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/amd/ae4dma/Makefile | 10 +++ drivers/dma/amd/ae4dma/ae4dma-dev.c | 157 ++++++++++++++++++++++++++++++++++++ drivers/dma/amd/ae4dma/ae4dma-pci.c | 156 +++++++++++++++++++++++++++++++++++ drivers/dma/amd/ae4dma/ae4dma.h | 102 +++++++++++++++++++++++ 4 files changed, 425 insertions(+) create mode 100644 drivers/dma/amd/ae4dma/Makefile create mode 100644 drivers/dma/amd/ae4dma/ae4dma-dev.c create mode 100644 drivers/dma/amd/ae4dma/ae4dma-pci.c create mode 100644 drivers/dma/amd/ae4dma/ae4dma.h (limited to 'drivers/dma/amd/ae4dma') diff --git a/drivers/dma/amd/ae4dma/Makefile b/drivers/dma/amd/ae4dma/Makefile new file mode 100644 index 000000000..e918f85a8 --- /dev/null +++ b/drivers/dma/amd/ae4dma/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# AMD AE4DMA driver +# + +obj-$(CONFIG_AMD_AE4DMA) += ae4dma.o + +ae4dma-objs := ae4dma-dev.o + +ae4dma-$(CONFIG_PCI) += ae4dma-pci.o diff --git a/drivers/dma/amd/ae4dma/ae4dma-dev.c b/drivers/dma/amd/ae4dma/ae4dma-dev.c new file mode 100644 index 000000000..8de3bef41 --- /dev/null +++ b/drivers/dma/amd/ae4dma/ae4dma-dev.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * AMD AE4DMA driver + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Basavaraj Natikar + */ + +#include "ae4dma.h" + +static unsigned int max_hw_q = 1; +module_param(max_hw_q, uint, 0444); +MODULE_PARM_DESC(max_hw_q, "max hw queues supported by engine (any non-zero value, default: 1)"); + +static void ae4_pending_work(struct work_struct *work) +{ + struct ae4_cmd_queue *ae4cmd_q = container_of(work, struct ae4_cmd_queue, p_work.work); + struct pt_cmd_queue *cmd_q = &ae4cmd_q->cmd_q; + struct pt_cmd *cmd; + u32 cridx; + + for (;;) { + wait_event_interruptible(ae4cmd_q->q_w, + ((atomic64_read(&ae4cmd_q->done_cnt)) < + atomic64_read(&ae4cmd_q->intr_cnt))); + + atomic64_inc(&ae4cmd_q->done_cnt); + + mutex_lock(&ae4cmd_q->cmd_lock); + cridx = readl(cmd_q->reg_control + AE4_RD_IDX_OFF); + while ((ae4cmd_q->dridx != cridx) && !list_empty(&ae4cmd_q->cmd)) { + cmd = list_first_entry(&ae4cmd_q->cmd, struct pt_cmd, entry); + list_del(&cmd->entry); + + ae4_check_status_error(ae4cmd_q, ae4cmd_q->dridx); + cmd->pt_cmd_callback(cmd->data, cmd->ret); + + ae4cmd_q->q_cmd_count--; + ae4cmd_q->dridx = (ae4cmd_q->dridx + 1) % CMD_Q_LEN; + + complete_all(&ae4cmd_q->cmp); + } + mutex_unlock(&ae4cmd_q->cmd_lock); + } +} + +static irqreturn_t ae4_core_irq_handler(int irq, void *data) +{ + struct ae4_cmd_queue *ae4cmd_q = data; + struct pt_cmd_queue *cmd_q; + struct pt_device *pt; + u32 status; + + cmd_q = &ae4cmd_q->cmd_q; + pt = cmd_q->pt; + + pt->total_interrupts++; + atomic64_inc(&ae4cmd_q->intr_cnt); + + status = readl(cmd_q->reg_control + AE4_INTR_STS_OFF); + if (status & BIT(0)) { + status &= GENMASK(31, 1); + writel(status, cmd_q->reg_control + AE4_INTR_STS_OFF); + } + + wake_up(&ae4cmd_q->q_w); + + return IRQ_HANDLED; +} + +void ae4_destroy_work(struct ae4_device *ae4) +{ + struct ae4_cmd_queue *ae4cmd_q; + int i; + + for (i = 0; i < ae4->cmd_q_count; i++) { + ae4cmd_q = &ae4->ae4cmd_q[i]; + + if (!ae4cmd_q->pws) + break; + + cancel_delayed_work_sync(&ae4cmd_q->p_work); + destroy_workqueue(ae4cmd_q->pws); + } +} + +int ae4_core_init(struct ae4_device *ae4) +{ + struct pt_device *pt = &ae4->pt; + struct ae4_cmd_queue *ae4cmd_q; + struct device *dev = pt->dev; + struct pt_cmd_queue *cmd_q; + int i, ret = 0; + + writel(max_hw_q, pt->io_regs); + + for (i = 0; i < max_hw_q; i++) { + ae4cmd_q = &ae4->ae4cmd_q[i]; + ae4cmd_q->id = ae4->cmd_q_count; + ae4->cmd_q_count++; + + cmd_q = &ae4cmd_q->cmd_q; + cmd_q->pt = pt; + + cmd_q->reg_control = pt->io_regs + ((i + 1) * AE4_Q_SZ); + + ret = devm_request_irq(dev, ae4->ae4_irq[i], ae4_core_irq_handler, 0, + dev_name(pt->dev), ae4cmd_q); + if (ret) + return ret; + + cmd_q->qsize = Q_SIZE(sizeof(struct ae4dma_desc)); + + cmd_q->qbase = dmam_alloc_coherent(dev, cmd_q->qsize, &cmd_q->qbase_dma, + GFP_KERNEL); + if (!cmd_q->qbase) + return -ENOMEM; + } + + for (i = 0; i < ae4->cmd_q_count; i++) { + ae4cmd_q = &ae4->ae4cmd_q[i]; + + cmd_q = &ae4cmd_q->cmd_q; + + cmd_q->reg_control = pt->io_regs + ((i + 1) * AE4_Q_SZ); + + /* Update the device registers with queue information. */ + writel(CMD_Q_LEN, cmd_q->reg_control + AE4_MAX_IDX_OFF); + + cmd_q->qdma_tail = cmd_q->qbase_dma; + writel(lower_32_bits(cmd_q->qdma_tail), cmd_q->reg_control + AE4_Q_BASE_L_OFF); + writel(upper_32_bits(cmd_q->qdma_tail), cmd_q->reg_control + AE4_Q_BASE_H_OFF); + + INIT_LIST_HEAD(&ae4cmd_q->cmd); + init_waitqueue_head(&ae4cmd_q->q_w); + + ae4cmd_q->pws = alloc_ordered_workqueue("ae4dma_%d", WQ_MEM_RECLAIM, ae4cmd_q->id); + if (!ae4cmd_q->pws) { + ae4_destroy_work(ae4); + return -ENOMEM; + } + INIT_DELAYED_WORK(&ae4cmd_q->p_work, ae4_pending_work); + queue_delayed_work(ae4cmd_q->pws, &ae4cmd_q->p_work, usecs_to_jiffies(100)); + + init_completion(&ae4cmd_q->cmp); + } + + ret = pt_dmaengine_register(pt); + if (ret) + ae4_destroy_work(ae4); + else + ptdma_debugfs_setup(pt); + + return ret; +} diff --git a/drivers/dma/amd/ae4dma/ae4dma-pci.c b/drivers/dma/amd/ae4dma/ae4dma-pci.c new file mode 100644 index 000000000..2c63907db --- /dev/null +++ b/drivers/dma/amd/ae4dma/ae4dma-pci.c @@ -0,0 +1,156 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * AMD AE4DMA driver + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Basavaraj Natikar + */ + +#include "ae4dma.h" + +static int ae4_get_irqs(struct ae4_device *ae4) +{ + struct ae4_msix *ae4_msix = ae4->ae4_msix; + struct pt_device *pt = &ae4->pt; + struct device *dev = pt->dev; + struct pci_dev *pdev; + int i, v, ret; + + pdev = to_pci_dev(dev); + + for (v = 0; v < ARRAY_SIZE(ae4_msix->msix_entry); v++) + ae4_msix->msix_entry[v].entry = v; + + ret = pci_alloc_irq_vectors(pdev, v, v, PCI_IRQ_MSIX); + if (ret != v) { + if (ret > 0) + pci_free_irq_vectors(pdev); + + dev_err(dev, "could not enable MSI-X (%d), trying MSI\n", ret); + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI); + if (ret < 0) { + dev_err(dev, "could not enable MSI (%d)\n", ret); + return ret; + } + + ret = pci_irq_vector(pdev, 0); + if (ret < 0) { + pci_free_irq_vectors(pdev); + return ret; + } + + for (i = 0; i < MAX_AE4_HW_QUEUES; i++) + ae4->ae4_irq[i] = ret; + + } else { + ae4_msix->msix_count = ret; + for (i = 0; i < ae4_msix->msix_count; i++) + ae4->ae4_irq[i] = pci_irq_vector(pdev, i); + } + + return ret; +} + +static void ae4_free_irqs(struct ae4_device *ae4) +{ + struct ae4_msix *ae4_msix = ae4->ae4_msix; + struct pt_device *pt = &ae4->pt; + struct device *dev = pt->dev; + struct pci_dev *pdev; + + pdev = to_pci_dev(dev); + + if (ae4_msix && (ae4_msix->msix_count || ae4->ae4_irq[MAX_AE4_HW_QUEUES - 1])) + pci_free_irq_vectors(pdev); +} + +static void ae4_deinit(struct ae4_device *ae4) +{ + ae4_free_irqs(ae4); +} + +static int ae4_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + struct device *dev = &pdev->dev; + struct ae4_device *ae4; + struct pt_device *pt; + int bar_mask; + int ret = 0; + + ae4 = devm_kzalloc(dev, sizeof(*ae4), GFP_KERNEL); + if (!ae4) + return -ENOMEM; + + ae4->ae4_msix = devm_kzalloc(dev, sizeof(struct ae4_msix), GFP_KERNEL); + if (!ae4->ae4_msix) + return -ENOMEM; + + ret = pcim_enable_device(pdev); + if (ret) + goto ae4_error; + + bar_mask = pci_select_bars(pdev, IORESOURCE_MEM); + ret = pcim_iomap_regions(pdev, bar_mask, "ae4dma"); + if (ret) + goto ae4_error; + + pt = &ae4->pt; + pt->dev = dev; + pt->ver = AE4_DMA_VERSION; + + pt->io_regs = pcim_iomap_table(pdev)[0]; + if (!pt->io_regs) { + ret = -ENOMEM; + goto ae4_error; + } + + ret = ae4_get_irqs(ae4); + if (ret < 0) + goto ae4_error; + + pci_set_master(pdev); + + dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48)); + + dev_set_drvdata(dev, ae4); + + ret = ae4_core_init(ae4); + if (ret) + goto ae4_error; + + return 0; + +ae4_error: + ae4_deinit(ae4); + + return ret; +} + +static void ae4_pci_remove(struct pci_dev *pdev) +{ + struct ae4_device *ae4 = dev_get_drvdata(&pdev->dev); + + ae4_destroy_work(ae4); + ae4_deinit(ae4); +} + +static const struct pci_device_id ae4_pci_table[] = { + { PCI_VDEVICE(AMD, 0x149B), }, + /* Last entry must be zero */ + { 0, } +}; +MODULE_DEVICE_TABLE(pci, ae4_pci_table); + +static struct pci_driver ae4_pci_driver = { + .name = "ae4dma", + .id_table = ae4_pci_table, + .probe = ae4_pci_probe, + .remove = ae4_pci_remove, +}; + +module_pci_driver(ae4_pci_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("AMD AE4DMA driver"); diff --git a/drivers/dma/amd/ae4dma/ae4dma.h b/drivers/dma/amd/ae4dma/ae4dma.h new file mode 100644 index 000000000..57f604872 --- /dev/null +++ b/drivers/dma/amd/ae4dma/ae4dma.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD AE4DMA driver + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Basavaraj Natikar + */ +#ifndef __AE4DMA_H__ +#define __AE4DMA_H__ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../ptdma/ptdma.h" +#include "../../virt-dma.h" + +#define MAX_AE4_HW_QUEUES 16 + +#define AE4_DESC_COMPLETED 0x03 + +#define AE4_MAX_IDX_OFF 0x08 +#define AE4_RD_IDX_OFF 0x0c +#define AE4_WR_IDX_OFF 0x10 +#define AE4_INTR_STS_OFF 0x14 +#define AE4_Q_BASE_L_OFF 0x18 +#define AE4_Q_BASE_H_OFF 0x1c +#define AE4_Q_SZ 0x20 + +#define AE4_DMA_VERSION 4 +#define CMD_AE4_DESC_DW0_VAL 2 + +#define AE4_TIME_OUT 5000 + +struct ae4_msix { + int msix_count; + struct msix_entry msix_entry[MAX_AE4_HW_QUEUES]; +}; + +struct ae4_cmd_queue { + struct ae4_device *ae4; + struct pt_cmd_queue cmd_q; + struct list_head cmd; + /* protect command operations */ + struct mutex cmd_lock; + struct delayed_work p_work; + struct workqueue_struct *pws; + struct completion cmp; + wait_queue_head_t q_w; + atomic64_t intr_cnt; + atomic64_t done_cnt; + u64 q_cmd_count; + u32 dridx; + u32 tail_wi; + u32 id; +}; + +union dwou { + u32 dw0; + struct dword0 { + u8 byte0; + u8 byte1; + u16 timestamp; + } dws; +}; + +struct dword1 { + u8 status; + u8 err_code; + u16 desc_id; +}; + +struct ae4dma_desc { + union dwou dwouv; + struct dword1 dw1; + u32 length; + u32 rsvd; + u32 src_hi; + u32 src_lo; + u32 dst_hi; + u32 dst_lo; +}; + +struct ae4_device { + struct pt_device pt; + struct ae4_msix *ae4_msix; + struct ae4_cmd_queue ae4cmd_q[MAX_AE4_HW_QUEUES]; + unsigned int ae4_irq[MAX_AE4_HW_QUEUES]; + unsigned int cmd_q_count; +}; + +int ae4_core_init(struct ae4_device *ae4); +void ae4_destroy_work(struct ae4_device *ae4); +void ae4_check_status_error(struct ae4_cmd_queue *ae4cmd_q, int idx); +#endif -- cgit v1.3.1