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, 250 insertions, 0 deletions

diff --git a/drivers/fpga/dfl-afu-error.c b/drivers/fpga/dfl-afu-error.c
new file mode 100644
index 000000000..0f392d1f6
--- /dev/null
+++ b/drivers/fpga/dfl-afu-error.c
@@ -0,0 +1,250 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Driver for FPGA Accelerated Function Unit (AFU) Error Reporting
+ *
+ * Copyright 2019 Intel Corporation, Inc.
+ *
+ * Authors:
+ *   Wu Hao <hao.wu@linux.intel.com>
+ *   Xiao Guangrong <guangrong.xiao@linux.intel.com>
+ *   Joseph Grecco <joe.grecco@intel.com>
+ *   Enno Luebbers <enno.luebbers@intel.com>
+ *   Tim Whisonant <tim.whisonant@intel.com>
+ *   Ananda Ravuri <ananda.ravuri@intel.com>
+ *   Mitchel Henry <henry.mitchel@intel.com>
+ */
+
+#include <linux/fpga-dfl.h>
+#include <linux/uaccess.h>
+
+#include "dfl-afu.h"
+
+#define PORT_ERROR_MASK		0x8
+#define PORT_ERROR		0x10
+#define PORT_FIRST_ERROR	0x18
+#define PORT_MALFORMED_REQ0	0x20
+#define PORT_MALFORMED_REQ1	0x28
+
+#define ERROR_MASK		GENMASK_ULL(63, 0)
+
+/* mask or unmask port errors by the error mask register. */
+static void __afu_port_err_mask(struct dfl_feature_dev_data *fdata, bool mask)
+{
+	void __iomem *base;
+
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_ERROR);
+
+	writeq(mask ? ERROR_MASK : 0, base + PORT_ERROR_MASK);
+}
+
+static void afu_port_err_mask(struct device *dev, bool mask)
+{
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
+
+	mutex_lock(&fdata->lock);
+	__afu_port_err_mask(fdata, mask);
+	mutex_unlock(&fdata->lock);
+}
+
+/* clear port errors. */
+static int afu_port_err_clear(struct device *dev, u64 err)
+{
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
+	void __iomem *base_err, *base_hdr;
+	int enable_ret = 0, ret = -EBUSY;
+	u64 v;
+
+	base_err = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_ERROR);
+	base_hdr = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_HEADER);
+
+	mutex_lock(&fdata->lock);
+
+	/*
+	 * clear Port Errors
+	 *
+	 * - Check for AP6 State
+	 * - Halt Port by keeping Port in reset
+	 * - Set PORT Error mask to all 1 to mask errors
+	 * - Clear all errors
+	 * - Set Port mask to all 0 to enable errors
+	 * - All errors start capturing new errors
+	 * - Enable Port by pulling the port out of reset
+	 */
+
+	/* if device is still in AP6 power state, can not clear any error. */
+	v = readq(base_hdr + PORT_HDR_STS);
+	if (FIELD_GET(PORT_STS_PWR_STATE, v) == PORT_STS_PWR_STATE_AP6) {
+		dev_err(dev, "Could not clear errors, device in AP6 state.\n");
+		goto done;
+	}
+
+	/* Halt Port by keeping Port in reset */
+	ret = __afu_port_disable(fdata);
+	if (ret)
+		goto done;
+
+	/* Mask all errors */
+	__afu_port_err_mask(fdata, true);
+
+	/* Clear errors if err input matches with current port errors.*/
+	v = readq(base_err + PORT_ERROR);
+
+	if (v == err) {
+		writeq(v, base_err + PORT_ERROR);
+
+		v = readq(base_err + PORT_FIRST_ERROR);
+		writeq(v, base_err + PORT_FIRST_ERROR);
+	} else {
+		dev_warn(dev, "%s: received 0x%llx, expected 0x%llx\n",
+			 __func__, v, err);
+		ret = -EINVAL;
+	}
+
+	/* Clear mask */
+	__afu_port_err_mask(fdata, false);
+
+	/* Enable the Port by clearing the reset */
+	enable_ret = __afu_port_enable(fdata);
+
+done:
+	mutex_unlock(&fdata->lock);
+	return enable_ret ? enable_ret : ret;
+}
+
+static ssize_t errors_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
+	void __iomem *base;
+	u64 error;
+
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_ERROR);
+
+	mutex_lock(&fdata->lock);
+	error = readq(base + PORT_ERROR);
+	mutex_unlock(&fdata->lock);
+
+	return sprintf(buf, "0x%llx\n", (unsigned long long)error);
+}
+
+static ssize_t errors_store(struct device *dev, struct device_attribute *attr,
+			    const char *buff, size_t count)
+{
+	u64 value;
+	int ret;
+
+	if (kstrtou64(buff, 0, &value))
+		return -EINVAL;
+
+	ret = afu_port_err_clear(dev, value);
+
+	return ret ? ret : count;
+}
+static DEVICE_ATTR_RW(errors);
+
+static ssize_t first_error_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
+	void __iomem *base;
+	u64 error;
+
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_ERROR);
+
+	mutex_lock(&fdata->lock);
+	error = readq(base + PORT_FIRST_ERROR);
+	mutex_unlock(&fdata->lock);
+
+	return sprintf(buf, "0x%llx\n", (unsigned long long)error);
+}
+static DEVICE_ATTR_RO(first_error);
+
+static ssize_t first_malformed_req_show(struct device *dev,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct dfl_feature_dev_data *fdata = to_dfl_feature_dev_data(dev);
+	void __iomem *base;
+	u64 req0, req1;
+
+	base = dfl_get_feature_ioaddr_by_id(fdata, PORT_FEATURE_ID_ERROR);
+
+	mutex_lock(&fdata->lock);
+	req0 = readq(base + PORT_MALFORMED_REQ0);
+	req1 = readq(base + PORT_MALFORMED_REQ1);
+	mutex_unlock(&fdata->lock);
+
+	return sprintf(buf, "0x%016llx%016llx\n",
+		       (unsigned long long)req1, (unsigned long long)req0);
+}
+static DEVICE_ATTR_RO(first_malformed_req);
+
+static struct attribute *port_err_attrs[] = {
+	&dev_attr_errors.attr,
+	&dev_attr_first_error.attr,
+	&dev_attr_first_malformed_req.attr,
+	NULL,
+};
+
+static umode_t port_err_attrs_visible(struct kobject *kobj,
+				      struct attribute *attr, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct dfl_feature_dev_data *fdata;
+
+	fdata = to_dfl_feature_dev_data(dev);
+	/*
+	 * sysfs entries are visible only if related private feature is
+	 * enumerated.
+	 */
+	if (!dfl_get_feature_by_id(fdata, PORT_FEATURE_ID_ERROR))
+		return 0;
+
+	return attr->mode;
+}
+
+const struct attribute_group port_err_group = {
+	.name       = "errors",
+	.attrs      = port_err_attrs,
+	.is_visible = port_err_attrs_visible,
+};
+
+static int port_err_init(struct platform_device *pdev,
+			 struct dfl_feature *feature)
+{
+	afu_port_err_mask(&pdev->dev, false);
+
+	return 0;
+}
+
+static void port_err_uinit(struct platform_device *pdev,
+			   struct dfl_feature *feature)
+{
+	afu_port_err_mask(&pdev->dev, true);
+}
+
+static long
+port_err_ioctl(struct platform_device *pdev, struct dfl_feature *feature,
+	       unsigned int cmd, unsigned long arg)
+{
+	switch (cmd) {
+	case DFL_FPGA_PORT_ERR_GET_IRQ_NUM:
+		return dfl_feature_ioctl_get_num_irqs(pdev, feature, arg);
+	case DFL_FPGA_PORT_ERR_SET_IRQ:
+		return dfl_feature_ioctl_set_irq(pdev, feature, arg);
+	default:
+		dev_dbg(&pdev->dev, "%x cmd not handled", cmd);
+		return -ENODEV;
+	}
+}
+
+const struct dfl_feature_id port_err_id_table[] = {
+	{.id = PORT_FEATURE_ID_ERROR,},
+	{0,}
+};
+
+const struct dfl_feature_ops port_err_ops = {
+	.init = port_err_init,
+	.uinit = port_err_uinit,
+	.ioctl = port_err_ioctl,
+};