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, 308 insertions, 0 deletions

diff --git a/block/bsg.c b/block/bsg.c
new file mode 100644
index 000000000..82aaf3cee
--- /dev/null
+++ b/block/bsg.c
@@ -0,0 +1,308 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * bsg.c - block layer implementation of the sg v4 interface
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/file.h>
+#include <linux/blkdev.h>
+#include <linux/cdev.h>
+#include <linux/jiffies.h>
+#include <linux/percpu.h>
+#include <linux/idr.h>
+#include <linux/bsg.h>
+#include <linux/slab.h>
+#include <linux/io_uring/cmd.h>
+
+#include <scsi/scsi.h>
+#include <scsi/scsi_ioctl.h>
+#include <scsi/sg.h>
+
+#define BSG_DESCRIPTION	"Block layer SCSI generic (bsg) driver"
+#define BSG_VERSION	"0.4"
+
+struct bsg_device {
+	struct request_queue *queue;
+	struct device device;
+	struct cdev cdev;
+	int max_queue;
+	unsigned int timeout;
+	unsigned int reserved_size;
+	bsg_sg_io_fn *sg_io_fn;
+	bsg_uring_cmd_fn *uring_cmd_fn;
+};
+
+static inline struct bsg_device *to_bsg_device(struct inode *inode)
+{
+	return container_of(inode->i_cdev, struct bsg_device, cdev);
+}
+
+#define BSG_DEFAULT_CMDS	64
+#define BSG_MAX_DEVS		(1 << MINORBITS)
+
+static DEFINE_IDA(bsg_minor_ida);
+static const struct class bsg_class;
+static int bsg_major;
+
+static unsigned int bsg_timeout(struct bsg_device *bd, struct sg_io_v4 *hdr)
+{
+	unsigned int timeout = BLK_DEFAULT_SG_TIMEOUT;
+
+	if (hdr->timeout)
+		timeout = msecs_to_jiffies(hdr->timeout);
+	else if (bd->timeout)
+		timeout = bd->timeout;
+
+	return max_t(unsigned int, timeout, BLK_MIN_SG_TIMEOUT);
+}
+
+static int bsg_sg_io(struct bsg_device *bd, bool open_for_write,
+		     void __user *uarg)
+{
+	struct sg_io_v4 hdr;
+	int ret;
+
+	if (copy_from_user(&hdr, uarg, sizeof(hdr)))
+		return -EFAULT;
+	if (hdr.guard != 'Q')
+		return -EINVAL;
+	ret = bd->sg_io_fn(bd->queue, &hdr, open_for_write,
+			   bsg_timeout(bd, &hdr));
+	if (!ret && copy_to_user(uarg, &hdr, sizeof(hdr)))
+		return -EFAULT;
+	return ret;
+}
+
+static int bsg_open(struct inode *inode, struct file *file)
+{
+	if (!blk_get_queue(to_bsg_device(inode)->queue))
+		return -ENXIO;
+	return 0;
+}
+
+static int bsg_release(struct inode *inode, struct file *file)
+{
+	blk_put_queue(to_bsg_device(inode)->queue);
+	return 0;
+}
+
+static int bsg_get_command_q(struct bsg_device *bd, int __user *uarg)
+{
+	return put_user(READ_ONCE(bd->max_queue), uarg);
+}
+
+static int bsg_set_command_q(struct bsg_device *bd, int __user *uarg)
+{
+	int max_queue;
+
+	if (get_user(max_queue, uarg))
+		return -EFAULT;
+	if (max_queue < 1)
+		return -EINVAL;
+	WRITE_ONCE(bd->max_queue, max_queue);
+	return 0;
+}
+
+static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct bsg_device *bd = to_bsg_device(file_inode(file));
+	struct request_queue *q = bd->queue;
+	void __user *uarg = (void __user *) arg;
+	int __user *intp = uarg;
+	int val;
+
+	switch (cmd) {
+	/*
+	 * Our own ioctls
+	 */
+	case SG_GET_COMMAND_Q:
+		return bsg_get_command_q(bd, uarg);
+	case SG_SET_COMMAND_Q:
+		return bsg_set_command_q(bd, uarg);
+
+	/*
+	 * SCSI/sg ioctls
+	 */
+	case SG_GET_VERSION_NUM:
+		return put_user(30527, intp);
+	case SCSI_IOCTL_GET_IDLUN:
+		return put_user(0, intp);
+	case SCSI_IOCTL_GET_BUS_NUMBER:
+		return put_user(0, intp);
+	case SG_SET_TIMEOUT:
+		if (get_user(val, intp))
+			return -EFAULT;
+		bd->timeout = clock_t_to_jiffies(val);
+		return 0;
+	case SG_GET_TIMEOUT:
+		return jiffies_to_clock_t(bd->timeout);
+	case SG_GET_RESERVED_SIZE:
+		return put_user(min(bd->reserved_size, queue_max_bytes(q)),
+				intp);
+	case SG_SET_RESERVED_SIZE:
+		if (get_user(val, intp))
+			return -EFAULT;
+		if (val < 0)
+			return -EINVAL;
+		bd->reserved_size =
+			min_t(unsigned int, val, queue_max_bytes(q));
+		return 0;
+	case SG_EMULATED_HOST:
+		return put_user(1, intp);
+	case SG_IO:
+		return bsg_sg_io(bd, file->f_mode & FMODE_WRITE, uarg);
+	case SCSI_IOCTL_SEND_COMMAND:
+		pr_warn_ratelimited("%s: calling unsupported SCSI_IOCTL_SEND_COMMAND\n",
+				current->comm);
+		return -EINVAL;
+	default:
+		return -ENOTTY;
+	}
+}
+
+static int bsg_check_uring_features(unsigned int issue_flags)
+{
+	/* BSG passthrough requires big SQE/CQE support */
+	if ((issue_flags & (IO_URING_F_SQE128|IO_URING_F_CQE32)) !=
+	    (IO_URING_F_SQE128|IO_URING_F_CQE32))
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+static int bsg_uring_cmd(struct io_uring_cmd *ioucmd, unsigned int issue_flags)
+{
+	struct bsg_device *bd = to_bsg_device(file_inode(ioucmd->file));
+	bool open_for_write = ioucmd->file->f_mode & FMODE_WRITE;
+	struct request_queue *q = bd->queue;
+	int ret;
+
+	ret = bsg_check_uring_features(issue_flags);
+	if (ret)
+		return ret;
+
+	if (!bd->uring_cmd_fn)
+		return -EOPNOTSUPP;
+
+	return bd->uring_cmd_fn(q, ioucmd, issue_flags, open_for_write);
+}
+
+static const struct file_operations bsg_fops = {
+	.open		=	bsg_open,
+	.release	=	bsg_release,
+	.unlocked_ioctl	=	bsg_ioctl,
+	.compat_ioctl	=	compat_ptr_ioctl,
+	.uring_cmd	=	bsg_uring_cmd,
+	.owner		=	THIS_MODULE,
+	.llseek		=	default_llseek,
+};
+
+static void bsg_device_release(struct device *dev)
+{
+	struct bsg_device *bd = container_of(dev, struct bsg_device, device);
+
+	ida_free(&bsg_minor_ida, MINOR(bd->device.devt));
+	kfree(bd);
+}
+
+void bsg_unregister_queue(struct bsg_device *bd)
+{
+	struct gendisk *disk = bd->queue->disk;
+
+	if (disk && disk->queue_kobj.sd)
+		sysfs_remove_link(&disk->queue_kobj, "bsg");
+	cdev_device_del(&bd->cdev, &bd->device);
+	put_device(&bd->device);
+}
+EXPORT_SYMBOL_GPL(bsg_unregister_queue);
+
+struct bsg_device *bsg_register_queue(struct request_queue *q,
+		struct device *parent, const char *name, bsg_sg_io_fn *sg_io_fn,
+		bsg_uring_cmd_fn *uring_cmd_fn)
+{
+	struct bsg_device *bd;
+	int ret;
+
+	bd = kzalloc_obj(*bd);
+	if (!bd)
+		return ERR_PTR(-ENOMEM);
+	bd->max_queue = BSG_DEFAULT_CMDS;
+	bd->reserved_size = INT_MAX;
+	bd->queue = q;
+	bd->sg_io_fn = sg_io_fn;
+	bd->uring_cmd_fn = uring_cmd_fn;
+
+	ret = ida_alloc_max(&bsg_minor_ida, BSG_MAX_DEVS - 1, GFP_KERNEL);
+	if (ret < 0) {
+		if (ret == -ENOSPC)
+			dev_err(parent, "bsg: too many bsg devices\n");
+		kfree(bd);
+		return ERR_PTR(ret);
+	}
+	bd->device.devt = MKDEV(bsg_major, ret);
+	bd->device.class = &bsg_class;
+	bd->device.parent = parent;
+	bd->device.release = bsg_device_release;
+	dev_set_name(&bd->device, "%s", name);
+	device_initialize(&bd->device);
+
+	cdev_init(&bd->cdev, &bsg_fops);
+	bd->cdev.owner = THIS_MODULE;
+	ret = cdev_device_add(&bd->cdev, &bd->device);
+	if (ret)
+		goto out_put_device;
+
+	if (q->disk && q->disk->queue_kobj.sd) {
+		ret = sysfs_create_link(&q->disk->queue_kobj, &bd->device.kobj,
+					"bsg");
+		if (ret)
+			goto out_device_del;
+	}
+
+	return bd;
+
+out_device_del:
+	cdev_device_del(&bd->cdev, &bd->device);
+out_put_device:
+	put_device(&bd->device);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(bsg_register_queue);
+
+static char *bsg_devnode(const struct device *dev, umode_t *mode)
+{
+	return kasprintf(GFP_KERNEL, "bsg/%s", dev_name(dev));
+}
+
+static const struct class bsg_class = {
+	.name		= "bsg",
+	.devnode	= bsg_devnode,
+};
+
+static int __init bsg_init(void)
+{
+	dev_t devid;
+	int ret;
+
+	ret = class_register(&bsg_class);
+	if (ret)
+		return ret;
+
+	ret = alloc_chrdev_region(&devid, 0, BSG_MAX_DEVS, "bsg");
+	if (ret)
+		goto destroy_bsg_class;
+	bsg_major = MAJOR(devid);
+
+	printk(KERN_INFO BSG_DESCRIPTION " version " BSG_VERSION
+	       " loaded (major %d)\n", bsg_major);
+	return 0;
+
+destroy_bsg_class:
+	class_unregister(&bsg_class);
+	return ret;
+}
+
+MODULE_AUTHOR("Jens Axboe");
+MODULE_DESCRIPTION(BSG_DESCRIPTION);
+MODULE_LICENSE("GPL");
+
+device_initcall(bsg_init);