From 034dd340b08be1f2f0477ad16131d609f9dbd53c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 30 Aug 2026 09:22:00 -0700 Subject: Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Fix error output of boot instance creation failure Currently if a boot instance creation fails, instead of printing out the name of the instance that failed, it prints "(null)". That is because it prints "cur_str" that had already been processed by strsep(). Print the saved name instead. While at it, print the error code of the failure. - Fix use-after-free for same named historgrams Histograms can be named so that they can be used in multiple events. But if the named histogram has a variable attached, the second event that uses the named histogram which duplicates it and needs to free the original after duplication leaves the old variable in place and still visible. If another histogram uses than variable, it will use the stale one which will try to reference the freed duplicate histogram and crash the kernel. Free the duplicate variables along with the duplicated histogram data. - Check return value of kthread_run() in event self test The events self tests uses a kthread for testing but does not check if it succeeded in creating a kthread. If the kthread creation were to fail, the code will still try to call kthread_stop() on the error returned. - Fix race between reading trace_pipe and updating subbuffer size If a user is reading the trace_pipe file at the same time they update the ring buffer sub-buffer size, can cause the trace_pipe read to read stale data. Add trace_access_lock() around updating the ring buffer sub-buffer size. - Fix eventfs_inode on failure path in creation of the events directory In the creation of the "events" directory, if after allocating the eventfs_inode a failure is detected, it calls cleanup_ei() which calls free_ei(). The free_ei() will test if eventfs_inode being freed has no children. It is a bug if it does. But on the failure case of the creation of the "events" directory, the children lists have not yet been initialized and the free will trigger a warning because list_empty() on an uninitialized list returns false. Move the initialization into init_ei() where it makes more sense and makes sure that a created eventfs_inode has its lists initialized upon creation. - Check return value of kthread_run() in ftrace direct sample code The sample code that shows how to use the ftrace direct calls does not test the return of kthread_run() to see if it succeeds. Return a failure if the kthread_run() doesn't succeed. - Clear user events state on fork in case of alloc failure On fork, the child gets a pointer to the parent's user events state. It makes a copy of it then updates the child's pointer to it. But if the allocation fails, the duplication function leaves the child with a pointer to its parent's descriptor. When the child cleans up its data, it will free the parent's descriptor while the parent is still using it. In the duplication function, set the child's user_event_mm to NULL before testing if the allocation succeeded, and when it exits it will not free the parent's descriptor. - Fix retry exhaustion in simple ring buffer reader swap simple_ring_buffer_swap_reader_page() starts with retry set to 8 and post-decrements it only after a failed link replacement. On the final attempt, a successful replacement leaves retry at zero, while a failed replacement leaves it at -1. But the check for success expects the retry value to be non-zero and exits with an error on zero. This is the opposite result. Fix it. - Fail nicely when the remote swap_reader_page() returns an error Currently, if the swap_reader_page() of a remote buffer fails, it triggers a WARN_ON_ONCE() and continues normally. Instead, have it exit with an error and a pr_warn() print instead of a full WARNING. * tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: ring-buffer: Stop remote reader update when page swap fails tracing: Fix retry exhaustion in simple ring buffer reader swap tracing/user_events: Clear copied tracing state before fork duplication samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify eventfs: Initialize ei->children and ei->list in init_ei() tracing: Fix use-after-free in trace_pipe read on sub-buffer order change tracing: Fix crash passing ERR_PTR to kthread_stop() tracing: Fix use-after-free with same-name named triggers tracing: Fix logged instance name on creation failure --- drivers/dma/idxd/submit.c | 222 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 222 insertions(+) create mode 100644 drivers/dma/idxd/submit.c (limited to 'drivers/dma/idxd/submit.c') diff --git a/drivers/dma/idxd/submit.c b/drivers/dma/idxd/submit.c new file mode 100644 index 000000000..03217041b --- /dev/null +++ b/drivers/dma/idxd/submit.c @@ -0,0 +1,222 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2019 Intel Corporation. All rights rsvd. */ +#include +#include +#include +#include +#include +#include "idxd.h" +#include "registers.h" + +static struct idxd_desc *__get_desc(struct idxd_wq *wq, int idx, int cpu) +{ + struct idxd_desc *desc; + struct idxd_device *idxd = wq->idxd; + + desc = wq->descs[idx]; + memset(desc->hw, 0, sizeof(struct dsa_hw_desc)); + memset(desc->completion, 0, idxd->data->compl_size); + desc->cpu = cpu; + + if (device_pasid_enabled(idxd)) + desc->hw->pasid = idxd->pasid; + + return desc; +} + +struct idxd_desc *idxd_alloc_desc(struct idxd_wq *wq, enum idxd_op_type optype) +{ + int cpu, idx; + struct idxd_device *idxd = wq->idxd; + DEFINE_SBQ_WAIT(wait); + struct sbq_wait_state *ws; + struct sbitmap_queue *sbq; + + if (idxd->state != IDXD_DEV_ENABLED) + return ERR_PTR(-EIO); + + sbq = &wq->sbq; + idx = sbitmap_queue_get(sbq, &cpu); + if (idx < 0) { + if (optype == IDXD_OP_NONBLOCK) + return ERR_PTR(-EAGAIN); + } else { + return __get_desc(wq, idx, cpu); + } + + ws = &sbq->ws[0]; + for (;;) { + sbitmap_prepare_to_wait(sbq, ws, &wait, TASK_INTERRUPTIBLE); + if (signal_pending_state(TASK_INTERRUPTIBLE, current)) + break; + idx = sbitmap_queue_get(sbq, &cpu); + if (idx >= 0) + break; + schedule(); + } + + sbitmap_finish_wait(sbq, ws, &wait); + if (idx < 0) + return ERR_PTR(-EAGAIN); + + return __get_desc(wq, idx, cpu); +} +EXPORT_SYMBOL_NS_GPL(idxd_alloc_desc, "IDXD"); + +void idxd_free_desc(struct idxd_wq *wq, struct idxd_desc *desc) +{ + int cpu = desc->cpu; + + desc->cpu = -1; + sbitmap_queue_clear(&wq->sbq, desc->id, cpu); +} +EXPORT_SYMBOL_NS_GPL(idxd_free_desc, "IDXD"); + +static struct idxd_desc *list_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie, + struct idxd_desc *desc) +{ + struct idxd_desc *d, *n; + + lockdep_assert_held(&ie->list_lock); + list_for_each_entry_safe(d, n, &ie->work_list, list) { + if (d == desc) { + list_del(&d->list); + return d; + } + } + + /* + * At this point, the desc needs to be aborted is held by the completion + * handler where it has taken it off the pending list but has not added to the + * work list. It will be cleaned up by the interrupt handler when it sees the + * IDXD_COMP_DESC_ABORT for completion status. + */ + return NULL; +} + +static void llist_abort_desc(struct idxd_wq *wq, struct idxd_irq_entry *ie, + struct idxd_desc *desc) +{ + struct idxd_desc *d, *t, *found = NULL; + struct llist_node *head; + LIST_HEAD(flist); + + desc->completion->status = IDXD_COMP_DESC_ABORT; + /* + * Grab the list lock so it will block the irq thread handler. This allows the + * abort code to locate the descriptor need to be aborted. + */ + spin_lock(&ie->list_lock); + head = llist_del_all(&ie->pending_llist); + if (head) { + llist_for_each_entry_safe(d, t, head, llnode) { + if (d == desc) { + found = desc; + continue; + } + + if (d->completion->status) + list_add_tail(&d->list, &flist); + else + list_add_tail(&d->list, &ie->work_list); + } + } + + if (!found) + found = list_abort_desc(wq, ie, desc); + spin_unlock(&ie->list_lock); + + if (found) + idxd_dma_complete_txd(found, IDXD_COMPLETE_ABORT, false, + NULL, NULL); + + /* + * completing the descriptor will return desc to allocator and + * the desc can be acquired by a different process and the + * desc->list can be modified. Delete desc from list so the + * list traversing does not get corrupted by the other process. + */ + list_for_each_entry_safe(d, t, &flist, list) { + list_del_init(&d->list); + idxd_dma_complete_txd(d, IDXD_COMPLETE_ABORT, true, + NULL, NULL); + } +} + +/* + * ENQCMDS typically fail when the WQ is inactive or busy. On host submission, the driver + * has better control of number of descriptors being submitted to a shared wq by limiting + * the number of driver allocated descriptors to the wq size. However, when the swq is + * exported to a guest kernel, it may be shared with multiple guest kernels. This means + * the likelihood of getting busy returned on the swq when submitting goes significantly up. + * Having a tunable retry mechanism allows the driver to keep trying for a bit before giving + * up. The sysfs knob can be tuned by the system administrator. + */ +int idxd_enqcmds(struct idxd_wq *wq, void __iomem *portal, const void *desc) +{ + unsigned int retries = wq->enqcmds_retries; + int rc; + + do { + rc = enqcmds(portal, desc); + if (rc == 0) + break; + cpu_relax(); + } while (retries--); + + return rc; +} + +int idxd_submit_desc(struct idxd_wq *wq, struct idxd_desc *desc) +{ + struct idxd_device *idxd = wq->idxd; + struct idxd_irq_entry *ie = NULL; + u32 desc_flags = desc->hw->flags; + void __iomem *portal; + int rc; + + if (idxd->state != IDXD_DEV_ENABLED) + return -EIO; + + if (!percpu_ref_tryget_live(&wq->wq_active)) { + wait_for_completion(&wq->wq_resurrect); + if (!percpu_ref_tryget_live(&wq->wq_active)) + return -ENXIO; + } + + portal = idxd_wq_portal_addr(wq); + + /* + * Pending the descriptor to the lockless list for the irq_entry + * that we designated the descriptor to. + */ + if (desc_flags & IDXD_OP_FLAG_RCI) { + ie = &wq->ie; + desc->hw->int_handle = ie->int_handle; + llist_add(&desc->llnode, &ie->pending_llist); + } + + /* + * The wmb() flushes writes to coherent DMA data before + * possibly triggering a DMA read. The wmb() is necessary + * even on UP because the recipient is a device. + */ + wmb(); + + if (wq_dedicated(wq)) { + iosubmit_cmds512(portal, desc->hw, 1); + } else { + rc = idxd_enqcmds(wq, portal, desc->hw); + if (rc < 0) { + percpu_ref_put(&wq->wq_active); + /* abort operation frees the descriptor */ + if (ie) + llist_abort_desc(wq, ie, desc); + return rc; + } + } + + percpu_ref_put(&wq->wq_active); + return 0; +} +EXPORT_SYMBOL_NS_GPL(idxd_submit_desc, "IDXD"); -- cgit v1.3.1