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, 340 insertions, 0 deletions

diff --git a/fs/udf/partition.c b/fs/udf/partition.c
new file mode 100644
index 000000000..ad8dcedca
--- /dev/null
+++ b/fs/udf/partition.c
@@ -0,0 +1,340 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * partition.c
+ *
+ * PURPOSE
+ *      Partition handling routines for the OSTA-UDF(tm) filesystem.
+ *
+ * COPYRIGHT
+ *  (C) 1998-2001 Ben Fennema
+ *
+ * HISTORY
+ *
+ * 12/06/98 blf  Created file.
+ *
+ */
+
+#include "udfdecl.h"
+#include "udf_sb.h"
+#include "udf_i.h"
+
+#include <linux/fs.h>
+#include <linux/string.h>
+#include <linux/mutex.h>
+
+uint32_t udf_get_pblock(struct super_block *sb, uint32_t block,
+			uint16_t partition, uint32_t offset)
+{
+	struct udf_sb_info *sbi = UDF_SB(sb);
+	struct udf_part_map *map;
+	if (partition >= sbi->s_partitions) {
+		udf_debug("block=%u, partition=%u, offset=%u: invalid partition\n",
+			  block, partition, offset);
+		return 0xFFFFFFFF;
+	}
+	map = &sbi->s_partmaps[partition];
+	if (map->s_partition_func)
+		return map->s_partition_func(sb, block, partition, offset);
+	else
+		return map->s_partition_root + block + offset;
+}
+
+uint32_t udf_get_pblock_virt15(struct super_block *sb, uint32_t block,
+			       uint16_t partition, uint32_t offset)
+{
+	struct buffer_head *bh = NULL;
+	uint32_t newblock;
+	uint32_t index;
+	uint32_t loc;
+	struct udf_sb_info *sbi = UDF_SB(sb);
+	struct udf_part_map *map;
+	struct udf_virtual_data *vdata;
+	struct udf_inode_info *iinfo = UDF_I(sbi->s_vat_inode);
+	int err;
+
+	map = &sbi->s_partmaps[partition];
+	vdata = &map->s_type_specific.s_virtual;
+
+	if (block >= vdata->s_num_entries) {
+		udf_debug("Trying to access block beyond end of VAT (%u max %u)\n",
+			  block, vdata->s_num_entries);
+		return 0xFFFFFFFF;
+	}
+
+	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) {
+		loc = le32_to_cpu(((__le32 *)(iinfo->i_data +
+			vdata->s_start_offset))[block]);
+		goto translate;
+	}
+	index = (sb->s_blocksize - vdata->s_start_offset) / sizeof(uint32_t);
+	if (block >= index) {
+		block -= index;
+		newblock = 1 + (block / (sb->s_blocksize / sizeof(uint32_t)));
+		index = block % (sb->s_blocksize / sizeof(uint32_t));
+	} else {
+		newblock = 0;
+		index = vdata->s_start_offset / sizeof(uint32_t) + block;
+	}
+
+	bh = udf_bread(sbi->s_vat_inode, newblock, 0, &err);
+	if (!bh) {
+		udf_debug("get_pblock(UDF_VIRTUAL_MAP:%p,%u,%u)\n",
+			  sb, block, partition);
+		return 0xFFFFFFFF;
+	}
+
+	loc = le32_to_cpu(((__le32 *)bh->b_data)[index]);
+
+	brelse(bh);
+
+translate:
+	if (iinfo->i_location.partitionReferenceNum == partition) {
+		udf_debug("recursive call to udf_get_pblock!\n");
+		return 0xFFFFFFFF;
+	}
+
+	return udf_get_pblock(sb, loc,
+			      iinfo->i_location.partitionReferenceNum,
+			      offset);
+}
+
+inline uint32_t udf_get_pblock_virt20(struct super_block *sb, uint32_t block,
+				      uint16_t partition, uint32_t offset)
+{
+	return udf_get_pblock_virt15(sb, block, partition, offset);
+}
+
+uint32_t udf_get_pblock_spar15(struct super_block *sb, uint32_t block,
+			       uint16_t partition, uint32_t offset)
+{
+	int i;
+	struct sparingTable *st = NULL;
+	struct udf_sb_info *sbi = UDF_SB(sb);
+	struct udf_part_map *map;
+	uint32_t packet;
+	struct udf_sparing_data *sdata;
+
+	map = &sbi->s_partmaps[partition];
+	sdata = &map->s_type_specific.s_sparing;
+	packet = (block + offset) & ~(sdata->s_packet_len - 1);
+
+	for (i = 0; i < 4; i++) {
+		if (sdata->s_spar_map[i] != NULL) {
+			st = (struct sparingTable *)
+					sdata->s_spar_map[i]->b_data;
+			break;
+		}
+	}
+
+	if (st) {
+		for (i = 0; i < le16_to_cpu(st->reallocationTableLen); i++) {
+			struct sparingEntry *entry = &st->mapEntry[i];
+			u32 origLoc = le32_to_cpu(entry->origLocation);
+			if (origLoc >= 0xFFFFFFF0)
+				break;
+			else if (origLoc == packet)
+				return le32_to_cpu(entry->mappedLocation) +
+					((block + offset) &
+						(sdata->s_packet_len - 1));
+			else if (origLoc > packet)
+				break;
+		}
+	}
+
+	return map->s_partition_root + block + offset;
+}
+
+int udf_relocate_blocks(struct super_block *sb, long old_block, long *new_block)
+{
+	struct udf_sparing_data *sdata;
+	struct sparingTable *st = NULL;
+	struct sparingEntry mapEntry;
+	uint32_t packet;
+	int i, j, k, l;
+	struct udf_sb_info *sbi = UDF_SB(sb);
+	u16 reallocationTableLen;
+	struct buffer_head *bh;
+	int ret = 0;
+
+	mutex_lock(&sbi->s_alloc_mutex);
+	for (i = 0; i < sbi->s_partitions; i++) {
+		struct udf_part_map *map = &sbi->s_partmaps[i];
+		if (old_block > map->s_partition_root &&
+		    old_block < map->s_partition_root + map->s_partition_len) {
+			sdata = &map->s_type_specific.s_sparing;
+			packet = (old_block - map->s_partition_root) &
+						~(sdata->s_packet_len - 1);
+
+			for (j = 0; j < 4; j++)
+				if (sdata->s_spar_map[j] != NULL) {
+					st = (struct sparingTable *)
+						sdata->s_spar_map[j]->b_data;
+					break;
+				}
+
+			if (!st) {
+				ret = 1;
+				goto out;
+			}
+
+			reallocationTableLen =
+					le16_to_cpu(st->reallocationTableLen);
+			for (k = 0; k < reallocationTableLen; k++) {
+				struct sparingEntry *entry = &st->mapEntry[k];
+				u32 origLoc = le32_to_cpu(entry->origLocation);
+
+				if (origLoc == 0xFFFFFFFF) {
+					for (; j < 4; j++) {
+						int len;
+						bh = sdata->s_spar_map[j];
+						if (!bh)
+							continue;
+
+						st = (struct sparingTable *)
+								bh->b_data;
+						entry->origLocation =
+							cpu_to_le32(packet);
+						len =
+						  sizeof(struct sparingTable) +
+						  reallocationTableLen *
+						  sizeof(struct sparingEntry);
+						udf_update_tag((char *)st, len);
+						mark_buffer_dirty(bh);
+					}
+					*new_block = le32_to_cpu(
+							entry->mappedLocation) +
+						     ((old_block -
+							map->s_partition_root) &
+						     (sdata->s_packet_len - 1));
+					ret = 0;
+					goto out;
+				} else if (origLoc == packet) {
+					*new_block = le32_to_cpu(
+							entry->mappedLocation) +
+						     ((old_block -
+							map->s_partition_root) &
+						     (sdata->s_packet_len - 1));
+					ret = 0;
+					goto out;
+				} else if (origLoc > packet)
+					break;
+			}
+
+			for (l = k; l < reallocationTableLen; l++) {
+				struct sparingEntry *entry = &st->mapEntry[l];
+				u32 origLoc = le32_to_cpu(entry->origLocation);
+
+				if (origLoc != 0xFFFFFFFF)
+					continue;
+
+				for (; j < 4; j++) {
+					bh = sdata->s_spar_map[j];
+					if (!bh)
+						continue;
+
+					st = (struct sparingTable *)bh->b_data;
+					mapEntry = st->mapEntry[l];
+					mapEntry.origLocation =
+							cpu_to_le32(packet);
+					memmove(&st->mapEntry[k + 1],
+						&st->mapEntry[k],
+						(l - k) *
+						sizeof(struct sparingEntry));
+					st->mapEntry[k] = mapEntry;
+					udf_update_tag((char *)st,
+						sizeof(struct sparingTable) +
+						reallocationTableLen *
+						sizeof(struct sparingEntry));
+					mark_buffer_dirty(bh);
+				}
+				*new_block =
+					le32_to_cpu(
+					      st->mapEntry[k].mappedLocation) +
+					((old_block - map->s_partition_root) &
+					 (sdata->s_packet_len - 1));
+				ret = 0;
+				goto out;
+			}
+
+			ret = 1;
+			goto out;
+		} /* if old_block */
+	}
+
+	if (i == sbi->s_partitions) {
+		/* outside of partitions */
+		/* for now, fail =) */
+		ret = 1;
+	}
+
+out:
+	mutex_unlock(&sbi->s_alloc_mutex);
+	return ret;
+}
+
+static uint32_t udf_try_read_meta(struct inode *inode, uint32_t block,
+					uint16_t partition, uint32_t offset)
+{
+	struct super_block *sb = inode->i_sb;
+	struct udf_part_map *map;
+	struct kernel_lb_addr eloc;
+	uint32_t elen;
+	sector_t ext_offset;
+	struct extent_position epos = {};
+	uint32_t phyblock;
+	int8_t etype;
+	int err = 0;
+
+	err = inode_bmap(inode, block, &epos, &eloc, &elen, &ext_offset, &etype);
+	if (err <= 0 || etype != (EXT_RECORDED_ALLOCATED >> 30))
+		phyblock = 0xFFFFFFFF;
+	else {
+		map = &UDF_SB(sb)->s_partmaps[partition];
+		/* map to sparable/physical partition desc */
+		phyblock = udf_get_pblock(sb, eloc.logicalBlockNum,
+			map->s_type_specific.s_metadata.s_phys_partition_ref,
+			ext_offset + offset);
+	}
+
+	brelse(epos.bh);
+	return phyblock;
+}
+
+uint32_t udf_get_pblock_meta25(struct super_block *sb, uint32_t block,
+				uint16_t partition, uint32_t offset)
+{
+	struct udf_sb_info *sbi = UDF_SB(sb);
+	struct udf_part_map *map;
+	struct udf_meta_data *mdata;
+	uint32_t retblk;
+	struct inode *inode;
+
+	udf_debug("READING from METADATA\n");
+
+	map = &sbi->s_partmaps[partition];
+	mdata = &map->s_type_specific.s_metadata;
+	inode = mdata->s_metadata_fe ? : mdata->s_mirror_fe;
+
+	if (!inode)
+		return 0xFFFFFFFF;
+
+	retblk = udf_try_read_meta(inode, block, partition, offset);
+	if (retblk == 0xFFFFFFFF && mdata->s_metadata_fe) {
+		udf_warn(sb, "error reading from METADATA, trying to read from MIRROR\n");
+		if (!(mdata->s_flags & MF_MIRROR_FE_LOADED)) {
+			mdata->s_mirror_fe = udf_find_metadata_inode_efe(sb,
+				mdata->s_mirror_file_loc,
+				mdata->s_phys_partition_ref);
+			if (IS_ERR(mdata->s_mirror_fe))
+				mdata->s_mirror_fe = NULL;
+			mdata->s_flags |= MF_MIRROR_FE_LOADED;
+		}
+
+		inode = mdata->s_mirror_fe;
+		if (!inode)
+			return 0xFFFFFFFF;
+		retblk = udf_try_read_meta(inode, block, partition, offset);
+	}
+
+	return retblk;
+}