_vpid() clearly states:
"Must be called with the tasklist_lock or rcu_read_lock() held."
Add proper rcu_read_lock/unlock() to protect the find_vpid().
Fixes: 4a8f635a60 ("bpf: remove unnecessary rcu_read_{lock,unlock}() in multi-uprobe attach logic")
Reported-by: Xuewen Yan <xuewen.yan@unisoc.com>
Signed-off-by: Di Shen <di.shen@unisoc.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20250520054943.5002-1-xuewen.yan@unisoc.com
Signed-off-by: Alexei Starovoitov <ast@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>
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>
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>
This patch introduces a new set of kfuncs for working with dynptrs in
BPF programs, enabling reading variable-length user or kernel data
into dynptr directly. To enable memory-safety, verifier allows only
constant-sized reads via existing bpf_probe_read_{user|kernel} etc.
kfuncs, dynptr-based kfuncs allow dynamically-sized reads without memory
safety shortcomings.
The following kfuncs are introduced:
* `bpf_probe_read_kernel_dynptr()`: probes kernel-space data into a dynptr
* `bpf_probe_read_user_dynptr()`: probes user-space data into a dynptr
* `bpf_probe_read_kernel_str_dynptr()`: probes kernel-space string into
a dynptr
* `bpf_probe_read_user_str_dynptr()`: probes user-space string into a
dynptr
* `bpf_copy_from_user_dynptr()`: sleepable, copies user-space data into
a dynptr for the current task
* `bpf_copy_from_user_str_dynptr()`: sleepable, copies user-space string
into a dynptr for the current task
* `bpf_copy_from_user_task_dynptr()`: sleepable, copies user-space data
of the task into a dynptr
* `bpf_copy_from_user_task_str_dynptr()`: sleepable, copies user-space
string of the task into a dynptr
The implementation is built on two generic functions:
* __bpf_dynptr_copy
* __bpf_dynptr_copy_str
These functions take function pointers as arguments, enabling the
copying of data from various sources, including both kernel and user
space.
Use __always_inline for generic functions and callbacks to make sure the
compiler doesn't generate indirect calls into callbacks, which is more
expensive, especially on some kernel configurations. Inlining allows
compiler to put direct calls into all the specific callback implementations
(copy_user_data_sleepable, copy_user_data_nofault, and so on).
Reviewed-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Mykyta Yatsenko <yatsenko@meta.com>
Link: https://lore.kernel.org/r/20250512205348.191079-3-mykyta.yatsenko5@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Make bpf_dynptr_slice_rdwr, bpf_dynptr_check_off_len and
__bpf_dynptr_write available outside of the helpers.c by
adding their prototypes into linux/include/bpf.h.
bpf_dynptr_check_off_len() implementation is moved to header and made
inline explicitly, as small function should typically be inlined.
These functions are going to be used from bpf_trace.c in the next
patch of this series.
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Mykyta Yatsenko <yatsenko@meta.com>
Link: https://lore.kernel.org/r/20250512205348.191079-2-mykyta.yatsenko5@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
In the kernel fq qdisc implementation, it only needs to look at
the fields of the first node in a list but does not always
need to remove it from the list. It is more convenient to have
a peek kfunc for the list. It works similar to the bpf_rbtree_first().
This patch adds bpf_list_{front,back} kfunc. The verifier is changed
such that the kfunc returning "struct bpf_list_node *" will be
marked as non-owning. The exception is the KF_ACQUIRE kfunc. The
net effect is only the new bpf_list_{front,back} kfuncs will
have its return pointer marked as non-owning.
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20250506015857.817950-8-martin.lau@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
The next patch will add bpf_list_{front,back} kfuncs to peek the head
and tail of a list. Both of them will return a 'struct bpf_list_node *'.
Follow the earlier change for rbtree, this patch checks the
return btf type is a 'struct bpf_list_node' pointer instead
of checking each kfuncs individually to decide if
mark_reg_graph_node should be called. This will make
the bpf_list_{front,back} kfunc addition easier in
the later patch.
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20250506015857.817950-7-martin.lau@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
The bpf_rbtree_{remove,left,right} requires the root's lock to be held.
They also check the node_internal->owner is still owned by that root
before proceeding, so it is safe to allow refcounted bpf_rb_node
pointer to be used in these kfuncs.
In a bpf fq implementation which is much closer to the kernel fq,
https://lore.kernel.org/bpf/20250418224652.105998-13-martin.lau@linux.dev/,
a networking flow (allocated by bpf_obj_new) can be added to two different
rbtrees. There are cases that the flow is searched from one rbtree,
held the refcount of the flow, and then removed from another rbtree:
struct fq_flow {
struct bpf_rb_node fq_node;
struct bpf_rb_node rate_node;
struct bpf_refcount refcount;
unsigned long sk_long;
};
int bpf_fq_enqueue(...)
{
/* ... */
bpf_spin_lock(&root->lock);
while (can_loop) {
/* ... */
if (!p)
break;
gc_f = bpf_rb_entry(p, struct fq_flow, fq_node);
if (gc_f->sk_long == sk_long) {
f = bpf_refcount_acquire(gc_f);
break;
}
/* ... */
}
bpf_spin_unlock(&root->lock);
if (f) {
bpf_spin_lock(&q->lock);
bpf_rbtree_remove(&q->delayed, &f->rate_node);
bpf_spin_unlock(&q->lock);
}
}
bpf_rbtree_{left,right} do not need this change but are relaxed together
with bpf_rbtree_remove instead of adding extra verifier logic
to exclude these kfuncs.
To avoid bi-sect failure, this patch also changes the selftests together.
The "rbtree_api_remove_unadded_node" is not expecting verifier's error.
The test now expects bpf_rbtree_remove(&groot, &m->node) to return NULL.
The test uses __retval(0) to ensure this NULL return value.
Some of the "only take non-owning..." failure messages are changed also.
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20250506015857.817950-5-martin.lau@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
In a bpf fq implementation that is much closer to the kernel fq,
it will need to traverse the rbtree:
https://lore.kernel.org/bpf/20250418224652.105998-13-martin.lau@linux.dev/
The much simplified logic that uses the bpf_rbtree_{root,left,right}
to traverse the rbtree is like:
struct fq_flow {
struct bpf_rb_node fq_node;
struct bpf_rb_node rate_node;
struct bpf_refcount refcount;
unsigned long sk_long;
};
struct fq_flow_root {
struct bpf_spin_lock lock;
struct bpf_rb_root root __contains(fq_flow, fq_node);
};
struct fq_flow *fq_classify(...)
{
struct bpf_rb_node *tofree[FQ_GC_MAX];
struct fq_flow_root *root;
struct fq_flow *gc_f, *f;
struct bpf_rb_node *p;
int i, fcnt = 0;
/* ... */
f = NULL;
bpf_spin_lock(&root->lock);
p = bpf_rbtree_root(&root->root);
while (can_loop) {
if (!p)
break;
gc_f = bpf_rb_entry(p, struct fq_flow, fq_node);
if (gc_f->sk_long == sk_long) {
f = bpf_refcount_acquire(gc_f);
break;
}
/* To be removed from the rbtree */
if (fcnt < FQ_GC_MAX && fq_gc_candidate(gc_f, jiffies_now))
tofree[fcnt++] = p;
if (gc_f->sk_long > sk_long)
p = bpf_rbtree_left(&root->root, p);
else
p = bpf_rbtree_right(&root->root, p);
}
/* remove from the rbtree */
for (i = 0; i < fcnt; i++) {
p = tofree[i];
tofree[i] = bpf_rbtree_remove(&root->root, p);
}
bpf_spin_unlock(&root->lock);
/* bpf_obj_drop the fq_flow(s) that have just been removed
* from the rbtree.
*/
for (i = 0; i < fcnt; i++) {
p = tofree[i];
if (p) {
gc_f = bpf_rb_entry(p, struct fq_flow, fq_node);
bpf_obj_drop(gc_f);
}
}
return f;
}
The above simplified code needs to traverse the rbtree for two purposes,
1) find the flow with the desired sk_long value
2) while searching for the sk_long, collect flows that are
the fq_gc_candidate. They will be removed from the rbtree.
This patch adds the bpf_rbtree_{root,left,right} kfunc to enable
the rbtree traversal. The returned bpf_rb_node pointer will be a
non-owning reference which is the same as the returned pointer
of the exisiting bpf_rbtree_first kfunc.
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20250506015857.817950-4-martin.lau@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
The current rbtree kfunc, bpf_rbtree_{first, remove}, returns the
bpf_rb_node pointer. The check_kfunc_call currently checks the
kfunc btf_id instead of its return pointer type to decide
if it needs to do mark_reg_graph_node(reg0) and ref_set_non_owning(reg0).
The later patch will add bpf_rbtree_{root,left,right} that will also
return a bpf_rb_node pointer. Instead of adding more kfunc btf_id
checks to the "if" case, this patch changes the test to check the
kfunc's return type. is_rbtree_node_type() function is added to
test if a pointer type is a bpf_rb_node. The callers have already
skipped the modifiers of the pointer type.
A note on the ref_set_non_owning(), although bpf_rbtree_remove()
also returns a bpf_rb_node pointer, the bpf_rbtree_remove()
has the KF_ACQUIRE flag. Thus, its reg0 will not become non-owning.
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20250506015857.817950-3-martin.lau@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
In a later patch, two new kfuncs will take the bpf_rb_node pointer arg.
struct bpf_rb_node *bpf_rbtree_left(struct bpf_rb_root *root,
struct bpf_rb_node *node);
struct bpf_rb_node *bpf_rbtree_right(struct bpf_rb_root *root,
struct bpf_rb_node *node);
In the check_kfunc_call, there is a "case KF_ARG_PTR_TO_RB_NODE"
to check if the reg->type should be an allocated pointer or should be
a non_owning_ref.
The later patch will need to ensure that the bpf_rb_node pointer passing
to the new bpf_rbtree_{left,right} must be a non_owning_ref. This
should be the same requirement as the existing bpf_rbtree_remove.
This patch swaps the current "if else" statement. Instead of checking
the bpf_rbtree_remove, it checks the bpf_rbtree_add. Then the new
bpf_rbtree_{left,right} will fall into the "else" case to make
the later patch simpler. bpf_rbtree_add should be the only
one that needs an allocated pointer.
This should be a no-op change considering there are only two kfunc(s)
taking bpf_rb_node pointer arg, rbtree_add and rbtree_remove.
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20250506015857.817950-2-martin.lau@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
In the current implementation if the program is dev-bound to a specific
device, it will not be possible to perform XDP_REDIRECT into a DEVMAP
or CPUMAP even if the program is running in the driver NAPI context and
it is not attached to any map entry. This seems in contrast with the
explanation available in bpf_prog_map_compatible routine.
Fix the issue introducing __bpf_prog_map_compatible utility routine in
order to avoid bpf_prog_is_dev_bound() check running bpf_check_tail_call()
at program load time (bpf_prog_select_runtime()).
Continue forbidding to attach a dev-bound program to XDP maps
(BPF_MAP_TYPE_PROG_ARRAY, BPF_MAP_TYPE_DEVMAP and BPF_MAP_TYPE_CPUMAP).
Fixes: 3d76a4d3d4 ("bpf: XDP metadata RX kfuncs")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Pull scheduler fix from Ingo Molnar:
"Fix sporadic crashes in dequeue_entities() due to ... bad math.
[ Arguably if pick_eevdf()/pick_next_entity() was less trusting of
complex math being correct it could have de-escalated a crash into
a warning, but that's for a different patch ]"
* tag 'sched-urgent-2025-04-26' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/eevdf: Fix se->slice being set to U64_MAX and resulting crash
Pull misc perf events fixes from Ingo Molnar:
- Use POLLERR for events in error state, instead of the ambiguous
POLLHUP error value
- Fix non-sampling (counting) events on certain x86 platforms
* tag 'perf-urgent-2025-04-26' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
perf/x86: Fix non-sampling (counting) events on certain x86 platforms
perf/core: Change to POLLERR for pinned events with error
There is a code path in dequeue_entities() that can set the slice of a
sched_entity to U64_MAX, which sometimes results in a crash.
The offending case is when dequeue_entities() is called to dequeue a
delayed group entity, and then the entity's parent's dequeue is delayed.
In that case:
1. In the if (entity_is_task(se)) else block at the beginning of
dequeue_entities(), slice is set to
cfs_rq_min_slice(group_cfs_rq(se)). If the entity was delayed, then
it has no queued tasks, so cfs_rq_min_slice() returns U64_MAX.
2. The first for_each_sched_entity() loop dequeues the entity.
3. If the entity was its parent's only child, then the next iteration
tries to dequeue the parent.
4. If the parent's dequeue needs to be delayed, then it breaks from the
first for_each_sched_entity() loop _without updating slice_.
5. The second for_each_sched_entity() loop sets the parent's ->slice to
the saved slice, which is still U64_MAX.
This throws off subsequent calculations with potentially catastrophic
results. A manifestation we saw in production was:
6. In update_entity_lag(), se->slice is used to calculate limit, which
ends up as a huge negative number.
7. limit is used in se->vlag = clamp(vlag, -limit, limit). Because limit
is negative, vlag > limit, so se->vlag is set to the same huge
negative number.
8. In place_entity(), se->vlag is scaled, which overflows and results in
another huge (positive or negative) number.
9. The adjusted lag is subtracted from se->vruntime, which increases or
decreases se->vruntime by a huge number.
10. pick_eevdf() calls entity_eligible()/vruntime_eligible(), which
incorrectly returns false because the vruntime is so far from the
other vruntimes on the queue, causing the
(vruntime - cfs_rq->min_vruntime) * load calulation to overflow.
11. Nothing appears to be eligible, so pick_eevdf() returns NULL.
12. pick_next_entity() tries to dereference the return value of
pick_eevdf() and crashes.
Dumping the cfs_rq states from the core dumps with drgn showed tell-tale
huge vruntime ranges and bogus vlag values, and I also traced se->slice
being set to U64_MAX on live systems (which was usually "benign" since
the rest of the runqueue needed to be in a particular state to crash).
Fix it in dequeue_entities() by always setting slice from the first
non-empty cfs_rq.
Fixes: aef6987d89 ("sched/eevdf: Propagate min_slice up the cgroup hierarchy")
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/f0c2d1072be229e1bdddc73c0703919a8b00c652.1745570998.git.osandov@fb.com
Pull bpf fixes from Alexei Starovoitov:
- Add namespace to BPF internal symbols (Alexei Starovoitov)
- Fix possible endless loop in BPF map iteration (Brandon Kammerdiener)
- Fix compilation failure for samples/bpf on LoongArch (Haoran Jiang)
- Disable a part of sockmap_ktls test (Ihor Solodrai)
- Correct typo in __clang_major__ macro (Peilin Ye)
* tag 'bpf-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
selftests/bpf: Correct typo in __clang_major__ macro
samples/bpf: Fix compilation failure for samples/bpf on LoongArch Fedora
bpf: Add namespace to BPF internal symbols
selftests/bpf: add test for softlock when modifying hashmap while iterating
bpf: fix possible endless loop in BPF map iteration
selftests/bpf: Mitigate sockmap_ktls disconnect_after_delete failure
Pull dma-maping fixes from Marek Szyprowski:
- avoid unused variable warnings (Arnd Bergmann, Marek Szyprowski)
- add runtume warnings and debug messages for devices with limited DMA
capabilities (Balbir Singh, Chen-Yu Tsai)
* tag 'dma-mapping-6.15-2025-04-25' of git://git.kernel.org/pub/scm/linux/kernel/git/mszyprowski/linux:
dma-coherent: Warn if OF reserved memory is beyond current coherent DMA mask
dma-mapping: Fix warning reported for missing prototype
dma-mapping: avoid potential unused data compilation warning
dma/mapping.c: dev_dbg support for dma_addressing_limited
dma/contiguous: avoid warning about unused size_bytes
Adding support to access arguments with const void pointer arguments
in tracing programs.
Currently we allow tracing programs to access void pointers. If we try to
access argument which is pointer to const void like 2nd argument in kfree,
verifier will fail to load the program with;
0: R1=ctx() R10=fp0
; asm volatile ("r2 = *(u64 *)(r1 + 8); ");
0: (79) r2 = *(u64 *)(r1 +8)
func 'kfree' arg1 type UNKNOWN is not a struct
Changing the is_int_ptr to void and generic integer check and renaming
it to is_void_or_int_ptr.
Signed-off-by: KaFai Wan <mannkafai@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20250423121329.3163461-2-mannkafai@gmail.com
Many conditional checks in switch-case are redundant
with bpf_base_func_proto and should be removed.
Regarding the permission checks bpf_base_func_proto:
The permission checks in bpf_prog_load (as outlined below)
ensure that the trace has both CAP_BPF and CAP_PERFMON capabilities,
thus enabling the use of corresponding prototypes
in bpf_base_func_proto without adverse effects.
bpf_prog_load
......
bpf_cap = bpf_token_capable(token, CAP_BPF);
......
if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
type != BPF_PROG_TYPE_CGROUP_SKB &&
!bpf_cap)
goto put_token;
......
if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON))
goto put_token;
......
Signed-off-by: Feng Yang <yangfeng@kylinos.cn>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/bpf/20250423073151.297103-1-yangfeng59949@163.com
Pull virtio fixes from Michael Tsirkin:
"A small number of fixes:
- virtgpu is exempt from reset shutdown fow now - a more complete fix
is in the works
- spec compliance fixes in:
- virtio-pci cap commands
- vhost_scsi_send_bad_target
- virtio console resize
- missing locking fix in vhost-scsi
- virtio ring - a KCSAN false positive fix
- VHOST_*_OWNER documentation fix"
* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
vhost-scsi: Fix vhost_scsi_send_status()
vhost-scsi: Fix vhost_scsi_send_bad_target()
vhost-scsi: protect vq->log_used with vq->mutex
vhost_task: fix vhost_task_create() documentation
virtio_console: fix order of fields cols and rows
virtio_console: fix missing byte order handling for cols and rows
virtgpu: don't reset on shutdown
virtio_ring: Fix data race by tagging event_triggered as racy for KCSAN
vhost: fix VHOST_*_OWNER documentation
virtio_pci: Use self group type for cap commands
When a reserved memory region described in the device tree is attached
to a device, it is expected that the device's limitations are correctly
included in that description.
However, if the device driver failed to implement DMA address masking
or addressing beyond the default 32 bits (on arm64), then bad things
could happen because the DMA address was truncated, such as playing
back audio with no actual audio coming out, or DMA overwriting random
blocks of kernel memory.
Check against the coherent DMA mask when the memory regions are attached
to the device. Give a warning when the memory region can not be covered
by the mask.
A warning instead of a hard error was chosen, because it is possible
that existing drivers could be working fine even if they forgot to
extend the coherent DMA mask.
Signed-off-by: Chen-Yu Tsai <wenst@chromium.org>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20250421083930.374173-1-wenst@chromium.org
Pull sched_ext fixes from Tejun Heo:
- Use kvzalloc() so that large exit_dump buffer allocations don't fail
easily
- Remove cpu.weight / cpu.idle unimplemented warnings which are more
annoying than helpful.
This makes SCX_OPS_HAS_CGROUP_WEIGHT unnecessary. Mark it for
deprecation
* tag 'sched_ext-for-6.15-rc3-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext:
sched_ext: Mark SCX_OPS_HAS_CGROUP_WEIGHT for deprecation
sched_ext: Remove cpu.weight / cpu.idle unimplemented warnings
sched_ext: Use kvzalloc for large exit_dump allocation
Pull cgroup fixes from Tejun Heo:
- Fix compilation in CONFIG_LOCKDEP && !CONFIG_PROVE_RCU configurations
- Allow "cpuset_v2_mode" mount option for "cpuset" filesystem type to
make life easier for android
* tag 'cgroup-for-6.15-rc3-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
cgroup/cpuset-v1: Add missing support for cpuset_v2_mode
cgroup: Fix compilation issue due to cgroup_mutex not being exported
Pull vfs fixes from Christian Brauner:
- Revert the hfs{plus} deprecation warning that's also included in this
pull request. The commit introducing the deprecation warning resides
rather early in this branch. So simply dropping it would've rebased
all other commits which I decided to avoid. Hence the revert in the
same branch
[ Background - the deprecation warning discussion resulted in people
stepping up, and so hfs{plus} will have a maintainer taking care of
it after all.. - Linus ]
- Switch CONFIG_SYSFS_SYCALL default to n and decouple from
CONFIG_EXPERT
- Fix an audit bug caused by changes to our kernel path lookup helpers
this cycle. Audit needs the parent path even if the dentry it tried
to look up is negative
- Ensure that the kernel path lookup helpers leave the passed in path
argument clean when they return an error. This is consistent with all
our other helpers
- Ensure that vfs_getattr_nosec() calls bdev_statx() so the relevant
information is available to kernel consumers as well
- Don't set a timer and call schedule() if the timer will expire
immediately in epoll
- Make netfs lookup tables with __nonstring
* tag 'vfs-6.15-rc3.fixes.2' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs:
Revert "hfs{plus}: add deprecation warning"
fs: move the bdex_statx call to vfs_getattr_nosec
netfs: Mark __nonstring lookup tables
eventpoll: Set epoll timeout if it's in the future
fs: ensure that *path_locked*() helpers leave passed path pristine
fs: add kern_path_locked_negative()
hfs{plus}: add deprecation warning
Kconfig: switch CONFIG_SYSFS_SYCALL default to n
Pull tracing fixes from Steven Rostedt:
- Initialize hash variables in ftrace subops logic
The fix that simplified the ftrace subops logic opened a path where
some variables could be used without being initialized, and done
subtly where the compiler did not catch it. Initialize those
variables to the EMPTY_HASH, which is the default hash.
- Reinitialize the hash pointers after they are freed
Some of the hash pointers in the subop logic were freed but may still
be referenced later. To prevent use-after-free bugs, initialize them
back to the EMPTY_HASH.
- Free the ftrace hashes when they are replaced
The fix that simplified the subops logic updated some hash pointers,
but left the original hash that they were pointing to where they are
no longer used. This caused a memory leak. Free the hashes that are
pointed to by the pointers when they are replaced.
- Fix size initialization of ftrace direct function hash
The ftrace direct function hash used by BPF initialized the hash size
incorrectly. It checked the size of items to a hard coded 32, which
made the hash bit size of 5. The hash size is supposed to be limited
by the bit size of the hash, as the bitmask is allowed to be greater
than 5. Rework the size check to first pass the number of elements to
fls() and then compare that to FTRACE_HASH_MAX_BITS before allocating
the hash.
- Fix format output of ftrace_graph_ent_entry event
The field depth of the ftrace_graph_ent_entry event is of size 4 but
the output showed it as unsigned long and use "%lu". Change it to
unsigned int and use "%u" in the print format that is displayed to
user space.
- Fix the trace event filter on strings
Events can be filtered on numbers or string values. The return value
checked from strncpy_from_kernel_nofault() and
strncpy_from_user_nofault() was used to determine if reading the
strings would fault or not. It would return fault if the value was
non zero, which is basically meant that it was always considering the
read as a fault.
- Add selftest to test trace event string filtering
In order to catch the breakage of the string filtering, add a self
test to make sure that it continues to work.
* tag 'trace-v6.15-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
tracing: selftests: Add testing a user string to filters
tracing: Fix filter string testing
ftrace: Fix type of ftrace_graph_ent_entry.depth
ftrace: fix incorrect hash size in register_ftrace_direct()
ftrace: Free ftrace hashes after they are replaced in the subops code
ftrace: Reinitialize hash to EMPTY_HASH after freeing
ftrace: Initialize variables for ftrace_startup/shutdown_subops()
