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, 357 insertions, 0 deletions

diff --git a/block/blk-lib.c b/block/blk-lib.c
new file mode 100644
index 000000000..688bc67cb
--- /dev/null
+++ b/block/blk-lib.c
@@ -0,0 +1,357 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Functions related to generic helpers functions
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/bio.h>
+#include <linux/blkdev.h>
+#include <linux/scatterlist.h>
+
+#include "blk.h"
+
+static sector_t bio_discard_limit(struct block_device *bdev, sector_t sector)
+{
+	unsigned int discard_granularity = bdev_discard_granularity(bdev);
+	sector_t granularity_aligned_sector;
+
+	if (bdev_is_partition(bdev))
+		sector += bdev->bd_start_sect;
+
+	granularity_aligned_sector =
+		round_up(sector, discard_granularity >> SECTOR_SHIFT);
+
+	/*
+	 * Make sure subsequent bios start aligned to the discard granularity if
+	 * it needs to be split.
+	 */
+	if (granularity_aligned_sector != sector)
+		return granularity_aligned_sector - sector;
+
+	/*
+	 * Align the bio size to the discard granularity to make splitting the bio
+	 * at discard granularity boundaries easier in the driver if needed.
+	 */
+	return round_down(BIO_MAX_SIZE, discard_granularity) >> SECTOR_SHIFT;
+}
+
+struct bio *blk_alloc_discard_bio(struct block_device *bdev,
+		sector_t *sector, sector_t *nr_sects, gfp_t gfp_mask)
+{
+	sector_t bio_sects = min(*nr_sects, bio_discard_limit(bdev, *sector));
+	struct bio *bio;
+
+	if (!bio_sects)
+		return NULL;
+
+	bio = bio_alloc(bdev, 0, REQ_OP_DISCARD, gfp_mask);
+	if (!bio)
+		return NULL;
+	bio->bi_iter.bi_sector = *sector;
+	bio->bi_iter.bi_size = bio_sects << SECTOR_SHIFT;
+	*sector += bio_sects;
+	*nr_sects -= bio_sects;
+	/*
+	 * We can loop for a long time in here if someone does full device
+	 * discards (like mkfs).  Be nice and allow us to schedule out to avoid
+	 * softlocking if preempt is disabled.
+	 */
+	cond_resched();
+	return bio;
+}
+
+void __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop)
+{
+	struct bio *bio;
+
+	while ((bio = blk_alloc_discard_bio(bdev, &sector, &nr_sects,
+			gfp_mask)))
+		*biop = bio_chain_and_submit(*biop, bio);
+}
+EXPORT_SYMBOL(__blkdev_issue_discard);
+
+/**
+ * blkdev_issue_discard - queue a discard
+ * @bdev:	blockdev to issue discard for
+ * @sector:	start sector
+ * @nr_sects:	number of sectors to discard
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
+ *
+ * Description:
+ *    Issue a discard request for the sectors in question.
+ */
+int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask)
+{
+	struct bio *bio = NULL;
+	struct blk_plug plug;
+	int ret = 0;
+
+	blk_start_plug(&plug);
+	__blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, &bio);
+	if (bio) {
+		ret = submit_bio_wait(bio);
+		if (ret == -EOPNOTSUPP)
+			ret = 0;
+		bio_put(bio);
+	}
+	blk_finish_plug(&plug);
+
+	return ret;
+}
+EXPORT_SYMBOL(blkdev_issue_discard);
+
+static sector_t bio_write_zeroes_limit(struct block_device *bdev)
+{
+	sector_t bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
+
+	return min(bdev_write_zeroes_sectors(bdev), BIO_MAX_SECTORS & ~bs_mask);
+}
+
+/*
+ * There is no reliable way for the SCSI subsystem to determine whether a
+ * device supports a WRITE SAME operation without actually performing a write
+ * to media. As a result, write_zeroes is enabled by default and will be
+ * disabled if a zeroing operation subsequently fails. This means that this
+ * queue limit is likely to change at runtime.
+ */
+static void __blkdev_issue_write_zeroes(struct block_device *bdev,
+		sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
+		struct bio **biop, unsigned flags, sector_t limit)
+{
+
+	while (nr_sects) {
+		unsigned int len = min(nr_sects, limit);
+		struct bio *bio;
+
+		if ((flags & BLKDEV_ZERO_KILLABLE) &&
+		    fatal_signal_pending(current))
+			break;
+
+		bio = bio_alloc(bdev, 0, REQ_OP_WRITE_ZEROES, gfp_mask);
+		bio->bi_iter.bi_sector = sector;
+		if (flags & BLKDEV_ZERO_NOUNMAP)
+			bio->bi_opf |= REQ_NOUNMAP;
+
+		bio->bi_iter.bi_size = len << SECTOR_SHIFT;
+		*biop = bio_chain_and_submit(*biop, bio);
+
+		nr_sects -= len;
+		sector += len;
+		cond_resched();
+	}
+}
+
+static int blkdev_issue_write_zeroes(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp, unsigned flags)
+{
+	sector_t limit = bio_write_zeroes_limit(bdev);
+	struct bio *bio = NULL;
+	struct blk_plug plug;
+	int ret = 0;
+
+	blk_start_plug(&plug);
+	__blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp, &bio,
+			flags, limit);
+	if (bio) {
+		ret = bio_submit_or_kill(bio, flags);
+		bio_put(bio);
+	}
+	blk_finish_plug(&plug);
+
+	/*
+	 * For some devices there is no non-destructive way to verify whether
+	 * WRITE ZEROES is actually supported.  These will clear the capability
+	 * on an I/O error, in which case we'll turn any error into
+	 * "not supported" here.
+	 */
+	if (ret && !bdev_write_zeroes_sectors(bdev))
+		return -EOPNOTSUPP;
+	return ret;
+}
+
+/*
+ * Convert a number of 512B sectors to a number of pages.
+ * The result is limited to a number of pages that can fit into a BIO.
+ * Also make sure that the result is always at least 1 (page) for the cases
+ * where nr_sects is lower than the number of sectors in a page.
+ */
+static unsigned int __blkdev_sectors_to_bio_pages(sector_t nr_sects)
+{
+	sector_t pages = DIV_ROUND_UP_SECTOR_T(nr_sects, PAGE_SIZE / 512);
+
+	return min(pages, (sector_t)BIO_MAX_VECS);
+}
+
+static void __blkdev_issue_zero_pages(struct block_device *bdev,
+		sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
+		struct bio **biop, unsigned int flags)
+{
+	struct folio *zero_folio = largest_zero_folio();
+
+	while (nr_sects) {
+		unsigned int nr_vecs = __blkdev_sectors_to_bio_pages(nr_sects);
+		struct bio *bio;
+
+		if ((flags & BLKDEV_ZERO_KILLABLE) &&
+		    fatal_signal_pending(current))
+			break;
+
+		bio = bio_alloc(bdev, nr_vecs, REQ_OP_WRITE, gfp_mask);
+		bio->bi_iter.bi_sector = sector;
+
+		do {
+			unsigned int len;
+
+			len = min_t(sector_t, folio_size(zero_folio),
+				    nr_sects << SECTOR_SHIFT);
+			if (!bio_add_folio(bio, zero_folio, len, 0))
+				break;
+			nr_sects -= len >> SECTOR_SHIFT;
+			sector += len >> SECTOR_SHIFT;
+		} while (nr_sects);
+
+		*biop = bio_chain_and_submit(*biop, bio);
+		cond_resched();
+	}
+}
+
+static int blkdev_issue_zero_pages(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp, unsigned flags)
+{
+	struct bio *bio = NULL;
+	struct blk_plug plug;
+	int ret = 0;
+
+	if (flags & BLKDEV_ZERO_NOFALLBACK)
+		return -EOPNOTSUPP;
+
+	blk_start_plug(&plug);
+	__blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp, &bio, flags);
+	if (bio) {
+		ret = bio_submit_or_kill(bio, flags);
+		bio_put(bio);
+	}
+	blk_finish_plug(&plug);
+
+	return ret;
+}
+
+/**
+ * __blkdev_issue_zeroout - generate number of zero filed write bios
+ * @bdev:	blockdev to issue
+ * @sector:	start sector
+ * @nr_sects:	number of sectors to write
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
+ * @biop:	pointer to anchor bio
+ * @flags:	controls detailed behavior
+ *
+ * Description:
+ *  Zero-fill a block range, either using hardware offload or by explicitly
+ *  writing zeroes to the device.
+ *
+ *  If a device is using logical block provisioning, the underlying space will
+ *  not be released if %flags contains BLKDEV_ZERO_NOUNMAP.
+ *
+ *  If %flags contains BLKDEV_ZERO_NOFALLBACK, the function will return
+ *  -EOPNOTSUPP if no explicit hardware offload for zeroing is provided.
+ */
+int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
+		unsigned flags)
+{
+	sector_t limit = bio_write_zeroes_limit(bdev);
+
+	if (bdev_read_only(bdev))
+		return -EPERM;
+
+	if (limit) {
+		__blkdev_issue_write_zeroes(bdev, sector, nr_sects,
+				gfp_mask, biop, flags, limit);
+	} else {
+		if (flags & BLKDEV_ZERO_NOFALLBACK)
+			return -EOPNOTSUPP;
+		__blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask,
+				biop, flags);
+	}
+	return 0;
+}
+EXPORT_SYMBOL(__blkdev_issue_zeroout);
+
+/**
+ * blkdev_issue_zeroout - zero-fill a block range
+ * @bdev:	blockdev to write
+ * @sector:	start sector
+ * @nr_sects:	number of sectors to write
+ * @gfp_mask:	memory allocation flags (for bio_alloc)
+ * @flags:	controls detailed behavior
+ *
+ * Description:
+ *  Zero-fill a block range, either using hardware offload or by explicitly
+ *  writing zeroes to the device.  See __blkdev_issue_zeroout() for the
+ *  valid values for %flags.
+ */
+int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp_mask, unsigned flags)
+{
+	int ret;
+
+	if ((sector | nr_sects) & ((bdev_logical_block_size(bdev) >> 9) - 1))
+		return -EINVAL;
+	if (bdev_read_only(bdev))
+		return -EPERM;
+
+	if (bdev_write_zeroes_sectors(bdev)) {
+		ret = blkdev_issue_write_zeroes(bdev, sector, nr_sects,
+				gfp_mask, flags);
+		if (ret != -EOPNOTSUPP)
+			return ret;
+	}
+
+	return blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask, flags);
+}
+EXPORT_SYMBOL(blkdev_issue_zeroout);
+
+int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp)
+{
+	sector_t bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
+	unsigned int max_sectors = bdev_max_secure_erase_sectors(bdev);
+	struct bio *bio = NULL;
+	struct blk_plug plug;
+	int ret = 0;
+
+	/* make sure that "len << SECTOR_SHIFT" doesn't overflow */
+	if (max_sectors > BIO_MAX_SECTORS)
+		max_sectors = BIO_MAX_SECTORS;
+	max_sectors &= ~bs_mask;
+
+	if (max_sectors == 0)
+		return -EOPNOTSUPP;
+	if ((sector | nr_sects) & bs_mask)
+		return -EINVAL;
+	if (bdev_read_only(bdev))
+		return -EPERM;
+
+	blk_start_plug(&plug);
+	while (nr_sects) {
+		unsigned int len = min_t(sector_t, nr_sects, max_sectors);
+
+		bio = blk_next_bio(bio, bdev, 0, REQ_OP_SECURE_ERASE, gfp);
+		bio->bi_iter.bi_sector = sector;
+		bio->bi_iter.bi_size = len << SECTOR_SHIFT;
+
+		sector += len;
+		nr_sects -= len;
+		cond_resched();
+	}
+	if (bio) {
+		ret = submit_bio_wait(bio);
+		bio_put(bio);
+	}
+	blk_finish_plug(&plug);
+
+	return ret;
+}
+EXPORT_SYMBOL(blkdev_issue_secure_erase);