From 450fec13d9170127678f991698ac1a5b05c02e2f Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Tue, 30 Nov 2021 12:31:23 -0500 Subject: tracing/histograms: String compares should not care about signed values When comparing two strings for the "onmatch" histogram trigger, fields that are strings use string comparisons, which do not care about being signed or not. Do not fail to match two string fields if one is unsigned char array and the other is a signed char array. Link: https://lore.kernel.org/all/20211129123043.5cfd687a@gandalf.local.home/ Cc: stable@vgerk.kernel.org Cc: Tom Zanussi Cc: Yafang Shao Fixes: b05e89ae7cf3b ("tracing: Accept different type for synthetic event fields") Reviewed-by: Masami Hiramatsu Reported-by: Sven Schnelle Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_hist.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 9555b8e1d1e3..319f9c8ca7e7 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -3757,7 +3757,7 @@ static int check_synth_field(struct synth_event *event, if (strcmp(field->type, hist_field->type) != 0) { if (field->size != hist_field->size || - field->is_signed != hist_field->is_signed) + (!field->is_string && field->is_signed != hist_field->is_signed)) return -EINVAL; } -- cgit v1.2.3 From f25667e5980a4333729cac3101e5de1bb851f71a Mon Sep 17 00:00:00 2001 From: Chen Jun Date: Wed, 24 Nov 2021 14:08:01 +0000 Subject: tracing: Fix a kmemleak false positive in tracing_map Doing the command: echo 'hist:key=common_pid.execname,common_timestamp' > /sys/kernel/debug/tracing/events/xxx/trigger Triggers many kmemleak reports: unreferenced object 0xffff0000c7ea4980 (size 128): comm "bash", pid 338, jiffies 4294912626 (age 9339.324s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000f3469921>] kmem_cache_alloc_trace+0x4c0/0x6f0 [<0000000054ca40c3>] hist_trigger_elt_data_alloc+0x140/0x178 [<00000000633bd154>] tracing_map_init+0x1f8/0x268 [<000000007e814ab9>] event_hist_trigger_func+0xca0/0x1ad0 [<00000000bf8520ed>] trigger_process_regex+0xd4/0x128 [<00000000f549355a>] event_trigger_write+0x7c/0x120 [<00000000b80f898d>] vfs_write+0xc4/0x380 [<00000000823e1055>] ksys_write+0x74/0xf8 [<000000008a9374aa>] __arm64_sys_write+0x24/0x30 [<0000000087124017>] do_el0_svc+0x88/0x1c0 [<00000000efd0dcd1>] el0_svc+0x1c/0x28 [<00000000dbfba9b3>] el0_sync_handler+0x88/0xc0 [<00000000e7399680>] el0_sync+0x148/0x180 unreferenced object 0xffff0000c7ea4980 (size 128): comm "bash", pid 338, jiffies 4294912626 (age 9339.324s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000f3469921>] kmem_cache_alloc_trace+0x4c0/0x6f0 [<0000000054ca40c3>] hist_trigger_elt_data_alloc+0x140/0x178 [<00000000633bd154>] tracing_map_init+0x1f8/0x268 [<000000007e814ab9>] event_hist_trigger_func+0xca0/0x1ad0 [<00000000bf8520ed>] trigger_process_regex+0xd4/0x128 [<00000000f549355a>] event_trigger_write+0x7c/0x120 [<00000000b80f898d>] vfs_write+0xc4/0x380 [<00000000823e1055>] ksys_write+0x74/0xf8 [<000000008a9374aa>] __arm64_sys_write+0x24/0x30 [<0000000087124017>] do_el0_svc+0x88/0x1c0 [<00000000efd0dcd1>] el0_svc+0x1c/0x28 [<00000000dbfba9b3>] el0_sync_handler+0x88/0xc0 [<00000000e7399680>] el0_sync+0x148/0x180 The reason is elts->pages[i] is alloced by get_zeroed_page. and kmemleak will not scan the area alloced by get_zeroed_page. The address stored in elts->pages will be regarded as leaked. That is, the elts->pages[i] will have pointers loaded onto it as well, and without telling kmemleak about it, those pointers will look like memory without a reference. To fix this, call kmemleak_alloc to tell kmemleak to scan elts->pages[i] Link: https://lkml.kernel.org/r/20211124140801.87121-1-chenjun102@huawei.com Signed-off-by: Chen Jun Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/tracing_map.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c index 39bb56d2dcbe..9628b5571846 100644 --- a/kernel/trace/tracing_map.c +++ b/kernel/trace/tracing_map.c @@ -15,6 +15,7 @@ #include #include #include +#include #include "tracing_map.h" #include "trace.h" @@ -307,6 +308,7 @@ static void tracing_map_array_free(struct tracing_map_array *a) for (i = 0; i < a->n_pages; i++) { if (!a->pages[i]) break; + kmemleak_free(a->pages[i]); free_page((unsigned long)a->pages[i]); } @@ -342,6 +344,7 @@ static struct tracing_map_array *tracing_map_array_alloc(unsigned int n_elts, a->pages[i] = (void *)get_zeroed_page(GFP_KERNEL); if (!a->pages[i]) goto free; + kmemleak_alloc(a->pages[i], PAGE_SIZE, 1, GFP_KERNEL); } out: return a; -- cgit v1.2.3 From 6bbfa44116689469267f1a6e3d233b52114139d2 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 1 Dec 2021 23:45:50 +0900 Subject: kprobes: Limit max data_size of the kretprobe instances The 'kprobe::data_size' is unsigned, thus it can not be negative. But if user sets it enough big number (e.g. (size_t)-8), the result of 'data_size + sizeof(struct kretprobe_instance)' becomes smaller than sizeof(struct kretprobe_instance) or zero. In result, the kretprobe_instance are allocated without enough memory, and kretprobe accesses outside of allocated memory. To avoid this issue, introduce a max limitation of the kretprobe::data_size. 4KB per instance should be OK. Link: https://lkml.kernel.org/r/163836995040.432120.10322772773821182925.stgit@devnote2 Cc: stable@vger.kernel.org Fixes: f47cd9b553aa ("kprobes: kretprobe user entry-handler") Reported-by: zhangyue Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) --- kernel/kprobes.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'kernel') diff --git a/kernel/kprobes.c b/kernel/kprobes.c index e9db0c810554..21eccc961bba 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -2086,6 +2086,9 @@ int register_kretprobe(struct kretprobe *rp) } } + if (rp->data_size > KRETPROBE_MAX_DATA_SIZE) + return -E2BIG; + rp->kp.pre_handler = pre_handler_kretprobe; rp->kp.post_handler = NULL; -- cgit v1.2.3 From 53e87e3cdc155f20c3417b689df8d2ac88d79576 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 26 Oct 2021 16:10:54 +0200 Subject: timers/nohz: Last resort update jiffies on nohz_full IRQ entry When at least one CPU runs in nohz_full mode, a dedicated timekeeper CPU is guaranteed to stay online and to never stop its tick. Meanwhile on some rare case, the dedicated timekeeper may be running with interrupts disabled for a while, such as in stop_machine. If jiffies stop being updated, a nohz_full CPU may end up endlessly programming the next tick in the past, taking the last jiffies update monotonic timestamp as a stale base, resulting in an tick storm. Here is a scenario where it matters: 0) CPU 0 is the timekeeper and CPU 1 a nohz_full CPU. 1) A stop machine callback is queued to execute somewhere. 2) CPU 0 reaches MULTI_STOP_DISABLE_IRQ while CPU 1 is still in MULTI_STOP_PREPARE. Hence CPU 0 can't do its timekeeping duty. CPU 1 can still take IRQs. 3) CPU 1 receives an IRQ which queues a timer callback one jiffy forward. 4) On IRQ exit, CPU 1 schedules the tick one jiffy forward, taking last_jiffies_update as a base. But last_jiffies_update hasn't been updated for 2 jiffies since the timekeeper has interrupts disabled. 5) clockevents_program_event(), which relies on ktime_get(), observes that the expiration is in the past and therefore programs the min delta event on the clock. 6) The tick fires immediately, goto 3) 7) Tick storm, the nohz_full CPU is drown and takes ages to reach MULTI_STOP_DISABLE_IRQ, which is the only way out of this situation. Solve this with unconditionally updating jiffies if the value is stale on nohz_full IRQ entry. IRQs and other disturbances are expected to be rare enough on nohz_full for the unconditional call to ktime_get() to actually matter. Reported-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker Signed-off-by: Thomas Gleixner Tested-by: Paul E. McKenney Link: https://lore.kernel.org/r/20211026141055.57358-2-frederic@kernel.org --- kernel/softirq.c | 3 ++- kernel/time/tick-sched.c | 7 +++++++ 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/softirq.c b/kernel/softirq.c index 322b65d45676..41f470929e99 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -595,7 +595,8 @@ void irq_enter_rcu(void) { __irq_enter_raw(); - if (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET)) + if (tick_nohz_full_cpu(smp_processor_id()) || + (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET))) tick_irq_enter(); account_hardirq_enter(current); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 6bffe5af8cb1..17a283ce2b20 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -1375,6 +1375,13 @@ static inline void tick_nohz_irq_enter(void) now = ktime_get(); if (ts->idle_active) tick_nohz_stop_idle(ts, now); + /* + * If all CPUs are idle. We may need to update a stale jiffies value. + * Note nohz_full is a special case: a timekeeper is guaranteed to stay + * alive but it might be busy looping with interrupts disabled in some + * rare case (typically stop machine). So we must make sure we have a + * last resort. + */ if (ts->tick_stopped) tick_nohz_update_jiffies(now); } -- cgit v1.2.3 From e7f2be115f0746b969c0df14c0d182f65f005ca5 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 26 Oct 2021 16:10:55 +0200 Subject: sched/cputime: Fix getrusage(RUSAGE_THREAD) with nohz_full getrusage(RUSAGE_THREAD) with nohz_full may return shorter utime/stime than the actual time. task_cputime_adjusted() snapshots utime and stime and then adjust their sum to match the scheduler maintained cputime.sum_exec_runtime. Unfortunately in nohz_full, sum_exec_runtime is only updated once per second in the worst case, causing a discrepancy against utime and stime that can be updated anytime by the reader using vtime. To fix this situation, perform an update of cputime.sum_exec_runtime when the cputime snapshot reports the task as actually running while the tick is disabled. The related overhead is then contained within the relevant situations. Reported-by: Hasegawa Hitomi Signed-off-by: Frederic Weisbecker Signed-off-by: Hasegawa Hitomi Signed-off-by: Thomas Gleixner Tested-by: Masayoshi Mizuma Acked-by: Phil Auld Link: https://lore.kernel.org/r/20211026141055.57358-3-frederic@kernel.org --- kernel/sched/cputime.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 872e481d5098..9392aea1804e 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -615,7 +615,8 @@ void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) .sum_exec_runtime = p->se.sum_exec_runtime, }; - task_cputime(p, &cputime.utime, &cputime.stime); + if (task_cputime(p, &cputime.utime, &cputime.stime)) + cputime.sum_exec_runtime = task_sched_runtime(p); cputime_adjust(&cputime, &p->prev_cputime, ut, st); } EXPORT_SYMBOL_GPL(task_cputime_adjusted); @@ -828,19 +829,21 @@ u64 task_gtime(struct task_struct *t) * add up the pending nohz execution time since the last * cputime snapshot. */ -void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) +bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime) { struct vtime *vtime = &t->vtime; unsigned int seq; u64 delta; + int ret; if (!vtime_accounting_enabled()) { *utime = t->utime; *stime = t->stime; - return; + return false; } do { + ret = false; seq = read_seqcount_begin(&vtime->seqcount); *utime = t->utime; @@ -850,6 +853,7 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) if (vtime->state < VTIME_SYS) continue; + ret = true; delta = vtime_delta(vtime); /* @@ -861,6 +865,8 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) else *utime += vtime->utime + delta; } while (read_seqcount_retry(&vtime->seqcount, seq)); + + return ret; } static int vtime_state_fetch(struct vtime *vtime, int cpu) -- cgit v1.2.3 From d9847eb8be3d895b2b5f514fdf3885d47a0b92a2 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 22 Nov 2021 20:17:40 +0530 Subject: bpf: Make CONFIG_DEBUG_INFO_BTF depend upon CONFIG_BPF_SYSCALL Vinicius Costa Gomes reported [0] that build fails when CONFIG_DEBUG_INFO_BTF is enabled and CONFIG_BPF_SYSCALL is disabled. This leads to btf.c not being compiled, and then no symbol being present in vmlinux for the declarations in btf.h. Since BTF is not useful without enabling BPF subsystem, disallow this combination. However, theoretically disabling both now could still fail, as the symbol for kfunc_btf_id_list variables is not available. This isn't a problem as the compiler usually optimizes the whole register/unregister call, but at lower optimization levels it can fail the build in linking stage. Fix that by adding dummy variables so that modules taking address of them still work, but the whole thing is a noop. [0]: https://lore.kernel.org/bpf/20211110205418.332403-1-vinicius.gomes@intel.com Fixes: 14f267d95fe4 ("bpf: btf: Introduce helpers for dynamic BTF set registration") Reported-by: Vinicius Costa Gomes Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Andrii Nakryiko Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20211122144742.477787-2-memxor@gmail.com --- kernel/bpf/btf.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index dbc3ad07e21b..ea3df9867cec 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6346,11 +6346,6 @@ BTF_ID_LIST_GLOBAL_SINGLE(btf_task_struct_ids, struct, task_struct) /* BTF ID set registration API for modules */ -struct kfunc_btf_id_list { - struct list_head list; - struct mutex mutex; -}; - #ifdef CONFIG_DEBUG_INFO_BTF_MODULES void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l, @@ -6389,8 +6384,6 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, return false; } -#endif - #define DEFINE_KFUNC_BTF_ID_LIST(name) \ struct kfunc_btf_id_list name = { LIST_HEAD_INIT(name.list), \ __MUTEX_INITIALIZER(name.mutex) }; \ @@ -6398,3 +6391,5 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, DEFINE_KFUNC_BTF_ID_LIST(bpf_tcp_ca_kfunc_list); DEFINE_KFUNC_BTF_ID_LIST(prog_test_kfunc_list); + +#endif -- cgit v1.2.3 From b12f031043247b80999bf5e03b8cded3b0b40f8d Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Mon, 22 Nov 2021 20:17:41 +0530 Subject: bpf: Fix bpf_check_mod_kfunc_call for built-in modules When module registering its set is built-in, THIS_MODULE will be NULL, hence we cannot return early in case owner is NULL. Fixes: 14f267d95fe4 ("bpf: btf: Introduce helpers for dynamic BTF set registration") Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Andrii Nakryiko Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20211122144742.477787-3-memxor@gmail.com --- kernel/bpf/btf.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index ea3df9867cec..9bdb03767db5 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -6371,8 +6371,6 @@ bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id, { struct kfunc_btf_id_set *s; - if (!owner) - return false; mutex_lock(&klist->mutex); list_for_each_entry(s, &klist->list, list) { if (s->owner == owner && btf_id_set_contains(s->set, kfunc_id)) { -- cgit v1.2.3 From 2fa7d94afc1afbb4d702760c058dc2d7ed30f226 Mon Sep 17 00:00:00 2001 From: Maxim Mikityanskiy Date: Tue, 30 Nov 2021 20:16:07 +0200 Subject: bpf: Fix the off-by-two error in range markings The first commit cited below attempts to fix the off-by-one error that appeared in some comparisons with an open range. Due to this error, arithmetically equivalent pieces of code could get different verdicts from the verifier, for example (pseudocode): // 1. Passes the verifier: if (data + 8 > data_end) return early read *(u64 *)data, i.e. [data; data+7] // 2. Rejected by the verifier (should still pass): if (data + 7 >= data_end) return early read *(u64 *)data, i.e. [data; data+7] The attempted fix, however, shifts the range by one in a wrong direction, so the bug not only remains, but also such piece of code starts failing in the verifier: // 3. Rejected by the verifier, but the check is stricter than in #1. if (data + 8 >= data_end) return early read *(u64 *)data, i.e. [data; data+7] The change performed by that fix converted an off-by-one bug into off-by-two. The second commit cited below added the BPF selftests written to ensure than code chunks like #3 are rejected, however, they should be accepted. This commit fixes the off-by-two error by adjusting new_range in the right direction and fixes the tests by changing the range into the one that should actually fail. Fixes: fb2a311a31d3 ("bpf: fix off by one for range markings with L{T, E} patterns") Fixes: b37242c773b2 ("bpf: add test cases to bpf selftests to cover all access tests") Signed-off-by: Maxim Mikityanskiy Signed-off-by: Daniel Borkmann Link: https://lore.kernel.org/bpf/20211130181607.593149-1-maximmi@nvidia.com --- kernel/bpf/verifier.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 50efda51515b..f3001937bbb9 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -8422,7 +8422,7 @@ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate, new_range = dst_reg->off; if (range_right_open) - new_range--; + new_range++; /* Examples for register markings: * -- cgit v1.2.3 From 9ed20bafc85806ca6c97c9128cec46c3ef80ae86 Mon Sep 17 00:00:00 2001 From: Andrew Halaney Date: Fri, 3 Dec 2021 17:32:03 -0600 Subject: preempt/dynamic: Fix setup_preempt_mode() return value __setup() callbacks expect 1 for success and 0 for failure. Correct the usage here to reflect that. Fixes: 826bfeb37bb4 ("preempt/dynamic: Support dynamic preempt with preempt= boot option") Reported-by: Mark Rutland Signed-off-by: Andrew Halaney Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20211203233203.133581-1-ahalaney@redhat.com --- kernel/sched/core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 76f9deeaa942..814c52d90c0f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6617,11 +6617,11 @@ static int __init setup_preempt_mode(char *str) int mode = sched_dynamic_mode(str); if (mode < 0) { pr_warn("Dynamic Preempt: unsupported mode: %s\n", str); - return 1; + return 0; } sched_dynamic_update(mode); - return 0; + return 1; } __setup("preempt=", setup_preempt_mode); -- cgit v1.2.3 From 315c4f884800c45cb6bd8c90422fad554a8b9588 Mon Sep 17 00:00:00 2001 From: Qais Yousef Date: Thu, 2 Dec 2021 11:20:33 +0000 Subject: sched/uclamp: Fix rq->uclamp_max not set on first enqueue Commit d81ae8aac85c ("sched/uclamp: Fix initialization of struct uclamp_rq") introduced a bug where uclamp_max of the rq is not reset to match the woken up task's uclamp_max when the rq is idle. The code was relying on rq->uclamp_max initialized to zero, so on first enqueue static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p, enum uclamp_id clamp_id) { ... if (uc_se->value > READ_ONCE(uc_rq->value)) WRITE_ONCE(uc_rq->value, uc_se->value); } was actually resetting it. But since commit d81ae8aac85c changed the default to 1024, this no longer works. And since rq->uclamp_flags is also initialized to 0, neither above code path nor uclamp_idle_reset() update the rq->uclamp_max on first wake up from idle. This is only visible from first wake up(s) until the first dequeue to idle after enabling the static key. And it only matters if the uclamp_max of this task is < 1024 since only then its uclamp_max will be effectively ignored. Fix it by properly initializing rq->uclamp_flags = UCLAMP_FLAG_IDLE to ensure uclamp_idle_reset() is called which then will update the rq uclamp_max value as expected. Fixes: d81ae8aac85c ("sched/uclamp: Fix initialization of struct uclamp_rq") Signed-off-by: Qais Yousef Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Valentin Schneider Tested-by: Dietmar Eggemann Link: https://lkml.kernel.org/r/20211202112033.1705279-1-qais.yousef@arm.com --- kernel/sched/core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 814c52d90c0f..77563109c0ea 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1918,7 +1918,7 @@ static void __init init_uclamp_rq(struct rq *rq) }; } - rq->uclamp_flags = 0; + rq->uclamp_flags = UCLAMP_FLAG_IDLE; } static void __init init_uclamp(void) -- cgit v1.2.3 From 7d5b7cad79da76f3dad4a9f6040e524217814e5a Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 6 Dec 2021 19:20:30 +0100 Subject: ftrace: Use direct_ops hash in unregister_ftrace_direct Now when we have *direct_multi interface the direct_functions hash is no longer owned just by direct_ops. It's also used by any other ftrace_ops passed to *direct_multi interface. Thus to find out that we are unregistering the last function from direct_ops, we need to check directly direct_ops's hash. Link: https://lkml.kernel.org/r/20211206182032.87248-2-jolsa@kernel.org Cc: Ingo Molnar Cc: Heiko Carstens Fixes: f64dd4627ec6 ("ftrace: Add multi direct register/unregister interface") Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 30bc880c3849..7f0594e28226 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5217,6 +5217,7 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr) { struct ftrace_direct_func *direct; struct ftrace_func_entry *entry; + struct ftrace_hash *hash; int ret = -ENODEV; mutex_lock(&direct_mutex); @@ -5225,7 +5226,8 @@ int unregister_ftrace_direct(unsigned long ip, unsigned long addr) if (!entry) goto out_unlock; - if (direct_functions->count == 1) + hash = direct_ops.func_hash->filter_hash; + if (hash->count == 1) unregister_ftrace_function(&direct_ops); ret = ftrace_set_filter_ip(&direct_ops, ip, 1, 0); -- cgit v1.2.3 From fea3ffa48c6d42a11dca766c89284d22eaf5603f Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Mon, 6 Dec 2021 19:20:31 +0100 Subject: ftrace: Add cleanup to unregister_ftrace_direct_multi Adding ops cleanup to unregister_ftrace_direct_multi, so it can be reused in another register call. Link: https://lkml.kernel.org/r/20211206182032.87248-3-jolsa@kernel.org Cc: Ingo Molnar Cc: Heiko Carstens Fixes: f64dd4627ec6 ("ftrace: Add multi direct register/unregister interface") Signed-off-by: Jiri Olsa Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/ftrace.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 7f0594e28226..be5f6b32a012 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5542,6 +5542,10 @@ int unregister_ftrace_direct_multi(struct ftrace_ops *ops, unsigned long addr) err = unregister_ftrace_function(ops); remove_direct_functions_hash(hash, addr); mutex_unlock(&direct_mutex); + + /* cleanup for possible another register call */ + ops->func = NULL; + ops->trampoline = 0; return err; } EXPORT_SYMBOL_GPL(unregister_ftrace_direct_multi); -- cgit v1.2.3 From c24be24aed405d64ebcf04526614c13b2adfb1d2 Mon Sep 17 00:00:00 2001 From: Miaoqian Lin Date: Thu, 9 Dec 2021 02:43:17 +0000 Subject: tracing: Fix possible memory leak in __create_synth_event() error path There's error paths in __create_synth_event() after the argv is allocated that fail to free it. Add a jump to free it when necessary. Link: https://lkml.kernel.org/r/20211209024317.11783-1-linmq006@gmail.com Suggested-by: Steven Rostedt (VMware) Signed-off-by: Miaoqian Lin [ Fixed up the patch and change log ] Signed-off-by: Steven Rostedt (VMware) --- kernel/trace/trace_events_synth.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index 22db3ce95e74..ca9c13b2ecf4 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -1237,9 +1237,8 @@ static int __create_synth_event(const char *name, const char *raw_fields) argv + consumed, &consumed, &field_version); if (IS_ERR(field)) { - argv_free(argv); ret = PTR_ERR(field); - goto err; + goto err_free_arg; } /* @@ -1262,18 +1261,19 @@ static int __create_synth_event(const char *name, const char *raw_fields) if (cmd_version > 1 && n_fields_this_loop >= 1) { synth_err(SYNTH_ERR_INVALID_CMD, errpos(field_str)); ret = -EINVAL; - goto err; + goto err_free_arg; } fields[n_fields++] = field; if (n_fields == SYNTH_FIELDS_MAX) { synth_err(SYNTH_ERR_TOO_MANY_FIELDS, 0); ret = -EINVAL; - goto err; + goto err_free_arg; } n_fields_this_loop++; } + argv_free(argv); if (consumed < argc) { synth_err(SYNTH_ERR_INVALID_CMD, 0); @@ -1281,7 +1281,6 @@ static int __create_synth_event(const char *name, const char *raw_fields) goto err; } - argv_free(argv); } if (n_fields == 0) { @@ -1307,6 +1306,8 @@ static int __create_synth_event(const char *name, const char *raw_fields) kfree(saved_fields); return ret; + err_free_arg: + argv_free(argv); err: for (i = 0; i < n_fields; i++) free_synth_field(fields[i]); -- cgit v1.2.3 From 42288cb44c4b5fff7653bc392b583a2b8bd6a8c0 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Wed, 8 Dec 2021 17:04:51 -0800 Subject: wait: add wake_up_pollfree() Several ->poll() implementations are special in that they use a waitqueue whose lifetime is the current task, rather than the struct file as is normally the case. This is okay for blocking polls, since a blocking poll occurs within one task; however, non-blocking polls require another solution. This solution is for the queue to be cleared before it is freed, using 'wake_up_poll(wq, EPOLLHUP | POLLFREE);'. However, that has a bug: wake_up_poll() calls __wake_up() with nr_exclusive=1. Therefore, if there are multiple "exclusive" waiters, and the wakeup function for the first one returns a positive value, only that one will be called. That's *not* what's needed for POLLFREE; POLLFREE is special in that it really needs to wake up everyone. Considering the three non-blocking poll systems: - io_uring poll doesn't handle POLLFREE at all, so it is broken anyway. - aio poll is unaffected, since it doesn't support exclusive waits. However, that's fragile, as someone could add this feature later. - epoll doesn't appear to be broken by this, since its wakeup function returns 0 when it sees POLLFREE. But this is fragile. Although there is a workaround (see epoll), it's better to define a function which always sends POLLFREE to all waiters. Add such a function. Also make it verify that the queue really becomes empty after all waiters have been woken up. Reported-by: Linus Torvalds Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20211209010455.42744-2-ebiggers@kernel.org Signed-off-by: Eric Biggers --- kernel/sched/wait.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 76577d1642a5..eca38107b32f 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -238,6 +238,13 @@ void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode) } EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ +void __wake_up_pollfree(struct wait_queue_head *wq_head) +{ + __wake_up(wq_head, TASK_NORMAL, 0, poll_to_key(EPOLLHUP | POLLFREE)); + /* POLLFREE must have cleared the queue. */ + WARN_ON_ONCE(waitqueue_active(wq_head)); +} + /* * Note: we use "set_current_state()" _after_ the wait-queue add, * because we need a memory barrier there on SMP, so that any -- cgit v1.2.3 From e4779015fd5d2fb8390c258268addff24d6077c7 Mon Sep 17 00:00:00 2001 From: SeongJae Park Date: Fri, 10 Dec 2021 14:46:22 -0800 Subject: timers: implement usleep_idle_range() Patch series "mm/damon: Fix fake /proc/loadavg reports", v3. This patchset fixes DAMON's fake load report issue. The first patch makes yet another variant of usleep_range() for this fix, and the second patch fixes the issue of DAMON by making it using the newly introduced function. This patch (of 2): Some kernel threads such as DAMON could need to repeatedly sleep in micro seconds level. Because usleep_range() sleeps in uninterruptible state, however, such threads would make /proc/loadavg reports fake load. To help such cases, this commit implements a variant of usleep_range() called usleep_idle_range(). It is same to usleep_range() but sets the state of the current task as TASK_IDLE while sleeping. Link: https://lkml.kernel.org/r/20211126145015.15862-1-sj@kernel.org Link: https://lkml.kernel.org/r/20211126145015.15862-2-sj@kernel.org Signed-off-by: SeongJae Park Suggested-by: Andrew Morton Reviewed-by: Thomas Gleixner Tested-by: Oleksandr Natalenko Cc: John Stultz Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/time/timer.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'kernel') diff --git a/kernel/time/timer.c b/kernel/time/timer.c index e3d2c23c413d..85f1021ad459 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -2054,26 +2054,28 @@ unsigned long msleep_interruptible(unsigned int msecs) EXPORT_SYMBOL(msleep_interruptible); /** - * usleep_range - Sleep for an approximate time - * @min: Minimum time in usecs to sleep - * @max: Maximum time in usecs to sleep + * usleep_range_state - Sleep for an approximate time in a given state + * @min: Minimum time in usecs to sleep + * @max: Maximum time in usecs to sleep + * @state: State of the current task that will be while sleeping * * In non-atomic context where the exact wakeup time is flexible, use - * usleep_range() instead of udelay(). The sleep improves responsiveness + * usleep_range_state() instead of udelay(). The sleep improves responsiveness * by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces * power usage by allowing hrtimers to take advantage of an already- * scheduled interrupt instead of scheduling a new one just for this sleep. */ -void __sched usleep_range(unsigned long min, unsigned long max) +void __sched usleep_range_state(unsigned long min, unsigned long max, + unsigned int state) { ktime_t exp = ktime_add_us(ktime_get(), min); u64 delta = (u64)(max - min) * NSEC_PER_USEC; for (;;) { - __set_current_state(TASK_UNINTERRUPTIBLE); + __set_current_state(state); /* Do not return before the requested sleep time has elapsed */ if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS)) break; } } -EXPORT_SYMBOL(usleep_range); +EXPORT_SYMBOL(usleep_range_state); -- cgit v1.2.3