Entries in list 'tr->err_log' will be reused after entry number
exceed TRACING_LOG_ERRS_MAX.
The cmd string of the to be reused entry will be freed first then
allocated a new one. If the allocation failed, then the entry will
still be in list 'tr->err_log' but its 'cmd' field is set to be NULL,
later access of 'cmd' is risky.
Currently above problem can cause the loss of 'cmd' information of first
entry in 'tr->err_log'. When execute `cat /sys/kernel/tracing/error_log`,
reproduce logs like:
[ 37.495100] trace_kprobe: error: Maxactive is not for kprobe(null) ^
[ 38.412517] trace_kprobe: error: Maxactive is not for kprobe
Command: p4:myprobe2 do_sys_openat2
^
Link: https://lore.kernel.org/linux-trace-kernel/20221114104632.3547266-1-zhengyejian1@huawei.com
Fixes: 1581a884b7 ("tracing: Remove size restriction on tracing_log_err cmd strings")
Signed-off-by: Zheng Yejian <zhengyejian1@huawei.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
This has nothing to do with random.c and everything to do with stack
protectors. Yes, it uses randomness. But many things use randomness.
random.h and random.c are concerned with the generation of randomness,
not with each and every use. So move this function into the more
specific stackprotector.h file where it belongs.
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
These cases were done with this Coccinelle:
@@
expression H;
expression L;
@@
- (get_random_u32_below(H) + L)
+ get_random_u32_inclusive(L, H + L - 1)
@@
expression H;
expression L;
expression E;
@@
get_random_u32_inclusive(L,
H
- + E
- - E
)
@@
expression H;
expression L;
expression E;
@@
get_random_u32_inclusive(L,
H
- - E
- + E
)
@@
expression H;
expression L;
expression E;
expression F;
@@
get_random_u32_inclusive(L,
H
- - E
+ F
- + E
)
@@
expression H;
expression L;
expression E;
expression F;
@@
get_random_u32_inclusive(L,
H
- + E
+ F
- - E
)
And then subsequently cleaned up by hand, with several automatic cases
rejected if it didn't make sense contextually.
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com> # for infiniband
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Since the eprobe filter was defined based on the eprobe's trace event
itself, it doesn't work correctly. Use the original trace event of
the eprobe when making the filter so that the filter works correctly.
Without this fix:
# echo 'e syscalls/sys_enter_openat \
flags_rename=$flags:u32 if flags < 1000' >> dynamic_events
# echo 1 > events/eprobes/sys_enter_openat/enable
[ 114.551550] event trace: Could not enable event sys_enter_openat
-bash: echo: write error: Invalid argument
With this fix:
# echo 'e syscalls/sys_enter_openat \
flags_rename=$flags:u32 if flags < 1000' >> dynamic_events
# echo 1 > events/eprobes/sys_enter_openat/enable
# tail trace
cat-241 [000] ...1. 266.498449: sys_enter_openat: (syscalls.sys_enter_openat) flags_rename=0
cat-242 [000] ...1. 266.977640: sys_enter_openat: (syscalls.sys_enter_openat) flags_rename=0
Link: https://lore.kernel.org/all/166823166395.1385292.8931770640212414483.stgit@devnote3/
Fixes: 752be5c5c9 ("tracing/eprobe: Add eprobe filter support")
Reported-by: Rafael Mendonca <rafaelmendsr@gmail.com>
Tested-by: Rafael Mendonca <rafaelmendsr@gmail.com>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
In __unregister_kprobe_top(), if the currently unregistered probe has
post_handler but other child probes of the aggrprobe do not have
post_handler, the post_handler of the aggrprobe is cleared. If this is
a ftrace-based probe, there is a problem. In later calls to
disarm_kprobe(), we will use kprobe_ftrace_ops because post_handler is
NULL. But we're armed with kprobe_ipmodify_ops. This triggers a WARN in
__disarm_kprobe_ftrace() and may even cause use-after-free:
Failed to disarm kprobe-ftrace at kernel_clone+0x0/0x3c0 (error -2)
WARNING: CPU: 5 PID: 137 at kernel/kprobes.c:1135 __disarm_kprobe_ftrace.isra.21+0xcf/0xe0
Modules linked in: testKprobe_007(-)
CPU: 5 PID: 137 Comm: rmmod Not tainted 6.1.0-rc4-dirty #18
[...]
Call Trace:
<TASK>
__disable_kprobe+0xcd/0xe0
__unregister_kprobe_top+0x12/0x150
? mutex_lock+0xe/0x30
unregister_kprobes.part.23+0x31/0xa0
unregister_kprobe+0x32/0x40
__x64_sys_delete_module+0x15e/0x260
? do_user_addr_fault+0x2cd/0x6b0
do_syscall_64+0x3a/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
[...]
For the kprobe-on-ftrace case, we keep the post_handler setting to
identify this aggrprobe armed with kprobe_ipmodify_ops. This way we
can disarm it correctly.
Link: https://lore.kernel.org/all/20221112070000.35299-1-lihuafei1@huawei.com/
Fixes: 0bc11ed5ab ("kprobes: Allow kprobes coexist with livepatch")
Reported-by: Zhao Gongyi <zhaogongyi@huawei.com>
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Li Huafei <lihuafei1@huawei.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
The @ftrace_mod is allocated by kzalloc(), so both the members {prev,next}
of @ftrace_mode->list are NULL, it's not a valid state to call list_del().
If kstrdup() for @ftrace_mod->{func|module} fails, it goes to @out_free
tag and calls free_ftrace_mod() to destroy @ftrace_mod, then list_del()
will write prev->next and next->prev, where null pointer dereference
happens.
BUG: kernel NULL pointer dereference, address: 0000000000000008
Oops: 0002 [#1] PREEMPT SMP NOPTI
Call Trace:
<TASK>
ftrace_mod_callback+0x20d/0x220
? do_filp_open+0xd9/0x140
ftrace_process_regex.isra.51+0xbf/0x130
ftrace_regex_write.isra.52.part.53+0x6e/0x90
vfs_write+0xee/0x3a0
? __audit_filter_op+0xb1/0x100
? auditd_test_task+0x38/0x50
ksys_write+0xa5/0xe0
do_syscall_64+0x3a/0x90
entry_SYSCALL_64_after_hwframe+0x63/0xcd
Kernel panic - not syncing: Fatal exception
So call INIT_LIST_HEAD() to initialize the list member to fix this issue.
Link: https://lkml.kernel.org/r/20221116015207.30858-1-xiujianfeng@huawei.com
Cc: stable@vger.kernel.org
Fixes: 673feb9d76 ("ftrace: Add :mod: caching infrastructure to trace_array")
Signed-off-by: Xiu Jianfeng <xiujianfeng@huawei.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
The first test of the kcsan selftest appears to test if get_random_u32()
returns two zeros in a row, and requires that it doesn't. This seems
like a bogus criteron. Remove it.
Acked-by: Marco Elver <elver@google.com>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Currently bpf_map_do_batch() first invokes fdget(batch.map_fd) to get
the target map file, then it invokes generic_map_update_batch() to do
batch update. generic_map_update_batch() will get the target map file
by using fdget(batch.map_fd) again and pass it to bpf_map_update_value().
The problem is map file returned by the second fdget() may be NULL or a
totally different file compared by map file in bpf_map_do_batch(). The
reason is that the first fdget() only guarantees the liveness of struct
file instead of file descriptor and the file description may be released
by concurrent close() through pick_file().
It doesn't incur any problem as for now, because maps with batch update
support don't use map file in .map_fd_get_ptr() ops. But it is better to
fix the potential access of an invalid map file.
Using __bpf_map_get() again in generic_map_update_batch() can not fix
the problem, because batch.map_fd may be closed and reopened, and the
returned map file may be different with map file got in
bpf_map_do_batch(), so just passing the map file directly to
.map_update_batch() in bpf_map_do_batch().
Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20221116075059.1551277-1-houtao@huaweicloud.com
As noted by Michal, the blkg_iostat_set's in the lockless list
hold reference to blkg's to protect against their removal. Those
blkg's hold reference to blkcg. When a cgroup is being destroyed,
cgroup_rstat_flush() is only called at css_release_work_fn() which is
called when the blkcg reference count reaches 0. This circular dependency
will prevent blkcg from being freed until some other events cause
cgroup_rstat_flush() to be called to flush out the pending blkcg stats.
To prevent this delayed blkcg removal, add a new cgroup_rstat_css_flush()
function to flush stats for a given css and cpu and call it at the blkgs
destruction path, blkcg_destroy_blkgs(), whenever there are still some
pending stats to be flushed. This will ensure that blkcg reference
count can reach 0 ASAP.
Signed-off-by: Waiman Long <longman@redhat.com>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20221105005902.407297-4-longman@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The function ring_buffer_nr_dirty_pages() was created to find out how many
pages are filled in the ring buffer. There's two running counters. One is
incremented whenever a new page is touched (pages_touched) and the other
is whenever a page is read (pages_read). The dirty count is the number
touched minus the number read. This is used to determine if a blocked task
should be woken up if the percentage of the ring buffer it is waiting for
is hit.
The problem is that it does not take into account dropped pages (when the
new writes overwrite pages that were not read). And then the dirty pages
will always be greater than the percentage.
This makes the "buffer_percent" file inaccurate, as the number of dirty
pages end up always being larger than the percentage, event when it's not
and this causes user space to be woken up more than it wants to be.
Add a new counter to keep track of lost pages, and include that in the
accounting of dirty pages so that it is actually accurate.
Link: https://lkml.kernel.org/r/20221021123013.55fb6055@gandalf.local.home
Fixes: 2c2b0a78b3 ("ring-buffer: Add percentage of ring buffer full to wake up reader")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Currently the way polling works on the ring buffer is broken. It will
return immediately if there's any data in the ring buffer whereas a read
will block until the watermark (defined by the tracefs buffer_percent file)
is hit.
That is, a select() or poll() will return as if there's data available,
but then the following read will block. This is broken for the way
select()s and poll()s are supposed to work.
Have the polling on the ring buffer also block the same way reads and
splice does on the ring buffer.
Link: https://lkml.kernel.org/r/20221020231427.41be3f26@gandalf.local.home
Cc: Linux Trace Kernel <linux-trace-kernel@vger.kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Primiano Tucci <primiano@google.com>
Cc: stable@vger.kernel.org
Fixes: 1e0d6714ac ("ring-buffer: Do not wake up a splice waiter when page is not full")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
We found a long tail latency in schbench whem m*t is close to nr_cpus.
(e.g., "schbench -m 2 -t 16" on a machine with 32 cpus.)
This is because when the wakee cpu is idle, rq->ttwu_pending is cleared
too early, and idle_cpu() will return true until the wakee task enqueued.
This will mislead the waker when selecting idle cpu, and wake multiple
worker threads on the same wakee cpu. This situation is enlarged by
commit f3dd3f6745 ("sched: Remove the limitation of WF_ON_CPU on
wakelist if wakee cpu is idle") because it tends to use wakelist.
Here is the result of "schbench -m 2 -t 16" on a VM with 32vcpu
(Intel(R) Xeon(R) Platinum 8369B).
Latency percentiles (usec):
base base+revert_f3dd3f674555 base+this_patch
50.0000th: 9 13 9
75.0000th: 12 19 12
90.0000th: 15 22 15
95.0000th: 18 24 17
*99.0000th: 27 31 24
99.5000th: 3364 33 27
99.9000th: 12560 36 30
We also tested on unixbench and hackbench, and saw no performance
change.
Signed-off-by: Tianchen Ding <dtcccc@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Link: https://lkml.kernel.org/r/20221104023601.12844-1-dtcccc@linux.alibaba.com
Propagate nullness information for branches of register to register
equality compare instructions. The following rules are used:
- suppose register A maybe null
- suppose register B is not null
- for JNE A, B, ... - A is not null in the false branch
- for JEQ A, B, ... - A is not null in the true branch
E.g. for program like below:
r6 = skb->sk;
r7 = sk_fullsock(r6);
r0 = sk_fullsock(r6);
if (r0 == 0) return 0; (a)
if (r0 != r7) return 0; (b)
*r7->type; (c)
return 0;
It is safe to dereference r7 at point (c), because of (a) and (b).
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/r/20221115224859.2452988-2-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
In pmu_dev_alloc(), when dev_set_name() failed, it will goto free_dev
and call put_device(pmu->dev) to release it.
However pmu->dev->release is assigned after this, which makes warning
and memleak.
Call dev_set_name() after pmu->dev->release = pmu_dev_release to fix it.
Device '(null)' does not have a release() function...
WARNING: CPU: 2 PID: 441 at drivers/base/core.c:2332 device_release+0x1b9/0x240
...
Call Trace:
<TASK>
kobject_put+0x17f/0x460
put_device+0x20/0x30
pmu_dev_alloc+0x152/0x400
perf_pmu_register+0x96b/0xee0
...
kmemleak: 1 new suspected memory leaks (see /sys/kernel/debug/kmemleak)
unreferenced object 0xffff888014759000 (size 2048):
comm "modprobe", pid 441, jiffies 4294931444 (age 38.332s)
backtrace:
[<0000000005aed3b4>] kmalloc_trace+0x27/0x110
[<000000006b38f9b8>] pmu_dev_alloc+0x50/0x400
[<00000000735f17be>] perf_pmu_register+0x96b/0xee0
[<00000000e38477f1>] 0xffffffffc0ad8603
[<000000004e162216>] do_one_initcall+0xd0/0x4e0
...
Fixes: abe4340057 ("perf: Sysfs enumeration")
Signed-off-by: Chen Zhongjin <chenzhongjin@huawei.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20221111103653.91058-1-chenzhongjin@huawei.com
For queueing packets in XDP we want to add a new redirect map type with
support for 64-bit indexes. To prepare fore this, expand the width of the
'key' argument to the bpf_redirect_map() helper. Since BPF registers are
always 64-bit, this should be safe to do after the fact.
Acked-by: Song Liu <song@kernel.org>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/r/20221108140601.149971-3-toke@redhat.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Since commit bfea9a8574 ("bpf: Add name to struct bpf_ksym"), when
reporting subprog ksymbol to perf, prog name instead of subprog name is
used. The backtrace of bpf program with subprogs will be incorrect as
shown below:
ffffffffc02deace bpf_prog_e44a3057dcb151f8_overwrite+0x66
ffffffffc02de9f7 bpf_prog_e44a3057dcb151f8_overwrite+0x9f
ffffffffa71d8d4e trace_call_bpf+0xce
ffffffffa71c2938 perf_call_bpf_enter.isra.0+0x48
overwrite is the entry program and it invokes the overwrite_htab subprog
through bpf_loop, but in above backtrace, overwrite program just jumps
inside itself.
Fixing it by using subprog name when reporting subprog ksymbol. After
the fix, the output of perf script will be correct as shown below:
ffffffffc031aad2 bpf_prog_37c0bec7d7c764a4_overwrite_htab+0x66
ffffffffc031a9e7 bpf_prog_c7eb827ef4f23e71_overwrite+0x9f
ffffffffa3dd8d4e trace_call_bpf+0xce
ffffffffa3dc2938 perf_call_bpf_enter.isra.0+0x48
Fixes: bfea9a8574 ("bpf: Add name to struct bpf_ksym")
Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20221114095733.158588-1-houtao@huaweicloud.com
Added test cases for basic functions and performance of functions
kallsyms_lookup_name(), kallsyms_on_each_symbol() and
kallsyms_on_each_match_symbol(). It also calculates the compression rate
of the kallsyms compression algorithm for the current symbol set.
The basic functions test begins by testing a set of symbols whose address
values are known. Then, traverse all symbol addresses and find the
corresponding symbol name based on the address. It's impossible to
determine whether these addresses are correct, but we can use the above
three functions along with the addresses to test each other. Due to the
traversal operation of kallsyms_on_each_symbol() is too slow, only 60
symbols can be tested in one second, so let it test on average once
every 128 symbols. The other two functions validate all symbols.
If the basic functions test is passed, print only performance test
results. If the test fails, print error information, but do not perform
subsequent performance tests.
Start self-test automatically after system startup if
CONFIG_KALLSYMS_SELFTEST=y.
Example of output content: (prefix 'kallsyms_selftest:' is omitted
start
---------------------------------------------------------
| nr_symbols | compressed size | original size | ratio(%) |
|---------------------------------------------------------|
| 107543 | 1357912 | 2407433 | 56.40 |
---------------------------------------------------------
kallsyms_lookup_name() looked up 107543 symbols
The time spent on each symbol is (ns): min=630, max=35295, avg=7353
kallsyms_on_each_symbol() traverse all: 11782628 ns
kallsyms_on_each_match_symbol() traverse all: 9261 ns
finish
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
Instead of having to pass multiple arguments that describe the register,
pass the bpf_reg_state into the btf_struct_access callback. Currently,
all call sites simply reuse the btf and btf_id of the reg they want to
check the access of. The only exception to this pattern is the callsite
in check_ptr_to_map_access, hence for that case create a dummy reg to
simulate PTR_TO_BTF_ID access.
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20221114191547.1694267-8-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Currently, verifier uses MEM_ALLOC type tag to specially tag memory
returned from bpf_ringbuf_reserve helper. However, this is currently
only used for this purpose and there is an implicit assumption that it
only refers to ringbuf memory (e.g. the check for ARG_PTR_TO_ALLOC_MEM
in check_func_arg_reg_off).
Hence, rename MEM_ALLOC to MEM_RINGBUF to indicate this special
relationship and instead open the use of MEM_ALLOC for more generic
allocations made for user types.
Also, since ARG_PTR_TO_ALLOC_MEM_OR_NULL is unused, simply drop it.
Finally, update selftests using 'alloc_' verifier string to 'ringbuf_'.
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20221114191547.1694267-7-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Currently, the verifier has two return types, RET_PTR_TO_ALLOC_MEM, and
RET_PTR_TO_ALLOC_MEM_OR_NULL, however the former is confusingly named to
imply that it carries MEM_ALLOC, while only the latter does. This causes
confusion during code review leading to conclusions like that the return
value of RET_PTR_TO_DYNPTR_MEM_OR_NULL (which is RET_PTR_TO_ALLOC_MEM |
PTR_MAYBE_NULL) may be consumable by bpf_ringbuf_{submit,commit}.
Rename it to make it clear MEM_ALLOC needs to be tacked on top of
RET_PTR_TO_MEM.
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20221114191547.1694267-6-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Add the support on the map side to parse, recognize, verify, and build
metadata table for a new special field of the type struct bpf_list_head.
To parameterize the bpf_list_head for a certain value type and the
list_node member it will accept in that value type, we use BTF
declaration tags.
The definition of bpf_list_head in a map value will be done as follows:
struct foo {
struct bpf_list_node node;
int data;
};
struct map_value {
struct bpf_list_head head __contains(foo, node);
};
Then, the bpf_list_head only allows adding to the list 'head' using the
bpf_list_node 'node' for the type struct foo.
The 'contains' annotation is a BTF declaration tag composed of four
parts, "contains:name:node" where the name is then used to look up the
type in the map BTF, with its kind hardcoded to BTF_KIND_STRUCT during
the lookup. The node defines name of the member in this type that has
the type struct bpf_list_node, which is actually used for linking into
the linked list. For now, 'kind' part is hardcoded as struct.
This allows building intrusive linked lists in BPF, using container_of
to obtain pointer to entry, while being completely type safe from the
perspective of the verifier. The verifier knows exactly the type of the
nodes, and knows that list helpers return that type at some fixed offset
where the bpf_list_node member used for this list exists. The verifier
also uses this information to disallow adding types that are not
accepted by a certain list.
For now, no elements can be added to such lists. Support for that is
coming in future patches, hence draining and freeing items is done with
a TODO that will be resolved in a future patch.
Note that the bpf_list_head_free function moves the list out to a local
variable under the lock and releases it, doing the actual draining of
the list items outside the lock. While this helps with not holding the
lock for too long pessimizing other concurrent list operations, it is
also necessary for deadlock prevention: unless every function called in
the critical section would be notrace, a fentry/fexit program could
attach and call bpf_map_update_elem again on the map, leading to the
same lock being acquired if the key matches and lead to a deadlock.
While this requires some special effort on part of the BPF programmer to
trigger and is highly unlikely to occur in practice, it is always better
if we can avoid such a condition.
While notrace would prevent this, doing the draining outside the lock
has advantages of its own, hence it is used to also fix the deadlock
related problem.
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20221114191547.1694267-5-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
In f71b2f6417 ("bpf: Refactor map->off_arr handling"), map->off_arr
was refactored to be btf_field_offs. The number of field offsets is
equal to maximum possible fields limited by BTF_FIELDS_MAX. Hence, reuse
BTF_FIELDS_MAX as spin_lock and timer no longer are to be handled
specially for offset sorting, fix the comment, and remove incorrect
WARN_ON as its rec->cnt can never exceed this value. The reason to keep
separate constant was the it was always more 2 more than total kptrs.
This is no longer the case.
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20221114191547.1694267-3-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
It was found that with the default hierarchy, enabling cpuset in the
child cgroups can trigger a cpuset_attach() call in each of the child
cgroups that have tasks with no change in effective cpus and mems. If
there are many processes in those child cgroups, it will burn quite a
lot of cpu cycles iterating all the tasks without doing useful work.
Optimizing this case by comparing between the old and new cpusets and
skip useless update if there is no change in effective cpus and mems.
Also mems_allowed are less likely to be changed than cpus_allowed. So
skip changing mm if there is no change in effective_mems and
CS_MEMORY_MIGRATE is not set.
By inserting some instrumentation code and running a simple command in
a container 200 times in a cgroup v2 system, it was found that all the
cpuset_attach() calls are skipped (401 times in total) as there was no
change in effective cpus and mems.
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Cpuset v2 has no spread flags to set. So we can skip spread
flags update if cpuset v2 is being used. Also change the name to
cpuset_update_task_spread_flags() to indicate that there are multiple
spread flags.
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
