From 1e0a2ba7afb1b60f02599093d84b72ce62ad11c0 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 13 Jan 2026 10:50:41 +0100 Subject: sched: Provide idle_rq() helper A fix for the dl_server 'requires' idle_cpu() usage, which made me note that it and available_idle_cpu() are extern function calls. And while idle_cpu() is used outside of kernel/sched/, available_idle_cpu() is not. This makes it hard to make idle_cpu() an inline helper, so provide idle_rq() and implement idle_cpu() and available_idle_cpu() using that. Signed-off-by: Peter Zijlstra (Intel) --- include/linux/sched.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index d395f2810fac..da0133524d08 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1874,7 +1874,6 @@ static inline int task_nice(const struct task_struct *p) extern int can_nice(const struct task_struct *p, const int nice); extern int task_curr(const struct task_struct *p); extern int idle_cpu(int cpu); -extern int available_idle_cpu(int cpu); extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *); extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); extern void sched_set_fifo(struct task_struct *p); -- cgit v1.2.3 From 76ed27608f7dd235b727ebbb12163438c2fbb617 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 29 Jan 2026 10:28:21 -0500 Subject: perf: sched: Fix perf crash with new is_user_task() helper In order to do a user space stacktrace the current task needs to be a user task that has executed in user space. It use to be possible to test if a task is a user task or not by simply checking the task_struct mm field. If it was non NULL, it was a user task and if not it was a kernel task. But things have changed over time, and some kernel tasks now have their own mm field. An idea was made to instead test PF_KTHREAD and two functions were used to wrap this check in case it became more complex to test if a task was a user task or not[1]. But this was rejected and the C code simply checked the PF_KTHREAD directly. It was later found that not all kernel threads set PF_KTHREAD. The io-uring helpers instead set PF_USER_WORKER and this needed to be added as well. But checking the flags is still not enough. There's a very small window when a task exits that it frees its mm field and it is set back to NULL. If perf were to trigger at this moment, the flags test would say its a user space task but when perf would read the mm field it would crash with at NULL pointer dereference. Now there are flags that can be used to test if a task is exiting, but they are set in areas that perf may still want to profile the user space task (to see where it exited). The only real test is to check both the flags and the mm field. Instead of making this modification in every location, create a new is_user_task() helper function that does all the tests needed to know if it is safe to read the user space memory or not. [1] https://lore.kernel.org/all/20250425204120.639530125@goodmis.org/ Fixes: 90942f9fac05 ("perf: Use current->flags & PF_KTHREAD|PF_USER_WORKER instead of current->mm == NULL") Closes: https://lore.kernel.org/all/0d877e6f-41a7-4724-875d-0b0a27b8a545@roeck-us.net/ Reported-by: Guenter Roeck Signed-off-by: Steven Rostedt (Google) Signed-off-by: Peter Zijlstra (Intel) Tested-by: Guenter Roeck Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260129102821.46484722@gandalf.local.home --- include/linux/sched.h | 5 +++++ kernel/events/callchain.c | 2 +- kernel/events/core.c | 6 +++--- 3 files changed, 9 insertions(+), 4 deletions(-) (limited to 'include/linux/sched.h') diff --git a/include/linux/sched.h b/include/linux/sched.h index da0133524d08..5f00b5ed0f3b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1776,6 +1776,11 @@ static __always_inline bool is_percpu_thread(void) (current->nr_cpus_allowed == 1); } +static __always_inline bool is_user_task(struct task_struct *task) +{ + return task->mm && !(task->flags & (PF_KTHREAD | PF_USER_WORKER)); +} + /* Per-process atomic flags. */ #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ #define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 1f6589578703..9d24b6e0c91f 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -246,7 +246,7 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, bool user, if (user && !crosstask) { if (!user_mode(regs)) { - if (current->flags & (PF_KTHREAD | PF_USER_WORKER)) + if (!is_user_task(current)) goto exit_put; regs = task_pt_regs(current); } diff --git a/kernel/events/core.c b/kernel/events/core.c index a0fa488bce84..8cca80094624 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -7460,7 +7460,7 @@ static void perf_sample_regs_user(struct perf_regs *regs_user, if (user_mode(regs)) { regs_user->abi = perf_reg_abi(current); regs_user->regs = regs; - } else if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER))) { + } else if (is_user_task(current)) { perf_get_regs_user(regs_user, regs); } else { regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE; @@ -8100,7 +8100,7 @@ static u64 perf_virt_to_phys(u64 virt) * Try IRQ-safe get_user_page_fast_only first. * If failed, leave phys_addr as 0. */ - if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER))) { + if (is_user_task(current)) { struct page *p; pagefault_disable(); @@ -8215,7 +8215,7 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs) { bool kernel = !event->attr.exclude_callchain_kernel; bool user = !event->attr.exclude_callchain_user && - !(current->flags & (PF_KTHREAD | PF_USER_WORKER)); + is_user_task(current); /* Disallow cross-task user callchains. */ bool crosstask = event->ctx->task && event->ctx->task != current; bool defer_user = IS_ENABLED(CONFIG_UNWIND_USER) && user && -- cgit v1.2.3