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, 232 insertions, 0 deletions

diff --git a/drivers/misc/open-dice.c b/drivers/misc/open-dice.c
new file mode 100644
index 000000000..b3cf59954
--- /dev/null
+++ b/drivers/misc/open-dice.c
@@ -0,0 +1,232 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 - Google LLC
+ * Author: David Brazdil <dbrazdil@google.com>
+ * Author: Song Guo <songguo@google.com>
+ *
+ * Driver for Open Profile for DICE.
+ *
+ * This driver takes ownership of a reserved memory region containing data
+ * generated by the Open Profile for DICE measured boot protocol. The memory
+ * contents are not interpreted by the kernel but can be mapped into a userspace
+ * process via a misc device. Userspace can also request a wipe of the memory.
+ *
+ * Userspace can access the data with (w/o error handling):
+ *
+ *     fd = open("/dev/open-dice0", O_RDWR);
+ *     read(fd, &size, sizeof(unsigned long));
+ *     data = mmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
+ *     write(fd, NULL, 0); // wipe
+ *     close(fd);
+ */
+
+#include <linux/acpi.h>
+#include <linux/io.h>
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/platform_device.h>
+
+#define DRIVER_NAME "open-dice"
+
+struct open_dice_drvdata {
+	struct mutex lock;
+	char name[16];
+	phys_addr_t mem_base;
+	resource_size_t mem_size;
+	struct miscdevice misc;
+};
+
+static inline struct open_dice_drvdata *to_open_dice_drvdata(struct file *filp)
+{
+	return container_of(filp->private_data, struct open_dice_drvdata, misc);
+}
+
+static int open_dice_wipe(struct open_dice_drvdata *drvdata)
+{
+	void *kaddr;
+
+	mutex_lock(&drvdata->lock);
+	kaddr = devm_memremap(drvdata->misc.this_device, drvdata->mem_base,
+			      drvdata->mem_size, MEMREMAP_WC);
+	if (IS_ERR(kaddr)) {
+		mutex_unlock(&drvdata->lock);
+		return PTR_ERR(kaddr);
+	}
+
+	memset(kaddr, 0, drvdata->mem_size);
+	devm_memunmap(drvdata->misc.this_device, kaddr);
+	mutex_unlock(&drvdata->lock);
+	return 0;
+}
+
+/*
+ * Copies the size of the reserved memory region to the user-provided buffer.
+ */
+static ssize_t open_dice_read(struct file *filp, char __user *ptr, size_t len,
+			      loff_t *off)
+{
+	unsigned long val = to_open_dice_drvdata(filp)->mem_size;
+
+	return simple_read_from_buffer(ptr, len, off, &val, sizeof(val));
+}
+
+/*
+ * Triggers a wipe of the reserved memory region. The user-provided pointer
+ * is never dereferenced.
+ */
+static ssize_t open_dice_write(struct file *filp, const char __user *ptr,
+			       size_t len, loff_t *off)
+{
+	if (open_dice_wipe(to_open_dice_drvdata(filp)))
+		return -EIO;
+
+	/* Consume the input buffer. */
+	return len;
+}
+
+/*
+ * Creates a mapping of the reserved memory region in user address space.
+ */
+static int open_dice_mmap_prepare(struct vm_area_desc *desc)
+{
+	struct file *filp = desc->file;
+	struct open_dice_drvdata *drvdata = to_open_dice_drvdata(filp);
+
+	if (vma_desc_test(desc, VMA_MAYSHARE_BIT)) {
+		/* Do not allow userspace to modify the underlying data. */
+		if (vma_desc_test(desc, VMA_WRITE_BIT))
+			return -EPERM;
+		/* Ensure userspace cannot acquire VM_WRITE later. */
+		vma_desc_clear_flags(desc, VMA_MAYWRITE_BIT);
+	}
+
+	/* Create write-combine mapping so all clients observe a wipe. */
+	desc->page_prot = pgprot_writecombine(desc->page_prot);
+	vma_desc_set_flags(desc, VMA_DONTCOPY_BIT, VMA_DONTDUMP_BIT);
+	mmap_action_simple_ioremap(desc, drvdata->mem_base,
+				   drvdata->mem_size);
+	return 0;
+}
+
+static const struct file_operations open_dice_fops = {
+	.owner = THIS_MODULE,
+	.read = open_dice_read,
+	.write = open_dice_write,
+	.mmap_prepare = open_dice_mmap_prepare,
+};
+
+static int __init open_dice_probe(struct platform_device *pdev)
+{
+	static unsigned int dev_idx;
+	struct device *dev = &pdev->dev;
+	struct open_dice_drvdata *drvdata;
+	phys_addr_t mem_base;
+	resource_size_t mem_size;
+	int ret;
+
+	if (dev->of_node) {
+		struct reserved_mem *rmem = of_reserved_mem_lookup(dev->of_node);
+
+		if (!rmem) {
+			dev_err(dev, "failed to lookup reserved memory\n");
+			return -EINVAL;
+		}
+		mem_base = rmem->base;
+		mem_size = rmem->size;
+	} else if (is_acpi_node(dev->fwnode)) {
+		struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+		if (!res) {
+			dev_err(dev, "failed to get MMIO resource\n");
+			return -EINVAL;
+		}
+		mem_base = res->start;
+		mem_size = resource_size(res);
+	} else {
+		dev_err(dev, "device not supported (no DT or ACPI node)\n");
+		return -EINVAL;
+	}
+
+	if (!mem_size || (mem_size > ULONG_MAX)) {
+		dev_err(dev, "invalid memory region size\n");
+		return -EINVAL;
+	}
+
+	if (!PAGE_ALIGNED(mem_base) || !PAGE_ALIGNED(mem_size)) {
+		dev_err(dev, "memory region must be page-aligned\n");
+		return -EINVAL;
+	}
+
+	drvdata = devm_kmalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	*drvdata = (struct open_dice_drvdata){
+		.mem_base = mem_base,
+		.mem_size = mem_size,
+		.misc = (struct miscdevice){
+			.parent	= dev,
+			.name	= drvdata->name,
+			.minor	= MISC_DYNAMIC_MINOR,
+			.fops	= &open_dice_fops,
+			.mode	= 0600,
+		},
+	};
+	mutex_init(&drvdata->lock);
+
+	/* Index overflow check not needed, misc_register() will fail. */
+	snprintf(drvdata->name, sizeof(drvdata->name), DRIVER_NAME"%u", dev_idx++);
+
+	ret = misc_register(&drvdata->misc);
+	if (ret) {
+		dev_err(dev, "failed to register misc device '%s': %d\n",
+			drvdata->name, ret);
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, drvdata);
+	return 0;
+}
+
+static void open_dice_remove(struct platform_device *pdev)
+{
+	struct open_dice_drvdata *drvdata = platform_get_drvdata(pdev);
+
+	misc_deregister(&drvdata->misc);
+}
+
+static const struct of_device_id open_dice_of_match[] = {
+	{ .compatible = "google,open-dice" },
+	{ }
+};
+
+static struct platform_driver open_dice_driver = {
+	.remove = open_dice_remove,
+	.driver = {
+		.name = DRIVER_NAME,
+		.of_match_table = open_dice_of_match,
+	},
+};
+
+static int __init open_dice_init(void)
+{
+	int ret = platform_driver_probe(&open_dice_driver, open_dice_probe);
+
+	/* DICE regions are optional. Succeed even with zero instances. */
+	return (ret == -ENODEV) ? 0 : ret;
+}
+
+static void __exit open_dice_exit(void)
+{
+	platform_driver_unregister(&open_dice_driver);
+}
+
+module_init(open_dice_init);
+module_exit(open_dice_exit);
+
+MODULE_DESCRIPTION("Driver for Open Profile for DICE.");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("David Brazdil <dbrazdil@google.com>");
+MODULE_AUTHOR("Song Guo <songguo@google.com>");