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/fs/exfat/cache.c b/fs/exfat/cache.c
new file mode 100644
index 000000000..7c8b4182f
--- /dev/null
+++ b/fs/exfat/cache.c
@@ -0,0 +1,357 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *  linux/fs/fat/cache.c
+ *
+ *  Written 1992,1993 by Werner Almesberger
+ *
+ *  Mar 1999. AV. Changed cache, so that it uses the starting cluster instead
+ *	of inode number.
+ *  May 1999. AV. Fixed the bogosity with FAT32 (read "FAT28"). Fscking lusers.
+ *  Copyright (C) 2012-2013 Samsung Electronics Co., Ltd.
+ */
+
+#include <linux/slab.h>
+#include <linux/unaligned.h>
+#include <linux/buffer_head.h>
+
+#include "exfat_raw.h"
+#include "exfat_fs.h"
+
+#define EXFAT_MAX_CACHE		16
+
+struct exfat_cache {
+	struct list_head cache_list;
+	unsigned int nr_contig;	/* number of contiguous clusters */
+	unsigned int fcluster;	/* cluster number in the file. */
+	unsigned int dcluster;	/* cluster number on disk. */
+};
+
+struct exfat_cache_id {
+	unsigned int id;
+	unsigned int nr_contig;
+	unsigned int fcluster;
+	unsigned int dcluster;
+};
+
+static struct kmem_cache *exfat_cachep;
+
+static void exfat_cache_init_once(void *c)
+{
+	struct exfat_cache *cache = (struct exfat_cache *)c;
+
+	INIT_LIST_HEAD(&cache->cache_list);
+}
+
+int exfat_cache_init(void)
+{
+	exfat_cachep = kmem_cache_create("exfat_cache",
+				sizeof(struct exfat_cache),
+				0, SLAB_RECLAIM_ACCOUNT,
+				exfat_cache_init_once);
+	if (!exfat_cachep)
+		return -ENOMEM;
+	return 0;
+}
+
+void exfat_cache_shutdown(void)
+{
+	if (!exfat_cachep)
+		return;
+	kmem_cache_destroy(exfat_cachep);
+}
+
+static inline struct exfat_cache *exfat_cache_alloc(void)
+{
+	return kmem_cache_alloc(exfat_cachep, GFP_NOFS);
+}
+
+static inline void exfat_cache_free(struct exfat_cache *cache)
+{
+	WARN_ON(!list_empty(&cache->cache_list));
+	kmem_cache_free(exfat_cachep, cache);
+}
+
+static inline void exfat_cache_update_lru(struct inode *inode,
+		struct exfat_cache *cache)
+{
+	struct exfat_inode_info *ei = EXFAT_I(inode);
+
+	if (ei->cache_lru.next != &cache->cache_list)
+		list_move(&cache->cache_list, &ei->cache_lru);
+}
+
+/*
+ * Find the cache that covers or precedes 'fclus' and return the last
+ * cluster before the next cache range.
+ */
+static inline unsigned int
+exfat_cache_lookup(struct inode *inode, struct exfat_cache_id *cid,
+		unsigned int fclus, unsigned int end,
+		unsigned int *cached_fclus, unsigned int *cached_dclus)
+{
+	struct exfat_inode_info *ei = EXFAT_I(inode);
+	static struct exfat_cache nohit = { .fcluster = 0, };
+	struct exfat_cache *hit = &nohit, *p;
+	unsigned int tail = 0;		/* End boundary of hit cache */
+
+	/*
+	 * Search range [fclus, end]. Stop early if:
+	 * 1. Cache covers entire range, or
+	 * 2. Next cache starts at current cache tail
+	 */
+	spin_lock(&ei->cache_lru_lock);
+	list_for_each_entry(p, &ei->cache_lru, cache_list) {
+		/* Find the cache of "fclus" or nearest cache. */
+		if (p->fcluster <= fclus) {
+			if (p->fcluster < hit->fcluster)
+				continue;
+
+			hit = p;
+			tail = hit->fcluster + hit->nr_contig;
+
+			/* Current cache covers [fclus, end] completely */
+			if (tail >= end)
+				break;
+		} else if (p->fcluster <= end) {
+			end = p->fcluster - 1;
+
+			/*
+			 * If we have a hit and next cache starts within/at
+			 * its tail, caches are contiguous, stop searching.
+			 */
+			if (tail && tail >= end)
+				break;
+		}
+	}
+	if (hit != &nohit) {
+		unsigned int offset;
+
+		exfat_cache_update_lru(inode, hit);
+		cid->id = ei->cache_valid_id;
+		cid->nr_contig = hit->nr_contig;
+		cid->fcluster = hit->fcluster;
+		cid->dcluster = hit->dcluster;
+
+		offset = min(cid->nr_contig, fclus - cid->fcluster);
+		*cached_fclus = cid->fcluster + offset;
+		*cached_dclus = cid->dcluster + offset;
+	}
+	spin_unlock(&ei->cache_lru_lock);
+
+	/* Return next cache start or 'end' if no more caches */
+	return end;
+}
+
+static struct exfat_cache *exfat_cache_merge(struct inode *inode,
+		struct exfat_cache_id *new)
+{
+	struct exfat_inode_info *ei = EXFAT_I(inode);
+	struct exfat_cache *p;
+
+	list_for_each_entry(p, &ei->cache_lru, cache_list) {
+		/* Find the same part as "new" in cluster-chain. */
+		if (p->fcluster == new->fcluster) {
+			if (new->nr_contig > p->nr_contig)
+				p->nr_contig = new->nr_contig;
+			return p;
+		}
+	}
+	return NULL;
+}
+
+static void exfat_cache_add(struct inode *inode,
+		struct exfat_cache_id *new)
+{
+	struct exfat_inode_info *ei = EXFAT_I(inode);
+	struct exfat_cache *cache, *tmp;
+
+	if (new->fcluster == EXFAT_EOF_CLUSTER) /* dummy cache */
+		return;
+
+	spin_lock(&ei->cache_lru_lock);
+	if (new->id != EXFAT_CACHE_VALID &&
+	    new->id != ei->cache_valid_id)
+		goto unlock;	/* this cache was invalidated */
+
+	cache = exfat_cache_merge(inode, new);
+	if (cache == NULL) {
+		if (ei->nr_caches < EXFAT_MAX_CACHE) {
+			ei->nr_caches++;
+			spin_unlock(&ei->cache_lru_lock);
+
+			tmp = exfat_cache_alloc();
+			if (!tmp) {
+				spin_lock(&ei->cache_lru_lock);
+				ei->nr_caches--;
+				spin_unlock(&ei->cache_lru_lock);
+				return;
+			}
+
+			spin_lock(&ei->cache_lru_lock);
+			cache = exfat_cache_merge(inode, new);
+			if (cache != NULL) {
+				ei->nr_caches--;
+				exfat_cache_free(tmp);
+				goto out_update_lru;
+			}
+			cache = tmp;
+		} else {
+			struct list_head *p = ei->cache_lru.prev;
+
+			cache = list_entry(p,
+					struct exfat_cache, cache_list);
+		}
+		cache->fcluster = new->fcluster;
+		cache->dcluster = new->dcluster;
+		cache->nr_contig = new->nr_contig;
+	}
+out_update_lru:
+	exfat_cache_update_lru(inode, cache);
+unlock:
+	spin_unlock(&ei->cache_lru_lock);
+}
+
+/*
+ * Cache invalidation occurs rarely, thus the LRU chain is not updated. It
+ * fixes itself after a while.
+ */
+static void __exfat_cache_inval_inode(struct inode *inode)
+{
+	struct exfat_inode_info *ei = EXFAT_I(inode);
+	struct exfat_cache *cache;
+
+	while (!list_empty(&ei->cache_lru)) {
+		cache = list_entry(ei->cache_lru.next,
+				   struct exfat_cache, cache_list);
+		list_del_init(&cache->cache_list);
+		ei->nr_caches--;
+		exfat_cache_free(cache);
+	}
+	/* Update. The copy of caches before this id is discarded. */
+	ei->cache_valid_id++;
+	if (ei->cache_valid_id == EXFAT_CACHE_VALID)
+		ei->cache_valid_id++;
+}
+
+void exfat_cache_inval_inode(struct inode *inode)
+{
+	struct exfat_inode_info *ei = EXFAT_I(inode);
+
+	spin_lock(&ei->cache_lru_lock);
+	__exfat_cache_inval_inode(inode);
+	spin_unlock(&ei->cache_lru_lock);
+}
+
+static inline int cache_contiguous(struct exfat_cache_id *cid,
+		unsigned int dclus)
+{
+	cid->nr_contig++;
+	return cid->dcluster + cid->nr_contig == dclus;
+}
+
+static inline void cache_init(struct exfat_cache_id *cid,
+		unsigned int fclus, unsigned int dclus)
+{
+	cid->id = EXFAT_CACHE_VALID;
+	cid->fcluster = fclus;
+	cid->dcluster = dclus;
+	cid->nr_contig = 0;
+}
+
+int exfat_get_cluster(struct inode *inode, unsigned int cluster,
+		unsigned int *dclus, unsigned int *count,
+		unsigned int *last_dclus)
+{
+	struct super_block *sb = inode->i_sb;
+	struct exfat_inode_info *ei = EXFAT_I(inode);
+	struct buffer_head *bh = NULL;
+	struct exfat_cache_id cid;
+	unsigned int content, fclus;
+	unsigned int end = cluster + *count - 1;
+
+	if (ei->start_clu == EXFAT_FREE_CLUSTER) {
+		exfat_fs_error(sb,
+			"invalid access to exfat cache (entry 0x%08x)",
+			ei->start_clu);
+		return -EIO;
+	}
+
+	fclus = 0;
+	*dclus = ei->start_clu;
+	*last_dclus = *dclus;
+
+	/*
+	 * This case should not exist, as exfat_map_cluster function doesn't
+	 * call this routine when start_clu == EXFAT_EOF_CLUSTER.
+	 * This case is retained here for routine completeness.
+	 */
+	if (*dclus == EXFAT_EOF_CLUSTER) {
+		*count = 0;
+		return 0;
+	}
+
+	/* If only the first cluster is needed, return now. */
+	if (fclus == cluster && *count == 1)
+		return 0;
+
+	cache_init(&cid, fclus, *dclus);
+	/*
+	 * Update the 'end' to exclude the next cache range, as clusters in
+	 * different cache are typically not contiguous.
+	 */
+	end = exfat_cache_lookup(inode, &cid, cluster, end, &fclus, dclus);
+
+	/* Return if the cache covers the entire range. */
+	if (cid.fcluster + cid.nr_contig >= end) {
+		*count = end - cluster + 1;
+		return 0;
+	}
+
+	/* Find the first cluster we need. */
+	while (fclus < cluster) {
+		if (exfat_ent_get(sb, *dclus, &content, &bh))
+			return -EIO;
+
+		*last_dclus = *dclus;
+		*dclus = content;
+		fclus++;
+
+		if (content == EXFAT_EOF_CLUSTER)
+			break;
+
+		if (!cache_contiguous(&cid, *dclus))
+			cache_init(&cid, fclus, *dclus);
+	}
+
+	/*
+	 * Now the cid cache contains the first cluster requested, collect
+	 * the remaining clusters of this contiguous extent.
+	 */
+	if (*dclus != EXFAT_EOF_CLUSTER) {
+		unsigned int clu = *dclus;
+
+		while (fclus < end) {
+			if (exfat_ent_get(sb, clu, &content, &bh))
+				return -EIO;
+			if (++clu != content)
+				break;
+			fclus++;
+		}
+		cid.nr_contig = fclus - cid.fcluster;
+		*count = fclus - cluster + 1;
+
+		/*
+		 * Cache this discontiguous cluster, we'll definitely need
+		 * it later
+		 */
+		if (fclus < end && content != EXFAT_EOF_CLUSTER) {
+			exfat_cache_add(inode, &cid);
+			cache_init(&cid, fclus + 1, content);
+		}
+	} else {
+		*count = 0;
+	}
+	brelse(bh);
+	exfat_cache_add(inode, &cid);
+	return 0;
+}