From e22bc9b481a90d7898984ea17621f04a653e2cd1 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 9 Mar 2021 19:49:02 -0700 Subject: kernel: make IO threads unfreezable by default The io-wq threads were already marked as no-freeze, but the manager was not. On resume, we perpetually have signal_pending() being true, and hence the manager will loop and spin 100% of the time. Just mark the tasks created by create_io_thread() as PF_NOFREEZE by default, and remove any knowledge of it in io-wq and io_uring. Reported-by: Kevin Locke Tested-by: Kevin Locke Signed-off-by: Jens Axboe --- kernel/fork.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index d3171e8e88e5..72e444cd0ffe 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2436,6 +2436,7 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) if (!IS_ERR(tsk)) { sigfillset(&tsk->blocked); sigdelsetmask(&tsk->blocked, sigmask(SIGKILL)); + tsk->flags |= PF_NOFREEZE; } return tsk; } -- cgit v1.2.3 From 16efa4fce3b7af17bb45d635c3e89992d721e0f3 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 12 Mar 2021 20:26:13 -0700 Subject: io_uring: allow IO worker threads to be frozen With the freezer using the proper signaling to notify us of when it's time to freeze a thread, we can re-enable normal freezer usage for the IO threads. Ensure that SQPOLL, io-wq, and the io-wq manager call try_to_freeze() appropriately, and remove the default setting of PF_NOFREEZE from create_io_thread(). Signed-off-by: Jens Axboe --- fs/io-wq.c | 6 +++++- fs/io_uring.c | 1 + kernel/fork.c | 1 - 3 files changed, 6 insertions(+), 2 deletions(-) (limited to 'kernel/fork.c') diff --git a/fs/io-wq.c b/fs/io-wq.c index 0ae9ecadf295..e05f996d088f 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -488,6 +488,8 @@ static int io_wqe_worker(void *data) set_task_comm(current, buf); while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { + long ret; + set_current_state(TASK_INTERRUPTIBLE); loop: raw_spin_lock_irq(&wqe->lock); @@ -498,7 +500,8 @@ loop: __io_worker_idle(wqe, worker); raw_spin_unlock_irq(&wqe->lock); io_flush_signals(); - if (schedule_timeout(WORKER_IDLE_TIMEOUT)) + ret = schedule_timeout(WORKER_IDLE_TIMEOUT); + if (try_to_freeze() || ret) continue; if (fatal_signal_pending(current)) break; @@ -709,6 +712,7 @@ static int io_wq_manager(void *data) set_current_state(TASK_INTERRUPTIBLE); io_wq_check_workers(wq); schedule_timeout(HZ); + try_to_freeze(); if (fatal_signal_pending(current)) set_bit(IO_WQ_BIT_EXIT, &wq->state); } while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)); diff --git a/fs/io_uring.c b/fs/io_uring.c index a4bce17af506..05adc4887ef3 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -6752,6 +6752,7 @@ static int io_sq_thread(void *data) up_read(&sqd->rw_lock); schedule(); + try_to_freeze(); down_read(&sqd->rw_lock); list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) io_ring_clear_wakeup_flag(ctx); diff --git a/kernel/fork.c b/kernel/fork.c index 72e444cd0ffe..d3171e8e88e5 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2436,7 +2436,6 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) if (!IS_ERR(tsk)) { sigfillset(&tsk->blocked); sigdelsetmask(&tsk->blocked, sigmask(SIGKILL)); - tsk->flags |= PF_NOFREEZE; } return tsk; } -- cgit v1.2.3 From 82e69a121be4b1597ce758534816a8ee04c8b761 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Fri, 12 Mar 2021 21:07:15 -0800 Subject: mm/fork: clear PASID for new mm When a new mm is created, its PASID should be cleared, i.e. the PASID is initialized to its init state 0 on both ARM and X86. This patch was part of the series introducing mm->pasid, but got lost along the way [1]. It still makes sense to have it, because each address space has a different PASID. And the IOMMU code in iommu_sva_alloc_pasid() expects the pasid field of a new mm struct to be cleared. [1] https://lore.kernel.org/linux-iommu/YDgh53AcQHT+T3L0@otcwcpicx3.sc.intel.com/ Link: https://lkml.kernel.org/r/20210302103837.2562625-1-jean-philippe@linaro.org Signed-off-by: Fenghua Yu Signed-off-by: Jean-Philippe Brucker Reviewed-by: Tony Luck Cc: Jacob Pan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 1 + kernel/fork.c | 8 ++++++++ 2 files changed, 9 insertions(+) (limited to 'kernel/fork.c') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 0974ad501a47..6613b26a8894 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -23,6 +23,7 @@ #endif #define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1)) +#define INIT_PASID 0 struct address_space; struct mem_cgroup; diff --git a/kernel/fork.c b/kernel/fork.c index d3171e8e88e5..54cc905e5fe0 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -994,6 +994,13 @@ static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) #endif } +static void mm_init_pasid(struct mm_struct *mm) +{ +#ifdef CONFIG_IOMMU_SUPPORT + mm->pasid = INIT_PASID; +#endif +} + static void mm_init_uprobes_state(struct mm_struct *mm) { #ifdef CONFIG_UPROBES @@ -1024,6 +1031,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); + mm_init_pasid(mm); RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); -- cgit v1.2.3 From b16b3855d89fba640996fefdd3a113c0aa0e380d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 26 Mar 2021 09:05:22 -0600 Subject: kernel: stop masking signals in create_io_thread() This is racy - move the blocking into when the task is created and we're marking it as PF_IO_WORKER anyway. The IO threads are now prepared to handle signals like SIGSTOP as well, so clear that from the mask to allow proper stopping of IO threads. Acked-by: "Eric W. Biederman" Reported-by: Oleg Nesterov Signed-off-by: Jens Axboe --- kernel/fork.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index d3171e8e88e5..ddaa15227071 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1940,8 +1940,14 @@ static __latent_entropy struct task_struct *copy_process( p = dup_task_struct(current, node); if (!p) goto fork_out; - if (args->io_thread) + if (args->io_thread) { + /* + * Mark us an IO worker, and block any signal that isn't + * fatal or STOP + */ p->flags |= PF_IO_WORKER; + siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); + } /* * This _must_ happen before we call free_task(), i.e. before we jump @@ -2430,14 +2436,8 @@ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) .stack_size = (unsigned long)arg, .io_thread = 1, }; - struct task_struct *tsk; - tsk = copy_process(NULL, 0, node, &args); - if (!IS_ERR(tsk)) { - sigfillset(&tsk->blocked); - sigdelsetmask(&tsk->blocked, sigmask(SIGKILL)); - } - return tsk; + return copy_process(NULL, 0, node, &args); } /* -- cgit v1.2.3