Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

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

1 files changed, 275 insertions, 0 deletions

diff --git a/drivers/iommu/amd/ppr.c b/drivers/iommu/amd/ppr.c
new file mode 100644
index 000000000..76296079b
--- /dev/null
+++ b/drivers/iommu/amd/ppr.c
@@ -0,0 +1,275 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023 Advanced Micro Devices, Inc.
+ */
+
+#define pr_fmt(fmt)     "AMD-Vi: " fmt
+#define dev_fmt(fmt)    pr_fmt(fmt)
+
+#include <linux/amd-iommu.h>
+#include <linux/delay.h>
+#include <linux/mmu_notifier.h>
+
+#include <asm/iommu.h>
+
+#include "amd_iommu.h"
+#include "amd_iommu_types.h"
+
+#include "../iommu-pages.h"
+
+int __init amd_iommu_alloc_ppr_log(struct amd_iommu *iommu)
+{
+	iommu->ppr_log = iommu_alloc_4k_pages(iommu, GFP_KERNEL | __GFP_ZERO,
+					      amd_iommu_pprlog_size);
+	return iommu->ppr_log ? 0 : -ENOMEM;
+}
+
+void amd_iommu_enable_ppr_log(struct amd_iommu *iommu)
+{
+	u64 entry;
+
+	if (iommu->ppr_log == NULL)
+		return;
+
+	iommu_feature_enable(iommu, CONTROL_PPR_EN);
+
+	entry = iommu_virt_to_phys(iommu->ppr_log);
+	entry |= (amd_iommu_pprlog_size == PPRLOG_SIZE_DEF) ?
+			PPRLOG_LEN_MASK_DEF : PPRLOG_LEN_MASK_MAX;
+
+	memcpy_toio(iommu->mmio_base + MMIO_PPR_LOG_OFFSET,
+		    &entry, sizeof(entry));
+
+	/* set head and tail to zero manually */
+	writel(0x00, iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
+	writel(0x00, iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
+
+	iommu_feature_enable(iommu, CONTROL_PPRINT_EN);
+	iommu_feature_enable(iommu, CONTROL_PPRLOG_EN);
+}
+
+void __init amd_iommu_free_ppr_log(struct amd_iommu *iommu)
+{
+	iommu_free_pages(iommu->ppr_log);
+}
+
+/*
+ * This function restarts ppr logging in case the IOMMU experienced
+ * PPR log overflow.
+ */
+void amd_iommu_restart_ppr_log(struct amd_iommu *iommu)
+{
+	amd_iommu_restart_log(iommu, "PPR", CONTROL_PPRINT_EN,
+			      CONTROL_PPRLOG_EN, MMIO_STATUS_PPR_RUN_MASK,
+			      MMIO_STATUS_PPR_OVERFLOW_MASK);
+}
+
+static inline u32 ppr_flag_to_fault_perm(u16 flag)
+{
+	int perm = 0;
+
+	if (flag & PPR_FLAG_READ)
+		perm |= IOMMU_FAULT_PERM_READ;
+	if (flag & PPR_FLAG_WRITE)
+		perm |= IOMMU_FAULT_PERM_WRITE;
+	if (flag & PPR_FLAG_EXEC)
+		perm |= IOMMU_FAULT_PERM_EXEC;
+	if (!(flag & PPR_FLAG_US))
+		perm |= IOMMU_FAULT_PERM_PRIV;
+
+	return perm;
+}
+
+static bool ppr_is_valid(struct amd_iommu *iommu, u64 *raw)
+{
+	struct device *dev = iommu->iommu.dev;
+	u16 devid = PPR_DEVID(raw[0]);
+
+	if (!(PPR_FLAGS(raw[0]) & PPR_FLAG_GN)) {
+		dev_dbg(dev, "PPR logged [Request ignored due to GN=0 (device=%04x:%02x:%02x.%x "
+			"pasid=0x%05llx address=0x%llx flags=0x%04llx tag=0x%03llx]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			PPR_PASID(raw[0]), raw[1], PPR_FLAGS(raw[0]), PPR_TAG(raw[0]));
+		return false;
+	}
+
+	if (PPR_FLAGS(raw[0]) & PPR_FLAG_RVSD) {
+		dev_dbg(dev, "PPR logged [Invalid request format (device=%04x:%02x:%02x.%x "
+			"pasid=0x%05llx address=0x%llx flags=0x%04llx tag=0x%03llx]\n",
+			iommu->pci_seg->id, PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			PPR_PASID(raw[0]), raw[1], PPR_FLAGS(raw[0]), PPR_TAG(raw[0]));
+		return false;
+	}
+
+	return true;
+}
+
+static void iommu_call_iopf_notifier(struct amd_iommu *iommu, u64 *raw)
+{
+	struct iommu_dev_data *dev_data;
+	struct iopf_fault event;
+	struct pci_dev *pdev;
+	u16 devid = PPR_DEVID(raw[0]);
+
+	if (PPR_REQ_TYPE(raw[0]) != PPR_REQ_FAULT) {
+		pr_info_ratelimited("Unknown PPR request received\n");
+		return;
+	}
+
+	pdev = pci_get_domain_bus_and_slot(iommu->pci_seg->id,
+					   PCI_BUS_NUM(devid), devid & 0xff);
+	if (!pdev)
+		return;
+
+	if (!ppr_is_valid(iommu, raw))
+		goto out;
+
+	memset(&event, 0, sizeof(struct iopf_fault));
+
+	event.fault.type = IOMMU_FAULT_PAGE_REQ;
+	event.fault.prm.perm = ppr_flag_to_fault_perm(PPR_FLAGS(raw[0]));
+	event.fault.prm.addr = (u64)(raw[1] & PAGE_MASK);
+	event.fault.prm.pasid = PPR_PASID(raw[0]);
+	event.fault.prm.grpid = PPR_TAG(raw[0]);
+
+	/*
+	 * PASID zero is used for requests from the I/O device without
+	 * a PASID
+	 */
+	dev_data = dev_iommu_priv_get(&pdev->dev);
+	if (event.fault.prm.pasid == 0 ||
+	    event.fault.prm.pasid >= dev_data->max_pasids) {
+		pr_info_ratelimited("Invalid PASID : 0x%x, device : 0x%x\n",
+				    event.fault.prm.pasid, dev_data->devid);
+		goto out;
+	}
+
+	event.fault.prm.flags |= IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID;
+	event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
+	if (PPR_TAG_LAST_PAGE(raw[0]))
+		event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
+
+	/* Submit event */
+	iommu_report_device_fault(&pdev->dev, &event);
+	pci_dev_put(pdev);
+	return;
+
+out:
+	/* Nobody cared, abort */
+	amd_iommu_complete_ppr(&pdev->dev, PPR_PASID(raw[0]),
+			       IOMMU_PAGE_RESP_FAILURE, PPR_TAG(raw[0]));
+	pci_dev_put(pdev);
+}
+
+void amd_iommu_poll_ppr_log(struct amd_iommu *iommu)
+{
+	u32 head, tail;
+
+	if (iommu->ppr_log == NULL)
+		return;
+
+	head = readl(iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
+	tail = readl(iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
+
+	while (head != tail) {
+		volatile u64 *raw;
+		u64 entry[2];
+		int i;
+
+		raw = (u64 *)(iommu->ppr_log + head);
+
+		/*
+		 * Hardware bug: Interrupt may arrive before the entry is
+		 * written to memory. If this happens we need to wait for the
+		 * entry to arrive.
+		 */
+		for (i = 0; i < LOOP_TIMEOUT; ++i) {
+			if (PPR_REQ_TYPE(raw[0]) != 0)
+				break;
+			udelay(1);
+		}
+
+		/* Avoid memcpy function-call overhead */
+		entry[0] = raw[0];
+		entry[1] = raw[1];
+
+		/*
+		 * To detect the hardware errata 733 we need to clear the
+		 * entry back to zero. This issue does not exist on SNP
+		 * enabled system. Also this buffer is not writeable on
+		 * SNP enabled system.
+		 */
+		if (!amd_iommu_snp_en)
+			raw[0] = raw[1] = 0UL;
+
+		/* Update head pointer of hardware ring-buffer */
+		head = (head + PPRLOG_ENTRY_SIZE) % amd_iommu_pprlog_size;
+		writel(head, iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
+
+		/* Handle PPR entry */
+		iommu_call_iopf_notifier(iommu, entry);
+	}
+}
+
+/**************************************************************
+ *
+ * IOPF handling stuff
+ */
+
+/* Setup per-IOMMU IOPF queue if not exist. */
+int amd_iommu_iopf_init(struct amd_iommu *iommu)
+{
+	int ret = 0;
+
+	if (iommu->iopf_queue)
+		return ret;
+
+	snprintf(iommu->iopfq_name, sizeof(iommu->iopfq_name), "amdvi-%#x",
+		 PCI_SEG_DEVID_TO_SBDF(iommu->pci_seg->id, iommu->devid));
+
+	iommu->iopf_queue = iopf_queue_alloc(iommu->iopfq_name);
+	if (!iommu->iopf_queue)
+		ret = -ENOMEM;
+
+	return ret;
+}
+
+/* Destroy per-IOMMU IOPF queue if no longer needed. */
+void amd_iommu_iopf_uninit(struct amd_iommu *iommu)
+{
+	iopf_queue_free(iommu->iopf_queue);
+	iommu->iopf_queue = NULL;
+}
+
+void amd_iommu_page_response(struct device *dev, struct iopf_fault *evt,
+			     struct iommu_page_response *resp)
+{
+	amd_iommu_complete_ppr(dev, resp->pasid, resp->code, resp->grpid);
+}
+
+int amd_iommu_iopf_add_device(struct amd_iommu *iommu,
+			      struct iommu_dev_data *dev_data)
+{
+	int ret = 0;
+
+	if (!dev_data->pri_enabled)
+		return ret;
+
+	if (!iommu->iopf_queue)
+		return -EINVAL;
+
+	ret = iopf_queue_add_device(iommu->iopf_queue, dev_data->dev);
+	if (ret)
+		return ret;
+
+	dev_data->ppr = true;
+	return 0;
+}
+
+/* Its assumed that caller has verified that device was added to iopf queue */
+void amd_iommu_iopf_remove_device(struct amd_iommu *iommu,
+				  struct iommu_dev_data *dev_data)
+{
+	iopf_queue_remove_device(iommu->iopf_queue, dev_data->dev);
+	dev_data->ppr = false;
+}