Skip to contentSkip to conversation

5.15.154-rc1 review

PATCH In review Greg Kroah-Hartman 8 participants 702 messages Apr 8, 2024 – Apr 10, 2024 Page 6 of 7

Subsystems (8)
lore
Share & tools
lore
author maintainer
#540 lore raw

PATCH 536/690 nfsd: allow reaping files still under writeback

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jeff Layton <[email protected]>

[ Upstream commit dcb779fcd4ed5984ad15991d574943d12a8693d1 ]

On most filesystems, there is no reason to delay reaping an nfsd_file just because its underlying inode is still under writeback. nfsd just relies on client activity or the local flusher threads to do writeback.

The main exception is NFS, which flushes all of its dirty data on last close. Add a new EXPORT_OP_FLUSH_ON_CLOSE flag to allow filesystems to signal that they do this, and only skip closing files under writeback on such filesystems.

Also, remove a redundant NULL file pointer check in nfsd_file_check_writeback, and clean up nfs's export op flag definitions.

[ cel: adjusted to apply to v5.15.y ]
---
 fs/nfs/export.c          |  9 ++++++---
 fs/nfsd/filecache.c      | 12 +++++++++++-
 include/linux/exportfs.h |  1 +
 3 files changed, 18 insertions(+), 4 deletions(-)
fs/nfs/export.c +6 -3
index 37a1a88df7717..eafa9d7b0911b 100644
@@ -178,7 +178,10 @@ const struct export_operations nfs_export_ops = {
 	.fh_to_dentry = nfs_fh_to_dentry,
 	.get_parent = nfs_get_parent,
 	.fetch_iversion = nfs_fetch_iversion,
-	.flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK|
-		EXPORT_OP_CLOSE_BEFORE_UNLINK|EXPORT_OP_REMOTE_FS|
-		EXPORT_OP_NOATOMIC_ATTR,
+	.flags = EXPORT_OP_NOWCC		|
+		 EXPORT_OP_NOSUBTREECHK		|
+		 EXPORT_OP_CLOSE_BEFORE_UNLINK	|
+		 EXPORT_OP_REMOTE_FS		|
+		 EXPORT_OP_NOATOMIC_ATTR	|
+		 EXPORT_OP_FLUSH_ON_CLOSE,
 };
fs/nfsd/filecache.c +11 -1
index 1d4c0387c4192..080d796547854 100644
@@ -401,13 +401,23 @@ nfsd_file_check_writeback(struct nfsd_file *nf)
 	struct file *file = nf->nf_file;
 	struct address_space *mapping;
 
-	if (!file || !(file->f_mode & FMODE_WRITE))
+	/* File not open for write? */
+	if (!(file->f_mode & FMODE_WRITE))
 		return false;
+
+	/*
+	 * Some filesystems (e.g. NFS) flush all dirty data on close.
+	 * On others, there is no need to wait for writeback.
+	 */
+	if (!(file_inode(file)->i_sb->s_export_op->flags & EXPORT_OP_FLUSH_ON_CLOSE))
+		return false;
+
 	mapping = file->f_mapping;
 	return mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) ||
 		mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK);
 }
 
+
 static bool nfsd_file_lru_add(struct nfsd_file *nf)
 {
 	set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags);
include/linux/exportfs.h +1 -0
index fe848901fcc3a..218fc5c54e901 100644
@@ -221,6 +221,7 @@ struct export_operations {
 #define EXPORT_OP_NOATOMIC_ATTR		(0x10) /* Filesystem cannot supply
 						  atomic attribute updates
 						*/
+#define EXPORT_OP_FLUSH_ON_CLOSE	(0x20) /* fs flushes file data on close */
 	unsigned long	flags;
 };
 
Signature · 1 line
2.43.0
author maintainer
#541 lore raw

PATCH 537/690 NFSD: Convert filecache to rhltable

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chuck Lever <[email protected]>

[ Upstream commit c4c649ab413ba6a785b25f0edbb12f617c87db2a ]

While we were converting the nfs4_file hashtable to use the kernel's resizable hashtable data structure, Neil Brown observed that the list variant (rhltable) would be better for managing nfsd_file items as well. The nfsd_file hash table will contain multiple entries for the same inode -- these should be kept together on a list. And, it could be possible for exotic or malicious client behavior to cause the hash table to resize itself on every insertion.

A nice simplification is that rhltable_lookup() can return a list that contains only nfsd_file items that match a given inode, which enables us to eliminate specialized hash table helper functions and use the default functions provided by the rhashtable implementation).

Since we are now storing nfsd_file items for the same inode on a single list, that effectively reduces the number of hash entries that have to be tracked in the hash table. The mininum bucket count is therefore lowered.

Light testing with fstests generic/531 show no regressions.

---
 fs/nfsd/filecache.c | 311 ++++++++++++++++++--------------------------
 fs/nfsd/filecache.h |   9 +-
 2 files changed, 133 insertions(+), 187 deletions(-)
fs/nfsd/filecache.c +128 -183
index 080d796547854..52e67ec267965 100644
@@ -73,70 +73,9 @@ static struct list_lru			nfsd_file_lru;
 static unsigned long			nfsd_file_flags;
 static struct fsnotify_group		*nfsd_file_fsnotify_group;
 static struct delayed_work		nfsd_filecache_laundrette;
-static struct rhashtable		nfsd_file_rhash_tbl
+static struct rhltable			nfsd_file_rhltable
 						____cacheline_aligned_in_smp;
 
-enum nfsd_file_lookup_type {
-	NFSD_FILE_KEY_INODE,
-	NFSD_FILE_KEY_FULL,
-};
-
-struct nfsd_file_lookup_key {
-	struct inode			*inode;
-	struct net			*net;
-	const struct cred		*cred;
-	unsigned char			need;
-	bool				gc;
-	enum nfsd_file_lookup_type	type;
-};
-
-/*
- * The returned hash value is based solely on the address of an in-code
- * inode, a pointer to a slab-allocated object. The entropy in such a
- * pointer is concentrated in its middle bits.
- */
-static u32 nfsd_file_inode_hash(const struct inode *inode, u32 seed)
-{
-	unsigned long ptr = (unsigned long)inode;
-	u32 k;
-
-	k = ptr >> L1_CACHE_SHIFT;
-	k &= 0x00ffffff;
-	return jhash2(&k, 1, seed);
-}
-
-/**
- * nfsd_file_key_hashfn - Compute the hash value of a lookup key
- * @data: key on which to compute the hash value
- * @len: rhash table's key_len parameter (unused)
- * @seed: rhash table's random seed of the day
- *
- * Return value:
- *   Computed 32-bit hash value
- */
-static u32 nfsd_file_key_hashfn(const void *data, u32 len, u32 seed)
-{
-	const struct nfsd_file_lookup_key *key = data;
-
-	return nfsd_file_inode_hash(key->inode, seed);
-}
-
-/**
- * nfsd_file_obj_hashfn - Compute the hash value of an nfsd_file
- * @data: object on which to compute the hash value
- * @len: rhash table's key_len parameter (unused)
- * @seed: rhash table's random seed of the day
- *
- * Return value:
- *   Computed 32-bit hash value
- */
-static u32 nfsd_file_obj_hashfn(const void *data, u32 len, u32 seed)
-{
-	const struct nfsd_file *nf = data;
-
-	return nfsd_file_inode_hash(nf->nf_inode, seed);
-}
-
 static bool
 nfsd_match_cred(const struct cred *c1, const struct cred *c2)
 {
@@ -157,55 +96,16 @@ nfsd_match_cred(const struct cred *c1, const struct cred *c2)
 	return true;
 }
 
-/**
- * nfsd_file_obj_cmpfn - Match a cache item against search criteria
- * @arg: search criteria
- * @ptr: cache item to check
- *
- * Return values:
- *   %0 - Item matches search criteria
- *   %1 - Item does not match search criteria
- */
-static int nfsd_file_obj_cmpfn(struct rhashtable_compare_arg *arg,
-			       const void *ptr)
-{
-	const struct nfsd_file_lookup_key *key = arg->key;
-	const struct nfsd_file *nf = ptr;
-
-	switch (key->type) {
-	case NFSD_FILE_KEY_INODE:
-		if (test_bit(NFSD_FILE_GC, &nf->nf_flags) != key->gc)
-			return 1;
-		if (nf->nf_inode != key->inode)
-			return 1;
-		break;
-	case NFSD_FILE_KEY_FULL:
-		if (nf->nf_inode != key->inode)
-			return 1;
-		if (nf->nf_may != key->need)
-			return 1;
-		if (nf->nf_net != key->net)
-			return 1;
-		if (!nfsd_match_cred(nf->nf_cred, key->cred))
-			return 1;
-		if (test_bit(NFSD_FILE_GC, &nf->nf_flags) != key->gc)
-			return 1;
-		if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0)
-			return 1;
-		break;
-	}
-	return 0;
-}
-
 static const struct rhashtable_params nfsd_file_rhash_params = {
 	.key_len		= sizeof_field(struct nfsd_file, nf_inode),
 	.key_offset		= offsetof(struct nfsd_file, nf_inode),
-	.head_offset		= offsetof(struct nfsd_file, nf_rhash),
-	.hashfn			= nfsd_file_key_hashfn,
-	.obj_hashfn		= nfsd_file_obj_hashfn,
-	.obj_cmpfn		= nfsd_file_obj_cmpfn,
-	/* Reduce resizing churn on light workloads */
-	.min_size		= 512,		/* buckets */
+	.head_offset		= offsetof(struct nfsd_file, nf_rlist),
+
+	/*
+	 * Start with a single page hash table to reduce resizing churn
+	 * on light workloads.
+	 */
+	.min_size		= 256,
 	.automatic_shrinking	= true,
 };
 
@@ -308,27 +208,27 @@ nfsd_file_mark_find_or_create(struct nfsd_file *nf, struct inode *inode)
 }
 
 static struct nfsd_file *
-nfsd_file_alloc(struct nfsd_file_lookup_key *key, unsigned int may)
+nfsd_file_alloc(struct net *net, struct inode *inode, unsigned char need,
+		bool want_gc)
 {
 	struct nfsd_file *nf;
 
 	nf = kmem_cache_alloc(nfsd_file_slab, GFP_KERNEL);
-	if (nf) {
-		INIT_LIST_HEAD(&nf->nf_lru);
-		nf->nf_birthtime = ktime_get();
-		nf->nf_file = NULL;
-		nf->nf_cred = get_current_cred();
-		nf->nf_net = key->net;
-		nf->nf_flags = 0;
-		__set_bit(NFSD_FILE_HASHED, &nf->nf_flags);
-		__set_bit(NFSD_FILE_PENDING, &nf->nf_flags);
-		if (key->gc)
-			__set_bit(NFSD_FILE_GC, &nf->nf_flags);
-		nf->nf_inode = key->inode;
-		refcount_set(&nf->nf_ref, 1);
-		nf->nf_may = key->need;
-		nf->nf_mark = NULL;
-	}
+	if (unlikely(!nf))
+		return NULL;
+
+	INIT_LIST_HEAD(&nf->nf_lru);
+	nf->nf_birthtime = ktime_get();
+	nf->nf_file = NULL;
+	nf->nf_cred = get_current_cred();
+	nf->nf_net = net;
+	nf->nf_flags = want_gc ?
+		BIT(NFSD_FILE_HASHED) | BIT(NFSD_FILE_PENDING) | BIT(NFSD_FILE_GC) :
+		BIT(NFSD_FILE_HASHED) | BIT(NFSD_FILE_PENDING);
+	nf->nf_inode = inode;
+	refcount_set(&nf->nf_ref, 1);
+	nf->nf_may = need;
+	nf->nf_mark = NULL;
 	return nf;
 }
 
@@ -353,8 +253,8 @@ static void
 nfsd_file_hash_remove(struct nfsd_file *nf)
 {
 	trace_nfsd_file_unhash(nf);
-	rhashtable_remove_fast(&nfsd_file_rhash_tbl, &nf->nf_rhash,
-			       nfsd_file_rhash_params);
+	rhltable_remove(&nfsd_file_rhltable, &nf->nf_rlist,
+			nfsd_file_rhash_params);
 }
 
 static bool
@@ -687,8 +587,8 @@ nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose)
  * @inode:   inode on which to close out nfsd_files
  * @dispose: list on which to gather nfsd_files to close out
  *
- * An nfsd_file represents a struct file being held open on behalf of nfsd. An
- * open file however can block other activity (such as leases), or cause
+ * An nfsd_file represents a struct file being held open on behalf of nfsd.
+ * An open file however can block other activity (such as leases), or cause
  * undesirable behavior (e.g. spurious silly-renames when reexporting NFS).
  *
  * This function is intended to find open nfsd_files when this sort of
@@ -701,21 +601,17 @@ nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose)
 static void
 nfsd_file_queue_for_close(struct inode *inode, struct list_head *dispose)
 {
-	struct nfsd_file_lookup_key key = {
-		.type	= NFSD_FILE_KEY_INODE,
-		.inode	= inode,
-		.gc	= true,
-	};
+	struct rhlist_head *tmp, *list;
 	struct nfsd_file *nf;
 
 	rcu_read_lock();
-	do {
-		nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key,
-				       nfsd_file_rhash_params);
-		if (!nf)
-			break;
+	list = rhltable_lookup(&nfsd_file_rhltable, &inode,
+			       nfsd_file_rhash_params);
+	rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) {
+		if (!test_bit(NFSD_FILE_GC, &nf->nf_flags))
+			continue;
 		nfsd_file_cond_queue(nf, dispose);
-	} while (1);
+	}
 	rcu_read_unlock();
 }
 
@@ -839,7 +735,7 @@ nfsd_file_cache_init(void)
 	if (test_and_set_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags) == 1)
 		return 0;
 
-	ret = rhashtable_init(&nfsd_file_rhash_tbl, &nfsd_file_rhash_params);
+	ret = rhltable_init(&nfsd_file_rhltable, &nfsd_file_rhash_params);
 	if (ret)
 		return ret;
 
@@ -907,7 +803,7 @@ nfsd_file_cache_init(void)
 	nfsd_file_mark_slab = NULL;
 	destroy_workqueue(nfsd_filecache_wq);
 	nfsd_filecache_wq = NULL;
-	rhashtable_destroy(&nfsd_file_rhash_tbl);
+	rhltable_destroy(&nfsd_file_rhltable);
 	goto out;
 }
 
@@ -926,7 +822,7 @@ __nfsd_file_cache_purge(struct net *net)
 	struct nfsd_file *nf;
 	LIST_HEAD(dispose);
 
-	rhashtable_walk_enter(&nfsd_file_rhash_tbl, &iter);
+	rhltable_walk_enter(&nfsd_file_rhltable, &iter);
 	do {
 		rhashtable_walk_start(&iter);
 
@@ -1032,7 +928,7 @@ nfsd_file_cache_shutdown(void)
 	nfsd_file_mark_slab = NULL;
 	destroy_workqueue(nfsd_filecache_wq);
 	nfsd_filecache_wq = NULL;
-	rhashtable_destroy(&nfsd_file_rhash_tbl);
+	rhltable_destroy(&nfsd_file_rhltable);
 
 	for_each_possible_cpu(i) {
 		per_cpu(nfsd_file_cache_hits, i) = 0;
@@ -1043,6 +939,35 @@ nfsd_file_cache_shutdown(void)
 	}
 }
 
+static struct nfsd_file *
+nfsd_file_lookup_locked(const struct net *net, const struct cred *cred,
+			struct inode *inode, unsigned char need,
+			bool want_gc)
+{
+	struct rhlist_head *tmp, *list;
+	struct nfsd_file *nf;
+
+	list = rhltable_lookup(&nfsd_file_rhltable, &inode,
+			       nfsd_file_rhash_params);
+	rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist) {
+		if (nf->nf_may != need)
+			continue;
+		if (nf->nf_net != net)
+			continue;
+		if (!nfsd_match_cred(nf->nf_cred, cred))
+			continue;
+		if (test_bit(NFSD_FILE_GC, &nf->nf_flags) != want_gc)
+			continue;
+		if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0)
+			continue;
+
+		if (!nfsd_file_get(nf))
+			continue;
+		return nf;
+	}
+	return NULL;
+}
+
 /**
  * nfsd_file_is_cached - are there any cached open files for this inode?
  * @inode: inode to check
@@ -1057,16 +982,20 @@ nfsd_file_cache_shutdown(void)
 bool
 nfsd_file_is_cached(struct inode *inode)
 {
-	struct nfsd_file_lookup_key key = {
-		.type	= NFSD_FILE_KEY_INODE,
-		.inode	= inode,
-		.gc	= true,
-	};
+	struct rhlist_head *tmp, *list;
+	struct nfsd_file *nf;
 	bool ret = false;
 
-	if (rhashtable_lookup_fast(&nfsd_file_rhash_tbl, &key,
-				   nfsd_file_rhash_params) != NULL)
-		ret = true;
+	rcu_read_lock();
+	list = rhltable_lookup(&nfsd_file_rhltable, &inode,
+			       nfsd_file_rhash_params);
+	rhl_for_each_entry_rcu(nf, tmp, list, nf_rlist)
+		if (test_bit(NFSD_FILE_GC, &nf->nf_flags)) {
+			ret = true;
+			break;
+		}
+	rcu_read_unlock();
+
 	trace_nfsd_file_is_cached(inode, (int)ret);
 	return ret;
 }
@@ -1076,14 +1005,12 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		     unsigned int may_flags, struct file *file,
 		     struct nfsd_file **pnf, bool want_gc)
 {
-	struct nfsd_file_lookup_key key = {
-		.type	= NFSD_FILE_KEY_FULL,
-		.need	= may_flags & NFSD_FILE_MAY_MASK,
-		.net	= SVC_NET(rqstp),
-		.gc	= want_gc,
-	};
+	unsigned char need = may_flags & NFSD_FILE_MAY_MASK;
+	struct net *net = SVC_NET(rqstp);
+	struct nfsd_file *new, *nf;
+	const struct cred *cred;
 	bool open_retry = true;
-	struct nfsd_file *nf;
+	struct inode *inode;
 	__be32 status;
 	int ret;
 
@@ -1091,14 +1018,12 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 				may_flags|NFSD_MAY_OWNER_OVERRIDE);
 	if (status != nfs_ok)
 		return status;
-	key.inode = d_inode(fhp->fh_dentry);
-	key.cred = get_current_cred();
+	inode = d_inode(fhp->fh_dentry);
+	cred = get_current_cred();
 
 retry:
 	rcu_read_lock();
-	nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key,
-			       nfsd_file_rhash_params);
-	nf = nfsd_file_get(nf);
+	nf = nfsd_file_lookup_locked(net, cred, inode, need, want_gc);
 	rcu_read_unlock();
 
 	if (nf) {
@@ -1112,21 +1037,32 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		goto wait_for_construction;
 	}
 
-	nf = nfsd_file_alloc(&key, may_flags);
-	if (!nf) {
+	new = nfsd_file_alloc(net, inode, need, want_gc);
+	if (!new) {
 		status = nfserr_jukebox;
 		goto out;
 	}
 
-	ret = rhashtable_lookup_insert_key(&nfsd_file_rhash_tbl,
-					   &key, &nf->nf_rhash,
-					   nfsd_file_rhash_params);
+	rcu_read_lock();
+	spin_lock(&inode->i_lock);
+	nf = nfsd_file_lookup_locked(net, cred, inode, need, want_gc);
+	if (unlikely(nf)) {
+		spin_unlock(&inode->i_lock);
+		rcu_read_unlock();
+		nfsd_file_slab_free(&new->nf_rcu);
+		goto wait_for_construction;
+	}
+	nf = new;
+	ret = rhltable_insert(&nfsd_file_rhltable, &nf->nf_rlist,
+			      nfsd_file_rhash_params);
+	spin_unlock(&inode->i_lock);
+	rcu_read_unlock();
 	if (likely(ret == 0))
 		goto open_file;
 
 	if (ret == -EEXIST)
 		goto retry;
-	trace_nfsd_file_insert_err(rqstp, key.inode, may_flags, ret);
+	trace_nfsd_file_insert_err(rqstp, inode, may_flags, ret);
 	status = nfserr_jukebox;
 	goto construction_err;
 
@@ -1135,7 +1071,7 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 
 	/* Did construction of this file fail? */
 	if (!test_bit(NFSD_FILE_HASHED, &nf->nf_flags)) {
-		trace_nfsd_file_cons_err(rqstp, key.inode, may_flags, nf);
+		trace_nfsd_file_cons_err(rqstp, inode, may_flags, nf);
 		if (!open_retry) {
 			status = nfserr_jukebox;
 			goto construction_err;
@@ -1157,13 +1093,13 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		nfsd_file_check_write_error(nf);
 		*pnf = nf;
 	}
-	put_cred(key.cred);
-	trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status);
+	put_cred(cred);
+	trace_nfsd_file_acquire(rqstp, inode, may_flags, nf, status);
 	return status;
 
 open_file:
 	trace_nfsd_file_alloc(nf);
-	nf->nf_mark = nfsd_file_mark_find_or_create(nf, key.inode);
+	nf->nf_mark = nfsd_file_mark_find_or_create(nf, inode);
 	if (nf->nf_mark) {
 		if (file) {
 			get_file(file);
@@ -1181,7 +1117,7 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	 * If construction failed, or we raced with a call to unlink()
 	 * then unhash.
 	 */
-	if (status == nfs_ok && key.inode->i_nlink == 0)
+	if (status != nfs_ok || inode->i_nlink == 0)
 		status = nfserr_jukebox;
 	if (status != nfs_ok)
 		nfsd_file_unhash(nf);
@@ -1208,8 +1144,11 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
  * seconds after the final nfsd_file_put() in case the caller
  * wants to re-use it.
  *
- * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in
- * network byte order is returned.
+ * Return values:
+ *   %nfs_ok - @pnf points to an nfsd_file with its reference
+ *   count boosted.
+ *
+ * On error, an nfsstat value in network byte order is returned.
  */
 __be32
 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp,
@@ -1229,8 +1168,11 @@ nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp,
  * but not garbage-collected. The object is unhashed after the
  * final nfsd_file_put().
  *
- * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in
- * network byte order is returned.
+ * Return values:
+ *   %nfs_ok - @pnf points to an nfsd_file with its reference
+ *   count boosted.
+ *
+ * On error, an nfsstat value in network byte order is returned.
  */
 __be32
 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
@@ -1251,8 +1193,11 @@ nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
  * and @file is non-NULL, use it to instantiate a new nfsd_file instead of
  * opening a new one.
  *
- * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in
- * network byte order is returned.
+ * Return values:
+ *   %nfs_ok - @pnf points to an nfsd_file with its reference
+ *   count boosted.
+ *
+ * On error, an nfsstat value in network byte order is returned.
  */
 __be32
 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp,
@@ -1283,7 +1228,7 @@ int nfsd_file_cache_stats_show(struct seq_file *m, void *v)
 		lru = list_lru_count(&nfsd_file_lru);
 
 		rcu_read_lock();
-		ht = &nfsd_file_rhash_tbl;
+		ht = &nfsd_file_rhltable.ht;
 		count = atomic_read(&ht->nelems);
 		tbl = rht_dereference_rcu(ht->tbl, ht);
 		buckets = tbl->size;
@@ -1299,7 +1244,7 @@ int nfsd_file_cache_stats_show(struct seq_file *m, void *v)
 		evictions += per_cpu(nfsd_file_evictions, i);
 	}
 
-	seq_printf(m, "total entries: %u\n", count);
+	seq_printf(m, "total inodes:  %u\n", count);
 	seq_printf(m, "hash buckets:  %u\n", buckets);
 	seq_printf(m, "lru entries:   %lu\n", lru);
 	seq_printf(m, "cache hits:    %lu\n", hits);
fs/nfsd/filecache.h +5 -4
index 41516a4263ea5..e54165a3224f0 100644
@@ -29,9 +29,8 @@ struct nfsd_file_mark {
  * never be dereferenced, only used for comparison.
  */
 struct nfsd_file {
-	struct rhash_head	nf_rhash;
-	struct list_head	nf_lru;
-	struct rcu_head		nf_rcu;
+	struct rhlist_head	nf_rlist;
+	void			*nf_inode;
 	struct file		*nf_file;
 	const struct cred	*nf_cred;
 	struct net		*nf_net;
@@ -40,10 +39,12 @@ struct nfsd_file {
 #define NFSD_FILE_REFERENCED	(2)
 #define NFSD_FILE_GC		(3)
 	unsigned long		nf_flags;
-	struct inode		*nf_inode;	/* don't deref */
 	refcount_t		nf_ref;
 	unsigned char		nf_may;
+
 	struct nfsd_file_mark	*nf_mark;
+	struct list_head	nf_lru;
+	struct rcu_head		nf_rcu;
 	ktime_t			nf_birthtime;
 };
 
Signature · 1 line
2.43.0
author maintainer
#542 lore raw

PATCH 538/690 nfsd: simplify the delayed disposal list code

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jeff Layton <[email protected]>

[ Upstream commit 92e4a6733f922f0fef1d0995f7b2d0eaff86c7ea ]

When queueing a dispose list to the appropriate "freeme" lists, it pointlessly queues the objects one at a time to an intermediate list.

Remove a few helpers and just open code a list_move to make it more clear and efficient. Better document the resulting functions with kerneldoc comments.

---
 fs/nfsd/filecache.c | 64 ++++++++++++++++-----------------------------
 1 file changed, 22 insertions(+), 42 deletions(-)
fs/nfsd/filecache.c +22 -42
index 52e67ec267965..6b8706f23eaf0 100644
@@ -401,49 +401,26 @@ nfsd_file_dispose_list(struct list_head *dispose)
 	}
 }
 
-static void
-nfsd_file_list_remove_disposal(struct list_head *dst,
-		struct nfsd_fcache_disposal *l)
-{
-	spin_lock(&l->lock);
-	list_splice_init(&l->freeme, dst);
-	spin_unlock(&l->lock);
-}
-
-static void
-nfsd_file_list_add_disposal(struct list_head *files, struct net *net)
-{
-	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
-	struct nfsd_fcache_disposal *l = nn->fcache_disposal;
-
-	spin_lock(&l->lock);
-	list_splice_tail_init(files, &l->freeme);
-	spin_unlock(&l->lock);
-	queue_work(nfsd_filecache_wq, &l->work);
-}
-
-static void
-nfsd_file_list_add_pernet(struct list_head *dst, struct list_head *src,
-		struct net *net)
-{
-	struct nfsd_file *nf, *tmp;
-
-	list_for_each_entry_safe(nf, tmp, src, nf_lru) {
-		if (nf->nf_net == net)
-			list_move_tail(&nf->nf_lru, dst);
-	}
-}
-
+/**
+ * nfsd_file_dispose_list_delayed - move list of dead files to net's freeme list
+ * @dispose: list of nfsd_files to be disposed
+ *
+ * Transfers each file to the "freeme" list for its nfsd_net, to eventually
+ * be disposed of by the per-net garbage collector.
+ */
 static void
 nfsd_file_dispose_list_delayed(struct list_head *dispose)
 {
-	LIST_HEAD(list);
-	struct nfsd_file *nf;
-
 	while(!list_empty(dispose)) {
-		nf = list_first_entry(dispose, struct nfsd_file, nf_lru);
-		nfsd_file_list_add_pernet(&list, dispose, nf->nf_net);
-		nfsd_file_list_add_disposal(&list, nf->nf_net);
+		struct nfsd_file *nf = list_first_entry(dispose,
+						struct nfsd_file, nf_lru);
+		struct nfsd_net *nn = net_generic(nf->nf_net, nfsd_net_id);
+		struct nfsd_fcache_disposal *l = nn->fcache_disposal;
+
+		spin_lock(&l->lock);
+		list_move_tail(&nf->nf_lru, &l->freeme);
+		spin_unlock(&l->lock);
+		queue_work(nfsd_filecache_wq, &l->work);
 	}
 }
 
@@ -664,8 +641,8 @@ nfsd_file_close_inode_sync(struct inode *inode)
  * nfsd_file_delayed_close - close unused nfsd_files
  * @work: dummy
  *
- * Walk the LRU list and destroy any entries that have not been used since
- * the last scan.
+ * Scrape the freeme list for this nfsd_net, and then dispose of them
+ * all.
  */
 static void
 nfsd_file_delayed_close(struct work_struct *work)
@@ -674,7 +651,10 @@ nfsd_file_delayed_close(struct work_struct *work)
 	struct nfsd_fcache_disposal *l = container_of(work,
 			struct nfsd_fcache_disposal, work);
 
-	nfsd_file_list_remove_disposal(&head, l);
+	spin_lock(&l->lock);
+	list_splice_init(&l->freeme, &head);
+	spin_unlock(&l->lock);
+
 	nfsd_file_dispose_list(&head);
 }
 
Signature · 1 line
2.43.0
author maintainer
#543 lore raw

PATCH 539/690 NFSD: Fix problem of COMMIT and NFS4ERR_DELAY in infinite loop

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dai Ngo <[email protected]>

[ Upstream commit 147abcacee33781e75588869e944ddb07528a897 ]

The following request sequence to the same file causes the NFS client and server getting into an infinite loop with COMMIT and NFS4ERR_DELAY:

OPEN
REMOVE
WRITE
COMMIT

Problem reported by recall11, recall12, recall14, recall20, recall22, recall40, recall42, recall48, recall50 of nfstest suite.

This patch restores the handling of race condition in nfsd_file_do_acquire with unlink to that prior of the regression.

Fixes ac3a2585f018 ("nfsd: rework refcounting in filecache")
---
 fs/nfsd/filecache.c | 2 --
 1 file changed, 2 deletions(-)
fs/nfsd/filecache.c +0 -2
index 6b8706f23eaf0..615ea8324911e 100644
@@ -1098,8 +1098,6 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	 * then unhash.
 	 */
 	if (status != nfs_ok || inode->i_nlink == 0)
-		status = nfserr_jukebox;
-	if (status != nfs_ok)
 		nfsd_file_unhash(nf);
 	clear_and_wake_up_bit(NFSD_FILE_PENDING, &nf->nf_flags);
 	if (status == nfs_ok)
Signature · 1 line
2.43.0
author maintainer
#544 lore raw

PATCH 540/690 nfsd: make a copy of struct iattr before calling notify_change

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jeff Layton <[email protected]>

[ Upstream commit d53d70084d27f56bcdf5074328f2c9ec861be596 ]

notify_change can modify the iattr structure. In particular it can end up setting ATTR_MODE when ATTR_KILL_SUID is already set, causing a BUG() if the same iattr is passed to notify_change more than once.

Make a copy of the struct iattr before calling notify_change.

Fixes 34b91dda7124 ("NFSD: Make nfsd4_setattr() wait before returning NFS4ERR_DELAY")
---
 fs/nfsd/vfs.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)
fs/nfsd/vfs.c +9 -1
index 71788a5e4a55c..76ce19d42336f 100644
@@ -533,7 +533,15 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 
 	inode_lock(inode);
 	for (retries = 1;;) {
-		host_err = __nfsd_setattr(dentry, iap);
+		struct iattr attrs;
+
+		/*
+		 * notify_change() can alter its iattr argument, making
+		 * @iap unsuitable for submission multiple times. Make a
+		 * copy for every loop iteration.
+		 */
+		attrs = *iap;
+		host_err = __nfsd_setattr(dentry, &attrs);
 		if (host_err != -EAGAIN || !retries--)
 			break;
 		if (!nfsd_wait_for_delegreturn(rqstp, inode))
Signature · 1 line
2.43.0
author maintainer
#545 lore raw

PATCH 541/690 nfsd: fix double fget() bug in __write_ports_addfd()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dan Carpenter <[email protected]>

[ Upstream commit c034203b6a9dae6751ef4371c18cb77983e30c28 ]

The bug here is that you cannot rely on getting the same socket from multiple calls to fget() because userspace can influence that. This is a kind of double fetch bug.

The fix is to delete the svc_alien_sock() function and instead do the checking inside the svc_addsock() function.

Fixes 3064639423c4 ("nfsd: check passed socket's net matches NFSd superblock's one")
---
 fs/nfsd/nfsctl.c               |  7 +------
 include/linux/sunrpc/svcsock.h |  7 +++----
 net/sunrpc/svcsock.c           | 24 ++++++------------------
 3 files changed, 10 insertions(+), 28 deletions(-)
fs/nfsd/nfsctl.c +1 -6
index c2577ee7ffb22..76a60e7a75097 100644
@@ -714,16 +714,11 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred
 	if (err != 0 || fd < 0)
 		return -EINVAL;
 
-	if (svc_alien_sock(net, fd)) {
-		printk(KERN_ERR "%s: socket net is different to NFSd's one\n", __func__);
-		return -EINVAL;
-	}
-
 	err = nfsd_create_serv(net);
 	if (err != 0)
 		return err;
 
-	err = svc_addsock(nn->nfsd_serv, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred);
+	err = svc_addsock(nn->nfsd_serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred);
 
 	if (err >= 0 &&
 	    !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
include/linux/sunrpc/svcsock.h +3 -4
index bcc555c7ae9c6..13aff355d5a13 100644
@@ -59,10 +59,9 @@ int		svc_recv(struct svc_rqst *, long);
 int		svc_send(struct svc_rqst *);
 void		svc_drop(struct svc_rqst *);
 void		svc_sock_update_bufs(struct svc_serv *serv);
-bool		svc_alien_sock(struct net *net, int fd);
-int		svc_addsock(struct svc_serv *serv, const int fd,
-					char *name_return, const size_t len,
-					const struct cred *cred);
+int		svc_addsock(struct svc_serv *serv, struct net *net,
+			    const int fd, char *name_return, const size_t len,
+			    const struct cred *cred);
 void		svc_init_xprt_sock(void);
 void		svc_cleanup_xprt_sock(void);
 struct svc_xprt *svc_sock_create(struct svc_serv *serv, int prot);
net/sunrpc/svcsock.c +6 -18
index be7081284a098..112236dd72901 100644
@@ -1334,25 +1334,10 @@ static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 	return svsk;
 }
 
-bool svc_alien_sock(struct net *net, int fd)
-{
-	int err;
-	struct socket *sock = sockfd_lookup(fd, &err);
-	bool ret = false;
-
-	if (!sock)
-		goto out;
-	if (sock_net(sock->sk) != net)
-		ret = true;
-	sockfd_put(sock);
-out:
-	return ret;
-}
-EXPORT_SYMBOL_GPL(svc_alien_sock);
-
 /**
  * svc_addsock - add a listener socket to an RPC service
  * @serv: pointer to RPC service to which to add a new listener
+ * @net: caller's network namespace
  * @fd: file descriptor of the new listener
  * @name_return: pointer to buffer to fill in with name of listener
  * @len: size of the buffer
@@ -1362,8 +1347,8 @@ EXPORT_SYMBOL_GPL(svc_alien_sock);
  * Name is terminated with '\n'.  On error, returns a negative errno
  * value.
  */
-int svc_addsock(struct svc_serv *serv, const int fd, char *name_return,
-		const size_t len, const struct cred *cred)
+int svc_addsock(struct svc_serv *serv, struct net *net, const int fd,
+		char *name_return, const size_t len, const struct cred *cred)
 {
 	int err = 0;
 	struct socket *so = sockfd_lookup(fd, &err);
@@ -1374,6 +1359,9 @@ int svc_addsock(struct svc_serv *serv, const int fd, char *name_return,
 
 	if (!so)
 		return err;
+	err = -EINVAL;
+	if (sock_net(so->sk) != net)
+		goto out;
 	err = -EAFNOSUPPORT;
 	if ((so->sk->sk_family != PF_INET) && (so->sk->sk_family != PF_INET6))
 		goto out;
Signature · 1 line
2.43.0
author maintainer
#546 lore raw

PATCH 542/690 lockd: drop inappropriate svc_get() from locked_get()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: NeilBrown <[email protected]>

[ Upstream commit 665e89ab7c5af1f2d260834c861a74b01a30f95f ]

The below-mentioned patch was intended to simplify refcounting on the svc_serv used by locked. The goal was to only ever have a single reference from the single thread. To that end we dropped a call to lockd_start_svc() (except when creating thread) which would take a reference, and dropped the svc_put(serv) that would drop that reference.

Unfortunately we didn't also remove the svc_get() from lockd_create_svc() in the case where the svc_serv already existed. So after the patch:
- on the first call the svc_serv was allocated and the one reference was given to the thread, so there are no extra references
- on subsequent calls svc_get() was called so there is now an extra reference.
This is clearly not consistent.

The inconsistency is also clear in the current code in lockd_get() takes *two* references, one on nlmsvc_serv and one by incrementing
nlmsvc_users. This clearly does not match lockd_put().

So: drop that svc_get() from lockd_get() (which used to be in lockd_create_svc().

Fixes b73a2972041b ("lockd: move lockd_start_svc() call into lockd_create_svc()")
---
 fs/lockd/svc.c | 1 -
 1 file changed, 1 deletion(-)
fs/lockd/svc.c +0 -1
index 59ef8a1f843f3..5579e67da17db 100644
@@ -355,7 +355,6 @@ static int lockd_get(void)
 	int error;
 
 	if (nlmsvc_serv) {
-		svc_get(nlmsvc_serv);
 		nlmsvc_users++;
 		return 0;
 	}
Signature · 1 line
2.43.0
author maintainer
#547 lore raw

PATCH 543/690 NFSD: Add an nfsd4_encode_nfstime4() helper

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chuck Lever <[email protected]>

[ Upstream commit 262176798b18b12fd8ab84c94cfece0a6a652476 ]

Clean up: de-duplicate some common code.

---
 fs/nfsd/nfs4xdr.c | 46 ++++++++++++++++++++++++++--------------------
 1 file changed, 26 insertions(+), 20 deletions(-)
fs/nfsd/nfs4xdr.c +26 -20
index 30c64c3f5fa05..c40876daf60c0 100644
@@ -2542,6 +2542,20 @@ static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode,
 	return p;
 }
 
+static __be32 nfsd4_encode_nfstime4(struct xdr_stream *xdr,
+				    struct timespec64 *tv)
+{
+	__be32 *p;
+
+	p = xdr_reserve_space(xdr, XDR_UNIT * 3);
+	if (!p)
+		return nfserr_resource;
+
+	p = xdr_encode_hyper(p, (s64)tv->tv_sec);
+	*p = cpu_to_be32(tv->tv_nsec);
+	return nfs_ok;
+}
+
 /*
  * ctime (in NFSv4, time_metadata) is not writeable, and the client
  * doesn't really care what resolution could theoretically be stored by
@@ -3347,11 +3361,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 		p = xdr_encode_hyper(p, dummy64);
 	}
 	if (bmval1 & FATTR4_WORD1_TIME_ACCESS) {
-		p = xdr_reserve_space(xdr, 12);
-		if (!p)
-			goto out_resource;
-		p = xdr_encode_hyper(p, (s64)stat.atime.tv_sec);
-		*p++ = cpu_to_be32(stat.atime.tv_nsec);
+		status = nfsd4_encode_nfstime4(xdr, &stat.atime);
+		if (status)
+			goto out;
 	}
 	if (bmval1 & FATTR4_WORD1_TIME_DELTA) {
 		p = xdr_reserve_space(xdr, 12);
@@ -3360,25 +3372,19 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 		p = encode_time_delta(p, d_inode(dentry));
 	}
 	if (bmval1 & FATTR4_WORD1_TIME_METADATA) {
-		p = xdr_reserve_space(xdr, 12);
-		if (!p)
-			goto out_resource;
-		p = xdr_encode_hyper(p, (s64)stat.ctime.tv_sec);
-		*p++ = cpu_to_be32(stat.ctime.tv_nsec);
+		status = nfsd4_encode_nfstime4(xdr, &stat.ctime);
+		if (status)
+			goto out;
 	}
 	if (bmval1 & FATTR4_WORD1_TIME_MODIFY) {
-		p = xdr_reserve_space(xdr, 12);
-		if (!p)
-			goto out_resource;
-		p = xdr_encode_hyper(p, (s64)stat.mtime.tv_sec);
-		*p++ = cpu_to_be32(stat.mtime.tv_nsec);
+		status = nfsd4_encode_nfstime4(xdr, &stat.mtime);
+		if (status)
+			goto out;
 	}
 	if (bmval1 & FATTR4_WORD1_TIME_CREATE) {
-		p = xdr_reserve_space(xdr, 12);
-		if (!p)
-			goto out_resource;
-		p = xdr_encode_hyper(p, (s64)stat.btime.tv_sec);
-		*p++ = cpu_to_be32(stat.btime.tv_nsec);
+		status = nfsd4_encode_nfstime4(xdr, &stat.btime);
+		if (status)
+			goto out;
 	}
 	if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) {
 		u64 ino = stat.ino;
Signature · 1 line
2.43.0
author maintainer
#548 lore raw

PATCH 544/690 nfsd: Fix creation time serialization order

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tavian Barnes <[email protected]>

[ Upstream commit d7dbed457c2ef83709a2a2723a2d58de43623449 ]

In nfsd4_encode_fattr(), TIME_CREATE was being written out after all other times. However, they should be written out in an order that matches the bit flags in bmval1, which in this case are

    #define FATTR4_WORD1_TIME_ACCESS        (1UL << 15)
    #define FATTR4_WORD1_TIME_CREATE        (1UL << 18)
    #define FATTR4_WORD1_TIME_DELTA         (1UL << 19)
    #define FATTR4_WORD1_TIME_METADATA      (1UL << 20)
    #define FATTR4_WORD1_TIME_MODIFY        (1UL << 21)

so TIME_CREATE should come second.

I noticed this on a FreeBSD NFSv4.2 client, which supports creation times. On this client, file times were weirdly permuted. With this patch applied on the server, times looked normal on the client.

Fixes e377a3e698fb ("nfsd: Add support for the birth time attribute")
---
 fs/nfsd/nfs4xdr.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)
fs/nfsd/nfs4xdr.c +5 -5
index c40876daf60c0..5b95499a1f344 100644
@@ -3365,6 +3365,11 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 		if (status)
 			goto out;
 	}
+	if (bmval1 & FATTR4_WORD1_TIME_CREATE) {
+		status = nfsd4_encode_nfstime4(xdr, &stat.btime);
+		if (status)
+			goto out;
+	}
 	if (bmval1 & FATTR4_WORD1_TIME_DELTA) {
 		p = xdr_reserve_space(xdr, 12);
 		if (!p)
@@ -3381,11 +3386,6 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 		if (status)
 			goto out;
 	}
-	if (bmval1 & FATTR4_WORD1_TIME_CREATE) {
-		status = nfsd4_encode_nfstime4(xdr, &stat.btime);
-		if (status)
-			goto out;
-	}
 	if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) {
 		u64 ino = stat.ino;
 
Signature · 1 line
2.43.0
author maintainer
#549 lore raw

PATCH 545/690 nfsd: dont allow nfsd threads to be signalled.

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: NeilBrown <[email protected]>

[ Upstream commit 3903902401451b1cd9d797a8c79769eb26ac7fe5 ]

The original implementation of nfsd used signals to stop threads during shutdown.
In Linux 2.3.46pre5 nfsd gained the ability to shutdown threads internally it if was asked to run "0" threads. After this user-space transitioned to using "rpc.nfsd 0" to stop nfsd and sending signals to threads was no longer an important part of the API.

In commit 3ebdbe5203a8 ("SUNRPC: discard svo_setup and rename svc_set_num_threads_sync()") (v5.17-rc1~75^2~41) we finally removed the use of signals for stopping threads, using kthread_stop() instead.

This patch makes the "obvious" next step and removes the ability to signal nfsd threads - or any svc threads. nfsd stops allowing signals and we don't check for their delivery any more.

This will allow for some simplification in later patches.

A change worth noting is in nfsd4_ssc_setup_dul(). There was previously a signal_pending() check which would only succeed when the thread was being shut down. It should really have tested kthread_should_stop() as well. Now it just does the latter, not the former.

---
 fs/nfs/callback.c     |  9 +--------
 fs/nfsd/nfs4proc.c    |  5 ++---
 fs/nfsd/nfssvc.c      | 12 ------------
 net/sunrpc/svc_xprt.c | 16 ++++++----------
 4 files changed, 9 insertions(+), 33 deletions(-)
fs/nfs/callback.c +1 -8
index 456af7d230cf1..46a0a2d6962e1 100644
@@ -80,9 +80,6 @@ nfs4_callback_svc(void *vrqstp)
 	set_freezable();
 
 	while (!kthread_freezable_should_stop(NULL)) {
-
-		if (signal_pending(current))
-			flush_signals(current);
 		/*
 		 * Listen for a request on the socket
 		 */
@@ -112,11 +109,7 @@ nfs41_callback_svc(void *vrqstp)
 	set_freezable();
 
 	while (!kthread_freezable_should_stop(NULL)) {
-
-		if (signal_pending(current))
-			flush_signals(current);
-
-		prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE);
+		prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_IDLE);
 		spin_lock_bh(&serv->sv_cb_lock);
 		if (!list_empty(&serv->sv_cb_list)) {
 			req = list_first_entry(&serv->sv_cb_list,
fs/nfsd/nfs4proc.c +2 -3
index ba53cd89ec62c..b6d768bd5ccca 100644
@@ -1313,12 +1313,11 @@ static __be32 nfsd4_ssc_setup_dul(struct nfsd_net *nn, char *ipaddr,
 		/* found a match */
 		if (ni->nsui_busy) {
 			/*  wait - and try again */
-			prepare_to_wait(&nn->nfsd_ssc_waitq, &wait,
-				TASK_INTERRUPTIBLE);
+			prepare_to_wait(&nn->nfsd_ssc_waitq, &wait, TASK_IDLE);
 			spin_unlock(&nn->nfsd_ssc_lock);
 
 			/* allow 20secs for mount/unmount for now - revisit */
-			if (signal_pending(current) ||
+			if (kthread_should_stop() ||
 					(schedule_timeout(20*HZ) == 0)) {
 				finish_wait(&nn->nfsd_ssc_waitq, &wait);
 				kfree(work);
fs/nfsd/nfssvc.c +0 -12
index a0ecec54d3d7d..8063fab2c0279 100644
@@ -952,15 +952,6 @@ nfsd(void *vrqstp)
 
 	current->fs->umask = 0;
 
-	/*
-	 * thread is spawned with all signals set to SIG_IGN, re-enable
-	 * the ones that will bring down the thread
-	 */
-	allow_signal(SIGKILL);
-	allow_signal(SIGHUP);
-	allow_signal(SIGINT);
-	allow_signal(SIGQUIT);
-
 	atomic_inc(&nfsdstats.th_cnt);
 
 	set_freezable();
@@ -985,9 +976,6 @@ nfsd(void *vrqstp)
 		validate_process_creds();
 	}
 
-	/* Clear signals before calling svc_exit_thread() */
-	flush_signals(current);
-
 	atomic_dec(&nfsdstats.th_cnt);
 
 out:
net/sunrpc/svc_xprt.c +6 -10
index 67ccf1a6459ae..b19592673eef2 100644
@@ -700,8 +700,8 @@ static int svc_alloc_arg(struct svc_rqst *rqstp)
 			/* Made progress, don't sleep yet */
 			continue;
 
-		set_current_state(TASK_INTERRUPTIBLE);
-		if (signalled() || kthread_should_stop()) {
+		set_current_state(TASK_IDLE);
+		if (kthread_should_stop()) {
 			set_current_state(TASK_RUNNING);
 			return -EINTR;
 		}
@@ -736,7 +736,7 @@ rqst_should_sleep(struct svc_rqst *rqstp)
 		return false;
 
 	/* are we shutting down? */
-	if (signalled() || kthread_should_stop())
+	if (kthread_should_stop())
 		return false;
 
 	/* are we freezing? */
@@ -758,11 +758,7 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
 	if (rqstp->rq_xprt)
 		goto out_found;
 
-	/*
-	 * We have to be able to interrupt this wait
-	 * to bring down the daemons ...
-	 */
-	set_current_state(TASK_INTERRUPTIBLE);
+	set_current_state(TASK_IDLE);
 	smp_mb__before_atomic();
 	clear_bit(SP_CONGESTED, &pool->sp_flags);
 	clear_bit(RQ_BUSY, &rqstp->rq_flags);
@@ -784,7 +780,7 @@ static struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
 	if (!time_left)
 		atomic_long_inc(&pool->sp_stats.threads_timedout);
 
-	if (signalled() || kthread_should_stop())
+	if (kthread_should_stop())
 		return ERR_PTR(-EINTR);
 	return ERR_PTR(-EAGAIN);
 out_found:
@@ -882,7 +878,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 	try_to_freeze();
 	cond_resched();
 	err = -EINTR;
-	if (signalled() || kthread_should_stop())
+	if (kthread_should_stop())
 		goto out;
 
 	xprt = svc_get_next_xprt(rqstp, timeout);
Signature · 1 line
2.43.0
author maintainer
#550 lore raw

PATCH 546/690 nfsd: Simplify code around svc_exit_thread() call in nfsd()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: NeilBrown <[email protected]>

[ Upstream commit 18e4cf915543257eae2925671934937163f5639b ]

Previously a thread could exit asynchronously (due to a signal) so some care was needed to hold nfsd_mutex over the last svc_put() call. Now a thread can only exit when svc_set_num_threads() is called, and this is always called under nfsd_mutex. So no care is needed.

Not only is the mutex held when a thread exits now, but the svc refcount is elevated, so the svc_put() in svc_exit_thread() will never be a final put, so the mutex isn't even needed at this point in the code.

---
 fs/nfsd/nfssvc.c           | 23 -----------------------
 include/linux/sunrpc/svc.h | 13 -------------
 2 files changed, 36 deletions(-)
fs/nfsd/nfssvc.c +0 -23
index 8063fab2c0279..8907dba22c3f2 100644
@@ -979,31 +979,8 @@ nfsd(void *vrqstp)
 	atomic_dec(&nfsdstats.th_cnt);
 
 out:
-	/* Take an extra ref so that the svc_put in svc_exit_thread()
-	 * doesn't call svc_destroy()
-	 */
-	svc_get(nn->nfsd_serv);
-
 	/* Release the thread */
 	svc_exit_thread(rqstp);
-
-	/* We need to drop a ref, but may not drop the last reference
-	 * without holding nfsd_mutex, and we cannot wait for nfsd_mutex as that
-	 * could deadlock with nfsd_shutdown_threads() waiting for us.
-	 * So three options are:
-	 * - drop a non-final reference,
-	 * - get the mutex without waiting
-	 * - sleep briefly andd try the above again
-	 */
-	while (!svc_put_not_last(nn->nfsd_serv)) {
-		if (mutex_trylock(&nfsd_mutex)) {
-			nfsd_put(net);
-			mutex_unlock(&nfsd_mutex);
-			break;
-		}
-		msleep(20);
-	}
-
 	return 0;
 }
 
include/linux/sunrpc/svc.h +0 -13
index 53405c282209f..6e48c1c88f1bb 100644
@@ -123,19 +123,6 @@ static inline void svc_put(struct svc_serv *serv)
 	kref_put(&serv->sv_refcnt, svc_destroy);
 }
 
-/**
- * svc_put_not_last - decrement non-final reference count on SUNRPC serv
- * @serv:  the svc_serv to have count decremented
- *
- * Returns: %true is refcount was decremented.
- *
- * If the refcount is 1, it is not decremented and instead failure is reported.
- */
-static inline bool svc_put_not_last(struct svc_serv *serv)
-{
-	return refcount_dec_not_one(&serv->sv_refcnt.refcount);
-}
-
 /*
  * Maximum payload size supported by a kernel RPC server.
  * This is use to determine the max number of pages nfsd is
Signature · 1 line
2.43.0
author maintainer
#551 lore raw

PATCH 547/690 nfsd: separate nfsd_last_thread() from nfsd_put()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: NeilBrown <[email protected]>

[ Upstream commit 9f28a971ee9fdf1bf8ce8c88b103f483be610277 ]

Now that the last nfsd thread is stopped by an explicit act of calling svc_set_num_threads() with a count of zero, we only have a limited number of places that can happen, and don't need to call nfsd_last_thread() in nfsd_put()

So separate that out and call it at the two places where the number of threads is set to zero.

Move the clearing of ->nfsd_serv and the call to svc_xprt_destroy_all() into nfsd_last_thread(), as they are really part of the same action.

nfsd_put() is now a thin wrapper around svc_put(), so make it a static inline.

nfsd_put() cannot be called after nfsd_last_thread(), so in a couple of places we have to use svc_put() instead.

---
 fs/nfsd/nfsd.h   |  7 ++++++-
 fs/nfsd/nfssvc.c | 52 ++++++++++++++++++------------------------------
 2 files changed, 25 insertions(+), 34 deletions(-)
fs/nfsd/nfsd.h +6 -1
index fa0144a742678..867dcfd64d426 100644
@@ -96,7 +96,12 @@ int		nfsd_pool_stats_open(struct inode *, struct file *);
 int		nfsd_pool_stats_release(struct inode *, struct file *);
 void		nfsd_shutdown_threads(struct net *net);
 
-void		nfsd_put(struct net *net);
+static inline void nfsd_put(struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	svc_put(nn->nfsd_serv);
+}
 
 bool		i_am_nfsd(void);
 
fs/nfsd/nfssvc.c +19 -33

114 lines not on this page · raw message

Signature · 1 line
2.43.0
author maintainer
#552 lore raw

PATCH 548/690 Documentation: Add missing documentation for EXPORT_OP flags

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chuck Lever <[email protected]>

[ Upstream commit b38a6023da6a12b561f0421c6a5a1f7624a1529c ]

The commits that introduced these flags neglected to update the Documentation/filesystems/nfs/exporting.rst file.

---
 Documentation/filesystems/nfs/exporting.rst | 26 +++++++++++++++++++++
 1 file changed, 26 insertions(+)
Documentation/filesystems/nfs/exporting.rst +26 -0
index 0e98edd353b5f..6f59a364f84cd 100644
@@ -215,3 +215,29 @@ following flags are defined:
     This flag causes nfsd to close any open files for this inode _before_
     calling into the vfs to do an unlink or a rename that would replace
     an existing file.
+
+  EXPORT_OP_REMOTE_FS - Backing storage for this filesystem is remote
+    PF_LOCAL_THROTTLE exists for loopback NFSD, where a thread needs to
+    write to one bdi (the final bdi) in order to free up writes queued
+    to another bdi (the client bdi). Such threads get a private balance
+    of dirty pages so that dirty pages for the client bdi do not imact
+    the daemon writing to the final bdi. For filesystems whose durable
+    storage is not local (such as exported NFS filesystems), this
+    constraint has negative consequences. EXPORT_OP_REMOTE_FS enables
+    an export to disable writeback throttling.
+
+  EXPORT_OP_NOATOMIC_ATTR - Filesystem does not update attributes atomically
+    EXPORT_OP_NOATOMIC_ATTR indicates that the exported filesystem
+    cannot provide the semantics required by the "atomic" boolean in
+    NFSv4's change_info4. This boolean indicates to a client whether the
+    returned before and after change attributes were obtained atomically
+    with the respect to the requested metadata operation (UNLINK,
+    OPEN/CREATE, MKDIR, etc).
+
+  EXPORT_OP_FLUSH_ON_CLOSE - Filesystem flushes file data on close(2)
+    On most filesystems, inodes can remain under writeback after the
+    file is closed. NFSD relies on client activity or local flusher
+    threads to handle writeback. Certain filesystems, such as NFS, flush
+    all of an inode's dirty data on last close. Exports that behave this
+    way should set EXPORT_OP_FLUSH_ON_CLOSE so that NFSD knows to skip
+    waiting for writeback when closing such files.
Signature · 1 line
2.43.0
author maintainer
#553 lore raw

PATCH 549/690 NFSD: fix possible oops when nfsd/pool_stats is closed.

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: NeilBrown <[email protected]>

[ Upstream commit 88956eabfdea7d01d550535af120d4ef265b1d02 ]

If /proc/fs/nfsd/pool_stats is open when the last nfsd thread exits, then when the file is closed a NULL pointer is dereferenced.
This is because nfsd_pool_stats_release() assumes that the pointer to the svc_serv cannot become NULL while a reference is held.

This used to be the case but a recent patch split nfsd_last_thread() out from nfsd_put(), and clearing the pointer is done in nfsd_last_thread().

This is easily reproduced by running
rpc.nfsd 8 ; ( rpc.nfsd 0;true) < /proc/fs/nfsd/pool_stats

Fortunately nfsd_pool_stats_release() has easy access to the svc_serv pointer, and so can call svc_put() on it directly.

Fixes 9f28a971ee9f ("nfsd: separate nfsd_last_thread() from nfsd_put()")
---
 fs/nfsd/nfssvc.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
fs/nfsd/nfssvc.c +3 -2
index ee5713fca1870..2a1dd580dfb94 100644
@@ -1084,11 +1084,12 @@ int nfsd_pool_stats_open(struct inode *inode, struct file *file)
 
 int nfsd_pool_stats_release(struct inode *inode, struct file *file)
 {
+	struct seq_file *seq = file->private_data;
+	struct svc_serv *serv = seq->private;
 	int ret = seq_release(inode, file);
-	struct net *net = inode->i_sb->s_fs_info;
 
 	mutex_lock(&nfsd_mutex);
-	nfsd_put(net);
+	svc_put(serv);
 	mutex_unlock(&nfsd_mutex);
 	return ret;
 }
Signature · 1 line
2.43.0
author maintainer
#554 lore raw

PATCH 550/690 lockd: introduce safe async lock op

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alexander Aring <[email protected]>

[ Upstream commit 2dd10de8e6bcbacf85ad758b904543c294820c63 ]

This patch reverts mostly commit 40595cdc93ed ("nfs: block notification on fs with its own ->lock") and introduces an EXPORT_OP_ASYNC_LOCK export flag to signal that the "own ->lock" implementation supports async lock requests. The only main user is DLM that is used by GFS2 and OCFS2 filesystem. Those implement their own lock() implementation and return FILE_LOCK_DEFERRED as return value. Since commit 40595cdc93ed ("nfs: block notification on fs with its own ->lock") the DLM implementation were never updated. This patch should prepare for DLM to set the EXPORT_OP_ASYNC_LOCK export flag and update the DLM plock implementation regarding to it.

---
 Documentation/filesystems/nfs/exporting.rst |  7 +++++++
 fs/lockd/svclock.c                          |  4 +---
 fs/nfsd/nfs4state.c                         | 10 +++++++---
 include/linux/exportfs.h                    | 14 ++++++++++++++
 4 files changed, 29 insertions(+), 6 deletions(-)
Documentation/filesystems/nfs/exporting.rst +7 -0
index 6f59a364f84cd..6a1cbd7de38df 100644
@@ -241,3 +241,10 @@ following flags are defined:
     all of an inode's dirty data on last close. Exports that behave this
     way should set EXPORT_OP_FLUSH_ON_CLOSE so that NFSD knows to skip
     waiting for writeback when closing such files.
+
+  EXPORT_OP_ASYNC_LOCK - Indicates a capable filesystem to do async lock
+    requests from lockd. Only set EXPORT_OP_ASYNC_LOCK if the filesystem has
+    it's own ->lock() functionality as core posix_lock_file() implementation
+    has no async lock request handling yet. For more information about how to
+    indicate an async lock request from a ->lock() file_operations struct, see
+    fs/locks.c and comment for the function vfs_lock_file().
fs/lockd/svclock.c +1 -3
index 4e30f3c509701..55c0a03311884 100644
@@ -470,9 +470,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 	    struct nlm_host *host, struct nlm_lock *lock, int wait,
 	    struct nlm_cookie *cookie, int reclaim)
 {
-#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 	struct inode		*inode = nlmsvc_file_inode(file);
-#endif
 	struct nlm_block	*block = NULL;
 	int			error;
 	int			mode;
@@ -486,7 +484,7 @@ nlmsvc_lock(struct svc_rqst *rqstp, struct nlm_file *file,
 				(long long)lock->fl.fl_end,
 				wait);
 
-	if (nlmsvc_file_file(file)->f_op->lock) {
+	if (!exportfs_lock_op_is_async(inode->i_sb->s_export_op)) {
 		async_block = wait;
 		wait = 0;
 	}
fs/nfsd/nfs4state.c +7 -3
index 69bc4622a95a4..4d95b2052c31a 100644
@@ -7424,6 +7424,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	struct nfsd4_blocked_lock *nbl = NULL;
 	struct file_lock *file_lock = NULL;
 	struct file_lock *conflock = NULL;
+	struct super_block *sb;
 	__be32 status = 0;
 	int lkflg;
 	int err;
@@ -7445,6 +7446,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		dprintk("NFSD: nfsd4_lock: permission denied!\n");
 		return status;
 	}
+	sb = cstate->current_fh.fh_dentry->d_sb;
 
 	if (lock->lk_is_new) {
 		if (nfsd4_has_session(cstate))
@@ -7496,7 +7498,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	fp = lock_stp->st_stid.sc_file;
 	switch (lock->lk_type) {
 		case NFS4_READW_LT:
-			if (nfsd4_has_session(cstate))
+			if (nfsd4_has_session(cstate) ||
+			    exportfs_lock_op_is_async(sb->s_export_op))
 				fl_flags |= FL_SLEEP;
 			fallthrough;
 		case NFS4_READ_LT:
@@ -7508,7 +7511,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			fl_type = F_RDLCK;
 			break;
 		case NFS4_WRITEW_LT:
-			if (nfsd4_has_session(cstate))
+			if (nfsd4_has_session(cstate) ||
+			    exportfs_lock_op_is_async(sb->s_export_op))
 				fl_flags |= FL_SLEEP;
 			fallthrough;
 		case NFS4_WRITE_LT:
@@ -7536,7 +7540,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	 * for file locks), so don't attempt blocking lock notifications
 	 * on those filesystems:
 	 */
-	if (nf->nf_file->f_op->lock)
+	if (!exportfs_lock_op_is_async(sb->s_export_op))
 		fl_flags &= ~FL_SLEEP;
 
 	nbl = find_or_allocate_block(lock_sop, &fp->fi_fhandle, nn);
include/linux/exportfs.h +14 -0
index 218fc5c54e901..6525f4b7eb97f 100644
@@ -222,9 +222,23 @@ struct export_operations {
 						  atomic attribute updates
 						*/
 #define EXPORT_OP_FLUSH_ON_CLOSE	(0x20) /* fs flushes file data on close */
+#define EXPORT_OP_ASYNC_LOCK		(0x40) /* fs can do async lock request */
 	unsigned long	flags;
 };
 
+/**
+ * exportfs_lock_op_is_async() - export op supports async lock operation
+ * @export_ops:	the nfs export operations to check
+ *
+ * Returns true if the nfs export_operations structure has
+ * EXPORT_OP_ASYNC_LOCK in their flags set
+ */
+static inline bool
+exportfs_lock_op_is_async(const struct export_operations *export_ops)
+{
+	return export_ops->flags & EXPORT_OP_ASYNC_LOCK;
+}
+
 extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,
 				    int *max_len, struct inode *parent);
 extern int exportfs_encode_fh(struct dentry *dentry, struct fid *fid,
Signature · 1 line
2.43.0
author maintainer
#555 lore raw

PATCH 551/690 nfsd: call nfsd_last_thread() before final nfsd_put()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: NeilBrown <[email protected]>

[ Upstream commit 2a501f55cd641eb4d3c16a2eab0d678693fac663 ]

If write_ports_addfd or write_ports_addxprt fail, they call nfsd_put() without calling nfsd_last_thread(). This leaves nn->nfsd_serv pointing to a structure that has been freed.

So remove 'static' from nfsd_last_thread() and call it when the nfsd_serv is about to be destroyed.

Fixes ec52361df99b ("SUNRPC: stop using ->sv_nrthreads as a refcount")
---
 fs/nfsd/nfsctl.c | 9 +++++++--
 fs/nfsd/nfsd.h   | 1 +
 fs/nfsd/nfssvc.c | 2 +-
 3 files changed, 9 insertions(+), 3 deletions(-)
fs/nfsd/nfsctl.c +7 -2
index 76a60e7a75097..eec442edb6556 100644
@@ -720,8 +720,10 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred
 
 	err = svc_addsock(nn->nfsd_serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred);
 
-	if (err >= 0 &&
-	    !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
+	if (err < 0 && !nn->nfsd_serv->sv_nrthreads && !nn->keep_active)
+		nfsd_last_thread(net);
+	else if (err >= 0 &&
+		 !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
 		svc_get(nn->nfsd_serv);
 
 	nfsd_put(net);
@@ -771,6 +773,9 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr
 		svc_xprt_put(xprt);
 	}
 out_err:
+	if (!nn->nfsd_serv->sv_nrthreads && !nn->keep_active)
+		nfsd_last_thread(net);
+
 	nfsd_put(net);
 	return err;
 }
fs/nfsd/nfsd.h +1 -0
index 867dcfd64d426..3796015dc7656 100644
@@ -138,6 +138,7 @@ int nfsd_vers(struct nfsd_net *nn, int vers, enum vers_op change);
 int nfsd_minorversion(struct nfsd_net *nn, u32 minorversion, enum vers_op change);
 void nfsd_reset_versions(struct nfsd_net *nn);
 int nfsd_create_serv(struct net *net);
+void nfsd_last_thread(struct net *net);
 
 extern int nfsd_max_blksize;
 
fs/nfsd/nfssvc.c +1 -1
index 2a1dd580dfb94..3d4fd40c987bd 100644
@@ -529,7 +529,7 @@ static struct notifier_block nfsd_inet6addr_notifier = {
 /* Only used under nfsd_mutex, so this atomic may be overkill: */
 static atomic_t nfsd_notifier_refcount = ATOMIC_INIT(0);
 
-static void nfsd_last_thread(struct net *net)
+void nfsd_last_thread(struct net *net)
 {
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	struct svc_serv *serv = nn->nfsd_serv;
Signature · 1 line
2.43.0
author maintainer
#556 lore raw

PATCH 552/690 nfsd: drop the nfsd_put helper

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jeff Layton <[email protected]>

[ Upstream commit 64e6304169f1e1f078e7f0798033f80a7fb0ea46 ]

It's not safe to call nfsd_put once nfsd_last_thread has been called, as that function will zero out the nn->nfsd_serv pointer.

Drop the nfsd_put helper altogether and open-code the svc_put in its callers instead. That allows us to not be reliant on the value of that pointer when handling an error.

Fixes 2a501f55cd64 ("nfsd: call nfsd_last_thread() before final nfsd_put()")
Cc NeilBrown <[email protected]>
---
 fs/nfsd/nfsctl.c | 31 +++++++++++++++++--------------
 fs/nfsd/nfsd.h   |  7 -------
 2 files changed, 17 insertions(+), 21 deletions(-)
fs/nfsd/nfsctl.c +17 -14
index eec442edb6556..f77f00c931723 100644
@@ -709,6 +709,7 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred
 	char *mesg = buf;
 	int fd, err;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct svc_serv *serv;
 
 	err = get_int(&mesg, &fd);
 	if (err != 0 || fd < 0)
@@ -718,15 +719,15 @@ static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred
 	if (err != 0)
 		return err;
 
-	err = svc_addsock(nn->nfsd_serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred);
+	serv = nn->nfsd_serv;
+	err = svc_addsock(serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred);
 
-	if (err < 0 && !nn->nfsd_serv->sv_nrthreads && !nn->keep_active)
+	if (err < 0 && !serv->sv_nrthreads && !nn->keep_active)
 		nfsd_last_thread(net);
-	else if (err >= 0 &&
-		 !nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
-		svc_get(nn->nfsd_serv);
+	else if (err >= 0 && !serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
+		svc_get(serv);
 
-	nfsd_put(net);
+	svc_put(serv);
 	return err;
 }
 
@@ -740,6 +741,7 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr
 	struct svc_xprt *xprt;
 	int port, err;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct svc_serv *serv;
 
 	if (sscanf(buf, "%15s %5u", transport, &port) != 2)
 		return -EINVAL;
@@ -751,32 +753,33 @@ static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cr
 	if (err != 0)
 		return err;
 
-	err = svc_xprt_create(nn->nfsd_serv, transport, net,
+	serv = nn->nfsd_serv;
+	err = svc_xprt_create(serv, transport, net,
 			      PF_INET, port, SVC_SOCK_ANONYMOUS, cred);
 	if (err < 0)
 		goto out_err;
 
-	err = svc_xprt_create(nn->nfsd_serv, transport, net,
+	err = svc_xprt_create(serv, transport, net,
 			      PF_INET6, port, SVC_SOCK_ANONYMOUS, cred);
 	if (err < 0 && err != -EAFNOSUPPORT)
 		goto out_close;
 
-	if (!nn->nfsd_serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
-		svc_get(nn->nfsd_serv);
+	if (!serv->sv_nrthreads && !xchg(&nn->keep_active, 1))
+		svc_get(serv);
 
-	nfsd_put(net);
+	svc_put(serv);
 	return 0;
 out_close:
-	xprt = svc_find_xprt(nn->nfsd_serv, transport, net, PF_INET, port);
+	xprt = svc_find_xprt(serv, transport, net, PF_INET, port);
 	if (xprt != NULL) {
 		svc_xprt_close(xprt);
 		svc_xprt_put(xprt);
 	}
 out_err:
-	if (!nn->nfsd_serv->sv_nrthreads && !nn->keep_active)
+	if (!serv->sv_nrthreads && !nn->keep_active)
 		nfsd_last_thread(net);
 
-	nfsd_put(net);
+	svc_put(serv);
 	return err;
 }
 
fs/nfsd/nfsd.h +0 -7
index 3796015dc7656..013bfa24ced21 100644
@@ -96,13 +96,6 @@ int		nfsd_pool_stats_open(struct inode *, struct file *);
 int		nfsd_pool_stats_release(struct inode *, struct file *);
 void		nfsd_shutdown_threads(struct net *net);
 
-static inline void nfsd_put(struct net *net)
-{
-	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
-
-	svc_put(nn->nfsd_serv);
-}
-
 bool		i_am_nfsd(void);
 
 struct nfsdfs_client {
Signature · 1 line
2.43.0
author maintainer
#557 lore raw

PATCH 553/690 nfsd: fix RELEASE_LOCKOWNER

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: NeilBrown <[email protected]>

[ Upstream commit edcf9725150e42beeca42d085149f4c88fa97afd ]

The test on so_count in nfsd4_release_lockowner() is nonsense and harmful. Revert to using check_for_locks(), changing that to not sleep.

First: harmful.
As is documented in the kdoc comment for nfsd4_release_lockowner(), the test on so_count can transiently return a false positive resulting in a return of NFS4ERR_LOCKS_HELD when in fact no locks are held. This is clearly a protocol violation and with the Linux NFS client it can cause incorrect behaviour.

If RELEASE_LOCKOWNER is sent while some other thread is still processing a LOCK request which failed because, at the time that request was received, the given owner held a conflicting lock, then the nfsd thread processing that LOCK request can hold a reference (conflock) to the lock owner that causes nfsd4_release_lockowner() to return an incorrect error.

The Linux NFS client ignores that NFS4ERR_LOCKS_HELD error because it never sends NFS4_RELEASE_LOCKOWNER without first releasing any locks, so it knows that the error is impossible. It assumes the lock owner was in fact released so it feels free to use the same lock owner identifier in some later locking request.

When it does reuse a lock owner identifier for which a previous RELEASE failed, it will naturally use a lock_seqid of zero. However the server, which didn't release the lock owner, will expect a larger lock_seqid and so will respond with NFS4ERR_BAD_SEQID.

So clearly it is harmful to allow a false positive, which testing so_count allows.

The test is nonsense because ... well... it doesn't mean anything.

so_count is the sum of three different counts.
1/ the set of states listed on so_stateids
2/ the set of active vfs locks owned by any of those states 3/ various transient counts such as for conflicting locks.

When it is tested against '2' it is clear that one of these is the transient reference obtained by find_lockowner_str_locked(). It is not clear what the other one is expected to be.

In practice, the count is often 2 because there is precisely one state on so_stateids. If there were more, this would fail.

In my testing I see two circumstances when RELEASE_LOCKOWNER is called. In one case, CLOSE is called before RELEASE_LOCKOWNER. That results in all the lock states being removed, and so the lockowner being discarded (it is removed when there are no more references which usually happens when the lock state is discarded). When nfsd4_release_lockowner() finds that the lock owner doesn't exist, it returns success.

The other case shows an so_count of '2' and precisely one state listed in so_stateid. It appears that the Linux client uses a separate lock owner for each file resulting in one lock state per lock owner, so this test on '2' is safe. For another client it might not be safe.

So this patch changes check_for_locks() to use the (newish) find_any_file_locked() so that it doesn't take a reference on the nfs4_file and so never calls nfsd_file_put(), and so never sleeps. With this check is it safe to restore the use of check_for_locks() rather than testing so_count against the mysterious '2'.

Fixes ce3c4ad7f4ce ("NFSD: Fix possible sleep during nfsd4_release_lockowner()")
---
 fs/nfsd/nfs4state.c | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)
fs/nfsd/nfs4state.c +15 -11
index 4d95b2052c31a..64a8567ea4c40 100644
@@ -7831,14 +7831,16 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
 {
 	struct file_lock *fl;
 	int status = false;
-	struct nfsd_file *nf = find_any_file(fp);
+	struct nfsd_file *nf;
 	struct inode *inode;
 	struct file_lock_context *flctx;
 
+	spin_lock(&fp->fi_lock);
+	nf = find_any_file_locked(fp);
 	if (!nf) {
 		/* Any valid lock stateid should have some sort of access */
 		WARN_ON_ONCE(1);
-		return status;
+		goto out;
 	}
 
 	inode = locks_inode(nf->nf_file);
@@ -7854,7 +7856,8 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
 		}
 		spin_unlock(&flctx->flc_lock);
 	}
-	nfsd_file_put(nf);
+out:
+	spin_unlock(&fp->fi_lock);
 	return status;
 }
 
@@ -7864,10 +7867,8 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
  * @cstate: NFSv4 COMPOUND state
  * @u: RELEASE_LOCKOWNER arguments
  *
- * The lockowner's so_count is bumped when a lock record is added
- * or when copying a conflicting lock. The latter case is brief,
- * but can lead to fleeting false positives when looking for
- * locks-in-use.
+ * Check if theree are any locks still held and if not - free the lockowner
+ * and any lock state that is owned.
  *
  * Return values:
  *   %nfs_ok: lockowner released or not found
@@ -7903,10 +7904,13 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
 		spin_unlock(&clp->cl_lock);
 		return nfs_ok;
 	}
-	if (atomic_read(&lo->lo_owner.so_count) != 2) {
-		spin_unlock(&clp->cl_lock);
-		nfs4_put_stateowner(&lo->lo_owner);
-		return nfserr_locks_held;
+
+	list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) {
+		if (check_for_locks(stp->st_stid.sc_file, lo)) {
+			spin_unlock(&clp->cl_lock);
+			nfs4_put_stateowner(&lo->lo_owner);
+			return nfserr_locks_held;
+		}
 	}
 	unhash_lockowner_locked(lo);
 	while (!list_empty(&lo->lo_owner.so_stateids)) {
Signature · 1 line
2.43.0
author maintainer
#558 lore raw

PATCH 554/690 nfsd: dont take fi_lock in nfsd_break_deleg_cb()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: NeilBrown <[email protected]>

[ Upstream commit 5ea9a7c5fe4149f165f0e3b624fe08df02b6c301 ]

A recent change to check_for_locks() changed it to take ->flc_lock while holding ->fi_lock. This creates a lock inversion (reported by lockdep) because there is a case where ->fi_lock is taken while holding ->flc_lock.

->flc_lock is held across ->fl_lmops callbacks, and nfsd_break_deleg_cb() is one of those and does take ->fi_lock. However it doesn't need to.

Prior to v4.17-rc1~110^2~22 ("nfsd: create a separate lease for each delegation") nfsd_break_deleg_cb() would walk the ->fi_delegations list and so needed the lock. Since then it doesn't walk the list and doesn't need the lock.

Two actions are performed under the lock. One is to call nfsd_break_one_deleg which calls nfsd4_run_cb(). These doesn't act on the nfs4_file at all, so don't need the lock.

The other is to set ->fi_had_conflict which is in the nfs4_file. This field is only ever set here (except when initialised to false) so there is no possible problem will multiple threads racing when setting it.

The field is tested twice in nfs4_set_delegation(). The first test does not hold a lock and is documented as an opportunistic optimisation, so it doesn't impose any need to hold ->fi_lock while setting ->fi_had_conflict.

The second test in nfs4_set_delegation() *is* make under ->fi_lock, so removing the locking when ->fi_had_conflict is set could make a change. The change could only be interesting if ->fi_had_conflict tested as false even though nfsd_break_one_deleg() ran before ->fi_lock was unlocked. i.e. while hash_delegation_locked() was running. As hash_delegation_lock() doesn't interact in any way with nfs4_run_cb() there can be no importance to this interaction.

So this patch removes the locking from nfsd_break_one_deleg() and moves the final test on ->fi_had_conflict out of the locked region to make it clear that locking isn't important to the test. It is still tested *after* vfs_setlease() has succeeded. This might be significant and as vfs_setlease() takes ->flc_lock, and nfsd_break_one_deleg() is called under ->flc_lock this "after" is a true ordering provided by a spinlock.

Fixes edcf9725150e ("nfsd: fix RELEASE_LOCKOWNER")
---
 fs/nfsd/nfs4state.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)
fs/nfsd/nfs4state.c +5 -6
index 64a8567ea4c40..0f1ece95bd642 100644
@@ -4950,10 +4950,8 @@ nfsd_break_deleg_cb(struct file_lock *fl)
 	 */
 	fl->fl_break_time = 0;
 
-	spin_lock(&fp->fi_lock);
 	fp->fi_had_conflict = true;
 	nfsd_break_one_deleg(dp);
-	spin_unlock(&fp->fi_lock);
 	return false;
 }
 
@@ -5541,12 +5539,13 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	if (status)
 		goto out_unlock;
 
+	status = -EAGAIN;
+	if (fp->fi_had_conflict)
+		goto out_unlock;
+
 	spin_lock(&state_lock);
 	spin_lock(&fp->fi_lock);
-	if (fp->fi_had_conflict)
-		status = -EAGAIN;
-	else
-		status = hash_delegation_locked(dp, fp);
+	status = hash_delegation_locked(dp, fp);
 	spin_unlock(&fp->fi_lock);
 	spin_unlock(&state_lock);
 
Signature · 1 line
2.43.0
author maintainer
#559 lore raw

PATCH 555/690 nfsd: dont call locks_release_private() twice concurrently

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: NeilBrown <[email protected]>

[ Upstream commit 05eda6e75773592760285e10ac86c56d683be17f ]

It is possible for free_blocked_lock() to be called twice concurrently, once from nfsd4_lock() and once from nfsd4_release_lockowner() calling remove_blocked_locks(). This is why a kref was added.

It is perfectly safe for locks_delete_block() and kref_put() to be called in parallel as they use locking or atomicity respectively as protection. However locks_release_private() has no locking. It is safe for it to be called twice sequentially, but not concurrently.

This patch moves that call from free_blocked_lock() where it could race with itself, to free_nbl() where it cannot. This will slightly delay the freeing of private info or release of the owner - but not by much. It is arguably more natural for this freeing to happen in free_nbl() where the structure itself is freed.

This bug was found by code inspection - it has not been seen in practice.

Fixes 47446d74f170 ("nfsd4: add refcount for nfsd4_blocked_lock")
---
 fs/nfsd/nfs4state.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
fs/nfsd/nfs4state.c +1 -1
index 0f1ece95bd642..ccc235a8bc1b4 100644
@@ -318,6 +318,7 @@ free_nbl(struct kref *kref)
 	struct nfsd4_blocked_lock *nbl;
 
 	nbl = container_of(kref, struct nfsd4_blocked_lock, nbl_kref);
+	locks_release_private(&nbl->nbl_lock);
 	kfree(nbl);
 }
 
@@ -325,7 +326,6 @@ static void
 free_blocked_lock(struct nfsd4_blocked_lock *nbl)
 {
 	locks_delete_block(&nbl->nbl_lock);
-	locks_release_private(&nbl->nbl_lock);
 	kref_put(&nbl->nbl_kref, free_nbl);
 }
 
Signature · 1 line
2.43.0
author maintainer
#560 lore raw

PATCH 556/690 nfsd: Fix a regression in nfsd_setattr()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Trond Myklebust <[email protected]>

[ Upstream commit 6412e44c40aaf8f1d7320b2099c5bdd6cb9126ac ]

Commit bb4d53d66e4b ("NFSD: use (un)lock_inode instead of fh_(un)lock for file operations") broke the NFSv3 pre/post op attributes behaviour when doing a SETATTR rpc call by stripping out the calls to fh_fill_pre_attrs() and fh_fill_post_attrs().

Fixes bb4d53d66e4b ("NFSD: use (un)lock_inode instead of fh_(un)lock for file operations")

Message-ID: <[email protected]>

[ cel: adjusted to apply to v5.15.y ]
---
 fs/nfsd/nfs4proc.c | 4 ++++
 fs/nfsd/vfs.c      | 6 ++++--
 2 files changed, 8 insertions(+), 2 deletions(-)
fs/nfsd/nfs4proc.c +4 -0
index b6d768bd5ccca..6779291efca9e 100644
@@ -1106,6 +1106,7 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	};
 	struct inode *inode;
 	__be32 status = nfs_ok;
+	bool save_no_wcc;
 	int err;
 
 	if (setattr->sa_iattr.ia_valid & ATTR_SIZE) {
@@ -1131,8 +1132,11 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	if (status)
 		goto out;
+	save_no_wcc = cstate->current_fh.fh_no_wcc;
+	cstate->current_fh.fh_no_wcc = true;
 	status = nfsd_setattr(rqstp, &cstate->current_fh, &attrs,
 				0, (time64_t)0);
+	cstate->current_fh.fh_no_wcc = save_no_wcc;
 	if (!status)
 		status = nfserrno(attrs.na_labelerr);
 	if (!status)
fs/nfsd/vfs.c +4 -2
index 76ce19d42336f..0f430548bfbbe 100644
@@ -474,7 +474,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	int		accmode = NFSD_MAY_SATTR;
 	umode_t		ftype = 0;
 	__be32		err;
-	int		host_err;
+	int		host_err = 0;
 	bool		get_write_count;
 	bool		size_change = (iap->ia_valid & ATTR_SIZE);
 	int		retries;
@@ -532,6 +532,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	}
 
 	inode_lock(inode);
+	fh_fill_pre_attrs(fhp);
 	for (retries = 1;;) {
 		struct iattr attrs;
 
@@ -559,13 +560,14 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		attr->na_aclerr = set_posix_acl(&init_user_ns,
 						inode, ACL_TYPE_DEFAULT,
 						attr->na_dpacl);
+	fh_fill_post_attrs(fhp);
 	inode_unlock(inode);
 	if (size_change)
 		put_write_access(inode);
 out:
 	if (!host_err)
 		host_err = commit_metadata(fhp);
-	return nfserrno(host_err);
+	return err != 0 ? err : nfserrno(host_err);
 }
 
 #if defined(CONFIG_NFSD_V4)
Signature · 1 line
2.43.0
author maintainer
#561 lore raw

PATCH 557/690 perf/core: Fix reentry problem in perf_output_read_group()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yang Jihong <[email protected]>

commit 6b959ba22d34ca793ffdb15b5715457c78e38b1a upstream.

perf_output_read_group may respond to IPI request of other cores and invoke __perf_install_in_context function. As a result, hwc configuration is modified. causing inconsistency and unexpected consequences.

Interrupts are not disabled when perf_output_read_group reads PMU counter. In this case, IPI request may be received from other cores.
As a result, PMU configuration is modified and an error occurs when reading PMU counter:

CPU0 CPU1
__se_sys_perf_event_open
perf_install_in_context
perf_output_read_group smp_call_function_single

    for_each_sibling_event(sub, leader) {                   generic_exec_single
      if ((sub != event) &&                                   remote_function
	  (sub->state == PERF_EVENT_STATE_ACTIVE))                    |
  <enter IPI handler: __perf_install_in_context>   <----RAISE IPI-----+
  __perf_install_in_context
    ctx_resched
      event_sched_out
	armpmu_del
	  ...
	  hwc->idx = -1; // event->hwc.idx is set to -1
  ...
  <exit IPI>
	      sub->pmu->read(sub);
		armpmu_read
		  armv8pmu_read_counter
		    armv8pmu_read_hw_counter
		      int idx = event->hw.idx; // idx = -1
		      u64 val = armv8pmu_read_evcntr(idx);
			u32 counter = ARMV8_IDX_TO_COUNTER(idx); // invalid counter = 30
			read_pmevcntrn(counter) // undefined instruction
---
 kernel/events/core.c |    9 +++++++++
 1 file changed, 9 insertions(+)
kernel/events/core.c +9 -0
@@ -7119,9 +7119,16 @@ static void perf_output_read_group(struc
 {
 	struct perf_event *leader = event->group_leader, *sub;
 	u64 read_format = event->attr.read_format;
+	unsigned long flags;
 	u64 values[6];
 	int n = 0;
 
+	/*
+	 * Disabling interrupts avoids all counter scheduling
+	 * (context switches, timer based rotation and IPIs).
+	 */
+	local_irq_save(flags);
+
 	values[n++] = 1 + leader->nr_siblings;
 
 	if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED)
@@ -7157,6 +7164,8 @@ static void perf_output_read_group(struc
 
 		__output_copy(handle, values, n * sizeof(u64));
 	}
+
+	local_irq_restore(flags);
 }
 
 #define PERF_FORMAT_TOTAL_TIMES (PERF_FORMAT_TOTAL_TIME_ENABLED|\
author maintainer
#562 lore raw

PATCH 558/690 efivarfs: Request at most 512 bytes for variable names

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tim Schumacher <[email protected]>

commit f45812cc23fb74bef62d4eb8a69fe7218f4b9f2a upstream.

Work around a quirk in a few old (2011-ish) UEFI implementations, where a call to GetNextVariableName with a buffer size larger than 512 bytes will always return EFI_INVALID_PARAMETER.

There is some lore around EFI variable names being up to 1024 bytes in size, but this has no basis in the UEFI specification, and the upper bounds are typically platform specific, and apply to the entire variable (name plus payload).

Given that Linux does not permit creating files with names longer than NAME_MAX (255) bytes, 512 bytes (== 256 UTF-16 characters) is a reasonable limit.

---
 drivers/firmware/efi/vars.c |   17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)
drivers/firmware/efi/vars.c +11 -6
@@ -415,7 +415,7 @@ int efivar_init(int (*func)(efi_char16_t
 		void *data, bool duplicates, struct list_head *head)
 {
 	const struct efivar_operations *ops;
-	unsigned long variable_name_size = 1024;
+	unsigned long variable_name_size = 512;
 	efi_char16_t *variable_name;
 	efi_status_t status;
 	efi_guid_t vendor_guid;
@@ -438,12 +438,13 @@ int efivar_init(int (*func)(efi_char16_t
 	}
 
 	/*
-	 * Per EFI spec, the maximum storage allocated for both
-	 * the variable name and variable data is 1024 bytes.
+	 * A small set of old UEFI implementations reject sizes
+	 * above a certain threshold, the lowest seen in the wild
+	 * is 512.
 	 */
 
 	do {
-		variable_name_size = 1024;
+		variable_name_size = 512;
 
 		status = ops->get_next_variable(&variable_name_size,
 						variable_name,
@@ -491,9 +492,13 @@ int efivar_init(int (*func)(efi_char16_t
 			break;
 		case EFI_NOT_FOUND:
 			break;
+		case EFI_BUFFER_TOO_SMALL:
+			pr_warn("efivars: Variable name size exceeds maximum (%lu > 512)\n",
+				variable_name_size);
+			status = EFI_NOT_FOUND;
+			break;
 		default:
-			printk(KERN_WARNING "efivars: get_next_variable: status=%lx\n",
-				status);
+			pr_warn("efivars: get_next_variable: status=%lx\n", status);
 			status = EFI_NOT_FOUND;
 			break;
 		}
author maintainer
#563 lore raw

PATCH 559/690 powerpc: xor_vmx: Add -mhard-float to CFLAGS

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nathan Chancellor <[email protected]>

commit 35f20786c481d5ced9283ff42de5c69b65e5ed13 upstream.

arch/powerpc/lib/xor_vmx.o is built with '-msoft-float' (from the main powerpc Makefile) and '-maltivec' (from its CFLAGS), which causes an error when building with clang after a recent change in main:

error: option '-msoft-float' cannot be specified with '-maltivec' make[6]: *** [scripts/Makefile.build:243: arch/powerpc/lib/xor_vmx.o] Error 1

Explicitly add '-mhard-float' before '-maltivec' in xor_vmx.o's CFLAGS to override the previous inclusion of '-msoft-float' (as the last option wins), which matches how other areas of the kernel use '-maltivec', such as AMDGPU.

---
 arch/powerpc/lib/Makefile |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/powerpc/lib/Makefile +1 -1
@@ -67,6 +67,6 @@ obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o
 obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o
 
 obj-$(CONFIG_ALTIVEC)	+= xor_vmx.o xor_vmx_glue.o
-CFLAGS_xor_vmx.o += -maltivec $(call cc-option,-mabi=altivec)
+CFLAGS_xor_vmx.o += -mhard-float -maltivec $(call cc-option,-mabi=altivec)
 
 obj-$(CONFIG_PPC64) += $(obj64-y)
author maintainer
#564 lore raw

PATCH 560/690 selftests: mptcp: diag: return KSFT_FAIL not test_cnt

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Geliang Tang <[email protected]>

commit 45bcc0346561daa3f59e19a753cc7f3e08e8dff1 upstream.

The test counter 'test_cnt' should not be returned in diag.sh, e.g. what if only the 4th test fail? Will do 'exit 4' which is 'exit ${KSFT_SKIP}', the whole test will be marked as skipped instead of 'failed'!

So we should do ret=${KSFT_FAIL} instead.

Fixes df62f2ec3df6 ("selftests/mptcp: add diag interface tests")
Fixes 42fb6cddec3b ("selftests: mptcp: more stable diag tests")
---
 tools/testing/selftests/net/mptcp/diag.sh |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
tools/testing/selftests/net/mptcp/diag.sh +3 -3
@@ -53,7 +53,7 @@ __chk_nr()
 	printf "%-50s" "$msg"
 	if [ $nr != $expected ]; then
 		echo "[ fail ] expected $expected found $nr"
-		ret=$test_cnt
+		ret=${KSFT_FAIL}
 	else
 		echo "[  ok  ]"
 	fi
@@ -88,10 +88,10 @@ wait_msk_nr()
 	printf "%-50s" "$msg"
 	if [ $i -ge $timeout ]; then
 		echo "[ fail ] timeout while expecting $expected max $max last $nr"
-		ret=$test_cnt
+		ret=${KSFT_FAIL}
 	elif [ $nr != $expected ]; then
 		echo "[ fail ] expected $expected found $nr"
-		ret=$test_cnt
+		ret=${KSFT_FAIL}
 	else
 		echo "[  ok  ]"
 	fi
author maintainer
#565 lore raw

PATCH 561/690 vfio/pci: Disable auto-enable of exclusive INTx IRQ

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alex Williamson <[email protected]>

[ Upstream commit fe9a7082684eb059b925c535682e68c34d487d43 ]

Currently for devices requiring masking at the irqchip for INTx, ie. devices without DisINTx support, the IRQ is enabled in request_irq() and subsequently disabled as necessary to align with the masked status flag. This presents a window where the interrupt could fire between these events, resulting in the IRQ incrementing the disable depth twice. This would be unrecoverable for a user since the masked flag prevents nested enables through vfio.

Instead, invert the logic using IRQF_NO_AUTOEN such that exclusive INTx is never auto-enabled, then unmask as required.

---
 drivers/vfio/pci/vfio_pci_intrs.c |   17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)
drivers/vfio/pci/vfio_pci_intrs.c +10 -7
@@ -199,8 +199,15 @@ static int vfio_intx_set_signal(struct v
 
 	vdev->ctx[0].trigger = trigger;
 
+	/*
+	 * Devices without DisINTx support require an exclusive interrupt,
+	 * IRQ masking is performed at the IRQ chip.  The masked status is
+	 * protected by vdev->irqlock. Setup the IRQ without auto-enable and
+	 * unmask as necessary below under lock.  DisINTx is unmodified by
+	 * the IRQ configuration and may therefore use auto-enable.
+	 */
 	if (!vdev->pci_2_3)
-		irqflags = 0;
+		irqflags = IRQF_NO_AUTOEN;
 
 	ret = request_irq(pdev->irq, vfio_intx_handler,
 			  irqflags, vdev->ctx[0].name, vdev);
@@ -211,13 +218,9 @@ static int vfio_intx_set_signal(struct v
 		return ret;
 	}
 
-	/*
-	 * INTx disable will stick across the new irq setup,
-	 * disable_irq won't.
-	 */
 	spin_lock_irqsave(&vdev->irqlock, flags);
-	if (!vdev->pci_2_3 && vdev->ctx[0].masked)
-		disable_irq_nosync(pdev->irq);
+	if (!vdev->pci_2_3 && !vdev->ctx[0].masked)
+		enable_irq(pdev->irq);
 	spin_unlock_irqrestore(&vdev->irqlock, flags);
 
 	return 0;
author maintainer
#566 lore raw

PATCH 562/690 vfio/pci: Lock external INTx masking ops

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alex Williamson <[email protected]>

[ Upstream commit 810cd4bb53456d0503cc4e7934e063835152c1b7 ]

Mask operations through config space changes to DisINTx may race INTx configuration changes via ioctl. Create wrappers that add locking for paths outside of the core interrupt code.

In particular, irq_type is updated holding igate, therefore testing is_intx() requires holding igate. For example clearing DisINTx from config space can otherwise race changes of the interrupt configuration.

This aligns interfaces which may trigger the INTx eventfd into two camps, one side serialized by igate and the other only enabled while INTx is configured. A subsequent patch introduces synchronization for the latter flows.

---
 drivers/vfio/pci/vfio_pci_intrs.c |   30 ++++++++++++++++++++++++------
 1 file changed, 24 insertions(+), 6 deletions(-)
drivers/vfio/pci/vfio_pci_intrs.c +24 -6
@@ -33,11 +33,13 @@ static void vfio_send_intx_eventfd(void
 		eventfd_signal(vdev->ctx[0].trigger, 1);
 }
 
-void vfio_pci_intx_mask(struct vfio_pci_core_device *vdev)
+static void __vfio_pci_intx_mask(struct vfio_pci_core_device *vdev)
 {
 	struct pci_dev *pdev = vdev->pdev;
 	unsigned long flags;
 
+	lockdep_assert_held(&vdev->igate);
+
 	spin_lock_irqsave(&vdev->irqlock, flags);
 
 	/*
@@ -65,6 +67,13 @@ void vfio_pci_intx_mask(struct vfio_pci_
 	spin_unlock_irqrestore(&vdev->irqlock, flags);
 }
 
+void vfio_pci_intx_mask(struct vfio_pci_core_device *vdev)
+{
+	mutex_lock(&vdev->igate);
+	__vfio_pci_intx_mask(vdev);
+	mutex_unlock(&vdev->igate);
+}
+
 /*
  * If this is triggered by an eventfd, we can't call eventfd_signal
  * or else we'll deadlock on the eventfd wait queue.  Return >0 when
@@ -107,12 +116,21 @@ static int vfio_pci_intx_unmask_handler(
 	return ret;
 }
 
-void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev)
+static void __vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev)
 {
+	lockdep_assert_held(&vdev->igate);
+
 	if (vfio_pci_intx_unmask_handler(vdev, NULL) > 0)
 		vfio_send_intx_eventfd(vdev, NULL);
 }
 
+void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev)
+{
+	mutex_lock(&vdev->igate);
+	__vfio_pci_intx_unmask(vdev);
+	mutex_unlock(&vdev->igate);
+}
+
 static irqreturn_t vfio_intx_handler(int irq, void *dev_id)
 {
 	struct vfio_pci_core_device *vdev = dev_id;
@@ -428,11 +446,11 @@ static int vfio_pci_set_intx_unmask(stru
 		return -EINVAL;
 
 	if (flags & VFIO_IRQ_SET_DATA_NONE) {
-		vfio_pci_intx_unmask(vdev);
+		__vfio_pci_intx_unmask(vdev);
 	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
 		uint8_t unmask = *(uint8_t *)data;
 		if (unmask)
-			vfio_pci_intx_unmask(vdev);
+			__vfio_pci_intx_unmask(vdev);
 	} else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
 		int32_t fd = *(int32_t *)data;
 		if (fd >= 0)
@@ -455,11 +473,11 @@ static int vfio_pci_set_intx_mask(struct
 		return -EINVAL;
 
 	if (flags & VFIO_IRQ_SET_DATA_NONE) {
-		vfio_pci_intx_mask(vdev);
+		__vfio_pci_intx_mask(vdev);
 	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
 		uint8_t mask = *(uint8_t *)data;
 		if (mask)
-			vfio_pci_intx_mask(vdev);
+			__vfio_pci_intx_mask(vdev);
 	} else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
 		return -ENOTTY; /* XXX implement me */
 	}
author maintainer
#567 lore raw

PATCH 563/690 vfio: Introduce interface to flush virqfd inject workqueue

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alex Williamson <[email protected]>

[ Upstream commit b620ecbd17a03cacd06f014a5d3f3a11285ce053 ]

In order to synchronize changes that can affect the thread callback, introduce an interface to force a flush of the inject workqueue. The irqfd pointer is only valid under spinlock, but the workqueue cannot be flushed under spinlock. Therefore the flush work for the irqfd is queued under spinlock. The vfio_irqfd_cleanup_wq workqueue is re-used for queuing this work such that flushing the workqueue is also ordered relative to shutdown.

---
 drivers/vfio/virqfd.c |   21 +++++++++++++++++++++
 include/linux/vfio.h  |    2 ++
 2 files changed, 23 insertions(+)
drivers/vfio/virqfd.c +21 -0
@@ -104,6 +104,13 @@ static void virqfd_inject(struct work_st
 		virqfd->thread(virqfd->opaque, virqfd->data);
 }
 
+static void virqfd_flush_inject(struct work_struct *work)
+{
+	struct virqfd *virqfd = container_of(work, struct virqfd, flush_inject);
+
+	flush_work(&virqfd->inject);
+}
+
 int vfio_virqfd_enable(void *opaque,
 		       int (*handler)(void *, void *),
 		       void (*thread)(void *, void *),
@@ -127,6 +134,7 @@ int vfio_virqfd_enable(void *opaque,
 
 	INIT_WORK(&virqfd->shutdown, virqfd_shutdown);
 	INIT_WORK(&virqfd->inject, virqfd_inject);
+	INIT_WORK(&virqfd->flush_inject, virqfd_flush_inject);
 
 	irqfd = fdget(fd);
 	if (!irqfd.file) {
@@ -217,6 +225,19 @@ void vfio_virqfd_disable(struct virqfd *
 }
 EXPORT_SYMBOL_GPL(vfio_virqfd_disable);
 
+void vfio_virqfd_flush_thread(struct virqfd **pvirqfd)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&virqfd_lock, flags);
+	if (*pvirqfd && (*pvirqfd)->thread)
+		queue_work(vfio_irqfd_cleanup_wq, &(*pvirqfd)->flush_inject);
+	spin_unlock_irqrestore(&virqfd_lock, flags);
+
+	flush_workqueue(vfio_irqfd_cleanup_wq);
+}
+EXPORT_SYMBOL_GPL(vfio_virqfd_flush_thread);
+
 module_init(vfio_virqfd_init);
 module_exit(vfio_virqfd_exit);
 
include/linux/vfio.h +2 -0
@@ -243,6 +243,7 @@ struct virqfd {
 	wait_queue_entry_t		wait;
 	poll_table		pt;
 	struct work_struct	shutdown;
+	struct work_struct	flush_inject;
 	struct virqfd		**pvirqfd;
 };
 
@@ -251,5 +252,6 @@ extern int vfio_virqfd_enable(void *opaq
 			      void (*thread)(void *, void *),
 			      void *data, struct virqfd **pvirqfd, int fd);
 extern void vfio_virqfd_disable(struct virqfd **pvirqfd);
+void vfio_virqfd_flush_thread(struct virqfd **pvirqfd);
 
 #endif /* VFIO_H */
author maintainer
#568 lore raw

PATCH 564/690 vfio/pci: Create persistent INTx handler

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alex Williamson <[email protected]>

[ Upstream commit 18c198c96a815c962adc2b9b77909eec0be7df4d ]

A vulnerability exists where the eventfd for INTx signaling can be deconfigured, which unregisters the IRQ handler but still allows eventfds to be signaled with a NULL context through the SET_IRQS ioctl or through unmask irqfd if the device interrupt is pending.

Ideally this could be solved with some additional locking; the igate mutex serializes the ioctl and config space accesses, and the interrupt handler is unregistered relative to the trigger, but the irqfd path runs asynchronous to those. The igate mutex cannot be acquired from the atomic context of the eventfd wake function. Disabling the irqfd relative to the eventfd registration is potentially incompatible with existing userspace.

As a result, the solution implemented here moves configuration of the INTx interrupt handler to track the lifetime of the INTx context object and irq_type configuration, rather than registration of a particular trigger eventfd. Synchronization is added between the ioctl path and eventfd_signal() wrapper such that the eventfd trigger can be dynamically updated relative to in-flight interrupts or irqfd callbacks.

---
 drivers/vfio/pci/vfio_pci_intrs.c |  149 ++++++++++++++++++++------------------
 1 file changed, 82 insertions(+), 67 deletions(-)
drivers/vfio/pci/vfio_pci_intrs.c +82 -67
@@ -29,8 +29,13 @@ static void vfio_send_intx_eventfd(void
 {
 	struct vfio_pci_core_device *vdev = opaque;
 
-	if (likely(is_intx(vdev) && !vdev->virq_disabled))
-		eventfd_signal(vdev->ctx[0].trigger, 1);
+	if (likely(is_intx(vdev) && !vdev->virq_disabled)) {
+		struct eventfd_ctx *trigger;
+
+		trigger = READ_ONCE(vdev->ctx[0].trigger);
+		if (likely(trigger))
+			eventfd_signal(trigger, 1);
+	}
 }
 
 static void __vfio_pci_intx_mask(struct vfio_pci_core_device *vdev)
@@ -157,98 +162,104 @@ static irqreturn_t vfio_intx_handler(int
 	return ret;
 }
 
-static int vfio_intx_enable(struct vfio_pci_core_device *vdev)
+static int vfio_intx_enable(struct vfio_pci_core_device *vdev,
+			    struct eventfd_ctx *trigger)
 {
+	struct pci_dev *pdev = vdev->pdev;
+	unsigned long irqflags;
+	char *name;
+	int ret;
+
 	if (!is_irq_none(vdev))
 		return -EINVAL;
 
-	if (!vdev->pdev->irq)
+	if (!pdev->irq)
 		return -ENODEV;
 
+	name = kasprintf(GFP_KERNEL, "vfio-intx(%s)", pci_name(pdev));
+	if (!name)
+		return -ENOMEM;
+
 	vdev->ctx = kzalloc(sizeof(struct vfio_pci_irq_ctx), GFP_KERNEL);
 	if (!vdev->ctx)
 		return -ENOMEM;
 
 	vdev->num_ctx = 1;
 
+	vdev->ctx[0].name = name;
+	vdev->ctx[0].trigger = trigger;
+
 	/*
-	 * If the virtual interrupt is masked, restore it.  Devices
-	 * supporting DisINTx can be masked at the hardware level
-	 * here, non-PCI-2.3 devices will have to wait until the
-	 * interrupt is enabled.
+	 * Fill the initial masked state based on virq_disabled.  After
+	 * enable, changing the DisINTx bit in vconfig directly changes INTx
+	 * masking.  igate prevents races during setup, once running masked
+	 * is protected via irqlock.
+	 *
+	 * Devices supporting DisINTx also reflect the current mask state in
+	 * the physical DisINTx bit, which is not affected during IRQ setup.
+	 *
+	 * Devices without DisINTx support require an exclusive interrupt.
+	 * IRQ masking is performed at the IRQ chip.  Again, igate protects
+	 * against races during setup and IRQ handlers and irqfds are not
+	 * yet active, therefore masked is stable and can be used to
+	 * conditionally auto-enable the IRQ.
+	 *
+	 * irq_type must be stable while the IRQ handler is registered,
+	 * therefore it must be set before request_irq().
 	 */
 	vdev->ctx[0].masked = vdev->virq_disabled;
-	if (vdev->pci_2_3)
-		pci_intx(vdev->pdev, !vdev->ctx[0].masked);
+	if (vdev->pci_2_3) {
+		pci_intx(pdev, !vdev->ctx[0].masked);
+		irqflags = IRQF_SHARED;
+	} else {
+		irqflags = vdev->ctx[0].masked ? IRQF_NO_AUTOEN : 0;
+	}
 
 	vdev->irq_type = VFIO_PCI_INTX_IRQ_INDEX;
 
+	ret = request_irq(pdev->irq, vfio_intx_handler,
+			  irqflags, vdev->ctx[0].name, vdev);
+	if (ret) {
+		vdev->irq_type = VFIO_PCI_NUM_IRQS;
+		kfree(name);
+		vdev->num_ctx = 0;
+		kfree(vdev->ctx);
+		return ret;
+	}
+
 	return 0;
 }
 
-static int vfio_intx_set_signal(struct vfio_pci_core_device *vdev, int fd)
+static int vfio_intx_set_signal(struct vfio_pci_core_device *vdev,
+				struct eventfd_ctx *trigger)
 {
 	struct pci_dev *pdev = vdev->pdev;
-	unsigned long irqflags = IRQF_SHARED;
-	struct eventfd_ctx *trigger;
-	unsigned long flags;
-	int ret;
-
-	if (vdev->ctx[0].trigger) {
-		free_irq(pdev->irq, vdev);
-		kfree(vdev->ctx[0].name);
-		eventfd_ctx_put(vdev->ctx[0].trigger);
-		vdev->ctx[0].trigger = NULL;
-	}
-
-	if (fd < 0) /* Disable only */
-		return 0;
-
-	vdev->ctx[0].name = kasprintf(GFP_KERNEL, "vfio-intx(%s)",
-				      pci_name(pdev));
-	if (!vdev->ctx[0].name)
-		return -ENOMEM;
-
-	trigger = eventfd_ctx_fdget(fd);
-	if (IS_ERR(trigger)) {
-		kfree(vdev->ctx[0].name);
-		return PTR_ERR(trigger);
-	}
+	struct eventfd_ctx *old;
 
-	vdev->ctx[0].trigger = trigger;
+	old = vdev->ctx[0].trigger;
 
-	/*
-	 * Devices without DisINTx support require an exclusive interrupt,
-	 * IRQ masking is performed at the IRQ chip.  The masked status is
-	 * protected by vdev->irqlock. Setup the IRQ without auto-enable and
-	 * unmask as necessary below under lock.  DisINTx is unmodified by
-	 * the IRQ configuration and may therefore use auto-enable.
-	 */
-	if (!vdev->pci_2_3)
-		irqflags = IRQF_NO_AUTOEN;
+	WRITE_ONCE(vdev->ctx[0].trigger, trigger);
 
-	ret = request_irq(pdev->irq, vfio_intx_handler,
-			  irqflags, vdev->ctx[0].name, vdev);
-	if (ret) {
-		vdev->ctx[0].trigger = NULL;
-		kfree(vdev->ctx[0].name);
-		eventfd_ctx_put(trigger);
-		return ret;
+	/* Releasing an old ctx requires synchronizing in-flight users */
+	if (old) {
+		synchronize_irq(pdev->irq);
+		vfio_virqfd_flush_thread(&vdev->ctx[0].unmask);
+		eventfd_ctx_put(old);
 	}
 
-	spin_lock_irqsave(&vdev->irqlock, flags);
-	if (!vdev->pci_2_3 && !vdev->ctx[0].masked)
-		enable_irq(pdev->irq);
-	spin_unlock_irqrestore(&vdev->irqlock, flags);
-
 	return 0;
 }
 
 static void vfio_intx_disable(struct vfio_pci_core_device *vdev)
 {
+	struct pci_dev *pdev = vdev->pdev;
+
 	vfio_virqfd_disable(&vdev->ctx[0].unmask);
 	vfio_virqfd_disable(&vdev->ctx[0].mask);
-	vfio_intx_set_signal(vdev, -1);
+	free_irq(pdev->irq, vdev);
+	if (vdev->ctx[0].trigger)
+		eventfd_ctx_put(vdev->ctx[0].trigger);
+	kfree(vdev->ctx[0].name);
 	vdev->irq_type = VFIO_PCI_NUM_IRQS;
 	vdev->num_ctx = 0;
 	kfree(vdev->ctx);
@@ -498,19 +509,23 @@ static int vfio_pci_set_intx_trigger(str
 		return -EINVAL;
 
 	if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
+		struct eventfd_ctx *trigger = NULL;
 		int32_t fd = *(int32_t *)data;
 		int ret;
 
+		if (fd >= 0) {
+			trigger = eventfd_ctx_fdget(fd);
+			if (IS_ERR(trigger))
+				return PTR_ERR(trigger);
+		}
+
 		if (is_intx(vdev))
-			return vfio_intx_set_signal(vdev, fd);
+			ret = vfio_intx_set_signal(vdev, trigger);
+		else
+			ret = vfio_intx_enable(vdev, trigger);
 
-		ret = vfio_intx_enable(vdev);
-		if (ret)
-			return ret;
-
-		ret = vfio_intx_set_signal(vdev, fd);
-		if (ret)
-			vfio_intx_disable(vdev);
+		if (ret && trigger)
+			eventfd_ctx_put(trigger);
 
 		return ret;
 	}
author maintainer
#569 lore raw

PATCH 565/690 vfio/platform: Create persistent IRQ handlers

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alex Williamson <[email protected]>

[ Upstream commit 675daf435e9f8e5a5eab140a9864dfad6668b375 ]

The vfio-platform SET_IRQS ioctl currently allows loopback triggering of an interrupt before a signaling eventfd has been configured by the user, which thereby allows a NULL pointer dereference.

Rather than register the IRQ relative to a valid trigger, register all IRQs in a disabled state in the device open path. This allows mask operations on the IRQ to nest within the overall enable state governed by a valid eventfd signal. This decouples @masked, protected by the @locked spinlock from @trigger, protected via the @igate mutex.

In doing so, it's guaranteed that changes to @trigger cannot race the IRQ handlers because the IRQ handler is synchronously disabled before modifying the trigger, and loopback triggering of the IRQ via ioctl is safe due to serialization with trigger changes via igate.

For compatibility, request_irq() failures are maintained to be local to the SET_IRQS ioctl rather than a fatal error in the open device path. This allows, for example, a userspace driver with polling mode support to continue to work regardless of moving the request_irq() call site. This necessarily blocks all SET_IRQS access to the failed index.

---
 drivers/vfio/platform/vfio_platform_irq.c |  101 ++++++++++++++++++++----------
 1 file changed, 68 insertions(+), 33 deletions(-)
drivers/vfio/platform/vfio_platform_irq.c +68 -33
@@ -136,6 +136,16 @@ static int vfio_platform_set_irq_unmask(
 	return 0;
 }
 
+/*
+ * The trigger eventfd is guaranteed valid in the interrupt path
+ * and protected by the igate mutex when triggered via ioctl.
+ */
+static void vfio_send_eventfd(struct vfio_platform_irq *irq_ctx)
+{
+	if (likely(irq_ctx->trigger))
+		eventfd_signal(irq_ctx->trigger, 1);
+}
+
 static irqreturn_t vfio_automasked_irq_handler(int irq, void *dev_id)
 {
 	struct vfio_platform_irq *irq_ctx = dev_id;
@@ -155,7 +165,7 @@ static irqreturn_t vfio_automasked_irq_h
 	spin_unlock_irqrestore(&irq_ctx->lock, flags);
 
 	if (ret == IRQ_HANDLED)
-		eventfd_signal(irq_ctx->trigger, 1);
+		vfio_send_eventfd(irq_ctx);
 
 	return ret;
 }
@@ -164,22 +174,19 @@ static irqreturn_t vfio_irq_handler(int
 {
 	struct vfio_platform_irq *irq_ctx = dev_id;
 
-	eventfd_signal(irq_ctx->trigger, 1);
+	vfio_send_eventfd(irq_ctx);
 
 	return IRQ_HANDLED;
 }
 
 static int vfio_set_trigger(struct vfio_platform_device *vdev, int index,
-			    int fd, irq_handler_t handler)
+			    int fd)
 {
 	struct vfio_platform_irq *irq = &vdev->irqs[index];
 	struct eventfd_ctx *trigger;
-	int ret;
 
 	if (irq->trigger) {
-		irq_clear_status_flags(irq->hwirq, IRQ_NOAUTOEN);
-		free_irq(irq->hwirq, irq);
-		kfree(irq->name);
+		disable_irq(irq->hwirq);
 		eventfd_ctx_put(irq->trigger);
 		irq->trigger = NULL;
 	}
@@ -187,30 +194,20 @@ static int vfio_set_trigger(struct vfio_
 	if (fd < 0) /* Disable only */
 		return 0;
 
-	irq->name = kasprintf(GFP_KERNEL, "vfio-irq[%d](%s)",
-						irq->hwirq, vdev->name);
-	if (!irq->name)
-		return -ENOMEM;
-
 	trigger = eventfd_ctx_fdget(fd);
-	if (IS_ERR(trigger)) {
-		kfree(irq->name);
+	if (IS_ERR(trigger))
 		return PTR_ERR(trigger);
-	}
 
 	irq->trigger = trigger;
 
-	irq_set_status_flags(irq->hwirq, IRQ_NOAUTOEN);
-	ret = request_irq(irq->hwirq, handler, 0, irq->name, irq);
-	if (ret) {
-		kfree(irq->name);
-		eventfd_ctx_put(trigger);
-		irq->trigger = NULL;
-		return ret;
-	}
-
-	if (!irq->masked)
-		enable_irq(irq->hwirq);
+	/*
+	 * irq->masked effectively provides nested disables within the overall
+	 * enable relative to trigger.  Specifically request_irq() is called
+	 * with NO_AUTOEN, therefore the IRQ is initially disabled.  The user
+	 * may only further disable the IRQ with a MASK operations because
+	 * irq->masked is initially false.
+	 */
+	enable_irq(irq->hwirq);
 
 	return 0;
 }
@@ -229,7 +226,7 @@ static int vfio_platform_set_irq_trigger
 		handler = vfio_irq_handler;
 
 	if (!count && (flags & VFIO_IRQ_SET_DATA_NONE))
-		return vfio_set_trigger(vdev, index, -1, handler);
+		return vfio_set_trigger(vdev, index, -1);
 
 	if (start != 0 || count != 1)
 		return -EINVAL;
@@ -237,7 +234,7 @@ static int vfio_platform_set_irq_trigger
 	if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
 		int32_t fd = *(int32_t *)data;
 
-		return vfio_set_trigger(vdev, index, fd, handler);
+		return vfio_set_trigger(vdev, index, fd);
 	}
 
 	if (flags & VFIO_IRQ_SET_DATA_NONE) {
@@ -261,6 +258,14 @@ int vfio_platform_set_irqs_ioctl(struct
 		    unsigned start, unsigned count, uint32_t flags,
 		    void *data) = NULL;
 
+	/*
+	 * For compatibility, errors from request_irq() are local to the
+	 * SET_IRQS path and reflected in the name pointer.  This allows,
+	 * for example, polling mode fallback for an exclusive IRQ failure.
+	 */
+	if (IS_ERR(vdev->irqs[index].name))
+		return PTR_ERR(vdev->irqs[index].name);
+
 	switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
 	case VFIO_IRQ_SET_ACTION_MASK:
 		func = vfio_platform_set_irq_mask;
@@ -281,7 +286,7 @@ int vfio_platform_set_irqs_ioctl(struct
 
 int vfio_platform_irq_init(struct vfio_platform_device *vdev)
 {
-	int cnt = 0, i;
+	int cnt = 0, i, ret = 0;
 
 	while (vdev->get_irq(vdev, cnt) >= 0)
 		cnt++;
@@ -292,29 +297,54 @@ int vfio_platform_irq_init(struct vfio_p
 
 	for (i = 0; i < cnt; i++) {
 		int hwirq = vdev->get_irq(vdev, i);
+		irq_handler_t handler = vfio_irq_handler;
 
-		if (hwirq < 0)
+		if (hwirq < 0) {
+			ret = -EINVAL;
 			goto err;
+		}
 
 		spin_lock_init(&vdev->irqs[i].lock);
 
 		vdev->irqs[i].flags = VFIO_IRQ_INFO_EVENTFD;
 
-		if (irq_get_trigger_type(hwirq) & IRQ_TYPE_LEVEL_MASK)
+		if (irq_get_trigger_type(hwirq) & IRQ_TYPE_LEVEL_MASK) {
 			vdev->irqs[i].flags |= VFIO_IRQ_INFO_MASKABLE
 						| VFIO_IRQ_INFO_AUTOMASKED;
+			handler = vfio_automasked_irq_handler;
+		}
 
 		vdev->irqs[i].count = 1;
 		vdev->irqs[i].hwirq = hwirq;
 		vdev->irqs[i].masked = false;
+		vdev->irqs[i].name = kasprintf(GFP_KERNEL,
+					       "vfio-irq[%d](%s)", hwirq,
+					       vdev->name);
+		if (!vdev->irqs[i].name) {
+			ret = -ENOMEM;
+			goto err;
+		}
+
+		ret = request_irq(hwirq, handler, IRQF_NO_AUTOEN,
+				  vdev->irqs[i].name, &vdev->irqs[i]);
+		if (ret) {
+			kfree(vdev->irqs[i].name);
+			vdev->irqs[i].name = ERR_PTR(ret);
+		}
 	}
 
 	vdev->num_irqs = cnt;
 
 	return 0;
 err:
+	for (--i; i >= 0; i--) {
+		if (!IS_ERR(vdev->irqs[i].name)) {
+			free_irq(vdev->irqs[i].hwirq, &vdev->irqs[i]);
+			kfree(vdev->irqs[i].name);
+		}
+	}
 	kfree(vdev->irqs);
-	return -EINVAL;
+	return ret;
 }
 
 void vfio_platform_irq_cleanup(struct vfio_platform_device *vdev)
@@ -324,7 +354,12 @@ void vfio_platform_irq_cleanup(struct vf
 	for (i = 0; i < vdev->num_irqs; i++) {
 		vfio_virqfd_disable(&vdev->irqs[i].mask);
 		vfio_virqfd_disable(&vdev->irqs[i].unmask);
-		vfio_set_trigger(vdev, i, -1, NULL);
+		if (!IS_ERR(vdev->irqs[i].name)) {
+			free_irq(vdev->irqs[i].hwirq, &vdev->irqs[i]);
+			if (vdev->irqs[i].trigger)
+				eventfd_ctx_put(vdev->irqs[i].trigger);
+			kfree(vdev->irqs[i].name);
+		}
 	}
 
 	vdev->num_irqs = 0;
author maintainer
#570 lore raw

PATCH 566/690 vfio/fsl-mc: Block calling interrupt handler without trigger

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alex Williamson <[email protected]>

[ Upstream commit 7447d911af699a15f8d050dfcb7c680a86f87012 ]

The eventfd_ctx trigger pointer of the vfio_fsl_mc_irq object is initially NULL and may become NULL if the user sets the trigger eventfd to -1. The interrupt handler itself is guaranteed that trigger is always valid between request_irq() and free_irq(), but the loopback testing mechanisms to invoke the handler function need to test the trigger. The triggering and setting ioctl paths both make use of igate and are therefore mutually exclusive.

The vfio-fsl-mc driver does not make use of irqfds, nor does it support any sort of masking operations, therefore unlike vfio-pci and vfio-platform, the flow can remain essentially unchanged.

---
 drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)
drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c +4 -3
@@ -142,13 +142,14 @@ static int vfio_fsl_mc_set_irq_trigger(s
 	irq = &vdev->mc_irqs[index];
 
 	if (flags & VFIO_IRQ_SET_DATA_NONE) {
-		vfio_fsl_mc_irq_handler(hwirq, irq);
+		if (irq->trigger)
+			eventfd_signal(irq->trigger, 1);
 
 	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
 		u8 trigger = *(u8 *)data;
 
-		if (trigger)
-			vfio_fsl_mc_irq_handler(hwirq, irq);
+		if (trigger && irq->trigger)
+			eventfd_signal(irq->trigger, 1);
 	}
 
 	return 0;
author maintainer
#571 lore raw

PATCH 567/690 serial: sc16is7xx: convert from _raw_ to _noinc_ regmap functions for FIFO

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hugo Villeneuve <[email protected]>

commit dbf4ab821804df071c8b566d9813083125e6d97b upstream.

The SC16IS7XX IC supports a burst mode to access the FIFOs where the initial register address is sent ($00), followed by all the FIFO data without having to resend the register address each time. In this mode, the IC doesn't increment the register address for each R/W byte.

The regmap_raw_read() and regmap_raw_write() are functions which can perform IO over multiple registers. They are currently used to read/write from/to the FIFO, and although they operate correctly in this burst mode on the SPI bus, they would corrupt the regmap cache if it was not disabled manually. The reason is that when the R/W size is more than 1 byte, these functions assume that the register address is incremented and handle the cache accordingly.

Convert FIFO R/W functions to use the regmap _noinc_ versions in order to remove the manual cache control which was a workaround when using the _raw_ versions. FIFO registers are properly declared as volatile so cache will not be used/updated for FIFO accesses.

---
 drivers/tty/serial/sc16is7xx.c |   15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)
drivers/tty/serial/sc16is7xx.c +9 -6
@@ -376,9 +376,7 @@ static void sc16is7xx_fifo_read(struct u
 	const u8 line = sc16is7xx_line(port);
 	u8 addr = (SC16IS7XX_RHR_REG << SC16IS7XX_REG_SHIFT) | line;
 
-	regcache_cache_bypass(s->regmap, true);
-	regmap_raw_read(s->regmap, addr, s->buf, rxlen);
-	regcache_cache_bypass(s->regmap, false);
+	regmap_noinc_read(s->regmap, addr, s->buf, rxlen);
 }
 
 static void sc16is7xx_fifo_write(struct uart_port *port, u8 to_send)
@@ -394,9 +392,7 @@ static void sc16is7xx_fifo_write(struct
 	if (unlikely(!to_send))
 		return;
 
-	regcache_cache_bypass(s->regmap, true);
-	regmap_raw_write(s->regmap, addr, s->buf, to_send);
-	regcache_cache_bypass(s->regmap, false);
+	regmap_noinc_write(s->regmap, addr, s->buf, to_send);
 }
 
 static void sc16is7xx_port_update(struct uart_port *port, u8 reg,
@@ -489,6 +485,11 @@ static bool sc16is7xx_regmap_precious(st
 	return false;
 }
 
+static bool sc16is7xx_regmap_noinc(struct device *dev, unsigned int reg)
+{
+	return reg == SC16IS7XX_RHR_REG;
+}
+
 static int sc16is7xx_set_baud(struct uart_port *port, int baud)
 {
 	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
@@ -1439,6 +1440,8 @@ static struct regmap_config regcfg = {
 	.cache_type = REGCACHE_RBTREE,
 	.volatile_reg = sc16is7xx_regmap_volatile,
 	.precious_reg = sc16is7xx_regmap_precious,
+	.writeable_noinc_reg = sc16is7xx_regmap_noinc,
+	.readable_noinc_reg = sc16is7xx_regmap_noinc,
 };
 
 #ifdef CONFIG_SERIAL_SC16IS7XX_SPI
author maintainer
#572 lore raw

PATCH 568/690 mm/migrate: set swap entry values of THP tail pages properly.

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Zi Yan <[email protected]>

The tail pages in a THP can have swap entry information stored in their private field. When migrating to a new page, all tail pages of the new page need to update ->private to avoid future data corruption.

This fix is stable-only, since after commit 07e09c483cbe ("mm/huge_memory:
work on folio->swap instead of page->private when splitting folio"), subpages of a swapcached THP no longer requires the maintenance.

Adding THPs to the swapcache was introduced in commit 38d8b4e6bdc87 ("mm, THP, swap: delay splitting THP during swap out"), where each subpage of a THP added to the swapcache had its own swapcache entry and required the ->private field to point to the correct swapcache entry. Later, when THP migration functionality was implemented in commit 616b8371539a6 ("mm: thp: enable thp migration in generic path"), it initially did not handle the subpages of swapcached THPs, failing to update their ->private fields or replace the subpage pointers in the swapcache. Subsequently, commit e71769ae5260 ("mm: enable thp migration for shmem thp") addressed the swapcache update aspect. This patch fixes the update of subpage ->private fields.

Fixes 616b8371539a ("mm: thp: enable thp migration in generic path")
---
 mm/migrate.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
mm/migrate.c +5 -1
@@ -424,8 +424,12 @@ int migrate_page_move_mapping(struct add
 	if (PageSwapBacked(page)) {
 		__SetPageSwapBacked(newpage);
 		if (PageSwapCache(page)) {
+			int i;
+
 			SetPageSwapCache(newpage);
-			set_page_private(newpage, page_private(page));
+			for (i = 0; i < (1 << compound_order(page)); i++)
+				set_page_private(newpage + i,
+						 page_private(page + i));
 		}
 	} else {
 		VM_BUG_ON_PAGE(PageSwapCache(page), page);
author maintainer
#573 lore raw

PATCH 569/690 init: open /initrd.image with O_LARGEFILE

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: John Sperbeck <[email protected]>

commit 4624b346cf67400ef46a31771011fb798dd2f999 upstream.

If initrd data is larger than 2Gb, we'll eventually fail to write to the /initrd.image file when we hit that limit, unless O_LARGEFILE is set.

---
 init/initramfs.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
init/initramfs.c +1 -1
@@ -655,7 +655,7 @@ static void __init populate_initrd_image
 
 	printk(KERN_INFO "rootfs image is not initramfs (%s); looks like an initrd\n",
 			err);
-	file = filp_open("/initrd.image", O_WRONLY | O_CREAT, 0700);
+	file = filp_open("/initrd.image", O_WRONLY|O_CREAT|O_LARGEFILE, 0700);
 	if (IS_ERR(file))
 		return;
 
author maintainer
#574 lore raw

PATCH 570/690 btrfs: zoned: use zone aware sb location for scrub

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Johannes Thumshirn <[email protected]>

commit 74098a989b9c3370f768140b7783a7aaec2759b3 upstream.

At the moment scrub_supers() doesn't grab the super block's location via the zoned device aware btrfs_sb_log_location() but via btrfs_sb_offset().

This leads to checksum errors on 'scrub' as we're not accessing the correct location of the super block.

So use btrfs_sb_log_location() for getting the super blocks location on scrub.

---
 fs/btrfs/scrub.c |   12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)
fs/btrfs/scrub.c +11 -1
@@ -3972,7 +3972,17 @@ static noinline_for_stack int scrub_supe
 		gen = fs_info->last_trans_committed;
 
 	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
-		bytenr = btrfs_sb_offset(i);
+		ret = btrfs_sb_log_location(scrub_dev, i, 0, &bytenr);
+		if (ret == -ENOENT)
+			break;
+
+		if (ret) {
+			spin_lock(&sctx->stat_lock);
+			sctx->stat.super_errors++;
+			spin_unlock(&sctx->stat_lock);
+			continue;
+		}
+
 		if (bytenr + BTRFS_SUPER_INFO_SIZE >
 		    scrub_dev->commit_total_bytes)
 			break;
author maintainer
#575 lore raw

PATCH 571/690 wifi: mac80211: check/clear fast rx for non-4addr sta VLAN changes

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Felix Fietkau <[email protected]>

commit 4f2bdb3c5e3189297e156b3ff84b140423d64685 upstream.

When moving a station out of a VLAN and deleting the VLAN afterwards, the fast_rx entry still holds a pointer to the VLAN's netdev, which can cause use-after-free bugs. Fix this by immediately calling ieee80211_check_fast_rx after the VLAN change.

---
 net/mac80211/cfg.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)
net/mac80211/cfg.c +2 -3
@@ -1845,15 +1845,14 @@ static int ieee80211_change_station(stru
 		}
 
 		if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
-		    sta->sdata->u.vlan.sta) {
-			ieee80211_clear_fast_rx(sta);
+		    sta->sdata->u.vlan.sta)
 			RCU_INIT_POINTER(sta->sdata->u.vlan.sta, NULL);
-		}
 
 		if (test_sta_flag(sta, WLAN_STA_AUTHORIZED))
 			ieee80211_vif_dec_num_mcast(sta->sdata);
 
 		sta->sdata = vlansdata;
+		ieee80211_check_fast_rx(sta);
 		ieee80211_check_fast_xmit(sta);
 
 		if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) {
author maintainer
#576 lore raw

PATCH 572/690 exec: Fix NOMMU linux_binprm::exec in transfer_args_to_stack()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Max Filippov <[email protected]>

commit 2aea94ac14d1e0a8ae9e34febebe208213ba72f7 upstream.

In NOMMU kernel the value of linux_binprm::p is the offset inside the temporary program arguments array maintained in separate pages in the linux_binprm::page. linux_binprm::exec being a copy of linux_binprm::p thus must be adjusted when that array is copied to the user stack. Without that adjustment the value passed by the NOMMU kernel to the ELF program in the AT_EXECFN entry of the aux array doesn't make any sense and it may break programs that try to access memory pointed to by that entry.

Adjust linux_binprm::exec before the successful return from the transfer_args_to_stack().

Fixes b6a2fea39318 ("mm: variable length argument support")
Fixes 5edc2a5123a7 ("binfmt_elf_fdpic: wire up AT_EXECFD, AT_EXECFN, AT_SECURE")
---
 fs/exec.c |    1 +
 1 file changed, 1 insertion(+)
fs/exec.c +1 -0
@@ -888,6 +888,7 @@ int transfer_args_to_stack(struct linux_
 			goto out;
 	}
 
+	bprm->exec += *sp_location - MAX_ARG_PAGES * PAGE_SIZE;
 	*sp_location = sp;
 
 out:
author maintainer
#577 lore raw

PATCH 573/690 hexagon: vmlinux.lds.S: handle attributes section

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nathan Chancellor <[email protected]>

commit 549aa9678a0b3981d4821bf244579d9937650562 upstream.

After the linked LLVM change, the build fails with CONFIG_LD_ORPHAN_WARN_LEVEL="error", which happens with allmodconfig:

ld.lld: error: vmlinux.a(init/main.o):(.hexagon.attributes) is being placed in '.hexagon.attributes'

Handle the attributes section in a similar manner as arm and riscv by adding it after the primary ELF_DETAILS grouping in vmlinux.lds.S, which fixes the error.

---
 arch/hexagon/kernel/vmlinux.lds.S |    1 +
 1 file changed, 1 insertion(+)
arch/hexagon/kernel/vmlinux.lds.S +1 -0
@@ -64,6 +64,7 @@ SECTIONS
 	STABS_DEBUG
 	DWARF_DEBUG
 	ELF_DETAILS
+	.hexagon.attributes 0 : { *(.hexagon.attributes) }
 
 	DISCARDS
 }
author maintainer
#578 lore raw

PATCH 574/690 mmc: core: Initialize mmc_blk_ioc_data

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mikko Rapeli <[email protected]>

commit 0cdfe5b0bf295c0dee97436a8ed13336933a0211 upstream.

Commit 4d0c8d0aef63 ("mmc: core: Use mrq.sbc in close-ended ffu") adds flags uint to struct mmc_blk_ioc_data, but it does not get initialized for RPMB ioctls which now fails.

Let's fix this by always initializing the struct and flags to zero.

---
 drivers/mmc/core/block.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/mmc/core/block.c +1 -1
@@ -412,7 +412,7 @@ static struct mmc_blk_ioc_data *mmc_blk_
 	struct mmc_blk_ioc_data *idata;
 	int err;
 
-	idata = kmalloc(sizeof(*idata), GFP_KERNEL);
+	idata = kzalloc(sizeof(*idata), GFP_KERNEL);
 	if (!idata) {
 		err = -ENOMEM;
 		goto out;
author maintainer
#579 lore raw

PATCH 575/690 mmc: core: Avoid negative index with array access

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mikko Rapeli <[email protected]>

commit cf55a7acd1ed38afe43bba1c8a0935b51d1dc014 upstream.

Commit 4d0c8d0aef63 ("mmc: core: Use mrq.sbc in close-ended ffu") assigns prev_idata = idatas[i - 1], but doesn't check that the iterator i is greater than zero. Let's fix this by adding a check.

---
 drivers/mmc/core/block.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/mmc/core/block.c +1 -1
@@ -485,7 +485,7 @@ static int __mmc_blk_ioctl_cmd(struct mm
 	if (idata->flags & MMC_BLK_IOC_DROP)
 		return 0;
 
-	if (idata->flags & MMC_BLK_IOC_SBC)
+	if (idata->flags & MMC_BLK_IOC_SBC && i > 0)
 		prev_idata = idatas[i - 1];
 
 	/*
author maintainer
#580 lore raw

PATCH 576/690 net: ll_temac: platform_get_resource replaced by wrong function

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Claus Hansen Ries <[email protected]>

commit 3a38a829c8bc27d78552c28e582eb1d885d07d11 upstream.

The function platform_get_resource was replaced with devm_platform_ioremap_resource_byname and is called using 0 as name.

This eventually ends up in platform_get_resource_byname in the call stack, where it causes a null pointer in strcmp.

	if (type == resource_type(r) && !strcmp(r->name, name))

It should have been replaced with devm_platform_ioremap_resource.

Fixes bd69058f50d5 ("net: ll_temac: Use devm_platform_ioremap_resource_byname()")
---
 drivers/net/ethernet/xilinx/ll_temac_main.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/xilinx/ll_temac_main.c +1 -1
@@ -1433,7 +1433,7 @@ static int temac_probe(struct platform_d
 	}
 
 	/* map device registers */
-	lp->regs = devm_platform_ioremap_resource_byname(pdev, 0);
+	lp->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(lp->regs)) {
 		dev_err(&pdev->dev, "could not map TEMAC registers\n");
 		return -ENOMEM;
author maintainer
#581 lore raw

PATCH 577/690 drm/i915/gt: Reset queue_priority_hint on parking

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Chris Wilson <[email protected]>

commit 4a3859ea5240365d21f6053ee219bb240d520895 upstream.

Originally, with strict in order execution, we could complete execution only when the queue was empty. Preempt-to-busy allows replacement of an active request that may complete before the preemption is processed by HW. If that happens, the request is retired from the queue, but the queue_priority_hint remains set, preventing direct submission until after the next CS interrupt is processed.

This preempt-to-busy race can be triggered by the heartbeat, which will also act as the power-management barrier and upon completion allow us to idle the HW. We may process the completion of the heartbeat, and begin parking the engine before the CS event that restores the queue_priority_hint, causing us to fail the assertion that it is MIN.

<3>[  166.210729] __engine_park:283 GEM_BUG_ON(engine->sched_engine->queue_priority_hint != (-((int)(~0U >> 1)) - 1))
<0>[  166.210781] Dumping ftrace buffer:
<0>[  166.210795] ---------------------------------
...
<0>[  167.302811] drm_fdin-1097      2..s1. 165741070us : trace_ports: 0000:00:02.0 rcs0: promote { ccid:20 1217:2 prio 0 }
<0>[  167.302861] drm_fdin-1097      2d.s2. 165741072us : execlists_submission_tasklet: 0000:00:02.0 rcs0: preempting last=1217:2, prio=0, hint=2147483646
<0>[  167.302928] drm_fdin-1097      2d.s2. 165741072us : __i915_request_unsubmit: 0000:00:02.0 rcs0: fence 1217:2, current 0
<0>[  167.302992] drm_fdin-1097      2d.s2. 165741073us : __i915_request_submit: 0000:00:02.0 rcs0: fence 3:4660, current 4659
<0>[  167.303044] drm_fdin-1097      2d.s1. 165741076us : execlists_submission_tasklet: 0000:00:02.0 rcs0: context:3 schedule-in, ccid:40
<0>[  167.303095] drm_fdin-1097      2d.s1. 165741077us : trace_ports: 0000:00:02.0 rcs0: submit { ccid:40 3:4660* prio 2147483646 }
<0>[  167.303159] kworker/-89       11..... 165741139us : i915_request_retire.part.0: 0000:00:02.0 rcs0: fence c90:2, current 2
<0>[  167.303208] kworker/-89       11..... 165741148us : __intel_context_do_unpin: 0000:00:02.0 rcs0: context:c90 unpin
<0>[  167.303272] kworker/-89       11..... 165741159us : i915_request_retire.part.0: 0000:00:02.0 rcs0: fence 1217:2, current 2
<0>[  167.303321] kworker/-89       11..... 165741166us : __intel_context_do_unpin: 0000:00:02.0 rcs0: context:1217 unpin
<0>[  167.303384] kworker/-89       11..... 165741170us : i915_request_retire.part.0: 0000:00:02.0 rcs0: fence 3:4660, current 4660
<0>[  167.303434] kworker/-89       11d..1. 165741172us : __intel_context_retire: 0000:00:02.0 rcs0: context:1216 retire runtime: { total:56028ns, avg:56028ns }
<0>[  167.303484] kworker/-89       11..... 165741198us : __engine_park: 0000:00:02.0 rcs0: parked
<0>[  167.303534]   <idle>-0         5d.H3. 165741207us : execlists_irq_handler: 0000:00:02.0 rcs0: semaphore yield: 00000040
<0>[  167.303583] kworker/-89       11..... 165741397us : __intel_context_retire: 0000:00:02.0 rcs0: context:1217 retire runtime: { total:325575ns, avg:0ns }
<0>[  167.303756] kworker/-89       11..... 165741777us : __intel_context_retire: 0000:00:02.0 rcs0: context:c90 retire runtime: { total:0ns, avg:0ns }
<0>[  167.303806] kworker/-89       11..... 165742017us : __engine_park: __engine_park:283 GEM_BUG_ON(engine->sched_engine->queue_priority_hint != (-((int)(~0U >> 1)) - 1))
<0>[  167.303811] ---------------------------------
<4>[  167.304722] ------------[ cut here ]------------
<2>[  167.304725] kernel BUG at drivers/gpu/drm/i915/gt/intel_engine_pm.c:283!
<4>[  167.304731] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI
<4>[  167.304734] CPU: 11 PID: 89 Comm: kworker/11:1 Tainted: G        W          6.8.0-rc2-CI_DRM_14193-gc655e0fd2804+ #1
<4>[  167.304736] Hardware name: Intel Corporation Rocket Lake Client Platform/RocketLake S UDIMM 6L RVP, BIOS RKLSFWI1.R00.3173.A03.2204210138 04/21/2022
<4>[  167.304738] Workqueue: i915-unordered retire_work_handler [i915]
<4>[  167.304839] RIP: 0010:__engine_park+0x3fd/0x680 [i915]
<4>[  167.304937] Code: 00 48 c7 c2 b0 e5 86 a0 48 8d 3d 00 00 00 00 e8 79 48 d4 e0 bf 01 00 00 00 e8 ef 0a d4 e0 31 f6 bf 09 00 00 00 e8 03 49 c0 e0 <0f> 0b 0f 0b be 01 00 00 00 e8 f5 61 fd ff 31 c0 e9 34 fd ff ff 48
<4>[  167.304940] RSP: 0018:ffffc9000059fce0 EFLAGS: 00010246
<4>[  167.304942] RAX: 0000000000000200 RBX: 0000000000000000 RCX: 0000000000000006
<4>[  167.304944] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000009
<4>[  167.304946] RBP: ffff8881330ca1b0 R08: 0000000000000001 R09: 0000000000000001
<4>[  167.304947] R10: 0000000000000001 R11: 0000000000000001 R12: ffff8881330ca000
<4>[  167.304948] R13: ffff888110f02aa0 R14: ffff88812d1d0205 R15: ffff88811277d4f0
<4>[  167.304950] FS:  0000000000000000(0000) GS:ffff88844f780000(0000) knlGS:0000000000000000
<4>[  167.304952] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
<4>[  167.304953] CR2: 00007fc362200c40 CR3: 000000013306e003 CR4: 0000000000770ef0
<4>[  167.304955] PKRU: 55555554
<4>[  167.304957] Call Trace:
<4>[  167.304958]  <TASK>
<4>[  167.305573]  ____intel_wakeref_put_last+0x1d/0x80 [i915]
<4>[  167.305685]  i915_request_retire.part.0+0x34f/0x600 [i915]
<4>[  167.305800]  retire_requests+0x51/0x80 [i915]
<4>[  167.305892]  intel_gt_retire_requests_timeout+0x27f/0x700 [i915]
<4>[  167.305985]  process_scheduled_works+0x2db/0x530
<4>[  167.305990]  worker_thread+0x18c/0x350
<4>[  167.305993]  kthread+0xfe/0x130
<4>[  167.305997]  ret_from_fork+0x2c/0x50
<4>[  167.306001]  ret_from_fork_asm+0x1b/0x30
<4>[  167.306004]  </TASK>

It is necessary for the queue_priority_hint to be lower than the next request submission upon waking up, as we rely on the hint to decide when to kick the tasklet to submit that first request.

Fixes 22b7a426bbe1 ("drm/i915/execlists: Preempt-to-busy")
Cc Mika Kuoppala <[email protected]>
Cc <[email protected]> # v5.4+
(cherry picked from commit 98850e96cf811dc2d0a7d0af491caff9f5d49c1e)
---
 drivers/gpu/drm/i915/gt/intel_engine_pm.c            |    3 ---
 drivers/gpu/drm/i915/gt/intel_execlists_submission.c |    3 +++
 2 files changed, 3 insertions(+), 3 deletions(-)
drivers/gpu/drm/i915/gt/intel_engine_pm.c +0 -3
@@ -274,9 +274,6 @@ static int __engine_park(struct intel_wa
 	intel_engine_park_heartbeat(engine);
 	intel_breadcrumbs_park(engine->breadcrumbs);
 
-	/* Must be reset upon idling, or we may miss the busy wakeup. */
-	GEM_BUG_ON(engine->sched_engine->queue_priority_hint != INT_MIN);
-
 	if (engine->park)
 		engine->park(engine);
 
drivers/gpu/drm/i915/gt/intel_execlists_submission.c +3 -0
@@ -3188,6 +3188,9 @@ static void execlists_park(struct intel_
 {
 	cancel_timer(&engine->execlists.timer);
 	cancel_timer(&engine->execlists.preempt);
+
+	/* Reset upon idling, or we may delay the busy wakeup. */
+	WRITE_ONCE(engine->sched_engine->queue_priority_hint, INT_MIN);
 }
 
 static void add_to_engine(struct i915_request *rq)
author maintainer
#582 lore raw

PATCH 578/690 usb: cdc-wdm: close race between read and workqueue

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Oliver Neukum <[email protected]>

commit 339f83612f3a569b194680768b22bf113c26a29d upstream.

wdm_read() cannot race with itself. However, in service_outstanding_interrupt() it can race with the workqueue, which can be triggered by error handling.

Hence we need to make sure that the WDM_RESPONDING flag is not just only set but tested.

---
 drivers/usb/class/cdc-wdm.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/usb/class/cdc-wdm.c +5 -1
@@ -485,6 +485,7 @@ out_free_mem:
 static int service_outstanding_interrupt(struct wdm_device *desc)
 {
 	int rv = 0;
+	int used;
 
 	/* submit read urb only if the device is waiting for it */
 	if (!desc->resp_count || !--desc->resp_count)
@@ -499,7 +500,10 @@ static int service_outstanding_interrupt
 		goto out;
 	}
 
-	set_bit(WDM_RESPONDING, &desc->flags);
+	used = test_and_set_bit(WDM_RESPONDING, &desc->flags);
+	if (used)
+		goto out;
+
 	spin_unlock_irq(&desc->iuspin);
 	rv = usb_submit_urb(desc->response, GFP_KERNEL);
 	spin_lock_irq(&desc->iuspin);
author maintainer
#583 lore raw

PATCH 579/690 drm/amdgpu: Use drm_mode_copy()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ville Syrjälä <[email protected]>

[ Upstream commit 426c89aa203bcec9d9cf6eea36735eafa1b1f099 ]

struct drm_display_mode embeds a list head, so overwriting the full struct with another one will corrupt the list (if the destination mode is on a list). Use drm_mode_copy() instead which explicitly preserves the list head of the destination mode.

Even if we know the destination mode is not on any list using drm_mode_copy() seems decent as it sets a good example. Bad examples of not using it might eventually get copied into code where preserving the list head actually matters.

Obviously one case not covered here is when the mode itself is embedded in a larger structure and the whole structure is copied. But if we are careful when copying into modes embedded in structures I think we can be a little more reassured that bogus list heads haven't been propagated in.

@is_mode_copy@
@@
drm_mode_copy(...)
{
...
}

@depends on !is_mode_copy@
struct drm_display_mode *mode;
expression E, S;
@@
(
- *mode = E
+ drm_mode_copy(mode, &E)
|
- memcpy(mode, E, S)
+ drm_mode_copy(mode, E)
)

@depends on !is_mode_copy@
struct drm_display_mode mode;
expression E;
@@
(
- mode = E
+ drm_mode_copy(&mode, &E)
|
- memcpy(&mode, E, S)
+ drm_mode_copy(&mode, E)
)

@@
struct drm_display_mode *mode;
@@
- &*mode
+ mode

Stable-dep-of: 79f3e38f60e5 ("drm/amd/display: Preserve original aspect ratio in create stream")

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c    | 4 ++--
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c +2 -2
index c777aff164b76..654f99f4107ea 100644
@@ -625,7 +625,7 @@ amdgpu_connector_fixup_lcd_native_mode(struct drm_encoder *encoder,
 		if (mode->type & DRM_MODE_TYPE_PREFERRED) {
 			if (mode->hdisplay != native_mode->hdisplay ||
 			    mode->vdisplay != native_mode->vdisplay)
-				memcpy(native_mode, mode, sizeof(*mode));
+				drm_mode_copy(native_mode, mode);
 		}
 	}
 
@@ -634,7 +634,7 @@ amdgpu_connector_fixup_lcd_native_mode(struct drm_encoder *encoder,
 		list_for_each_entry_safe(mode, t, &connector->probed_modes, head) {
 			if (mode->hdisplay == native_mode->hdisplay &&
 			    mode->vdisplay == native_mode->vdisplay) {
-				*native_mode = *mode;
+				drm_mode_copy(native_mode, mode);
 				drm_mode_set_crtcinfo(native_mode, CRTC_INTERLACE_HALVE_V);
 				DRM_DEBUG_KMS("Determined LVDS native mode details from EDID\n");
 				break;
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +3 -3
index 7385efe699f88..9356decd14513 100644
@@ -6219,7 +6219,7 @@ get_highest_refresh_rate_mode(struct amdgpu_dm_connector *aconnector,
 		}
 	}
 
-	aconnector->freesync_vid_base = *m_pref;
+	drm_mode_copy(&aconnector->freesync_vid_base, m_pref);
 	return m_pref;
 }
 
@@ -6333,8 +6333,8 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 				 is_freesync_video_mode(&mode, aconnector);
 		if (recalculate_timing) {
 			freesync_mode = get_highest_refresh_rate_mode(aconnector, false);
-			saved_mode = mode;
-			mode = *freesync_mode;
+			drm_mode_copy(&saved_mode, &mode);
+			drm_mode_copy(&mode, freesync_mode);
 		} else {
 			decide_crtc_timing_for_drm_display_mode(
 				&mode, preferred_mode, scale);
Signature · 1 line
2.43.0
author maintainer
#584 lore raw

PATCH 580/690 drm/amd/display: Preserve original aspect ratio in create stream

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Tom Chung <[email protected]>

[ Upstream commit 79f3e38f60e5b2416ba99804d83d22e69ae592a3 ]

[Why]
The original picture aspect ratio in mode struct may have chance be overwritten with wrong aspect ratio data in create_stream_for_sink(). It will create a different VIC output and cause HDMI compliance test failed.

[How]
Preserve the original picture aspect ratio data during create the stream.

---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 ++
 1 file changed, 2 insertions(+)
drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +2 -0
index 9356decd14513..b7b8a2d77da67 100644
@@ -6334,7 +6334,9 @@ create_stream_for_sink(struct amdgpu_dm_connector *aconnector,
 		if (recalculate_timing) {
 			freesync_mode = get_highest_refresh_rate_mode(aconnector, false);
 			drm_mode_copy(&saved_mode, &mode);
+			saved_mode.picture_aspect_ratio = mode.picture_aspect_ratio;
 			drm_mode_copy(&mode, freesync_mode);
+			mode.picture_aspect_ratio = saved_mode.picture_aspect_ratio;
 		} else {
 			decide_crtc_timing_for_drm_display_mode(
 				&mode, preferred_mode, scale);
Signature · 1 line
2.43.0
author maintainer
#585 lore raw

PATCH 581/690 ALSA: sh: aica: reorder cleanup operations to avoid UAF bugs

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Duoming Zhou <[email protected]>

commit 051e0840ffa8ab25554d6b14b62c9ab9e4901457 upstream.

The dreamcastcard->timer could schedule the spu_dma_work and the spu_dma_work could also arm the dreamcastcard->timer.

When the snd_pcm_substream is closing, the aica_channel will be deallocated. But it could still be dereferenced in the worker thread. The reason is that del_timer() will return directly regardless of whether the timer handler is running or not and the worker could be rescheduled in the timer handler. As a result, the UAF bug will happen. The racy situation is shown below:

      (Thread 1)                 |      (Thread 2)
snd_aicapcm_pcm_close()          |
 ...                             |  run_spu_dma() //worker
                                 |    mod_timer()
  flush_work()                   |
  del_timer()                    |  aica_period_elapsed() //timer
  kfree(dreamcastcard->channel)  |    schedule_work()
                                 |  run_spu_dma() //worker
  ...                            |    dreamcastcard->channel-> //USE

In order to mitigate this bug and other possible corner cases, call mod_timer() conditionally in run_spu_dma(), then implement PCM sync_stop op to cancel both the timer and worker. The sync_stop op will be called from PCM core appropriately when needed.

Fixes 198de43d758c ("[ALSA] Add ALSA support for the SEGA Dreamcast PCM device")

Message-ID: <[email protected]>

---
 sound/sh/aica.c |   17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)
sound/sh/aica.c +14 -3
@@ -278,7 +278,8 @@ static void run_spu_dma(struct work_stru
 		dreamcastcard->clicks++;
 		if (unlikely(dreamcastcard->clicks >= AICA_PERIOD_NUMBER))
 			dreamcastcard->clicks %= AICA_PERIOD_NUMBER;
-		mod_timer(&dreamcastcard->timer, jiffies + 1);
+		if (snd_pcm_running(dreamcastcard->substream))
+			mod_timer(&dreamcastcard->timer, jiffies + 1);
 	}
 }
 
@@ -290,6 +291,8 @@ static void aica_period_elapsed(struct t
 	/*timer function - so cannot sleep */
 	int play_period;
 	struct snd_pcm_runtime *runtime;
+	if (!snd_pcm_running(substream))
+		return;
 	runtime = substream->runtime;
 	dreamcastcard = substream->pcm->private_data;
 	/* Have we played out an additional period? */
@@ -350,12 +353,19 @@ static int snd_aicapcm_pcm_open(struct s
 	return 0;
 }
 
+static int snd_aicapcm_pcm_sync_stop(struct snd_pcm_substream *substream)
+{
+	struct snd_card_aica *dreamcastcard = substream->pcm->private_data;
+
+	del_timer_sync(&dreamcastcard->timer);
+	cancel_work_sync(&dreamcastcard->spu_dma_work);
+	return 0;
+}
+
 static int snd_aicapcm_pcm_close(struct snd_pcm_substream
 				 *substream)
 {
 	struct snd_card_aica *dreamcastcard = substream->pcm->private_data;
-	flush_work(&(dreamcastcard->spu_dma_work));
-	del_timer(&dreamcastcard->timer);
 	dreamcastcard->substream = NULL;
 	kfree(dreamcastcard->channel);
 	spu_disable();
@@ -401,6 +411,7 @@ static const struct snd_pcm_ops snd_aica
 	.prepare = snd_aicapcm_pcm_prepare,
 	.trigger = snd_aicapcm_pcm_trigger,
 	.pointer = snd_aicapcm_pcm_pointer,
+	.sync_stop = snd_aicapcm_pcm_sync_stop,
 };
 
 /* TO DO: set up to handle more than one pcm instance */
author maintainer
#586 lore raw

PATCH 582/690 scsi: core: Fix unremoved procfs host directory regression

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Guilherme G. Piccoli <[email protected]>

commit f23a4d6e07570826fe95023ca1aa96a011fa9f84 upstream.

Commit fc663711b944 ("scsi: core: Remove the /proc/scsi/${proc_name} directory earlier") fixed a bug related to modules loading/unloading, by adding a call to scsi_proc_hostdir_rm() on scsi_remove_host(). But that led to a potential duplicate call to the hostdir_rm() routine, since it's also called from scsi_host_dev_release(). That triggered a regression report, which was then fixed by commit be03df3d4bfe ("scsi: core: Fix a procfs host directory removal regression"). The fix just dropped the hostdir_rm() call from dev_release().

But it happens that this proc directory is created on scsi_host_alloc(), and that function "pairs" with scsi_host_dev_release(), while scsi_remove_host() pairs with scsi_add_host(). In other words, it seems the reason for removing the proc directory on dev_release() was meant to cover cases in which a SCSI host structure was allocated, but the call to scsi_add_host() didn't happen. And that pattern happens to exist in some error paths, for example.

Syzkaller causes that by using USB raw gadget device, error'ing on usb-storage driver, at usb_stor_probe2(). By checking that path, we can see that the BadDevice label leads to a scsi_host_put() after a SCSI host allocation, but there's no call to scsi_add_host() in such path. That leads to messages like this in dmesg (and a leak of the SCSI host proc structure):

usb-storage 4-1:87.51: USB Mass Storage device detected proc_dir_entry 'scsi/usb-storage' already registered

WARNING: CPU: 1 PID: 3519 at fs/proc/generic.c:377 proc_register+0x347/0x4e0 fs/proc/generic.c:376

The proper fix seems to still call scsi_proc_hostdir_rm() on dev_release(), but guard that with the state check for SHOST_CREATED; there is even a comment in scsi_host_dev_release() detailing that: such conditional is meant for cases where the SCSI host was allocated but there was no calls to {add,remove}_host(), like the usb-storage case.

This is what we propose here and with that, the error path of usb-storage does not trigger the warning anymore.

Reported-by [email protected]
Fixes be03df3d4bfe ("scsi: core: Fix a procfs host directory removal regression")
Cc Bart Van Assche <[email protected]>
Cc John Garry <[email protected]>
Cc Shin'ichiro Kawasaki <[email protected]>
---
 drivers/scsi/hosts.c |    7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)
drivers/scsi/hosts.c +4 -3
@@ -334,12 +334,13 @@ static void scsi_host_dev_release(struct
 
 	if (shost->shost_state == SHOST_CREATED) {
 		/*
-		 * Free the shost_dev device name here if scsi_host_alloc()
-		 * and scsi_host_put() have been called but neither
+		 * Free the shost_dev device name and remove the proc host dir
+		 * here if scsi_host_{alloc,put}() have been called but neither
 		 * scsi_host_add() nor scsi_host_remove() has been called.
 		 * This avoids that the memory allocated for the shost_dev
-		 * name is leaked.
+		 * name as well as the proc dir structure are leaked.
 		 */
+		scsi_proc_hostdir_rm(shost->hostt);
 		kfree(dev_name(&shost->shost_dev));
 	}
 
author maintainer
#587 lore raw

PATCH 583/690 staging: vc04_services: changen strncpy() to strscpy_pad()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Arnd Bergmann <[email protected]>

commit ef25725b7f8aaffd7756974d3246ec44fae0a5cf upstream.

gcc-14 warns about this strncpy() that results in a non-terminated string for an overflow:

In file included from include/linux/string.h:369,
from drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c:20:
In function 'strncpy',
inlined from 'create_component' at drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c:940:2:
include/linux/fortify-string.h:108:33: error: '__builtin_strncpy' specified bound 128 equals destination size [-Werror=stringop-truncation]

Change it to strscpy_pad(), which produces a properly terminated and zero-padded string.

---
 drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c +2 -2
@@ -940,8 +940,8 @@ static int create_component(struct vchiq
 	/* build component create message */
 	m.h.type = MMAL_MSG_TYPE_COMPONENT_CREATE;
 	m.u.component_create.client_component = component->client_component;
-	strncpy(m.u.component_create.name, name,
-		sizeof(m.u.component_create.name));
+	strscpy_pad(m.u.component_create.name, name,
+		    sizeof(m.u.component_create.name));
 
 	ret = send_synchronous_mmal_msg(instance, &m,
 					sizeof(m.u.component_create),
author maintainer
#588 lore raw

PATCH 584/690 staging: vc04_services: fix information leak in create_component()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Dan Carpenter <[email protected]>

commit f37e76abd614b68987abc8e5c22d986013349771 upstream.

The m.u.component_create.pid field is for debugging and in the mainline kernel it's not used anything. However, it still needs to be set to something to prevent disclosing uninitialized stack data. Set it to zero.

Fixes 7b3ad5abf027 ("staging: Import the BCM2835 MMAL-based V4L2 camera driver.")
Cc stable <[email protected]>
---
 drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c |    1 +
 1 file changed, 1 insertion(+)
drivers/staging/vc04_services/vchiq-mmal/mmal-vchiq.c +1 -0
@@ -942,6 +942,7 @@ static int create_component(struct vchiq
 	m.u.component_create.client_component = component->client_component;
 	strscpy_pad(m.u.component_create.name, name,
 		    sizeof(m.u.component_create.name));
+	m.u.component_create.pid = 0;
 
 	ret = send_synchronous_mmal_msg(instance, &m,
 					sizeof(m.u.component_create),
author maintainer
#589 lore raw

PATCH 585/690 USB: core: Add hub_get() and hub_put() routines

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alan Stern <[email protected]>

commit ee113b860aa169e9a4d2c167c95d0f1961c6e1b8 upstream.

Create hub_get() and hub_put() routines to encapsulate the kref_get() and kref_put() calls in hub.c. The new routines will be used by the next patch in this series.

---
 drivers/usb/core/hub.c |   23 ++++++++++++++++-------
 drivers/usb/core/hub.h |    2 ++
 2 files changed, 18 insertions(+), 7 deletions(-)
drivers/usb/core/hub.c +16 -7
@@ -116,7 +116,6 @@ EXPORT_SYMBOL_GPL(ehci_cf_port_reset_rws
 #define HUB_DEBOUNCE_STEP	  25
 #define HUB_DEBOUNCE_STABLE	 100
 
-static void hub_release(struct kref *kref);
 static int usb_reset_and_verify_device(struct usb_device *udev);
 static int hub_port_disable(struct usb_hub *hub, int port1, int set_state);
 static bool hub_port_warm_reset_required(struct usb_hub *hub, int port1,
@@ -678,14 +677,14 @@ static void kick_hub_wq(struct usb_hub *
 	 */
 	intf = to_usb_interface(hub->intfdev);
 	usb_autopm_get_interface_no_resume(intf);
-	kref_get(&hub->kref);
+	hub_get(hub);
 
 	if (queue_work(hub_wq, &hub->events))
 		return;
 
 	/* the work has already been scheduled */
 	usb_autopm_put_interface_async(intf);
-	kref_put(&hub->kref, hub_release);
+	hub_put(hub);
 }
 
 void usb_kick_hub_wq(struct usb_device *hdev)
@@ -1053,7 +1052,7 @@ static void hub_activate(struct usb_hub
 			goto init2;
 		goto init3;
 	}
-	kref_get(&hub->kref);
+	hub_get(hub);
 
 	/* The superspeed hub except for root hub has to use Hub Depth
 	 * value as an offset into the route string to locate the bits
@@ -1301,7 +1300,7 @@ static void hub_activate(struct usb_hub
 		device_unlock(&hdev->dev);
 	}
 
-	kref_put(&hub->kref, hub_release);
+	hub_put(hub);
 }
 
 /* Implement the continuations for the delays above */
@@ -1717,6 +1716,16 @@ static void hub_release(struct kref *kre
 	kfree(hub);
 }
 
+void hub_get(struct usb_hub *hub)
+{
+	kref_get(&hub->kref);
+}
+
+void hub_put(struct usb_hub *hub)
+{
+	kref_put(&hub->kref, hub_release);
+}
+
 static unsigned highspeed_hubs;
 
 static void hub_disconnect(struct usb_interface *intf)
@@ -1763,7 +1772,7 @@ static void hub_disconnect(struct usb_in
 	if (hub->quirk_disable_autosuspend)
 		usb_autopm_put_interface(intf);
 
-	kref_put(&hub->kref, hub_release);
+	hub_put(hub);
 }
 
 static bool hub_descriptor_is_sane(struct usb_host_interface *desc)
@@ -5853,7 +5862,7 @@ out_hdev_lock:
 
 	/* Balance the stuff in kick_hub_wq() and allow autosuspend */
 	usb_autopm_put_interface(intf);
-	kref_put(&hub->kref, hub_release);
+	hub_put(hub);
 
 	kcov_remote_stop();
 }
drivers/usb/core/hub.h +2 -0
@@ -117,6 +117,8 @@ extern void usb_hub_remove_port_device(s
 extern int usb_hub_set_port_power(struct usb_device *hdev, struct usb_hub *hub,
 		int port1, bool set);
 extern struct usb_hub *usb_hub_to_struct_hub(struct usb_device *hdev);
+extern void hub_get(struct usb_hub *hub);
+extern void hub_put(struct usb_hub *hub);
 extern int hub_port_debounce(struct usb_hub *hub, int port1,
 		bool must_be_connected);
 extern int usb_clear_port_feature(struct usb_device *hdev,
author maintainer
#590 lore raw

PATCH 586/690 usb: dwc2: host: Fix remote wakeup from hibernation

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Minas Harutyunyan <[email protected]>

commit bae2bc73a59c200db53b6c15fb26bb758e2c6108 upstream.

Starting from core v4.30a changed order of programming GPWRDN_PMUACTV to 0 in case of exit from hibernation on remote wakeup signaling from device.

---
 drivers/usb/dwc2/core.h |    1 +
 drivers/usb/dwc2/hcd.c  |   17 +++++++++++++----
 2 files changed, 14 insertions(+), 4 deletions(-)
drivers/usb/dwc2/core.h +1 -0
@@ -1107,6 +1107,7 @@ struct dwc2_hsotg {
 	bool needs_byte_swap;
 
 	/* DWC OTG HW Release versions */
+#define DWC2_CORE_REV_4_30a	0x4f54430a
 #define DWC2_CORE_REV_2_71a	0x4f54271a
 #define DWC2_CORE_REV_2_72a     0x4f54272a
 #define DWC2_CORE_REV_2_80a	0x4f54280a
drivers/usb/dwc2/hcd.c +13 -4
@@ -5641,10 +5641,12 @@ int dwc2_host_exit_hibernation(struct dw
 	dwc2_writel(hsotg, hr->hcfg, HCFG);
 
 	/* De-assert Wakeup Logic */
-	gpwrdn = dwc2_readl(hsotg, GPWRDN);
-	gpwrdn &= ~GPWRDN_PMUACTV;
-	dwc2_writel(hsotg, gpwrdn, GPWRDN);
-	udelay(10);
+	if (!(rem_wakeup && hsotg->hw_params.snpsid >= DWC2_CORE_REV_4_30a)) {
+		gpwrdn = dwc2_readl(hsotg, GPWRDN);
+		gpwrdn &= ~GPWRDN_PMUACTV;
+		dwc2_writel(hsotg, gpwrdn, GPWRDN);
+		udelay(10);
+	}
 
 	hprt0 = hr->hprt0;
 	hprt0 |= HPRT0_PWR;
@@ -5669,6 +5671,13 @@ int dwc2_host_exit_hibernation(struct dw
 		hprt0 |= HPRT0_RES;
 		dwc2_writel(hsotg, hprt0, HPRT0);
 
+		/* De-assert Wakeup Logic */
+		if ((rem_wakeup && hsotg->hw_params.snpsid >= DWC2_CORE_REV_4_30a)) {
+			gpwrdn = dwc2_readl(hsotg, GPWRDN);
+			gpwrdn &= ~GPWRDN_PMUACTV;
+			dwc2_writel(hsotg, gpwrdn, GPWRDN);
+			udelay(10);
+		}
 		/* Wait for Resume time and then program HPRT again */
 		mdelay(100);
 		hprt0 &= ~HPRT0_RES;
author maintainer
#591 lore raw

PATCH 587/690 usb: dwc2: host: Fix hibernation flow

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Minas Harutyunyan <[email protected]>

commit 3c7b9856a82227db01a20171d2e24c7ce305d59b upstream.

Added to backup/restore registers HFLBADDR, HCCHARi, HCSPLTi, HCTSIZi, HCDMAi and HCDMABi.

Fixes 58e52ff6a6c3 ("usb: dwc2: Move register save and restore functions")
Fixes d17ee77b3044 ("usb: dwc2: add controller hibernation support")
---
 drivers/usb/dwc2/core.h |   12 ++++++++++++
 drivers/usb/dwc2/hcd.c  |   18 ++++++++++++++++--
 2 files changed, 28 insertions(+), 2 deletions(-)
drivers/usb/dwc2/core.h +12 -0
@@ -755,8 +755,14 @@ struct dwc2_dregs_backup {
  * struct dwc2_hregs_backup - Holds host registers state before
  * entering partial power down
  * @hcfg:		Backup of HCFG register
+ * @hflbaddr:		Backup of HFLBADDR register
  * @haintmsk:		Backup of HAINTMSK register
+ * @hcchar:		Backup of HCCHAR register
+ * @hcsplt:		Backup of HCSPLT register
  * @hcintmsk:		Backup of HCINTMSK register
+ * @hctsiz:		Backup of HCTSIZ register
+ * @hdma:		Backup of HCDMA register
+ * @hcdmab:		Backup of HCDMAB register
  * @hprt0:		Backup of HPTR0 register
  * @hfir:		Backup of HFIR register
  * @hptxfsiz:		Backup of HPTXFSIZ register
@@ -764,8 +770,14 @@ struct dwc2_dregs_backup {
  */
 struct dwc2_hregs_backup {
 	u32 hcfg;
+	u32 hflbaddr;
 	u32 haintmsk;
+	u32 hcchar[MAX_EPS_CHANNELS];
+	u32 hcsplt[MAX_EPS_CHANNELS];
 	u32 hcintmsk[MAX_EPS_CHANNELS];
+	u32 hctsiz[MAX_EPS_CHANNELS];
+	u32 hcidma[MAX_EPS_CHANNELS];
+	u32 hcidmab[MAX_EPS_CHANNELS];
 	u32 hprt0;
 	u32 hfir;
 	u32 hptxfsiz;
drivers/usb/dwc2/hcd.c +16 -2
@@ -5437,9 +5437,16 @@ int dwc2_backup_host_registers(struct dw
 	/* Backup Host regs */
 	hr = &hsotg->hr_backup;
 	hr->hcfg = dwc2_readl(hsotg, HCFG);
+	hr->hflbaddr = dwc2_readl(hsotg, HFLBADDR);
 	hr->haintmsk = dwc2_readl(hsotg, HAINTMSK);
-	for (i = 0; i < hsotg->params.host_channels; ++i)
+	for (i = 0; i < hsotg->params.host_channels; ++i) {
+		hr->hcchar[i] = dwc2_readl(hsotg, HCCHAR(i));
+		hr->hcsplt[i] = dwc2_readl(hsotg, HCSPLT(i));
 		hr->hcintmsk[i] = dwc2_readl(hsotg, HCINTMSK(i));
+		hr->hctsiz[i] = dwc2_readl(hsotg, HCTSIZ(i));
+		hr->hcidma[i] = dwc2_readl(hsotg, HCDMA(i));
+		hr->hcidmab[i] = dwc2_readl(hsotg, HCDMAB(i));
+	}
 
 	hr->hprt0 = dwc2_read_hprt0(hsotg);
 	hr->hfir = dwc2_readl(hsotg, HFIR);
@@ -5473,10 +5480,17 @@ int dwc2_restore_host_registers(struct d
 	hr->valid = false;
 
 	dwc2_writel(hsotg, hr->hcfg, HCFG);
+	dwc2_writel(hsotg, hr->hflbaddr, HFLBADDR);
 	dwc2_writel(hsotg, hr->haintmsk, HAINTMSK);
 
-	for (i = 0; i < hsotg->params.host_channels; ++i)
+	for (i = 0; i < hsotg->params.host_channels; ++i) {
+		dwc2_writel(hsotg, hr->hcchar[i], HCCHAR(i));
+		dwc2_writel(hsotg, hr->hcsplt[i], HCSPLT(i));
 		dwc2_writel(hsotg, hr->hcintmsk[i], HCINTMSK(i));
+		dwc2_writel(hsotg, hr->hctsiz[i], HCTSIZ(i));
+		dwc2_writel(hsotg, hr->hcidma[i], HCDMA(i));
+		dwc2_writel(hsotg, hr->hcidmab[i], HCDMAB(i));
+	}
 
 	dwc2_writel(hsotg, hr->hprt0, HPRT0);
 	dwc2_writel(hsotg, hr->hfir, HFIR);
author maintainer
#592 lore raw

PATCH 588/690 usb: dwc2: host: Fix ISOC flow in DDMA mode

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Minas Harutyunyan <[email protected]>

commit b258e42688501cadb1a6dd658d6f015df9f32d8f upstream.

Fixed ISOC completion flow in DDMA mode. Added isoc descriptor actual length value and update urb's start_frame value.
Fixed initialization of ISOC DMA descriptors flow.

Fixes 56f5b1cff22a ("staging: Core files for the DWC2 driver")
Fixes 20f2eb9c4cf8 ("staging: dwc2: add microframe scheduler from downstream Pi kernel")
Fixes c17b337c1ea4 ("usb: dwc2: host: program descriptor for next frame")
Fixes dc4c76e7b22c ("staging: HCD descriptor DMA support for the DWC2 driver")
Fixes 762d3a1a9cd7 ("usb: dwc2: host: process all completed urbs")
---
 drivers/usb/dwc2/hcd.c      |   12 ++++++++++--
 drivers/usb/dwc2/hcd_ddma.c |   17 +++++++++++------
 drivers/usb/dwc2/hw.h       |    2 +-
 3 files changed, 22 insertions(+), 9 deletions(-)
drivers/usb/dwc2/hcd.c +10 -2
@@ -2734,8 +2734,11 @@ enum dwc2_transaction_type dwc2_hcd_sele
 			hsotg->available_host_channels--;
 		}
 		qh = list_entry(qh_ptr, struct dwc2_qh, qh_list_entry);
-		if (dwc2_assign_and_init_hc(hsotg, qh))
+		if (dwc2_assign_and_init_hc(hsotg, qh)) {
+			if (hsotg->params.uframe_sched)
+				hsotg->available_host_channels++;
 			break;
+		}
 
 		/*
 		 * Move the QH from the periodic ready schedule to the
@@ -2768,8 +2771,11 @@ enum dwc2_transaction_type dwc2_hcd_sele
 			hsotg->available_host_channels--;
 		}
 
-		if (dwc2_assign_and_init_hc(hsotg, qh))
+		if (dwc2_assign_and_init_hc(hsotg, qh)) {
+			if (hsotg->params.uframe_sched)
+				hsotg->available_host_channels++;
 			break;
+		}
 
 		/*
 		 * Move the QH from the non-periodic inactive schedule to the
@@ -4176,6 +4182,8 @@ void dwc2_host_complete(struct dwc2_hsot
 			 urb->actual_length);
 
 	if (usb_pipetype(urb->pipe) == PIPE_ISOCHRONOUS) {
+		if (!hsotg->params.dma_desc_enable)
+			urb->start_frame = qtd->qh->start_active_frame;
 		urb->error_count = dwc2_hcd_urb_get_error_count(qtd->urb);
 		for (i = 0; i < urb->number_of_packets; ++i) {
 			urb->iso_frame_desc[i].actual_length =
drivers/usb/dwc2/hcd_ddma.c +11 -6
@@ -589,7 +589,7 @@ static void dwc2_init_isoc_dma_desc(stru
 	idx = qh->td_last;
 	inc = qh->host_interval;
 	hsotg->frame_number = dwc2_hcd_get_frame_number(hsotg);
-	cur_idx = dwc2_frame_list_idx(hsotg->frame_number);
+	cur_idx = idx;
 	next_idx = dwc2_desclist_idx_inc(qh->td_last, inc, qh->dev_speed);
 
 	/*
@@ -896,6 +896,8 @@ static int dwc2_cmpl_host_isoc_dma_desc(
 {
 	struct dwc2_dma_desc *dma_desc;
 	struct dwc2_hcd_iso_packet_desc *frame_desc;
+	u16 frame_desc_idx;
+	struct urb *usb_urb = qtd->urb->priv;
 	u16 remain = 0;
 	int rc = 0;
 
@@ -908,8 +910,11 @@ static int dwc2_cmpl_host_isoc_dma_desc(
 				DMA_FROM_DEVICE);
 
 	dma_desc = &qh->desc_list[idx];
+	frame_desc_idx = (idx - qtd->isoc_td_first) & (usb_urb->number_of_packets - 1);
 
-	frame_desc = &qtd->urb->iso_descs[qtd->isoc_frame_index_last];
+	frame_desc = &qtd->urb->iso_descs[frame_desc_idx];
+	if (idx == qtd->isoc_td_first)
+		usb_urb->start_frame = dwc2_hcd_get_frame_number(hsotg);
 	dma_desc->buf = (u32)(qtd->urb->dma + frame_desc->offset);
 	if (chan->ep_is_in)
 		remain = (dma_desc->status & HOST_DMA_ISOC_NBYTES_MASK) >>
@@ -930,7 +935,7 @@ static int dwc2_cmpl_host_isoc_dma_desc(
 		frame_desc->status = 0;
 	}
 
-	if (++qtd->isoc_frame_index == qtd->urb->packet_count) {
+	if (++qtd->isoc_frame_index == usb_urb->number_of_packets) {
 		/*
 		 * urb->status is not used for isoc transfers here. The
 		 * individual frame_desc status are used instead.
@@ -1035,11 +1040,11 @@ static void dwc2_complete_isoc_xfer_ddma
 				return;
 			idx = dwc2_desclist_idx_inc(idx, qh->host_interval,
 						    chan->speed);
-			if (!rc)
+			if (rc == 0)
 				continue;
 
-			if (rc == DWC2_CMPL_DONE)
-				break;
+			if (rc == DWC2_CMPL_DONE || rc == DWC2_CMPL_STOP)
+				goto stop_scan;
 
 			/* rc == DWC2_CMPL_STOP */
 
drivers/usb/dwc2/hw.h +1 -1
@@ -728,7 +728,7 @@
 #define TXSTS_QTOP_TOKEN_MASK		(0x3 << 25)
 #define TXSTS_QTOP_TOKEN_SHIFT		25
 #define TXSTS_QTOP_TERMINATE		BIT(24)
-#define TXSTS_QSPCAVAIL_MASK		(0xff << 16)
+#define TXSTS_QSPCAVAIL_MASK		(0x7f << 16)
 #define TXSTS_QSPCAVAIL_SHIFT		16
 #define TXSTS_FSPCAVAIL_MASK		(0xffff << 0)
 #define TXSTS_FSPCAVAIL_SHIFT		0
author maintainer
#593 lore raw

PATCH 589/690 usb: dwc2: gadget: Fix exiting from clock gating

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Minas Harutyunyan <[email protected]>

commit 31f42da31417bec88158f3cf62d19db836217f1e upstream.

Added exiting from the clock gating mode on USB Reset Detect interrupt if core in the clock gating mode.
Added new condition to check core in clock gating mode or no.

Fixes 9b4965d77e11 ("usb: dwc2: Add exit clock gating from session request interrupt")
Fixes 5d240efddc7f ("usb: dwc2: Add exit clock gating from wakeup interrupt")
Fixes 16c729f90bdf ("usb: dwc2: Allow exit clock gating in urb enqueue")
Fixes 401411bbc4e6 ("usb: dwc2: Add exit clock gating before removing driver")
---
 drivers/usb/dwc2/core_intr.c |    9 ++++++---
 drivers/usb/dwc2/gadget.c    |    6 ++++++
 drivers/usb/dwc2/hcd.c       |    2 +-
 drivers/usb/dwc2/platform.c  |    2 +-
 4 files changed, 14 insertions(+), 5 deletions(-)
drivers/usb/dwc2/core_intr.c +6 -3
@@ -327,7 +327,8 @@ static void dwc2_handle_session_req_intr
 
 			/* Exit gadget mode clock gating. */
 			if (hsotg->params.power_down ==
-			    DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended)
+			    DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended &&
+			    !hsotg->params.no_clock_gating)
 				dwc2_gadget_exit_clock_gating(hsotg, 0);
 		}
 
@@ -438,7 +439,8 @@ static void dwc2_handle_wakeup_detected_
 
 			/* Exit gadget mode clock gating. */
 			if (hsotg->params.power_down ==
-			    DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended)
+			    DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended &&
+			    !hsotg->params.no_clock_gating)
 				dwc2_gadget_exit_clock_gating(hsotg, 0);
 		} else {
 			/* Change to L0 state */
@@ -455,7 +457,8 @@ static void dwc2_handle_wakeup_detected_
 			}
 
 			if (hsotg->params.power_down ==
-			    DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended)
+			    DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended &&
+			    !hsotg->params.no_clock_gating)
 				dwc2_host_exit_clock_gating(hsotg, 1);
 
 			/*
drivers/usb/dwc2/gadget.c +6 -0
@@ -3728,6 +3728,12 @@ irq_retry:
 		if (hsotg->in_ppd && hsotg->lx_state == DWC2_L2)
 			dwc2_exit_partial_power_down(hsotg, 0, true);
 
+		/* Exit gadget mode clock gating. */
+		if (hsotg->params.power_down ==
+		    DWC2_POWER_DOWN_PARAM_NONE && hsotg->bus_suspended &&
+		    !hsotg->params.no_clock_gating)
+			dwc2_gadget_exit_clock_gating(hsotg, 0);
+
 		hsotg->lx_state = DWC2_L0;
 	}
 
drivers/usb/dwc2/hcd.c +1 -1
@@ -4690,7 +4690,7 @@ static int _dwc2_hcd_urb_enqueue(struct
 	}
 
 	if (hsotg->params.power_down == DWC2_POWER_DOWN_PARAM_NONE &&
-	    hsotg->bus_suspended) {
+	    hsotg->bus_suspended && !hsotg->params.no_clock_gating) {
 		if (dwc2_is_device_mode(hsotg))
 			dwc2_gadget_exit_clock_gating(hsotg, 0);
 		else
drivers/usb/dwc2/platform.c +1 -1
@@ -344,7 +344,7 @@ static int dwc2_driver_remove(struct pla
 
 	/* Exit clock gating when driver is removed. */
 	if (hsotg->params.power_down == DWC2_POWER_DOWN_PARAM_NONE &&
-	    hsotg->bus_suspended) {
+	    hsotg->bus_suspended && !hsotg->params.no_clock_gating) {
 		if (dwc2_is_device_mode(hsotg))
 			dwc2_gadget_exit_clock_gating(hsotg, 0);
 		else
author maintainer
#594 lore raw

PATCH 590/690 usb: dwc2: gadget: LPM flow fix

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Minas Harutyunyan <[email protected]>

commit 5d69a3b54e5a630c90d82a4c2bdce3d53dc78710 upstream.

Added functionality to exit from L1 state by device initiation using remote wakeup signaling, in case when function driver queuing request while core in L1 state.

Fixes 273d576c4d41 ("usb: dwc2: gadget: Add functionality to exit from LPM L1 state")
Fixes 88b02f2cb1e1 ("usb: dwc2: Add core state checking")
---
 drivers/usb/dwc2/core.h      |    1 
 drivers/usb/dwc2/core_intr.c |   65 ++++++++++++++++++++++++++++---------------
 drivers/usb/dwc2/gadget.c    |    4 ++
 3 files changed, 48 insertions(+), 22 deletions(-)
drivers/usb/dwc2/core.h +1 -0
@@ -1358,6 +1358,7 @@ int dwc2_backup_global_registers(struct
 int dwc2_restore_global_registers(struct dwc2_hsotg *hsotg);
 
 void dwc2_enable_acg(struct dwc2_hsotg *hsotg);
+void dwc2_wakeup_from_lpm_l1(struct dwc2_hsotg *hsotg, bool remotewakeup);
 
 /* This function should be called on every hardware interrupt. */
 irqreturn_t dwc2_handle_common_intr(int irq, void *dev);
drivers/usb/dwc2/core_intr.c +43 -22

97 lines not on this page · raw message

drivers/usb/dwc2/gadget.c +4 -0
@@ -1416,6 +1416,10 @@ static int dwc2_hsotg_ep_queue(struct us
 		ep->name, req, req->length, req->buf, req->no_interrupt,
 		req->zero, req->short_not_ok);
 
+	if (hs->lx_state == DWC2_L1) {
+		dwc2_wakeup_from_lpm_l1(hs, true);
+	}
+
 	/* Prevent new request submission when controller is suspended */
 	if (hs->lx_state != DWC2_L0) {
 		dev_dbg(hs->dev, "%s: submit request only in active state\n",
author maintainer
#595 lore raw

PATCH 591/690 usb: udc: remove warning when queue disabled ep

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: yuan linyu <[email protected]>

commit 2a587a035214fa1b5ef598aea0b81848c5b72e5e upstream.

It is possible trigger below warning message from mass storage function,

WARNING: CPU: 6 PID: 3839 at drivers/usb/gadget/udc/core.c:294 usb_ep_queue+0x7c/0x104
pc : usb_ep_queue+0x7c/0x104
lr : fsg_main_thread+0x494/0x1b3c

Root cause is mass storage function try to queue request from main thread, but other thread may already disable ep when function disable.

As there is no function failure in the driver, in order to avoid effort to fix warning, change WARN_ON_ONCE() in usb_ep_queue() to pr_debug().

---
 drivers/usb/gadget/udc/core.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/usb/gadget/udc/core.c +3 -1
@@ -275,7 +275,9 @@ int usb_ep_queue(struct usb_ep *ep,
 {
 	int ret = 0;
 
-	if (WARN_ON_ONCE(!ep->enabled && ep->address)) {
+	if (!ep->enabled && ep->address) {
+		pr_debug("USB gadget: queue request to disabled ep 0x%x (%s)\n",
+				 ep->address, ep->name);
 		ret = -ESHUTDOWN;
 		goto out;
 	}
author maintainer
#596 lore raw

PATCH 592/690 usb: typec: ucsi: Ack unsupported commands

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christian A. Ehrhardt <[email protected]>

commit 6b5c85ddeea77d18c4b69e3bda60e9374a20c304 upstream.

If a command completes the OPM must send an ack. This applies to unsupported commands, too.

Send the required ACK for unsupported commands.

---
 drivers/usb/typec/ucsi/ucsi.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/usb/typec/ucsi/ucsi.c +5 -1
@@ -138,8 +138,12 @@ static int ucsi_exec_command(struct ucsi
 	if (!(cci & UCSI_CCI_COMMAND_COMPLETE))
 		return -EIO;
 
-	if (cci & UCSI_CCI_NOT_SUPPORTED)
+	if (cci & UCSI_CCI_NOT_SUPPORTED) {
+		if (ucsi_acknowledge_command(ucsi) < 0)
+			dev_err(ucsi->dev,
+				"ACK of unsupported command failed\n");
 		return -EOPNOTSUPP;
+	}
 
 	if (cci & UCSI_CCI_ERROR) {
 		if (cmd == UCSI_GET_ERROR_STATUS)
author maintainer
#597 lore raw

PATCH 593/690 usb: typec: ucsi: Clear UCSI_CCI_RESET_COMPLETE before reset

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christian A. Ehrhardt <[email protected]>

commit 3de4f996a0b5412aa451729008130a488f71563e upstream.

Check the UCSI_CCI_RESET_COMPLETE complete flag before starting another reset. Use a UCSI_SET_NOTIFICATION_ENABLE command to clear the flag if it is set.

---
 drivers/usb/typec/ucsi/ucsi.c |   36 +++++++++++++++++++++++++++++++++++-
 1 file changed, 35 insertions(+), 1 deletion(-)
drivers/usb/typec/ucsi/ucsi.c +35 -1
@@ -879,13 +879,47 @@ static int ucsi_reset_connector(struct u
 
 static int ucsi_reset_ppm(struct ucsi *ucsi)
 {
-	u64 command = UCSI_PPM_RESET;
+	u64 command;
 	unsigned long tmo;
 	u32 cci;
 	int ret;
 
 	mutex_lock(&ucsi->ppm_lock);
 
+	ret = ucsi->ops->read(ucsi, UCSI_CCI, &cci, sizeof(cci));
+	if (ret < 0)
+		goto out;
+
+	/*
+	 * If UCSI_CCI_RESET_COMPLETE is already set we must clear
+	 * the flag before we start another reset. Send a
+	 * UCSI_SET_NOTIFICATION_ENABLE command to achieve this.
+	 * Ignore a timeout and try the reset anyway if this fails.
+	 */
+	if (cci & UCSI_CCI_RESET_COMPLETE) {
+		command = UCSI_SET_NOTIFICATION_ENABLE;
+		ret = ucsi->ops->async_write(ucsi, UCSI_CONTROL, &command,
+					     sizeof(command));
+		if (ret < 0)
+			goto out;
+
+		tmo = jiffies + msecs_to_jiffies(UCSI_TIMEOUT_MS);
+		do {
+			ret = ucsi->ops->read(ucsi, UCSI_CCI,
+					      &cci, sizeof(cci));
+			if (ret < 0)
+				goto out;
+			if (cci & UCSI_CCI_COMMAND_COMPLETE)
+				break;
+			if (time_is_before_jiffies(tmo))
+				break;
+			msleep(20);
+		} while (1);
+
+		WARN_ON(cci & UCSI_CCI_RESET_COMPLETE);
+	}
+
+	command = UCSI_PPM_RESET;
 	ret = ucsi->ops->async_write(ucsi, UCSI_CONTROL, &command,
 				     sizeof(command));
 	if (ret < 0)
author maintainer
#598 lore raw

PATCH 594/690 scsi: qla2xxx: Prevent command send on chip reset

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Quinn Tran <[email protected]>

commit 4895009c4bb72f71f2e682f1e7d2c2d96e482087 upstream.

Currently IOCBs are allowed to push through while chip reset could be in progress. During chip reset the outstanding_cmds array is cleared twice. Once when any command on this array is returned as failed and secondly when the array is initialize to zero. If a command is inserted on to the array between these intervals, then the command will be lost. Check for chip reset before sending IOCB.

---
 drivers/scsi/qla2xxx/qla_init.c |    8 ++++++--
 drivers/scsi/qla2xxx/qla_iocb.c |   33 +++++++++++++++++++++++++++++++--
 2 files changed, 37 insertions(+), 4 deletions(-)
drivers/scsi/qla2xxx/qla_init.c +6 -2
@@ -1188,8 +1188,12 @@ int qla24xx_async_gnl(struct scsi_qla_ho
 	return rval;
 
 done_free_sp:
-	/* ref: INIT */
-	kref_put(&sp->cmd_kref, qla2x00_sp_release);
+	/*
+	 * use qla24xx_async_gnl_sp_done to purge all pending gnl request.
+	 * kref_put is call behind the scene.
+	 */
+	sp->u.iocb_cmd.u.mbx.in_mb[0] = MBS_COMMAND_ERROR;
+	qla24xx_async_gnl_sp_done(sp, QLA_COMMAND_ERROR);
 	fcport->flags &= ~(FCF_ASYNC_SENT);
 done:
 	fcport->flags &= ~(FCF_ASYNC_ACTIVE);
drivers/scsi/qla2xxx/qla_iocb.c +31 -2
@@ -2588,6 +2588,33 @@ void
 qla2x00_sp_release(struct kref *kref)
 {
 	struct srb *sp = container_of(kref, struct srb, cmd_kref);
+	struct scsi_qla_host *vha = sp->vha;
+
+	switch (sp->type) {
+	case SRB_CT_PTHRU_CMD:
+		/* GPSC & GFPNID use fcport->ct_desc.ct_sns for both req & rsp */
+		if (sp->u.iocb_cmd.u.ctarg.req &&
+			(!sp->fcport ||
+			 sp->u.iocb_cmd.u.ctarg.req != sp->fcport->ct_desc.ct_sns)) {
+			dma_free_coherent(&vha->hw->pdev->dev,
+			    sp->u.iocb_cmd.u.ctarg.req_allocated_size,
+			    sp->u.iocb_cmd.u.ctarg.req,
+			    sp->u.iocb_cmd.u.ctarg.req_dma);
+			sp->u.iocb_cmd.u.ctarg.req = NULL;
+		}
+		if (sp->u.iocb_cmd.u.ctarg.rsp &&
+			(!sp->fcport ||
+			 sp->u.iocb_cmd.u.ctarg.rsp != sp->fcport->ct_desc.ct_sns)) {
+			dma_free_coherent(&vha->hw->pdev->dev,
+			    sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
+			    sp->u.iocb_cmd.u.ctarg.rsp,
+			    sp->u.iocb_cmd.u.ctarg.rsp_dma);
+			sp->u.iocb_cmd.u.ctarg.rsp = NULL;
+		}
+		break;
+	default:
+		break;
+	}
 
 	sp->free(sp);
 }
@@ -2693,7 +2720,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *v
 	 */
 	sp = qla2x00_get_sp(vha, fcport, GFP_KERNEL);
 	if (!sp) {
-		kfree(fcport);
+		qla2x00_free_fcport(fcport);
 		ql_log(ql_log_info, vha, 0x70e6,
 		 "SRB allocation failed\n");
 		return -ENOMEM;
@@ -2748,6 +2775,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *v
 	if (rval != QLA_SUCCESS) {
 		/* ref: INIT */
 		kref_put(&sp->cmd_kref, qla2x00_sp_release);
+		qla2x00_free_fcport(fcport);
 		return QLA_FUNCTION_FAILED;
 	}
 
@@ -2757,6 +2785,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *v
 	    fcport->d_id.b.area, fcport->d_id.b.al_pa);
 
 	wait_for_completion(&elsio->u.els_logo.comp);
+	qla2x00_free_fcport(fcport);
 
 	/* ref: INIT */
 	kref_put(&sp->cmd_kref, qla2x00_sp_release);
@@ -3916,7 +3945,7 @@ qla2x00_start_sp(srb_t *sp)
 		return -EAGAIN;
 	}
 
-	pkt = __qla2x00_alloc_iocbs(sp->qpair, sp);
+	pkt = qla2x00_alloc_iocbs_ready(sp->qpair, sp);
 	if (!pkt) {
 		rval = -EAGAIN;
 		ql_log(ql_log_warn, vha, 0x700c,
author maintainer
#599 lore raw

PATCH 595/690 scsi: qla2xxx: Fix N2N stuck connection

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Quinn Tran <[email protected]>

commit 881eb861ca3877300570db10abbf11494e48548d upstream.

Disk failed to rediscover after chip reset error injection. The chip reset happens at the time when a PLOGI is being sent. This causes a flag to be left on which blocks the retry. Clear the blocking flag.

---
 drivers/scsi/qla2xxx/qla_gbl.h  |    2 +-
 drivers/scsi/qla2xxx/qla_iocb.c |   32 +++++++++++---------------------
 drivers/scsi/qla2xxx/qla_os.c   |    2 +-
 3 files changed, 13 insertions(+), 23 deletions(-)
drivers/scsi/qla2xxx/qla_gbl.h +1 -1
@@ -44,7 +44,7 @@ extern int qla2x00_fabric_login(scsi_qla
 extern int qla2x00_local_device_login(scsi_qla_host_t *, fc_port_t *);
 
 extern int qla24xx_els_dcmd_iocb(scsi_qla_host_t *, int, port_id_t);
-extern int qla24xx_els_dcmd2_iocb(scsi_qla_host_t *, int, fc_port_t *, bool);
+extern int qla24xx_els_dcmd2_iocb(scsi_qla_host_t *, int, fc_port_t *);
 extern void qla2x00_els_dcmd2_free(scsi_qla_host_t *vha,
 				   struct els_plogi *els_plogi);
 
drivers/scsi/qla2xxx/qla_iocb.c +11 -21
@@ -3042,7 +3042,7 @@ static void qla2x00_els_dcmd2_sp_done(sr
 
 int
 qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
-    fc_port_t *fcport, bool wait)
+			fc_port_t *fcport)
 {
 	srb_t *sp;
 	struct srb_iocb *elsio = NULL;
@@ -3057,8 +3057,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *
 	if (!sp) {
 		ql_log(ql_log_info, vha, 0x70e6,
 		 "SRB allocation failed\n");
-		fcport->flags &= ~FCF_ASYNC_ACTIVE;
-		return -ENOMEM;
+		goto done;
 	}
 
 	fcport->flags |= FCF_ASYNC_SENT;
@@ -3067,9 +3066,6 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *
 	ql_dbg(ql_dbg_io, vha, 0x3073,
 	       "%s Enter: PLOGI portid=%06x\n", __func__, fcport->d_id.b24);
 
-	if (wait)
-		sp->flags = SRB_WAKEUP_ON_COMP;
-
 	sp->type = SRB_ELS_DCMD;
 	sp->name = "ELS_DCMD";
 	sp->fcport = fcport;
@@ -3085,7 +3081,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *
 
 	if (!elsio->u.els_plogi.els_plogi_pyld) {
 		rval = QLA_FUNCTION_FAILED;
-		goto out;
+		goto done_free_sp;
 	}
 
 	resp_ptr = elsio->u.els_plogi.els_resp_pyld =
@@ -3094,7 +3090,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *
 
 	if (!elsio->u.els_plogi.els_resp_pyld) {
 		rval = QLA_FUNCTION_FAILED;
-		goto out;
+		goto done_free_sp;
 	}
 
 	ql_dbg(ql_dbg_io, vha, 0x3073, "PLOGI %p %p\n", ptr, resp_ptr);
@@ -3109,7 +3105,6 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *
 
 	if (els_opcode == ELS_DCMD_PLOGI && DBELL_ACTIVE(vha)) {
 		struct fc_els_flogi *p = ptr;
-
 		p->fl_csp.sp_features |= cpu_to_be16(FC_SP_FT_SEC);
 	}
 
@@ -3118,10 +3113,11 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *
 	    (uint8_t *)elsio->u.els_plogi.els_plogi_pyld,
 	    sizeof(*elsio->u.els_plogi.els_plogi_pyld));
 
-	init_completion(&elsio->u.els_plogi.comp);
 	rval = qla2x00_start_sp(sp);
 	if (rval != QLA_SUCCESS) {
-		rval = QLA_FUNCTION_FAILED;
+		fcport->flags |= FCF_LOGIN_NEEDED;
+		set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+		goto done_free_sp;
 	} else {
 		ql_dbg(ql_dbg_disc, vha, 0x3074,
 		    "%s PLOGI sent, hdl=%x, loopid=%x, to port_id %06x from port_id %06x\n",
@@ -3129,21 +3125,15 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *
 		    fcport->d_id.b24, vha->d_id.b24);
 	}
 
-	if (wait) {
-		wait_for_completion(&elsio->u.els_plogi.comp);
-
-		if (elsio->u.els_plogi.comp_status != CS_COMPLETE)
-			rval = QLA_FUNCTION_FAILED;
-	} else {
-		goto done;
-	}
+	return rval;
 
-out:
-	fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE);
+done_free_sp:
 	qla2x00_els_dcmd2_free(vha, &elsio->u.els_plogi);
 	/* ref: INIT */
 	kref_put(&sp->cmd_kref, qla2x00_sp_release);
 done:
+	fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE);
+	qla2x00_set_fcport_disc_state(fcport, DSC_DELETED);
 	return rval;
 }
 
drivers/scsi/qla2xxx/qla_os.c +1 -1
@@ -5530,7 +5530,7 @@ qla2x00_do_work(struct scsi_qla_host *vh
 			break;
 		case QLA_EVT_ELS_PLOGI:
 			qla24xx_els_dcmd2_iocb(vha, ELS_DCMD_PLOGI,
-			    e->u.fcport.fcport, false);
+			    e->u.fcport.fcport);
 			break;
 		case QLA_EVT_SA_REPLACE:
 			rc = qla24xx_issue_sa_replace_iocb(vha, e);
author maintainer
#600 lore raw

PATCH 596/690 scsi: qla2xxx: Split FCE|EFT trace control

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Quinn Tran <[email protected]>

commit 76a192e1a566e15365704b9f8fb3b70825f85064 upstream.

Current code combines the allocation of FCE|EFT trace buffers and enables the features all in 1 step.

Split this step into separate steps in preparation for follow-on patch to allow user to have a choice to enable / disable FCE trace feature.

---
 drivers/scsi/qla2xxx/qla_init.c |  102 ++++++++++++++++------------------------
 1 file changed, 41 insertions(+), 61 deletions(-)
drivers/scsi/qla2xxx/qla_init.c +41 -61
@@ -2671,6 +2671,40 @@ exit:
 	return rval;
 }
 
+static void qla_enable_fce_trace(scsi_qla_host_t *vha)
+{
+	int rval;
+	struct qla_hw_data *ha = vha->hw;
+
+	if (ha->fce) {
+		ha->flags.fce_enabled = 1;
+		memset(ha->fce, 0, fce_calc_size(ha->fce_bufs));
+		rval = qla2x00_enable_fce_trace(vha,
+		    ha->fce_dma, ha->fce_bufs, ha->fce_mb, &ha->fce_bufs);
+
+		if (rval) {
+			ql_log(ql_log_warn, vha, 0x8033,
+			    "Unable to reinitialize FCE (%d).\n", rval);
+			ha->flags.fce_enabled = 0;
+		}
+	}
+}
+
+static void qla_enable_eft_trace(scsi_qla_host_t *vha)
+{
+	int rval;
+	struct qla_hw_data *ha = vha->hw;
+
+	if (ha->eft) {
+		memset(ha->eft, 0, EFT_SIZE);
+		rval = qla2x00_enable_eft_trace(vha, ha->eft_dma, EFT_NUM_BUFFERS);
+
+		if (rval) {
+			ql_log(ql_log_warn, vha, 0x8034,
+			    "Unable to reinitialize EFT (%d).\n", rval);
+		}
+	}
+}
 /*
 * qla2x00_initialize_adapter
 *      Initialize board.
@@ -3674,9 +3708,8 @@ qla24xx_chip_diag(scsi_qla_host_t *vha)
 }
 
 static void
-qla2x00_init_fce_trace(scsi_qla_host_t *vha)
+qla2x00_alloc_fce_trace(scsi_qla_host_t *vha)
 {
-	int rval;
 	dma_addr_t tc_dma;
 	void *tc;
 	struct qla_hw_data *ha = vha->hw;
@@ -3705,27 +3738,17 @@ qla2x00_init_fce_trace(scsi_qla_host_t *
 		return;
 	}
 
-	rval = qla2x00_enable_fce_trace(vha, tc_dma, FCE_NUM_BUFFERS,
-					ha->fce_mb, &ha->fce_bufs);
-	if (rval) {
-		ql_log(ql_log_warn, vha, 0x00bf,
-		       "Unable to initialize FCE (%d).\n", rval);
-		dma_free_coherent(&ha->pdev->dev, FCE_SIZE, tc, tc_dma);
-		return;
-	}
-
 	ql_dbg(ql_dbg_init, vha, 0x00c0,
 	       "Allocated (%d KB) for FCE...\n", FCE_SIZE / 1024);
 
-	ha->flags.fce_enabled = 1;
 	ha->fce_dma = tc_dma;
 	ha->fce = tc;
+	ha->fce_bufs = FCE_NUM_BUFFERS;
 }
 
 static void
-qla2x00_init_eft_trace(scsi_qla_host_t *vha)
+qla2x00_alloc_eft_trace(scsi_qla_host_t *vha)
 {
-	int rval;
 	dma_addr_t tc_dma;
 	void *tc;
 	struct qla_hw_data *ha = vha->hw;
@@ -3750,14 +3773,6 @@ qla2x00_init_eft_trace(scsi_qla_host_t *
 		return;
 	}
 
-	rval = qla2x00_enable_eft_trace(vha, tc_dma, EFT_NUM_BUFFERS);
-	if (rval) {
-		ql_log(ql_log_warn, vha, 0x00c2,
-		       "Unable to initialize EFT (%d).\n", rval);
-		dma_free_coherent(&ha->pdev->dev, EFT_SIZE, tc, tc_dma);
-		return;
-	}
-
 	ql_dbg(ql_dbg_init, vha, 0x00c3,
 	       "Allocated (%d KB) EFT ...\n", EFT_SIZE / 1024);
 
@@ -3765,13 +3780,6 @@ qla2x00_init_eft_trace(scsi_qla_host_t *
 	ha->eft = tc;
 }
 
-static void
-qla2x00_alloc_offload_mem(scsi_qla_host_t *vha)
-{
-	qla2x00_init_fce_trace(vha);
-	qla2x00_init_eft_trace(vha);
-}
-
 void
 qla2x00_alloc_fw_dump(scsi_qla_host_t *vha)
 {
@@ -3826,10 +3834,10 @@ qla2x00_alloc_fw_dump(scsi_qla_host_t *v
 		if (ha->tgt.atio_ring)
 			mq_size += ha->tgt.atio_q_length * sizeof(request_t);
 
-		qla2x00_init_fce_trace(vha);
+		qla2x00_alloc_fce_trace(vha);
 		if (ha->fce)
 			fce_size = sizeof(struct qla2xxx_fce_chain) + FCE_SIZE;
-		qla2x00_init_eft_trace(vha);
+		qla2x00_alloc_eft_trace(vha);
 		if (ha->eft)
 			eft_size = EFT_SIZE;
 	}
@@ -4259,7 +4267,6 @@ qla2x00_setup_chip(scsi_qla_host_t *vha)
 	struct qla_hw_data *ha = vha->hw;
 	struct device_reg_2xxx __iomem *reg = &ha->iobase->isp;
 	unsigned long flags;
-	uint16_t fw_major_version;
 	int done_once = 0;
 
 	if (IS_P3P_TYPE(ha)) {
@@ -4326,7 +4333,6 @@ execute_fw_with_lr:
 					goto failed;
 
 enable_82xx_npiv:
-				fw_major_version = ha->fw_major_version;
 				if (IS_P3P_TYPE(ha))
 					qla82xx_check_md_needed(vha);
 				else
@@ -4355,12 +4361,11 @@ enable_82xx_npiv:
 				if (rval != QLA_SUCCESS)
 					goto failed;
 
-				if (!fw_major_version && !(IS_P3P_TYPE(ha)))
-					qla2x00_alloc_offload_mem(vha);
-
 				if (ql2xallocfwdump && !(IS_P3P_TYPE(ha)))
 					qla2x00_alloc_fw_dump(vha);
 
+				qla_enable_fce_trace(vha);
+				qla_enable_eft_trace(vha);
 			} else {
 				goto failed;
 			}
@@ -7572,7 +7577,6 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_
 int
 qla2x00_abort_isp(scsi_qla_host_t *vha)
 {
-	int rval;
 	uint8_t        status = 0;
 	struct qla_hw_data *ha = vha->hw;
 	struct scsi_qla_host *vp, *tvp;
@@ -7663,31 +7667,7 @@ qla2x00_abort_isp(scsi_qla_host_t *vha)
 
 			if (IS_QLA81XX(ha) || IS_QLA8031(ha))
 				qla2x00_get_fw_version(vha);
-			if (ha->fce) {
-				ha->flags.fce_enabled = 1;
-				memset(ha->fce, 0,
-				    fce_calc_size(ha->fce_bufs));
-				rval = qla2x00_enable_fce_trace(vha,
-				    ha->fce_dma, ha->fce_bufs, ha->fce_mb,
-				    &ha->fce_bufs);
-				if (rval) {
-					ql_log(ql_log_warn, vha, 0x8033,
-					    "Unable to reinitialize FCE "
-					    "(%d).\n", rval);
-					ha->flags.fce_enabled = 0;
-				}
-			}
 
-			if (ha->eft) {
-				memset(ha->eft, 0, EFT_SIZE);
-				rval = qla2x00_enable_eft_trace(vha,
-				    ha->eft_dma, EFT_NUM_BUFFERS);
-				if (rval) {
-					ql_log(ql_log_warn, vha, 0x8034,
-					    "Unable to reinitialize EFT "
-					    "(%d).\n", rval);
-				}
-			}
 		} else {	/* failed the ISP abort */
 			vha->flags.online = 1;
 			if (test_bit(ISP_ABORT_RETRY, &vha->dpc_flags)) {
author maintainer
#601 lore raw

PATCH 597/690 scsi: qla2xxx: NVME|FCP prefer flag not being honored

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Quinn Tran <[email protected]>

commit 69aecdd410106dc3a8f543a4f7ec6379b995b8d0 upstream.

Changing of [FCP|NVME] prefer flag in flash has no effect on driver. For device that supports both FCP + NVMe over the same connection, driver continues to connect to this device using the previous successful login mode.

On completion of flash update, adapter will be reset. Driver will reset the prefer flag based on setting from flash.

---
 drivers/scsi/qla2xxx/qla_init.c |   18 ++++++++++++++++++
 1 file changed, 18 insertions(+)
drivers/scsi/qla2xxx/qla_init.c +18 -0
@@ -7582,6 +7582,7 @@ qla2x00_abort_isp(scsi_qla_host_t *vha)
 	struct scsi_qla_host *vp, *tvp;
 	struct req_que *req = ha->req_q_map[0];
 	unsigned long flags;
+	fc_port_t *fcport;
 
 	if (vha->flags.online) {
 		qla2x00_abort_isp_cleanup(vha);
@@ -7647,6 +7648,15 @@ qla2x00_abort_isp(scsi_qla_host_t *vha)
 			       "ISP Abort - ISP reg disconnect post nvmram config, exiting.\n");
 			return status;
 		}
+
+		/* User may have updated [fcp|nvme] prefer in flash */
+		list_for_each_entry(fcport, &vha->vp_fcports, list) {
+			if (NVME_PRIORITY(ha, fcport))
+				fcport->do_prli_nvme = 1;
+			else
+				fcport->do_prli_nvme = 0;
+		}
+
 		if (!qla2x00_restart_isp(vha)) {
 			clear_bit(RESET_MARKER_NEEDED, &vha->dpc_flags);
 
@@ -7717,6 +7727,14 @@ qla2x00_abort_isp(scsi_qla_host_t *vha)
 				atomic_inc(&vp->vref_count);
 				spin_unlock_irqrestore(&ha->vport_slock, flags);
 
+				/* User may have updated [fcp|nvme] prefer in flash */
+				list_for_each_entry(fcport, &vp->vp_fcports, list) {
+					if (NVME_PRIORITY(ha, fcport))
+						fcport->do_prli_nvme = 1;
+					else
+						fcport->do_prli_nvme = 0;
+				}
+
 				qla2x00_vp_abort_isp(vp);
 
 				spin_lock_irqsave(&ha->vport_slock, flags);
author maintainer
#602 lore raw

PATCH 598/690 scsi: qla2xxx: Fix command flush on cable pull

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Quinn Tran <[email protected]>

commit a27d4d0e7de305def8a5098a614053be208d1aa1 upstream.

System crash due to command failed to flush back to SCSI layer.

 BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
 PGD 0 P4D 0
 Oops: 0000 [#1] SMP NOPTI
 CPU: 27 PID: 793455 Comm: kworker/u130:6 Kdump: loaded Tainted: G           OE    --------- -  - 4.18.0-372.9.1.el8.x86_64 #1
 Hardware name: HPE ProLiant DL360 Gen10/ProLiant DL360 Gen10, BIOS U32 09/03/2021
 Workqueue: nvme-wq nvme_fc_connect_ctrl_work [nvme_fc]
 RIP: 0010:__wake_up_common+0x4c/0x190
 Code: 24 10 4d 85 c9 74 0a 41 f6 01 04 0f 85 9d 00 00 00 48 8b 43 08 48 83 c3 08 4c 8d 48 e8 49 8d 41 18 48 39 c3 0f 84 f0 00 00 00 <49> 8b 41 18 89 54 24 08 31 ed 4c 8d 70 e8 45 8b 29 41 f6 c5 04 75
 RSP: 0018:ffff95f3e0cb7cd0 EFLAGS: 00010086
 RAX: 0000000000000000 RBX: ffff8b08d3b26328 RCX: 0000000000000000
 RDX: 0000000000000001 RSI: 0000000000000003 RDI: ffff8b08d3b26320
 RBP: 0000000000000001 R08: 0000000000000000 R09: ffffffffffffffe8
 R10: 0000000000000000 R11: ffff95f3e0cb7a60 R12: ffff95f3e0cb7d20
 R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000000
 FS:  0000000000000000(0000) GS:ffff8b2fdf6c0000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000000 CR3: 0000002f1e410002 CR4: 00000000007706e0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 PKRU: 55555554
 Call Trace:
  __wake_up_common_lock+0x7c/0xc0
  qla_nvme_ls_req+0x355/0x4c0 [qla2xxx]
 qla2xxx [0000:12:00.1]-f084:3: qlt_free_session_done: se_sess 0000000000000000 / sess ffff8ae1407ca000 from port 21:32:00:02:ac:07:ee:b8 loop_id 0x02 s_id 01:02:00 logout 1 keep 0 els_logo 0
 ? __nvme_fc_send_ls_req+0x260/0x380 [nvme_fc]
 qla2xxx [0000:12:00.1]-207d:3: FCPort 21:32:00:02:ac:07:ee:b8 state transitioned from ONLINE to LOST - portid=010200.
  ? nvme_fc_send_ls_req.constprop.42+0x1a/0x45 [nvme_fc]
 qla2xxx [0000:12:00.1]-2109:3: qla2x00_schedule_rport_del 21320002ac07eeb8. rport ffff8ae598122000 roles 1
 ? nvme_fc_connect_ctrl_work.cold.63+0x1e3/0xa7d [nvme_fc]
 qla2xxx [0000:12:00.1]-f084:3: qlt_free_session_done: se_sess 0000000000000000 / sess ffff8ae14801e000 from port 21:32:01:02:ad:f7:ee:b8 loop_id 0x04 s_id 01:02:01 logout 1 keep 0 els_logo 0
  ? __switch_to+0x10c/0x450
 ? process_one_work+0x1a7/0x360
 qla2xxx [0000:12:00.1]-207d:3: FCPort 21:32:01:02:ad:f7:ee:b8 state transitioned from ONLINE to LOST - portid=010201.
  ? worker_thread+0x1ce/0x390
  ? create_worker+0x1a0/0x1a0
 qla2xxx [0000:12:00.1]-2109:3: qla2x00_schedule_rport_del 21320102adf7eeb8. rport ffff8ae3b2312800 roles 70
  ? kthread+0x10a/0x120
 qla2xxx [0000:12:00.1]-2112:3: qla_nvme_unregister_remote_port: unregister remoteport on ffff8ae14801e000 21320102adf7eeb8
  ? set_kthread_struct+0x40/0x40
 qla2xxx [0000:12:00.1]-2110:3: remoteport_delete of ffff8ae14801e000 21320102adf7eeb8 completed.
  ? ret_from_fork+0x1f/0x40
 qla2xxx [0000:12:00.1]-f086:3: qlt_free_session_done: waiting for sess ffff8ae14801e000 logout

The system was under memory stress where driver was not able to allocate an SRB to carry out error recovery of cable pull. The failure to flush causes upper layer to start modifying scsi_cmnd. When the system frees up some memory, the subsequent cable pull trigger another command flush. At this point the driver access a null pointer when attempting to DMA unmap the SGL.

Add a check to make sure commands are flush back on session tear down to prevent the null pointer access.

---
 drivers/scsi/qla2xxx/qla_target.c |   10 ++++++++++
 1 file changed, 10 insertions(+)
drivers/scsi/qla2xxx/qla_target.c +10 -0
@@ -1083,6 +1083,16 @@ void qlt_free_session_done(struct work_s
 		    "%s: sess %p logout completed\n", __func__, sess);
 	}
 
+	/* check for any straggling io left behind */
+	if (!(sess->flags & FCF_FCP2_DEVICE) &&
+	    qla2x00_eh_wait_for_pending_commands(sess->vha, sess->d_id.b24, 0, WAIT_TARGET)) {
+		ql_log(ql_log_warn, vha, 0x3027,
+		    "IO not return. Resetting.\n");
+		set_bit(ISP_ABORT_NEEDED, &vha->dpc_flags);
+		qla2xxx_wake_dpc(vha);
+		qla2x00_wait_for_chip_reset(vha);
+	}
+
 	if (sess->logo_ack_needed) {
 		sess->logo_ack_needed = 0;
 		qla24xx_async_notify_ack(vha, sess,
author maintainer
#603 lore raw

PATCH 599/690 scsi: qla2xxx: Fix double free of fcport

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Saurav Kashyap <[email protected]>

commit 82f522ae0d97119a43da53e0f729275691b9c525 upstream.

The server was crashing after LOGO because fcport was getting freed twice.

-----------[ cut here ]-----------
kernel BUG at mm/slub.c:371!
invalid opcode: 0000 1 SMP PTI

 CPU: 35 PID: 4610 Comm: bash Kdump: loaded Tainted: G OE --------- - - 4.18.0-425.3.1.el8.x86_64 #1
 Hardware name: HPE ProLiant DL360 Gen10/ProLiant DL360 Gen10, BIOS U32 09/03/2021
 RIP: 0010:set_freepointer.part.57+0x0/0x10
 RSP: 0018:ffffb07107027d90 EFLAGS: 00010246
 RAX: ffff9cb7e3150000 RBX: ffff9cb7e332b9c0 RCX: ffff9cb7e3150400
 RDX: 0000000000001f37 RSI: 0000000000000000 RDI: ffff9cb7c0005500
 RBP: fffff693448c5400 R08: 0000000080000000 R09: 0000000000000009
 R10: 0000000000000000 R11: 0000000000132af0 R12: ffff9cb7c0005500
 R13: ffff9cb7e3150000 R14: ffffffffc06990e0 R15: ffff9cb7ea85ea58
 FS: 00007ff6b79c2740(0000) GS:ffff9cb8f7ec0000(0000) knlGS:0000000000000000
 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 000055b426b7d700 CR3: 0000000169c18002 CR4: 00000000007706e0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 PKRU: 55555554
 Call Trace:
 kfree+0x238/0x250
 qla2x00_els_dcmd_sp_free+0x20/0x230 [qla2xxx]
 ? qla24xx_els_dcmd_iocb+0x607/0x690 [qla2xxx]
 qla2x00_issue_logo+0x28c/0x2a0 [qla2xxx]
 ? qla2x00_issue_logo+0x28c/0x2a0 [qla2xxx]
 ? kernfs_fop_write+0x11e/0x1a0

Remove one of the free calls and add check for valid fcport. Also use function qla2x00_free_fcport() instead of kfree().

---
 drivers/scsi/qla2xxx/qla_iocb.c |    5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/scsi/qla2xxx/qla_iocb.c +3 -2
@@ -2638,7 +2638,8 @@ static void qla2x00_els_dcmd_sp_free(srb
 {
 	struct srb_iocb *elsio = &sp->u.iocb_cmd;
 
-	kfree(sp->fcport);
+	if (sp->fcport)
+		qla2x00_free_fcport(sp->fcport);
 
 	if (elsio->u.els_logo.els_logo_pyld)
 		dma_free_coherent(&sp->vha->hw->pdev->dev, DMA_POOL_SIZE,
@@ -2751,6 +2752,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *v
 	if (!elsio->u.els_logo.els_logo_pyld) {
 		/* ref: INIT */
 		kref_put(&sp->cmd_kref, qla2x00_sp_release);
+		qla2x00_free_fcport(fcport);
 		return QLA_FUNCTION_FAILED;
 	}
 
@@ -2785,7 +2787,6 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *v
 	    fcport->d_id.b.area, fcport->d_id.b.al_pa);
 
 	wait_for_completion(&elsio->u.els_logo.comp);
-	qla2x00_free_fcport(fcport);
 
 	/* ref: INIT */
 	kref_put(&sp->cmd_kref, qla2x00_sp_release);
author maintainer
#604 lore raw

PATCH 600/690 scsi: qla2xxx: Change debug message during driver unload

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Saurav Kashyap <[email protected]>

commit b5a30840727a3e41d12a336d19f6c0716b299161 upstream.

Upon driver unload, purge_mbox flag is set and the heartbeat monitor thread detects this flag and does not send the mailbox command down to FW with a debug message "Error detected: purge[1] eeh[0] cmd=0x0, Exiting". This being not a real error, change the debug message.

---
 drivers/scsi/qla2xxx/qla_mbx.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/scsi/qla2xxx/qla_mbx.c +1 -1
@@ -194,7 +194,7 @@ qla2x00_mailbox_command(scsi_qla_host_t
 	if (ha->flags.purge_mbox || chip_reset != ha->chip_reset ||
 	    ha->flags.eeh_busy) {
 		ql_log(ql_log_warn, vha, 0xd035,
-		       "Error detected: purge[%d] eeh[%d] cmd=0x%x, Exiting.\n",
+		       "Purge mbox: purge[%d] eeh[%d] cmd=0x%x, Exiting.\n",
 		       ha->flags.purge_mbox, ha->flags.eeh_busy, mcp->mb[0]);
 		rval = QLA_ABORTED;
 		goto premature_exit;
author maintainer
#605 lore raw

PATCH 601/690 scsi: qla2xxx: Delay I/O Abort on PCI error

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Quinn Tran <[email protected]>

commit 591c1fdf2016d118b8fbde427b796fac13f3f070 upstream.

Currently when PCI error is detected, I/O is aborted manually through the ABORT IOCB mechanism which is not guaranteed to succeed.

Instead, wait for the OS or system to notify driver to wind down I/O through the pci_error_handlers api. Set eeh_busy flag to pause all traffic and wait for I/O to drain.

---
 drivers/scsi/qla2xxx/qla_attr.c |   14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)
drivers/scsi/qla2xxx/qla_attr.c +12 -2
@@ -2732,7 +2732,13 @@ qla2x00_dev_loss_tmo_callbk(struct fc_rp
 		return;
 
 	if (unlikely(pci_channel_offline(fcport->vha->hw->pdev))) {
-		qla2x00_abort_all_cmds(fcport->vha, DID_NO_CONNECT << 16);
+		/* Will wait for wind down of adapter */
+		ql_dbg(ql_dbg_aer, fcport->vha, 0x900c,
+		    "%s pci offline detected (id %06x)\n", __func__,
+		    fcport->d_id.b24);
+		qla_pci_set_eeh_busy(fcport->vha);
+		qla2x00_eh_wait_for_pending_commands(fcport->vha, fcport->d_id.b24,
+		    0, WAIT_TARGET);
 		return;
 	}
 }
@@ -2754,7 +2760,11 @@ qla2x00_terminate_rport_io(struct fc_rpo
 	vha = fcport->vha;
 
 	if (unlikely(pci_channel_offline(fcport->vha->hw->pdev))) {
-		qla2x00_abort_all_cmds(fcport->vha, DID_NO_CONNECT << 16);
+		/* Will wait for wind down of adapter */
+		ql_dbg(ql_dbg_aer, fcport->vha, 0x900b,
+		    "%s pci offline detected (id %06x)\n", __func__,
+		    fcport->d_id.b24);
+		qla_pci_set_eeh_busy(vha);
 		qla2x00_eh_wait_for_pending_commands(fcport->vha, fcport->d_id.b24,
 			0, WAIT_TARGET);
 		return;
author maintainer
#606 lore raw

PATCH 602/690 x86/cpu: Enable STIBP on AMD if Automatic IBRS is enabled

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kim Phillips <[email protected]>

commit fd470a8beed88440b160d690344fbae05a0b9b1b upstream.

Unlike Intel's Enhanced IBRS feature, AMD's Automatic IBRS does not provide protection to processes running at CPL3/user mode, see section "Extended Feature Enable Register (EFER)" in the APM v2 at
https://bugzilla.kernel.org/attachment.cgi?id=304652

Explicitly enable STIBP to protect against cross-thread CPL3 branch target injections on systems with Automatic IBRS enabled.

Also update the relevant documentation.

---
 Documentation/admin-guide/hw-vuln/spectre.rst |   11 +++++++----
 arch/x86/kernel/cpu/bugs.c                    |   15 +++++++++------
 2 files changed, 16 insertions(+), 10 deletions(-)
Documentation/admin-guide/hw-vuln/spectre.rst +7 -4
@@ -484,11 +484,14 @@ Spectre variant 2
 
    Systems which support enhanced IBRS (eIBRS) enable IBRS protection once at
    boot, by setting the IBRS bit, and they're automatically protected against
-   Spectre v2 variant attacks, including cross-thread branch target injections
-   on SMT systems (STIBP). In other words, eIBRS enables STIBP too.
+   Spectre v2 variant attacks.
 
-   Legacy IBRS systems clear the IBRS bit on exit to userspace and
-   therefore explicitly enable STIBP for that
+   On Intel's enhanced IBRS systems, this includes cross-thread branch target
+   injections on SMT systems (STIBP). In other words, Intel eIBRS enables
+   STIBP, too.
+
+   AMD Automatic IBRS does not protect userspace, and Legacy IBRS systems clear
+   the IBRS bit on exit to userspace, therefore both explicitly enable STIBP.
 
    The retpoline mitigation is turned on by default on vulnerable
    CPUs. It can be forced on or off by the administrator
arch/x86/kernel/cpu/bugs.c +9 -6
@@ -1354,19 +1354,21 @@ spectre_v2_user_select_mitigation(void)
 	}
 
 	/*
-	 * If no STIBP, enhanced IBRS is enabled, or SMT impossible, STIBP
+	 * If no STIBP, Intel enhanced IBRS is enabled, or SMT impossible, STIBP
 	 * is not required.
 	 *
-	 * Enhanced IBRS also protects against cross-thread branch target
+	 * Intel's Enhanced IBRS also protects against cross-thread branch target
 	 * injection in user-mode as the IBRS bit remains always set which
 	 * implicitly enables cross-thread protections.  However, in legacy IBRS
 	 * mode, the IBRS bit is set only on kernel entry and cleared on return
-	 * to userspace. This disables the implicit cross-thread protection,
-	 * so allow for STIBP to be selected in that case.
+	 * to userspace.  AMD Automatic IBRS also does not protect userspace.
+	 * These modes therefore disable the implicit cross-thread protection,
+	 * so allow for STIBP to be selected in those cases.
 	 */
 	if (!boot_cpu_has(X86_FEATURE_STIBP) ||
 	    !smt_possible ||
-	    spectre_v2_in_eibrs_mode(spectre_v2_enabled))
+	    (spectre_v2_in_eibrs_mode(spectre_v2_enabled) &&
+	     !boot_cpu_has(X86_FEATURE_AUTOIBRS)))
 		return;
 
 	/*
@@ -2666,7 +2668,8 @@ static ssize_t rfds_show_state(char *buf
 
 static char *stibp_state(void)
 {
-	if (spectre_v2_in_eibrs_mode(spectre_v2_enabled))
+	if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) &&
+	    !boot_cpu_has(X86_FEATURE_AUTOIBRS))
 		return "";
 
 	switch (spectre_v2_user_stibp) {
author maintainer
#607 lore raw

PATCH 603/690 PCI/DPC: Quirk PIO log size for Intel Ice Lake Root Ports

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mika Westerberg <[email protected]>

commit 3b8803494a0612acdeee714cb72aa142b1e05ce5 upstream.

Commit 5459c0b70467 ("PCI/DPC: Quirk PIO log size for certain Intel Root Ports") added quirks for Tiger and Alder Lake Root Ports but missed that the same issue exists also in the previous generation, Ice Lake.

Apply the quirk for Ice Lake Root Ports as well. This prevents kernel complaints like:

DPC: RP PIO log size 0 is invalid

and also enables the DPC driver to dump the RP PIO Log registers when DPC is triggered.

---
 drivers/pci/quirks.c |    9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)
drivers/pci/quirks.c +7 -2
@@ -5953,8 +5953,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_I
 
 #ifdef CONFIG_PCIE_DPC
 /*
- * Intel Tiger Lake and Alder Lake BIOS has a bug that clears the DPC
- * RP PIO Log Size of the integrated Thunderbolt PCIe Root Ports.
+ * Intel Ice Lake, Tiger Lake and Alder Lake BIOS has a bug that clears
+ * the DPC RP PIO Log Size of the integrated Thunderbolt PCIe Root
+ * Ports.
  */
 static void dpc_log_size(struct pci_dev *dev)
 {
@@ -5977,6 +5978,10 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_I
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x462f, dpc_log_size);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x463f, dpc_log_size);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x466e, dpc_log_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a1d, dpc_log_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a1f, dpc_log_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a21, dpc_log_size);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x8a23, dpc_log_size);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a23, dpc_log_size);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a25, dpc_log_size);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x9a27, dpc_log_size);
author maintainer
#608 lore raw

PATCH 604/690 scsi: lpfc: Correct size for wqe for memset()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Muhammad Usama Anjum <[email protected]>

commit 28d41991182c210ec1654f8af2e140ef4cc73f20 upstream.

The wqe is of type lpfc_wqe128. It should be memset with the same type.

Fixes 6c621a2229b0 ("scsi: lpfc: Separate NVMET RQ buffer posting from IO resources SGL/iocbq/context")
---
 drivers/scsi/lpfc/lpfc_nvmet.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/scsi/lpfc/lpfc_nvmet.c +1 -1
@@ -1586,7 +1586,7 @@ lpfc_nvmet_setup_io_context(struct lpfc_
 		wqe = &nvmewqe->wqe;
 
 		/* Initialize WQE */
-		memset(wqe, 0, sizeof(union lpfc_wqe));
+		memset(wqe, 0, sizeof(*wqe));
 
 		ctx_buf->iocbq->context1 = NULL;
 		spin_lock(&phba->sli4_hba.sgl_list_lock);
author maintainer
#609 lore raw

PATCH 605/690 USB: core: Fix deadlock in usb_deauthorize_interface()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alan Stern <[email protected]>

commit 80ba43e9f799cbdd83842fc27db667289b3150f5 upstream.

Among the attribute file callback routines in drivers/usb/core/sysfs.c, the interface_authorized_store() function is the only one which acquires a device lock on an ancestor device: It calls usb_deauthorize_interface(), which locks the interface's parent USB device.

The will lead to deadlock if another process already owns that lock and tries to remove the interface, whether through a configuration change or because the device has been disconnected. As part of the removal procedure, device_del() waits for all ongoing sysfs attribute callbacks to complete. But usb_deauthorize_interface() can't complete until the device lock has been released, and the lock won't be released until the removal has finished.

The mechanism provided by sysfs to prevent this kind of deadlock is to use the sysfs_break_active_protection() function, which tells sysfs not to wait for the attribute callback.

Reported-and-tested by: Yue Sun <[email protected]> Reported by: xingwei lee <[email protected]>

---
 drivers/usb/core/sysfs.c |   16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)
drivers/usb/core/sysfs.c +13 -3
@@ -1169,14 +1169,24 @@ static ssize_t interface_authorized_stor
 {
 	struct usb_interface *intf = to_usb_interface(dev);
 	bool val;
+	struct kernfs_node *kn;
 
 	if (strtobool(buf, &val) != 0)
 		return -EINVAL;
 
-	if (val)
+	if (val) {
 		usb_authorize_interface(intf);
-	else
-		usb_deauthorize_interface(intf);
+	} else {
+		/*
+		 * Prevent deadlock if another process is concurrently
+		 * trying to unregister intf.
+		 */
+		kn = sysfs_break_active_protection(&dev->kobj, &attr->attr);
+		if (kn) {
+			usb_deauthorize_interface(intf);
+			sysfs_unbreak_active_protection(kn);
+		}
+	}
 
 	return count;
 }
author maintainer
#610 lore raw

PATCH 606/690 scsi: usb: Call scsi_done() directly

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bart Van Assche <[email protected]>

[ Upstream commit 46c97948e9b5bc8b67fd72741a2fe723ac1d14d7 ]

Conditional statements are faster than indirect calls. Hence call scsi_done() directly.

Stable-dep-of: cd5432c71235 ("USB: UAS: return ENODEV when submit urbs fail with device not attached")

---
 drivers/usb/storage/scsiglue.c |  1 -
 drivers/usb/storage/uas.c      | 10 ++++------
 drivers/usb/storage/usb.c      |  4 ++--
 3 files changed, 6 insertions(+), 9 deletions(-)
drivers/usb/storage/scsiglue.c +0 -1
index b8e1109f0e0d4..e104aa651ccc7 100644
@@ -393,7 +393,6 @@ static int queuecommand_lck(struct scsi_cmnd *srb,
 	}
 
 	/* enqueue the command and wake up the control thread */
-	srb->scsi_done = done;
 	us->srb = srb;
 	complete(&us->cmnd_ready);
 
drivers/usb/storage/uas.c +4 -6
index bef89c6bd1d7f..774d18907f472 100644
@@ -256,7 +256,7 @@ static int uas_try_complete(struct scsi_cmnd *cmnd, const char *caller)
 		return -EBUSY;
 	devinfo->cmnd[cmdinfo->uas_tag - 1] = NULL;
 	uas_free_unsubmitted_urbs(cmnd);
-	cmnd->scsi_done(cmnd);
+	scsi_done(cmnd);
 	return 0;
 }
 
@@ -653,7 +653,7 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd,
 		memcpy(cmnd->sense_buffer, usb_stor_sense_invalidCDB,
 		       sizeof(usb_stor_sense_invalidCDB));
 		cmnd->result = SAM_STAT_CHECK_CONDITION;
-		cmnd->scsi_done(cmnd);
+		scsi_done(cmnd);
 		return 0;
 	}
 
@@ -661,7 +661,7 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd,
 
 	if (devinfo->resetting) {
 		set_host_byte(cmnd, DID_ERROR);
-		cmnd->scsi_done(cmnd);
+		scsi_done(cmnd);
 		goto zombie;
 	}
 
@@ -675,8 +675,6 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd,
 		return SCSI_MLQUEUE_DEVICE_BUSY;
 	}
 
-	cmnd->scsi_done = done;
-
 	memset(cmdinfo, 0, sizeof(*cmdinfo));
 	cmdinfo->uas_tag = idx + 1; /* uas-tag == usb-stream-id, so 1 based */
 	cmdinfo->state = SUBMIT_STATUS_URB | ALLOC_CMD_URB | SUBMIT_CMD_URB;
@@ -706,7 +704,7 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd,
 	 */
 	if (err == -ENODEV) {
 		set_host_byte(cmnd, DID_ERROR);
-		cmnd->scsi_done(cmnd);
+		scsi_done(cmnd);
 		goto zombie;
 	}
 	if (err) {
drivers/usb/storage/usb.c +2 -2
index 90aa9c12ffac5..8b543f2c98575 100644
@@ -388,7 +388,7 @@ static int usb_stor_control_thread(void * __us)
 		if (srb->result == DID_ABORT << 16) {
 SkipForAbort:
 			usb_stor_dbg(us, "scsi command aborted\n");
-			srb = NULL;	/* Don't call srb->scsi_done() */
+			srb = NULL;	/* Don't call scsi_done() */
 		}
 
 		/*
@@ -417,7 +417,7 @@ static int usb_stor_control_thread(void * __us)
 		if (srb) {
 			usb_stor_dbg(us, "scsi cmd done, result=0x%x\n",
 					srb->result);
-			srb->scsi_done(srb);
+			scsi_done(srb);
 		}
 	} /* for (;;) */
 
Signature · 1 line
2.43.0
author maintainer
#611 lore raw

PATCH 607/690 scsi: usb: Stop using the SCSI pointer

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bart Van Assche <[email protected]>

[ Upstream commit 5dfcf1ad933fe877cb44e9fb7a661dfc22190101 ]

Set scsi_host_template.cmd_size instead of using the SCSI pointer for storing driver-private data. Change the type of the argument of uas_add_work() from struct uas_cmd_info * into struct scsi_cmnd * because it is easier to convert a SCSI command pointer into a uas_cmd_info pointer than the other way around.

This patch prepares for removal of the SCSI pointer from struct scsi_cmnd.

Stable-dep-of: cd5432c71235 ("USB: UAS: return ENODEV when submit urbs fail with device not attached")

---
 drivers/usb/storage/uas.c | 43 ++++++++++++++++++---------------------
 1 file changed, 20 insertions(+), 23 deletions(-)
drivers/usb/storage/uas.c +20 -23
index 774d18907f472..d11a9481f6d00 100644
@@ -113,7 +113,7 @@ static void uas_do_work(struct work_struct *work)
 			continue;
 
 		cmnd = devinfo->cmnd[i];
-		cmdinfo = (void *)&cmnd->SCp;
+		cmdinfo = scsi_cmd_priv(cmnd);
 
 		if (!(cmdinfo->state & IS_IN_WORK_LIST))
 			continue;
@@ -139,10 +139,9 @@ static void uas_scan_work(struct work_struct *work)
 	dev_dbg(&devinfo->intf->dev, "scan complete\n");
 }
 
-static void uas_add_work(struct uas_cmd_info *cmdinfo)
+static void uas_add_work(struct scsi_cmnd *cmnd)
 {
-	struct scsi_pointer *scp = (void *)cmdinfo;
-	struct scsi_cmnd *cmnd = container_of(scp, struct scsi_cmnd, SCp);
+	struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd);
 	struct uas_dev_info *devinfo = cmnd->device->hostdata;
 
 	lockdep_assert_held(&devinfo->lock);
@@ -163,7 +162,7 @@ static void uas_zap_pending(struct uas_dev_info *devinfo, int result)
 			continue;
 
 		cmnd = devinfo->cmnd[i];
-		cmdinfo = (void *)&cmnd->SCp;
+		cmdinfo = scsi_cmd_priv(cmnd);
 		uas_log_cmd_state(cmnd, __func__, 0);
 		/* Sense urbs were killed, clear COMMAND_INFLIGHT manually */
 		cmdinfo->state &= ~COMMAND_INFLIGHT;
@@ -200,15 +199,14 @@ static void uas_sense(struct urb *urb, struct scsi_cmnd *cmnd)
 static void uas_log_cmd_state(struct scsi_cmnd *cmnd, const char *prefix,
 			      int status)
 {
-	struct uas_cmd_info *ci = (void *)&cmnd->SCp;
-	struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp;
+	struct uas_cmd_info *ci = scsi_cmd_priv(cmnd);
 
 	if (status == -ENODEV) /* too late */
 		return;
 
 	scmd_printk(KERN_INFO, cmnd,
 		    "%s %d uas-tag %d inflight:%s%s%s%s%s%s%s%s%s%s%s%s ",
-		    prefix, status, cmdinfo->uas_tag,
+		    prefix, status, ci->uas_tag,
 		    (ci->state & SUBMIT_STATUS_URB)     ? " s-st"  : "",
 		    (ci->state & ALLOC_DATA_IN_URB)     ? " a-in"  : "",
 		    (ci->state & SUBMIT_DATA_IN_URB)    ? " s-in"  : "",
@@ -231,7 +229,7 @@ static void uas_free_unsubmitted_urbs(struct scsi_cmnd *cmnd)
 	if (!cmnd)
 		return;
 
-	cmdinfo = (void *)&cmnd->SCp;
+	cmdinfo = scsi_cmd_priv(cmnd);
 
 	if (cmdinfo->state & SUBMIT_CMD_URB)
 		usb_free_urb(cmdinfo->cmd_urb);
@@ -245,7 +243,7 @@ static void uas_free_unsubmitted_urbs(struct scsi_cmnd *cmnd)
 
 static int uas_try_complete(struct scsi_cmnd *cmnd, const char *caller)
 {
-	struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp;
+	struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd);
 	struct uas_dev_info *devinfo = (void *)cmnd->device->hostdata;
 
 	lockdep_assert_held(&devinfo->lock);
@@ -263,13 +261,13 @@ static int uas_try_complete(struct scsi_cmnd *cmnd, const char *caller)
 static void uas_xfer_data(struct urb *urb, struct scsi_cmnd *cmnd,
 			  unsigned direction)
 {
-	struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp;
+	struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd);
 	int err;
 
 	cmdinfo->state |= direction | SUBMIT_STATUS_URB;
 	err = uas_submit_urbs(cmnd, cmnd->device->hostdata);
 	if (err) {
-		uas_add_work(cmdinfo);
+		uas_add_work(cmnd);
 	}
 }
 
@@ -329,7 +327,7 @@ static void uas_stat_cmplt(struct urb *urb)
 	}
 
 	cmnd = devinfo->cmnd[idx];
-	cmdinfo = (void *)&cmnd->SCp;
+	cmdinfo = scsi_cmd_priv(cmnd);
 
 	if (!(cmdinfo->state & COMMAND_INFLIGHT)) {
 		uas_log_cmd_state(cmnd, "unexpected status cmplt", 0);
@@ -394,7 +392,7 @@ static void uas_stat_cmplt(struct urb *urb)
 static void uas_data_cmplt(struct urb *urb)
 {
 	struct scsi_cmnd *cmnd = urb->context;
-	struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp;
+	struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd);
 	struct uas_dev_info *devinfo = (void *)cmnd->device->hostdata;
 	struct scsi_data_buffer *sdb = &cmnd->sdb;
 	unsigned long flags;
@@ -446,7 +444,7 @@ static struct urb *uas_alloc_data_urb(struct uas_dev_info *devinfo, gfp_t gfp,
 				      enum dma_data_direction dir)
 {
 	struct usb_device *udev = devinfo->udev;
-	struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp;
+	struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd);
 	struct urb *urb = usb_alloc_urb(0, gfp);
 	struct scsi_data_buffer *sdb = &cmnd->sdb;
 	unsigned int pipe = (dir == DMA_FROM_DEVICE)
@@ -468,7 +466,7 @@ static struct urb *uas_alloc_sense_urb(struct uas_dev_info *devinfo, gfp_t gfp,
 				       struct scsi_cmnd *cmnd)
 {
 	struct usb_device *udev = devinfo->udev;
-	struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp;
+	struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd);
 	struct urb *urb = usb_alloc_urb(0, gfp);
 	struct sense_iu *iu;
 
@@ -496,7 +494,7 @@ static struct urb *uas_alloc_cmd_urb(struct uas_dev_info *devinfo, gfp_t gfp,
 {
 	struct usb_device *udev = devinfo->udev;
 	struct scsi_device *sdev = cmnd->device;
-	struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp;
+	struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd);
 	struct urb *urb = usb_alloc_urb(0, gfp);
 	struct command_iu *iu;
 	int len;
@@ -558,7 +556,7 @@ static struct urb *uas_submit_sense_urb(struct scsi_cmnd *cmnd, gfp_t gfp)
 static int uas_submit_urbs(struct scsi_cmnd *cmnd,
 			   struct uas_dev_info *devinfo)
 {
-	struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp;
+	struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd);
 	struct urb *urb;
 	int err;
 
@@ -638,12 +636,10 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd,
 {
 	struct scsi_device *sdev = cmnd->device;
 	struct uas_dev_info *devinfo = sdev->hostdata;
-	struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp;
+	struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd);
 	unsigned long flags;
 	int idx, err;
 
-	BUILD_BUG_ON(sizeof(struct uas_cmd_info) > sizeof(struct scsi_pointer));
-
 	/* Re-check scsi_block_requests now that we've the host-lock */
 	if (cmnd->device->host->host_self_blocked)
 		return SCSI_MLQUEUE_DEVICE_BUSY;
@@ -713,7 +709,7 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd,
 			spin_unlock_irqrestore(&devinfo->lock, flags);
 			return SCSI_MLQUEUE_DEVICE_BUSY;
 		}
-		uas_add_work(cmdinfo);
+		uas_add_work(cmnd);
 	}
 
 	devinfo->cmnd[idx] = cmnd;
@@ -731,7 +727,7 @@ static DEF_SCSI_QCMD(uas_queuecommand)
  */
 static int uas_eh_abort_handler(struct scsi_cmnd *cmnd)
 {
-	struct uas_cmd_info *cmdinfo = (void *)&cmnd->SCp;
+	struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd);
 	struct uas_dev_info *devinfo = (void *)cmnd->device->hostdata;
 	struct urb *data_in_urb = NULL;
 	struct urb *data_out_urb = NULL;
@@ -911,6 +907,7 @@ static struct scsi_host_template uas_host_template = {
 	.this_id = -1,
 	.skip_settle_delay = 1,
 	.dma_boundary = PAGE_SIZE - 1,
+	.cmd_size = sizeof(struct uas_cmd_info),
 };
 
 #define UNUSUAL_DEV(id_vendor, id_product, bcdDeviceMin, bcdDeviceMax, \
Signature · 1 line
2.43.0
author maintainer
#612 lore raw

PATCH 608/690 USB: UAS: return ENODEV when submit urbs fail with device not attached

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Weitao Wang <[email protected]>

[ Upstream commit cd5432c712351a3d5f82512908f5febfca946ca6 ]

In the scenario of entering hibernation with udisk in the system, if the udisk was gone or resume fail in the thaw phase of hibernation. Its state will be set to NOTATTACHED. At this point, usb_hub_wq was already freezed and can't not handle disconnect event. Next, in the poweroff phase of hibernation, SYNCHRONIZE_CACHE SCSI command will be sent to this udisk when poweroff this scsi device, which will cause uas_submit_urbs to be called to submit URB for sense/data/cmd pipe. However, these URBs will submit fail as device was set to NOTATTACHED state. Then, uas_submit_urbs will return a value SCSI_MLQUEUE_DEVICE_BUSY to the caller. That will lead the SCSI layer go into an ugly loop and system fail to go into hibernation.

On the other hand, when we specially check for -ENODEV in function uas_queuecommand_lck, returning DID_ERROR to SCSI layer will cause device poweroff fail and system shutdown instead of entering hibernation.

To fix this issue, let uas_submit_urbs to return original generic error when submitting URB failed. At the same time, we need to translate -ENODEV to DID_NOT_CONNECT for the SCSI layer.

---
 drivers/usb/storage/uas.c | 28 +++++++++++++---------------
 1 file changed, 13 insertions(+), 15 deletions(-)
drivers/usb/storage/uas.c +13 -15
index d11a9481f6d00..11a551a9cd057 100644
@@ -533,7 +533,7 @@ static struct urb *uas_alloc_cmd_urb(struct uas_dev_info *devinfo, gfp_t gfp,
  * daft to me.
  */
 
-static struct urb *uas_submit_sense_urb(struct scsi_cmnd *cmnd, gfp_t gfp)
+static int uas_submit_sense_urb(struct scsi_cmnd *cmnd, gfp_t gfp)
 {
 	struct uas_dev_info *devinfo = cmnd->device->hostdata;
 	struct urb *urb;
@@ -541,30 +541,28 @@ static struct urb *uas_submit_sense_urb(struct scsi_cmnd *cmnd, gfp_t gfp)
 
 	urb = uas_alloc_sense_urb(devinfo, gfp, cmnd);
 	if (!urb)
-		return NULL;
+		return -ENOMEM;
 	usb_anchor_urb(urb, &devinfo->sense_urbs);
 	err = usb_submit_urb(urb, gfp);
 	if (err) {
 		usb_unanchor_urb(urb);
 		uas_log_cmd_state(cmnd, "sense submit err", err);
 		usb_free_urb(urb);
-		return NULL;
 	}
-	return urb;
+	return err;
 }
 
 static int uas_submit_urbs(struct scsi_cmnd *cmnd,
 			   struct uas_dev_info *devinfo)
 {
 	struct uas_cmd_info *cmdinfo = scsi_cmd_priv(cmnd);
-	struct urb *urb;
 	int err;
 
 	lockdep_assert_held(&devinfo->lock);
 	if (cmdinfo->state & SUBMIT_STATUS_URB) {
-		urb = uas_submit_sense_urb(cmnd, GFP_ATOMIC);
-		if (!urb)
-			return SCSI_MLQUEUE_DEVICE_BUSY;
+		err = uas_submit_sense_urb(cmnd, GFP_ATOMIC);
+		if (err)
+			return err;
 		cmdinfo->state &= ~SUBMIT_STATUS_URB;
 	}
 
@@ -572,7 +570,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd,
 		cmdinfo->data_in_urb = uas_alloc_data_urb(devinfo, GFP_ATOMIC,
 							cmnd, DMA_FROM_DEVICE);
 		if (!cmdinfo->data_in_urb)
-			return SCSI_MLQUEUE_DEVICE_BUSY;
+			return -ENOMEM;
 		cmdinfo->state &= ~ALLOC_DATA_IN_URB;
 	}
 
@@ -582,7 +580,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd,
 		if (err) {
 			usb_unanchor_urb(cmdinfo->data_in_urb);
 			uas_log_cmd_state(cmnd, "data in submit err", err);
-			return SCSI_MLQUEUE_DEVICE_BUSY;
+			return err;
 		}
 		cmdinfo->state &= ~SUBMIT_DATA_IN_URB;
 		cmdinfo->state |= DATA_IN_URB_INFLIGHT;
@@ -592,7 +590,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd,
 		cmdinfo->data_out_urb = uas_alloc_data_urb(devinfo, GFP_ATOMIC,
 							cmnd, DMA_TO_DEVICE);
 		if (!cmdinfo->data_out_urb)
-			return SCSI_MLQUEUE_DEVICE_BUSY;
+			return -ENOMEM;
 		cmdinfo->state &= ~ALLOC_DATA_OUT_URB;
 	}
 
@@ -602,7 +600,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd,
 		if (err) {
 			usb_unanchor_urb(cmdinfo->data_out_urb);
 			uas_log_cmd_state(cmnd, "data out submit err", err);
-			return SCSI_MLQUEUE_DEVICE_BUSY;
+			return err;
 		}
 		cmdinfo->state &= ~SUBMIT_DATA_OUT_URB;
 		cmdinfo->state |= DATA_OUT_URB_INFLIGHT;
@@ -611,7 +609,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd,
 	if (cmdinfo->state & ALLOC_CMD_URB) {
 		cmdinfo->cmd_urb = uas_alloc_cmd_urb(devinfo, GFP_ATOMIC, cmnd);
 		if (!cmdinfo->cmd_urb)
-			return SCSI_MLQUEUE_DEVICE_BUSY;
+			return -ENOMEM;
 		cmdinfo->state &= ~ALLOC_CMD_URB;
 	}
 
@@ -621,7 +619,7 @@ static int uas_submit_urbs(struct scsi_cmnd *cmnd,
 		if (err) {
 			usb_unanchor_urb(cmdinfo->cmd_urb);
 			uas_log_cmd_state(cmnd, "cmd submit err", err);
-			return SCSI_MLQUEUE_DEVICE_BUSY;
+			return err;
 		}
 		cmdinfo->cmd_urb = NULL;
 		cmdinfo->state &= ~SUBMIT_CMD_URB;
@@ -699,7 +697,7 @@ static int uas_queuecommand_lck(struct scsi_cmnd *cmnd,
 	 * of queueing, no matter how fatal the error
 	 */
 	if (err == -ENODEV) {
-		set_host_byte(cmnd, DID_ERROR);
+		set_host_byte(cmnd, DID_NO_CONNECT);
 		scsi_done(cmnd);
 		goto zombie;
 	}
Signature · 1 line
2.43.0
author maintainer
#613 lore raw

PATCH 609/690 nfc: nci: Fix uninit-value in nci_dev_up and nci_ntf_packet

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ryosuke Yasuoka <[email protected]>

[ Upstream commit d24b03535e5eb82e025219c2f632b485409c898f ]

syzbot reported the following uninit-value access issue [1][2]:

nci_rx_work() parses and processes received packet. When the payload length is zero, each message type handler reads uninitialized payload and KMSAN detects this issue. The receipt of a packet with a zero-size payload is considered unexpected, and therefore, such packets should be silently discarded.

This patch resolved this issue by checking payload size before calling each message type handler codes.

---
 net/nfc/nci/core.c | 5 +++++
 1 file changed, 5 insertions(+)
net/nfc/nci/core.c +5 -0
index 419a1d0ba4c92..2a821f2b2ffe8 100644
@@ -1516,6 +1516,11 @@ static void nci_rx_work(struct work_struct *work)
 		nfc_send_to_raw_sock(ndev->nfc_dev, skb,
 				     RAW_PAYLOAD_NCI, NFC_DIRECTION_RX);
 
+		if (!nci_plen(skb->data)) {
+			kfree_skb(skb);
+			break;
+		}
+
 		/* Process frame */
 		switch (nci_mt(skb->data)) {
 		case NCI_MT_RSP_PKT:
Signature · 1 line
2.43.0
author maintainer
#614 lore raw

PATCH 610/690 mlxbf_gige: stop PHY during open() error paths

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Thompson <[email protected]>

[ Upstream commit d6c30c5a168f8586b8bcc0d8e42e2456eb05209b ]

The mlxbf_gige_open() routine starts the PHY as part of normal initialization. The mlxbf_gige_open() routine must stop the PHY during its error paths.

Fixes f92e1869d74e ("Add Mellanox BlueField Gigabit Ethernet driver")
---
 drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)
drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +4 -1
index 679415a64f25c..621594061fb57 100644
@@ -159,7 +159,7 @@ static int mlxbf_gige_open(struct net_device *netdev)
 
 	err = mlxbf_gige_tx_init(priv);
 	if (err)
-		goto free_irqs;
+		goto phy_deinit;
 	err = mlxbf_gige_rx_init(priv);
 	if (err)
 		goto tx_deinit;
@@ -187,6 +187,9 @@ static int mlxbf_gige_open(struct net_device *netdev)
 tx_deinit:
 	mlxbf_gige_tx_deinit(priv);
 
+phy_deinit:
+	phy_stop(phydev);
+
 free_irqs:
 	mlxbf_gige_free_irqs(priv);
 	return err;
Signature · 1 line
2.43.0
author maintainer
#615 lore raw

PATCH 611/690 iwlwifi: mvm: rfi: use kmemdup() to replace kzalloc + memcpy

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bixuan Cui <[email protected]>

[ Upstream commit 08186e2501eec554cde8bae53b1d1de4d54abdf4 ]

Fix memdup.cocci warning:
./drivers/net/wireless/intel/iwlwifi/mvm/rfi.c:110:8-15: WARNING opportunity for kmemdup

Stable-dep-of: 06a093807eb7 ("wifi: iwlwifi: mvm: rfi: fix potential response leaks")

---
 drivers/net/wireless/intel/iwlwifi/mvm/rfi.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)
drivers/net/wireless/intel/iwlwifi/mvm/rfi.c +1 -3
index 44344216a1a90..1954b4cdb90b4 100644
@@ -107,12 +107,10 @@ struct iwl_rfi_freq_table_resp_cmd *iwl_rfi_get_freq_table(struct iwl_mvm *mvm)
 	if (WARN_ON_ONCE(iwl_rx_packet_payload_len(cmd.resp_pkt) != resp_size))
 		return ERR_PTR(-EIO);
 
-	resp = kzalloc(resp_size, GFP_KERNEL);
+	resp = kmemdup(cmd.resp_pkt->data, resp_size, GFP_KERNEL);
 	if (!resp)
 		return ERR_PTR(-ENOMEM);
 
-	memcpy(resp, cmd.resp_pkt->data, resp_size);
-
 	iwl_free_resp(&cmd);
 	return resp;
 }
Signature · 1 line
2.43.0
author maintainer
#616 lore raw

PATCH 612/690 wifi: iwlwifi: mvm: rfi: fix potential response leaks

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Johannes Berg <[email protected]>

[ Upstream commit 06a093807eb7b5c5b29b6cff49f8174a4e702341 ]

If the rx payload length check fails, or if kmemdup() fails, we still need to free the command response. Fix that.

---
 drivers/net/wireless/intel/iwlwifi/mvm/rfi.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
drivers/net/wireless/intel/iwlwifi/mvm/rfi.c +6 -2
index 1954b4cdb90b4..4deb242df7b37 100644
@@ -104,13 +104,17 @@ struct iwl_rfi_freq_table_resp_cmd *iwl_rfi_get_freq_table(struct iwl_mvm *mvm)
 	if (ret)
 		return ERR_PTR(ret);
 
-	if (WARN_ON_ONCE(iwl_rx_packet_payload_len(cmd.resp_pkt) != resp_size))
+	if (WARN_ON_ONCE(iwl_rx_packet_payload_len(cmd.resp_pkt) !=
+			 resp_size)) {
+		iwl_free_resp(&cmd);
 		return ERR_PTR(-EIO);
+	}
 
 	resp = kmemdup(cmd.resp_pkt->data, resp_size, GFP_KERNEL);
+	iwl_free_resp(&cmd);
+
 	if (!resp)
 		return ERR_PTR(-ENOMEM);
 
-	iwl_free_resp(&cmd);
 	return resp;
 }
Signature · 1 line
2.43.0
author maintainer
#617 lore raw

PATCH 613/690 ixgbe: avoid sleeping allocation in ixgbe_ipsec_vf_add_sa()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Przemek Kitszel <[email protected]>

[ Upstream commit aec806fb4afba5fe80b09e29351379a4292baa43 ]

Change kzalloc() flags used in ixgbe_ipsec_vf_add_sa() to GFP_ATOMIC, to avoid sleeping in IRQ context.

Dan Carpenter, with the help of Smatch, has found following issue:
The patch eda0333ac293: "ixgbe: add VF IPsec management" from Aug 13, 2018 (linux-next), leads to the following Smatch static checker
warning: drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c:917 ixgbe_ipsec_vf_add_sa()
warn: sleeping in IRQ context

The call tree that Smatch is worried about is:
ixgbe_msix_other() <- IRQ handler
-> ixgbe_msg_task()
-> ixgbe_rcv_msg_from_vf()

      -> ixgbe_ipsec_vf_add_sa()
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)
drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +8 -8
index 69d11ff7677d6..ac198c00b44f5 100644
@@ -909,7 +909,13 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
 		goto err_out;
 	}
 
-	xs = kzalloc(sizeof(*xs), GFP_KERNEL);
+	algo = xfrm_aead_get_byname(aes_gcm_name, IXGBE_IPSEC_AUTH_BITS, 1);
+	if (unlikely(!algo)) {
+		err = -ENOENT;
+		goto err_out;
+	}
+
+	xs = kzalloc(sizeof(*xs), GFP_ATOMIC);
 	if (unlikely(!xs)) {
 		err = -ENOMEM;
 		goto err_out;
@@ -925,14 +931,8 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf)
 		memcpy(&xs->id.daddr.a4, sam->addr, sizeof(xs->id.daddr.a4));
 	xs->xso.dev = adapter->netdev;
 
-	algo = xfrm_aead_get_byname(aes_gcm_name, IXGBE_IPSEC_AUTH_BITS, 1);
-	if (unlikely(!algo)) {
-		err = -ENOENT;
-		goto err_xs;
-	}
-
 	aead_len = sizeof(*xs->aead) + IXGBE_IPSEC_KEY_BITS / 8;
-	xs->aead = kzalloc(aead_len, GFP_KERNEL);
+	xs->aead = kzalloc(aead_len, GFP_ATOMIC);
 	if (unlikely(!xs->aead)) {
 		err = -ENOMEM;
 		goto err_xs;
Signature · 1 line
2.43.0
author maintainer
#618 lore raw

PATCH 614/690 s390/qeth: handle deferred cc1

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alexandra Winter <[email protected]>

[ Upstream commit afb373ff3f54c9d909efc7f810dc80a9742807b2 ]

The IO subsystem expects a driver to retry a ccw_device_start, when the subsequent interrupt response block (irb) contains a deferred condition code 1.

Symptoms before this commit:
On the read channel we always trigger the next read anyhow, so no different behaviour here.
On the write channel we may experience timeout errors, because the expected reply will never be received without the retry. Other callers of qeth_send_control_data() may wrongly assume that the ccw was successful, which may cause problems later.

Note that since
commit 2297791c92d0 ("s390/cio: dont unregister subchannel from child-drivers") and
commit 5ef1dc40ffa6 ("s390/cio: fix invalid -EBUSY on ccw_device_start") deferred CC1s are much more likely to occur. See the commit message of the latter for more background information.

---
 drivers/s390/net/qeth_core_main.c | 38 +++++++++++++++++++++++++++++--
 1 file changed, 36 insertions(+), 2 deletions(-)
drivers/s390/net/qeth_core_main.c +36 -2
index 62e7576bff536..c1346c4e2242d 100644
@@ -1142,6 +1142,20 @@ static int qeth_check_irb_error(struct qeth_card *card, struct ccw_device *cdev,
 	}
 }
 
+/**
+ * qeth_irq() - qeth interrupt handler
+ * @cdev: ccw device
+ * @intparm: expect pointer to iob
+ * @irb: Interruption Response Block
+ *
+ * In the good path:
+ * corresponding qeth channel is locked with last used iob as active_cmd.
+ * But this function is also called for error interrupts.
+ *
+ * Caller ensures that:
+ * Interrupts are disabled; ccw device lock is held;
+ *
+ */
 static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
 		struct irb *irb)
 {
@@ -1183,11 +1197,10 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
 		iob = (struct qeth_cmd_buffer *) (addr_t)intparm;
 	}
 
-	qeth_unlock_channel(card, channel);
-
 	rc = qeth_check_irb_error(card, cdev, irb);
 	if (rc) {
 		/* IO was terminated, free its resources. */
+		qeth_unlock_channel(card, channel);
 		if (iob)
 			qeth_cancel_cmd(iob, rc);
 		return;
@@ -1231,6 +1244,7 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
 		rc = qeth_get_problem(card, cdev, irb);
 		if (rc) {
 			card->read_or_write_problem = 1;
+			qeth_unlock_channel(card, channel);
 			if (iob)
 				qeth_cancel_cmd(iob, rc);
 			qeth_clear_ipacmd_list(card);
@@ -1239,6 +1253,26 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm,
 		}
 	}
 
+	if (scsw_cmd_is_valid_cc(&irb->scsw) && irb->scsw.cmd.cc == 1 && iob) {
+		/* channel command hasn't started: retry.
+		 * active_cmd is still set to last iob
+		 */
+		QETH_CARD_TEXT(card, 2, "irqcc1");
+		rc = ccw_device_start_timeout(cdev, __ccw_from_cmd(iob),
+					      (addr_t)iob, 0, 0, iob->timeout);
+		if (rc) {
+			QETH_DBF_MESSAGE(2,
+					 "ccw retry on %x failed, rc = %i\n",
+					 CARD_DEVID(card), rc);
+			QETH_CARD_TEXT_(card, 2, " err%d", rc);
+			qeth_unlock_channel(card, channel);
+			qeth_cancel_cmd(iob, rc);
+		}
+		return;
+	}
+
+	qeth_unlock_channel(card, channel);
+
 	if (iob) {
 		/* sanity check: */
 		if (irb->scsw.cmd.count > iob->length) {
Signature · 1 line
2.43.0
author maintainer
#619 lore raw

PATCH 615/690 tcp: properly terminate timers for kernel sockets

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

[ Upstream commit 151c9c724d05d5b0dd8acd3e11cb69ef1f2dbada ]

We had various syzbot reports about tcp timers firing after the corresponding netns has been dismantled.

Fortunately Josef Bacik could trigger the issue more often, and could test a patch I wrote two years ago.

When TCP sockets are closed, we call inet_csk_clear_xmit_timers() to 'stop' the timers.

inet_csk_clear_xmit_timers() can be called from any context, including when socket lock is held.
This is the reason it uses sk_stop_timer(), aka del_timer(). This means that ongoing timers might finish much later.

For user sockets, this is fine because each running timer holds a reference on the socket, and the user socket holds a reference on the netns.

For kernel sockets, we risk that the netns is freed before timer can complete, because kernel sockets do not hold reference on the netns.

This patch adds inet_csk_clear_xmit_timers_sync() function that using sk_stop_timer_sync() to make sure all timers are terminated before the kernel socket is released. Modules using kernel sockets close them in their netns exit() handler.

Also add sock_not_owned_by_me() helper to get LOCKDEP support : inet_csk_clear_xmit_timers_sync() must not be called while socket lock is held.

It is very possible we can revert in the future commit 3a58f13a881e ("net: rds: acquire refcount on TCP sockets") which attempted to solve the issue in rds only. (net/smc/af_smc.c and net/mptcp/subflow.c have similar code)

We probably can remove the check_net() tests from tcp_out_of_resources() and __tcp_close() in the future.

Fixes 26abe14379f8 ("net: Modify sk_alloc to not reference count the netns of kernel sockets.")
Fixes 8a68173691f0 ("net: sk_clone_lock() should only do get_net() if the parent is not a kernel socket")
Cc Tetsuo Handa <[email protected]>
---
 include/net/inet_connection_sock.h |  1 +
 include/net/sock.h                 |  7 +++++++
 net/ipv4/inet_connection_sock.c    | 14 ++++++++++++++
 net/ipv4/tcp.c                     |  2 ++
 4 files changed, 24 insertions(+)
include/net/inet_connection_sock.h +1 -0
index 798aad21694e2..b6b7e210f9d7a 100644
@@ -169,6 +169,7 @@ void inet_csk_init_xmit_timers(struct sock *sk,
 			       void (*delack_handler)(struct timer_list *),
 			       void (*keepalive_handler)(struct timer_list *));
 void inet_csk_clear_xmit_timers(struct sock *sk);
+void inet_csk_clear_xmit_timers_sync(struct sock *sk);
 
 static inline void inet_csk_schedule_ack(struct sock *sk)
 {
include/net/sock.h +7 -0
index e19eebaf59f73..44ebec3fdda64 100644
@@ -1751,6 +1751,13 @@ static inline void sock_owned_by_me(const struct sock *sk)
 #endif
 }
 
+static inline void sock_not_owned_by_me(const struct sock *sk)
+{
+#ifdef CONFIG_LOCKDEP
+	WARN_ON_ONCE(lockdep_sock_is_held(sk) && debug_locks);
+#endif
+}
+
 static inline bool sock_owned_by_user(const struct sock *sk)
 {
 	sock_owned_by_me(sk);
net/ipv4/inet_connection_sock.c +14 -0
index da43957a58438..27975a44d1f9d 100644
@@ -589,6 +589,20 @@ void inet_csk_clear_xmit_timers(struct sock *sk)
 }
 EXPORT_SYMBOL(inet_csk_clear_xmit_timers);
 
+void inet_csk_clear_xmit_timers_sync(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	/* ongoing timer handlers need to acquire socket lock. */
+	sock_not_owned_by_me(sk);
+
+	icsk->icsk_pending = icsk->icsk_ack.pending = 0;
+
+	sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer);
+	sk_stop_timer_sync(sk, &icsk->icsk_delack_timer);
+	sk_stop_timer_sync(sk, &sk->sk_timer);
+}
+
 void inet_csk_delete_keepalive_timer(struct sock *sk)
 {
 	sk_stop_timer(sk, &sk->sk_timer);
net/ipv4/tcp.c +2 -0
index 521c15962c719..16fd3da68e9f6 100644
@@ -2916,6 +2916,8 @@ void tcp_close(struct sock *sk, long timeout)
 	lock_sock(sk);
 	__tcp_close(sk, timeout);
 	release_sock(sk);
+	if (!sk->sk_net_refcnt)
+		inet_csk_clear_xmit_timers_sync(sk);
 	sock_put(sk);
 }
 EXPORT_SYMBOL(tcp_close);
Signature · 1 line
2.43.0
author maintainer
#620 lore raw

PATCH 616/690 ACPICA: debugger: check status of acpi_evaluate_object() in acpi_db_walk_for_fields()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Nikita Kiryushin <[email protected]>

[ Upstream commit 40e2710860e57411ab57a1529c5a2748abbe8a19 ]

ACPICA commit 9061cd9aa131205657c811a52a9f8325a040c6c9

Errors in acpi_evaluate_object() can lead to incorrect state of buffer.

This can lead to access to data in previously ACPI_FREEd buffer and secondary ACPI_FREE to the same buffer later.

Handle errors in acpi_evaluate_object the same way it is done earlier with acpi_ns_handle_to_pathname.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes 5fd033288a86 ("ACPICA: debugger: add command to dump all fields of particular subtype")
---
 drivers/acpi/acpica/dbnames.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
drivers/acpi/acpica/dbnames.c +6 -2
index b91155ea9c343..c9131259f717b 100644
@@ -550,8 +550,12 @@ acpi_db_walk_for_fields(acpi_handle obj_handle,
 	ACPI_FREE(buffer.pointer);
 
 	buffer.length = ACPI_ALLOCATE_LOCAL_BUFFER;
-	acpi_evaluate_object(obj_handle, NULL, NULL, &buffer);
-
+	status = acpi_evaluate_object(obj_handle, NULL, NULL, &buffer);
+	if (ACPI_FAILURE(status)) {
+		acpi_os_printf("Could Not evaluate object %p\n",
+			       obj_handle);
+		return (AE_OK);
+	}
 	/*
 	 * Since this is a field unit, surround the output in braces
 	 */
Signature · 1 line
2.43.0
author maintainer
#621 lore raw

PATCH 617/690 mlxbf_gige: call request_irq() after NAPI initialized

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Thompson <[email protected]>

[ Upstream commit f7442a634ac06b953fc1f7418f307b25acd4cfbc ]

The mlxbf_gige driver encounters a NULL pointer exception in mlxbf_gige_open() when kdump is enabled. The sequence to reproduce the exception is as follows:
a) enable kdump
b) trigger kdump via "echo c > /proc/sysrq-trigger"
c) kdump kernel executes
d) kdump kernel loads mlxbf_gige module
e) the mlxbf_gige module runs its open() as the
the "oob_net0" interface is brought up
f) mlxbf_gige module will experience an exception
during its open(), something like:

     Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
     Mem abort info:
       ESR = 0x0000000086000004
       EC = 0x21: IABT (current EL), IL = 32 bits
       SET = 0, FnV = 0
       EA = 0, S1PTW = 0
       FSC = 0x04: level 0 translation fault
     user pgtable: 4k pages, 48-bit VAs, pgdp=00000000e29a4000
     [0000000000000000] pgd=0000000000000000, p4d=0000000000000000
     Internal error: Oops: 0000000086000004 [#1] SMP
     CPU: 0 PID: 812 Comm: NetworkManager Tainted: G           OE     5.15.0-1035-bluefield #37-Ubuntu
     Hardware name: https://www.mellanox.com BlueField-3 SmartNIC Main Card/BlueField-3 SmartNIC Main Card, BIOS 4.6.0.13024 Jan 19 2024
     pstate: 80400009 (Nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
     pc : 0x0
     lr : __napi_poll+0x40/0x230
     sp : ffff800008003e00
     x29: ffff800008003e00 x28: 0000000000000000 x27: 00000000ffffffff
     x26: ffff000066027238 x25: ffff00007cedec00 x24: ffff800008003ec8
     x23: 000000000000012c x22: ffff800008003eb7 x21: 0000000000000000
     x20: 0000000000000001 x19: ffff000066027238 x18: 0000000000000000
     x17: ffff578fcb450000 x16: ffffa870b083c7c0 x15: 0000aaab010441d0
     x14: 0000000000000001 x13: 00726f7272655f65 x12: 6769675f6662786c
     x11: 0000000000000000 x10: 0000000000000000 x9 : ffffa870b0842398
     x8 : 0000000000000004 x7 : fe5a48b9069706ea x6 : 17fdb11fc84ae0d2
     x5 : d94a82549d594f35 x4 : 0000000000000000 x3 : 0000000000400100
     x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff000066027238
     Call trace:
      0x0
      net_rx_action+0x178/0x360
      __do_softirq+0x15c/0x428
      __irq_exit_rcu+0xac/0xec
      irq_exit+0x18/0x2c
      handle_domain_irq+0x6c/0xa0
      gic_handle_irq+0xec/0x1b0
      call_on_irq_stack+0x20/0x2c
      do_interrupt_handler+0x5c/0x70
      el1_interrupt+0x30/0x50
      el1h_64_irq_handler+0x18/0x2c
      el1h_64_irq+0x7c/0x80
      __setup_irq+0x4c0/0x950
      request_threaded_irq+0xf4/0x1bc
      mlxbf_gige_request_irqs+0x68/0x110 [mlxbf_gige]
      mlxbf_gige_open+0x5c/0x170 [mlxbf_gige]
      __dev_open+0x100/0x220
      __dev_change_flags+0x16c/0x1f0
      dev_change_flags+0x2c/0x70
      do_setlink+0x220/0xa40
      __rtnl_newlink+0x56c/0x8a0
      rtnl_newlink+0x58/0x84
      rtnetlink_rcv_msg+0x138/0x3c4
      netlink_rcv_skb+0x64/0x130
      rtnetlink_rcv+0x20/0x30
      netlink_unicast+0x2ec/0x360
      netlink_sendmsg+0x278/0x490
      __sock_sendmsg+0x5c/0x6c
      ____sys_sendmsg+0x290/0x2d4
      ___sys_sendmsg+0x84/0xd0
      __sys_sendmsg+0x70/0xd0
      __arm64_sys_sendmsg+0x2c/0x40
      invoke_syscall+0x78/0x100
      el0_svc_common.constprop.0+0x54/0x184
      do_el0_svc+0x30/0xac
      el0_svc+0x48/0x160
      el0t_64_sync_handler+0xa4/0x12c
      el0t_64_sync+0x1a4/0x1a8
     Code: bad PC value
     ---[ end trace 7d1c3f3bf9d81885 ]---
     Kernel panic - not syncing: Oops: Fatal exception in interrupt
     Kernel Offset: 0x2870a7a00000 from 0xffff800008000000
     PHYS_OFFSET: 0x80000000
     CPU features: 0x0,000005c1,a3332a5a
     Memory Limit: none
     ---[ end Kernel panic - not syncing: Oops: Fatal exception in interrupt ]---

The exception happens because there is a pending RX interrupt before the call to request_irq(RX IRQ) executes. Then, the RX IRQ handler fires immediately after this request_irq() completes. The RX IRQ handler runs "napi_schedule()" before NAPI is fully initialized via "netif_napi_add()" and "napi_enable()", both which happen later in the open() logic.

The logic in mlxbf_gige_open() must fully initialize NAPI before any calls to request_irq() execute.

Fixes f92e1869d74e ("Add Mellanox BlueField Gigabit Ethernet driver")
---
 .../mellanox/mlxbf_gige/mlxbf_gige_main.c      | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)
drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +11 -7
index 621594061fb57..6b93889900434 100644
@@ -141,13 +141,10 @@ static int mlxbf_gige_open(struct net_device *netdev)
 	control |= MLXBF_GIGE_CONTROL_PORT_EN;
 	writeq(control, priv->base + MLXBF_GIGE_CONTROL);
 
-	err = mlxbf_gige_request_irqs(priv);
-	if (err)
-		return err;
 	mlxbf_gige_cache_stats(priv);
 	err = mlxbf_gige_clean_port(priv);
 	if (err)
-		goto free_irqs;
+		return err;
 
 	/* Clear driver's valid_polarity to match hardware,
 	 * since the above call to clean_port() resets the
@@ -168,6 +165,10 @@ static int mlxbf_gige_open(struct net_device *netdev)
 	napi_enable(&priv->napi);
 	netif_start_queue(netdev);
 
+	err = mlxbf_gige_request_irqs(priv);
+	if (err)
+		goto napi_deinit;
+
 	/* Set bits in INT_EN that we care about */
 	int_en = MLXBF_GIGE_INT_EN_HW_ACCESS_ERROR |
 		 MLXBF_GIGE_INT_EN_TX_CHECKSUM_INPUTS |
@@ -184,14 +185,17 @@ static int mlxbf_gige_open(struct net_device *netdev)
 
 	return 0;
 
+napi_deinit:
+	netif_stop_queue(netdev);
+	napi_disable(&priv->napi);
+	netif_napi_del(&priv->napi);
+	mlxbf_gige_rx_deinit(priv);
+
 tx_deinit:
 	mlxbf_gige_tx_deinit(priv);
 
 phy_deinit:
 	phy_stop(phydev);
-
-free_irqs:
-	mlxbf_gige_free_irqs(priv);
 	return err;
 }
 
Signature · 1 line
2.43.0
author maintainer
#622 lore raw

PATCH 618/690 bpf: Protect against int overflow for stack access size

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Andrei Matei <[email protected]>

[ Upstream commit ecc6a2101840177e57c925c102d2d29f260d37c8 ]

This patch re-introduces protection against the size of access to stack memory being negative; the access size can appear negative as a result of overflowing its signed int representation. This should not actually happen, as there are other protections along the way, but we should protect against it anyway. One code path was missing such protections (fixed in the previous patch in the series), causing out-of-bounds array accesses in check_stack_range_initialized(). This patch causes the verification of a program with such a non-sensical access size to fail.

This check used to exist in a more indirect way, but was inadvertendly removed in a833a17aeac7.

---
 kernel/bpf/verifier.c | 5 +++++
 1 file changed, 5 insertions(+)
kernel/bpf/verifier.c +5 -0
index f099c5481b662..008ddb694c8a1 100644
@@ -4320,6 +4320,11 @@ static int check_stack_access_within_bounds(
 	err = check_stack_slot_within_bounds(min_off, state, type);
 	if (!err && max_off > 0)
 		err = -EINVAL; /* out of stack access into non-negative offsets */
+	if (!err && access_size < 0)
+		/* access_size should not be negative (or overflow an int); others checks
+		 * along the way should have prevented such an access.
+		 */
+		err = -EFAULT; /* invalid negative access size; integer overflow? */
 
 	if (err) {
 		if (tnum_is_const(reg->var_off)) {
Signature · 1 line
2.43.0
author maintainer
#623 lore raw

PATCH 619/690 Octeontx2-af: fix pause frame configuration in GMP mode

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hariprasad Kelam <[email protected]>

[ Upstream commit 40d4b4807cadd83fb3f46cc8cd67a945b5b25461 ]

The Octeontx2 MAC block (CGX) has separate data paths (SMU and GMP) for different speeds, allowing for efficient data transfer.

The previous patch which added pause frame configuration has a bug due to which pause frame feature is not working in GMP mode.

This patch fixes the issue by configurating appropriate registers.

Fixes f7e086e754fe ("octeontx2-af: Pause frame configuration at cgx")
---
 drivers/net/ethernet/marvell/octeontx2/af/cgx.c | 5 +++++
 1 file changed, 5 insertions(+)
drivers/net/ethernet/marvell/octeontx2/af/cgx.c +5 -0
index 3ade1a6e2f1e0..4dec201158956 100644
@@ -787,6 +787,11 @@ static int cgx_lmac_enadis_pause_frm(void *cgxd, int lmac_id,
 	if (!is_lmac_valid(cgx, lmac_id))
 		return -ENODEV;
 
+	cfg = cgx_read(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL);
+	cfg &= ~CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK;
+	cfg |= rx_pause ? CGX_GMP_GMI_RXX_FRM_CTL_CTL_BCK : 0x0;
+	cgx_write(cgx, lmac_id, CGXX_GMP_GMI_RXX_FRM_CTL, cfg);
+
 	cfg = cgx_read(cgx, lmac_id, CGXX_SMUX_RX_FRM_CTL);
 	cfg &= ~CGX_SMUX_RX_FRM_CTL_CTL_BCK;
 	cfg |= rx_pause ? CGX_SMUX_RX_FRM_CTL_CTL_BCK : 0x0;
Signature · 1 line
2.43.0
author maintainer
#624 lore raw

PATCH 620/690 dm integrity: fix out-of-range warning

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Arnd Bergmann <[email protected]>

[ Upstream commit 8e91c2342351e0f5ef6c0a704384a7f6fc70c3b2 ]

Depending on the value of CONFIG_HZ, clang complains about a pointless comparison:

drivers/md/dm-integrity.c:4085:12: error: result of comparison of
constant 42949672950 with expression of type 'unsigned int' is always false [-Werror,-Wtautological-constant-out-of-range-compare] if (val >= (uint64_t)UINT_MAX * 1000 / HZ) {

As the check remains useful for other configurations, shut up the warning by adding a second type cast to uint64_t.

Fixes 468dfca38b1a ("dm integrity: add a bitmap mode")
---
 drivers/md/dm-integrity.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/md/dm-integrity.c +1 -1
index df743650d8a9d..ae372bc44fbfc 100644
@@ -4083,7 +4083,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
 		} else if (sscanf(opt_string, "sectors_per_bit:%llu%c", &llval, &dummy) == 1) {
 			log2_sectors_per_bitmap_bit = !llval ? 0 : __ilog2_u64(llval);
 		} else if (sscanf(opt_string, "bitmap_flush_interval:%u%c", &val, &dummy) == 1) {
-			if (val >= (uint64_t)UINT_MAX * 1000 / HZ) {
+			if ((uint64_t)val >= (uint64_t)UINT_MAX * 1000 / HZ) {
 				r = -EINVAL;
 				ti->error = "Invalid bitmap_flush_interval argument";
 				goto bad;
Signature · 1 line
2.43.0
author maintainer
#625 lore raw

PATCH 621/690 r8169: fix issue caused by buggy BIOS on certain boards with RTL8168d

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Heiner Kallweit <[email protected]>

commit 5d872c9f46bd2ea3524af3c2420a364a13667135 upstream.

On some boards with this chip version the BIOS is buggy and misses to reset the PHY page selector. This results in the PHY ID read accessing registers on a different page, returning a more or less random value. Fix this by resetting the page selector first.

---
 drivers/net/ethernet/realtek/r8169_main.c |    9 +++++++++
 1 file changed, 9 insertions(+)
drivers/net/ethernet/realtek/r8169_main.c +9 -0
@@ -5138,6 +5138,15 @@ static int r8169_mdio_register(struct rt
 	struct mii_bus *new_bus;
 	int ret;
 
+	/* On some boards with this chip version the BIOS is buggy and misses
+	 * to reset the PHY page selector. This results in the PHY ID read
+	 * accessing registers on a different page, returning a more or
+	 * less random value. Fix this by resetting the page selector first.
+	 */
+	if (tp->mac_version == RTL_GIGA_MAC_VER_25 ||
+	    tp->mac_version == RTL_GIGA_MAC_VER_26)
+		r8169_mdio_write(tp, 0x1f, 0);
+
 	new_bus = devm_mdiobus_alloc(&pdev->dev);
 	if (!new_bus)
 		return -ENOMEM;
author maintainer
#626 lore raw

PATCH 622/690 x86/cpufeatures: Add new word for scattered features

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sandipan Das <[email protected]>

commit 7f274e609f3d5f45c22b1dd59053f6764458b492 upstream.

Add a new word for scattered features because all free bits among the existing Linux-defined auxiliary flags have been exhausted.

---
 arch/x86/include/asm/cpufeature.h        |    6 ++++--
 arch/x86/include/asm/cpufeatures.h       |    2 +-
 arch/x86/include/asm/disabled-features.h |    3 ++-
 arch/x86/include/asm/required-features.h |    3 ++-
 4 files changed, 9 insertions(+), 5 deletions(-)
arch/x86/include/asm/cpufeature.h +4 -2
@@ -93,8 +93,9 @@ extern const char * const x86_bug_flags[
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) ||	\
 	   REQUIRED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 21))
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 22))
 
 #define DISABLED_MASK_BIT_SET(feature_bit)				\
 	 ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  0, feature_bit) ||	\
@@ -118,8 +119,9 @@ extern const char * const x86_bug_flags[
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) ||	\
 	   DISABLED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 21))
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 22))
 
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
arch/x86/include/asm/cpufeatures.h +1 -1
@@ -13,7 +13,7 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS			21	   /* N 32-bit words worth of info */
+#define NCAPINTS			22	   /* N 32-bit words worth of info */
 #define NBUGINTS			2	   /* N 32-bit bug flags */
 
 /*
arch/x86/include/asm/disabled-features.h +2 -1
@@ -109,6 +109,7 @@
 #define DISABLED_MASK18	0
 #define DISABLED_MASK19	0
 #define DISABLED_MASK20	0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
+#define DISABLED_MASK21	0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */
arch/x86/include/asm/required-features.h +2 -1
@@ -103,6 +103,7 @@
 #define REQUIRED_MASK18	0
 #define REQUIRED_MASK19	0
 #define REQUIRED_MASK20	0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
+#define REQUIRED_MASK21	0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */
author maintainer
#627 lore raw

PATCH 623/690 x86/cpufeatures: Add CPUID_LNX_5 to track recently added Linux-defined word

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sean Christopherson <[email protected]>

commit 8cb4a9a82b21623dbb4b3051dd30d98356cf95bc upstream.

Add CPUID_LNX_5 to track cpufeatures' word 21, and add the appropriate compile-time assert in KVM to prevent direct lookups on the features in CPUID_LNX_5. KVM uses X86_FEATURE_* flags to manage guest CPUID, and so must translate features that are scattered by Linux from the Linux-defined bit to the hardware-defined bit, i.e. should never try to directly access scattered features in guest CPUID.

Opportunistically add NR_CPUID_WORDS to enum cpuid_leafs, along with a compile-time assert in KVM's CPUID infrastructure to ensure that future additions update cpuid_leafs along with NCAPINTS.

No functional change intended.

Fixes 7f274e609f3d ("x86/cpufeatures: Add new word for scattered features")
Cc Sandipan Das <[email protected]>
---
 arch/x86/include/asm/cpufeature.h |    2 ++
 arch/x86/kvm/reverse_cpuid.h      |    2 ++
 2 files changed, 4 insertions(+)
arch/x86/include/asm/cpufeature.h +2 -0
@@ -33,6 +33,8 @@ enum cpuid_leafs
 	CPUID_7_EDX,
 	CPUID_8000_001F_EAX,
 	CPUID_8000_0021_EAX,
+	CPUID_LNX_5,
+	NR_CPUID_WORDS,
 };
 
 #ifdef CONFIG_X86_FEATURE_NAMES
arch/x86/kvm/reverse_cpuid.h +2 -0
@@ -83,10 +83,12 @@ static const struct cpuid_reg reverse_cp
  */
 static __always_inline void reverse_cpuid_check(unsigned int x86_leaf)
 {
+	BUILD_BUG_ON(NR_CPUID_WORDS != NCAPINTS);
 	BUILD_BUG_ON(x86_leaf == CPUID_LNX_1);
 	BUILD_BUG_ON(x86_leaf == CPUID_LNX_2);
 	BUILD_BUG_ON(x86_leaf == CPUID_LNX_3);
 	BUILD_BUG_ON(x86_leaf == CPUID_LNX_4);
+	BUILD_BUG_ON(x86_leaf == CPUID_LNX_5);
 	BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid));
 	BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0);
 }
author maintainer
#628 lore raw

PATCH 624/690 arm64: dts: qcom: sc7180-trogdor: mark bluetooth address as broken

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Johan Hovold <[email protected]>

commit e12e28009e584c8f8363439f6a928ec86278a106 upstream.

Several Qualcomm Bluetooth controllers lack persistent storage for the device address and instead one can be provided by the boot firmware using the 'local-bd-address' devicetree property.

The Bluetooth bindings clearly states that the address should be specified in little-endian order, but due to a long-standing bug in the Qualcomm driver which reversed the address some boot firmware has been providing the address in big-endian order instead.

The boot firmware in SC7180 Trogdor Chromebooks is known to be affected so mark the 'local-bd-address' property as broken to maintain backwards compatibility with older firmware when fixing the underlying driver bug.

Note that ChromeOS always updates the kernel and devicetree in lockstep so that there is no need to handle backwards compatibility with older devicetrees.

Fixes 7ec3e67307f8 ("arm64: dts: qcom: sc7180-trogdor: add initial trogdor and lazor dt")
Cc Rob Clark <[email protected]>
---
 arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi |    2 ++
 1 file changed, 2 insertions(+)
arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi +2 -0
@@ -911,6 +911,8 @@ ap_spi_fp: &spi10 {
 		vddrf-supply = <&pp1300_l2c>;
 		vddch0-supply = <&pp3300_l10c>;
 		max-speed = <3200000>;
+
+		qcom,local-bd-address-broken;
 	};
 };
 
author maintainer
#629 lore raw

PATCH 625/690 Bluetooth: hci_event: set the conn encrypted before conn establishes

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hui Wang <[email protected]>

commit c569242cd49287d53b73a94233db40097d838535 upstream.

We have a BT headset (Lenovo Thinkplus XT99), the pairing and connecting has no problem, once this headset is paired, bluez will remember this device and will auto re-connect it whenever the device is powered on. The auto re-connecting works well with Windows and Android, but with Linux, it always fails. Through debugging, we found at the rfcomm connection stage, the bluetooth stack reports "Connection refused - security block (0x0003)".

For this device, the re-connecting negotiation process is different from other BT headsets, it sends the Link_KEY_REQUEST command before the CONNECT_REQUEST completes, and it doesn't send ENCRYPT_CHANGE command during the negotiation. When the device sends the "connect complete" to hci, the ev->encr_mode is 1.

So here in the conn_complete_evt(), if ev->encr_mode is 1, link type is ACL and HCI_CONN_ENCRYPT is not set, we set HCI_CONN_ENCRYPT to this conn, and update conn->enc_key_size accordingly.

After this change, this BT headset could re-connect with Linux successfully. This is the btmon log after applying the patch, after receiving the "Connect Complete" with "Encryption: Enabled", will send the command to read encryption key size:

Quoted 1 line

HCI Event: Connect Request (0x04) plen 10

Address: 8C:3C:AA:D8:11:67 (OUI 8C-3C-AA)
Class: 0x240404
Major class: Audio/Video (headset, speaker, stereo, video, vcr) Minor class: Wearable Headset Device
Rendering (Printing, Speaker)
Audio (Speaker, Microphone, Headset)
Link type: ACL (0x01)
...

Quoted 1 line

HCI Event: Link Key Request (0x17) plen 6

        Address: 8C:3C:AA:D8:11:67 (OUI 8C-3C-AA)
< HCI Command: Link Key Request Reply (0x01|0x000b) plen 22
        Address: 8C:3C:AA:D8:11:67 (OUI 8C-3C-AA)
        Link key: ${32-hex-digits-key}

...

Quoted 1 line

HCI Event: Connect Complete (0x03) plen 11

        Status: Success (0x00)
        Handle: 256
        Address: 8C:3C:AA:D8:11:67 (OUI 8C-3C-AA)
        Link type: ACL (0x01)
        Encryption: Enabled (0x01)
< HCI Command: Read Encryption Key... (0x05|0x0008) plen 2
        Handle: 256
< ACL Data TX: Handle 256 flags 0x00 dlen 10
      L2CAP: Information Request (0x0a) ident 1 len 2
        Type: Extended features supported (0x0002)
Quoted 1 line

HCI Event: Command Complete (0x0e) plen 7

      Read Encryption Key Size (0x05|0x0008) ncmd 1
        Status: Success (0x00)
        Handle: 256
        Key size: 16
---
 net/bluetooth/hci_event.c |   25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)
net/bluetooth/hci_event.c +25 -0
@@ -2729,6 +2729,31 @@ static void hci_conn_complete_evt(struct
 		if (test_bit(HCI_ENCRYPT, &hdev->flags))
 			set_bit(HCI_CONN_ENCRYPT, &conn->flags);
 
+		/* "Link key request" completed ahead of "connect request" completes */
+		if (ev->encr_mode == 1 && !test_bit(HCI_CONN_ENCRYPT, &conn->flags) &&
+		    ev->link_type == ACL_LINK) {
+			struct link_key *key;
+			struct hci_cp_read_enc_key_size cp;
+
+			key = hci_find_link_key(hdev, &ev->bdaddr);
+			if (key) {
+				set_bit(HCI_CONN_ENCRYPT, &conn->flags);
+
+				if (!(hdev->commands[20] & 0x10)) {
+					conn->enc_key_size = HCI_LINK_KEY_SIZE;
+				} else {
+					cp.handle = cpu_to_le16(conn->handle);
+					if (hci_send_cmd(hdev, HCI_OP_READ_ENC_KEY_SIZE,
+							 sizeof(cp), &cp)) {
+						bt_dev_err(hdev, "sending read key size failed");
+						conn->enc_key_size = HCI_LINK_KEY_SIZE;
+					}
+				}
+
+				hci_encrypt_cfm(conn, ev->status);
+			}
+		}
+
 		/* Get remote features */
 		if (conn->type == ACL_LINK) {
 			struct hci_cp_read_remote_features cp;
author maintainer
#630 lore raw

PATCH 626/690 Bluetooth: Fix TOCTOU in HCI debugfs implementation

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bastien Nocera <[email protected]>

commit 7835fcfd132eb88b87e8eb901f88436f63ab60f7 upstream.

struct hci_dev members conn_info_max_age, conn_info_min_age, le_conn_max_interval, le_conn_min_interval, le_adv_max_interval, and le_adv_min_interval can be modified from the HCI core code, as well through debugfs.

The debugfs implementation, that's only available to privileged users, will check for boundaries, making sure that the minimum value being set is strictly above the maximum value that already exists, and vice-versa.

However, as both minimum and maximum values can be changed concurrently to us modifying them, we need to make sure that the value we check is the value we end up using.

For example, with ->conn_info_max_age set to 10, conn_info_min_age_set() gets called from vfs handlers to set conn_info_min_age to 8.

In conn_info_min_age_set(), this goes through:

	if (val == 0 || val > hdev->conn_info_max_age)
		return -EINVAL;

Concurrently, conn_info_max_age_set() gets called to set to set the conn_info_max_age to 7:

	if (val == 0 || val > hdev->conn_info_max_age)
		return -EINVAL;

That check will also pass because we used the old value (10) for conn_info_max_age.

After those checks that both passed, the struct hci_dev access is mutex-locked, disabling concurrent access, but that does not matter because the invalid value checks both passed, and we'll end up with conn_info_min_age = 8 and conn_info_max_age = 7

To fix this problem, we need to lock the structure access before so the check and assignment are not interrupted.

This fix was originally devised by the BassCheck[1] team, and considered the problem to be an atomicity one. This isn't the case as there aren't any concerns about the variable changing while we check it, but rather after we check it parallel to another change.

This patch fixes CVE-2024-24858 and CVE-2024-24857.

[1] https://sites.google.com/view/basscheck/

Fixes 31ad169148df ("Bluetooth: Add conn info lifetime parameters to debugfs")
Fixes 729a1051da6f ("Bluetooth: Expose default LE advertising interval via debugfs")
Fixes 71c3b60ec6d2 ("Bluetooth: Move BR/EDR debugfs file creation into hci_debugfs.c")
---
 net/bluetooth/hci_debugfs.c |   48 +++++++++++++++++++++++++++++---------------
 1 file changed, 32 insertions(+), 16 deletions(-)
net/bluetooth/hci_debugfs.c +32 -16
@@ -216,10 +216,12 @@ static int conn_info_min_age_set(void *d
 {
 	struct hci_dev *hdev = data;
 
-	if (val == 0 || val > hdev->conn_info_max_age)
+	hci_dev_lock(hdev);
+	if (val == 0 || val > hdev->conn_info_max_age) {
+		hci_dev_unlock(hdev);
 		return -EINVAL;
+	}
 
-	hci_dev_lock(hdev);
 	hdev->conn_info_min_age = val;
 	hci_dev_unlock(hdev);
 
@@ -244,10 +246,12 @@ static int conn_info_max_age_set(void *d
 {
 	struct hci_dev *hdev = data;
 
-	if (val == 0 || val < hdev->conn_info_min_age)
+	hci_dev_lock(hdev);
+	if (val == 0 || val < hdev->conn_info_min_age) {
+		hci_dev_unlock(hdev);
 		return -EINVAL;
+	}
 
-	hci_dev_lock(hdev);
 	hdev->conn_info_max_age = val;
 	hci_dev_unlock(hdev);
 
@@ -565,10 +569,12 @@ static int sniff_min_interval_set(void *
 {
 	struct hci_dev *hdev = data;
 
-	if (val == 0 || val % 2 || val > hdev->sniff_max_interval)
+	hci_dev_lock(hdev);
+	if (val == 0 || val % 2 || val > hdev->sniff_max_interval) {
+		hci_dev_unlock(hdev);
 		return -EINVAL;
+	}
 
-	hci_dev_lock(hdev);
 	hdev->sniff_min_interval = val;
 	hci_dev_unlock(hdev);
 
@@ -593,10 +599,12 @@ static int sniff_max_interval_set(void *
 {
 	struct hci_dev *hdev = data;
 
-	if (val == 0 || val % 2 || val < hdev->sniff_min_interval)
+	hci_dev_lock(hdev);
+	if (val == 0 || val % 2 || val < hdev->sniff_min_interval) {
+		hci_dev_unlock(hdev);
 		return -EINVAL;
+	}
 
-	hci_dev_lock(hdev);
 	hdev->sniff_max_interval = val;
 	hci_dev_unlock(hdev);
 
@@ -848,10 +856,12 @@ static int conn_min_interval_set(void *d
 {
 	struct hci_dev *hdev = data;
 
-	if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval)
+	hci_dev_lock(hdev);
+	if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval) {
+		hci_dev_unlock(hdev);
 		return -EINVAL;
+	}
 
-	hci_dev_lock(hdev);
 	hdev->le_conn_min_interval = val;
 	hci_dev_unlock(hdev);
 
@@ -876,10 +886,12 @@ static int conn_max_interval_set(void *d
 {
 	struct hci_dev *hdev = data;
 
-	if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval)
+	hci_dev_lock(hdev);
+	if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval) {
+		hci_dev_unlock(hdev);
 		return -EINVAL;
+	}
 
-	hci_dev_lock(hdev);
 	hdev->le_conn_max_interval = val;
 	hci_dev_unlock(hdev);
 
@@ -988,10 +1000,12 @@ static int adv_min_interval_set(void *da
 {
 	struct hci_dev *hdev = data;
 
-	if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval)
+	hci_dev_lock(hdev);
+	if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval) {
+		hci_dev_unlock(hdev);
 		return -EINVAL;
+	}
 
-	hci_dev_lock(hdev);
 	hdev->le_adv_min_interval = val;
 	hci_dev_unlock(hdev);
 
@@ -1016,10 +1030,12 @@ static int adv_max_interval_set(void *da
 {
 	struct hci_dev *hdev = data;
 
-	if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval)
+	hci_dev_lock(hdev);
+	if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval) {
+		hci_dev_unlock(hdev);
 		return -EINVAL;
+	}
 
-	hci_dev_lock(hdev);
 	hdev->le_adv_max_interval = val;
 	hci_dev_unlock(hdev);
 
author maintainer
#631 lore raw

PATCH 627/690 xen-netfront: Add missing skb_mark_for_recycle

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jesper Dangaard Brouer <[email protected]>

commit 037965402a010898d34f4e35327d22c0a95cd51f upstream.

Notice that skb_mark_for_recycle() is introduced later than fixes tag in commit 6a5bcd84e886 ("page_pool: Allow drivers to hint on SKB recycling").

It is believed that fixes tag were missing a call to page_pool_release_page() between v5.9 to v5.14, after which is should have used skb_mark_for_recycle(). Since v6.6 the call page_pool_release_page() were removed (in commit 535b9c61bdef ("net: page_pool: hide page_pool_release_page()") and remaining callers converted (in commit 6bfef2ec0172 ("Merge branch 'net-page_pool-remove-page_pool_release_page'")).

This leak became visible in v6.8 via commit dba1b8a7ab68 ("mm/page_pool: catch page_pool memory leaks").

---
 drivers/net/xen-netfront.c |    1 +
 1 file changed, 1 insertion(+)
drivers/net/xen-netfront.c +1 -0
@@ -287,6 +287,7 @@ static struct sk_buff *xennet_alloc_one_
 		return NULL;
 	}
 	skb_add_rx_frag(skb, 0, page, 0, 0, PAGE_SIZE);
+	skb_mark_for_recycle(skb);
 
 	/* Align ip header to a 16 bytes boundary */
 	skb_reserve(skb, NET_IP_ALIGN);
author maintainer
#632 lore raw

PATCH 628/690 net/rds: fix possible cp null dereference

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mahmoud Adam <[email protected]>

commit 62fc3357e079a07a22465b9b6ef71bb6ea75ee4b upstream.

cp might be null, calling cp->cp_conn would produce null dereference

[Simon Horman adds:]

Analysis:

* cp is a parameter of __rds_rdma_map and is not reassigned.

* The following call-sites pass a NULL cp argument to __rds_rdma_map()

- rds_get_mr()
- rds_get_mr_for_dest

* Prior to the code above, the following assumes that cp may be NULL (which is indicative, but could itself be unnecessary)

	trans_private = rs->rs_transport->get_mr(
		sg, nents, rs, &mr->r_key, cp ? cp->cp_conn : NULL,
		args->vec.addr, args->vec.bytes,
		need_odp ? ODP_ZEROBASED : ODP_NOT_NEEDED);

* The code modified by this patch is guarded by IS_ERR(trans_private), where trans_private is assigned as per the previous point in this analysis.

The only implementation of get_mr that I could locate is rds_ib_get_mr() which can return an ERR_PTR if the conn (4th) argument is NULL.

* ret is set to PTR_ERR(trans_private).
rds_ib_get_mr can return ERR_PTR(-ENODEV) if the conn (4th) argument is NULL. Thus ret may be -ENODEV in which case the code in question will execute.

Conclusion:
* cp may be NULL at the point where this patch adds a check; this patch does seem to address a possible bug

Fixes c055fc00c07b ("net/rds: fix WARNING in rds_conn_connect_if_down")
Cc [email protected] # v4.19+
---
 net/rds/rdma.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
net/rds/rdma.c +1 -1
@@ -302,7 +302,7 @@ static int __rds_rdma_map(struct rds_soc
 		}
 		ret = PTR_ERR(trans_private);
 		/* Trigger connection so that its ready for the next retry */
-		if (ret == -ENODEV)
+		if (ret == -ENODEV && cp)
 			rds_conn_connect_if_down(cp->cp_conn);
 		goto out;
 	}
author maintainer
#633 lore raw

PATCH 629/690 locking/rwsem: Disable preemption while trying for rwsem lock

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Gokul krishna Krishnakumar <[email protected]>

commit 48dfb5d2560d36fb16c7d430c229d1604ea7d185 upstream.

Make the region inside the rwsem_write_trylock non preemptible.

We observe RT task is hogging CPU when trying to acquire rwsem lock which was acquired by a kworker task but before the rwsem owner was set.

Here is the scenario:
1. CFS task (affined to a particular CPU) takes rwsem lock.

2. CFS task gets preempted by a RT task before setting owner.

3. RT task (FIFO) is trying to acquire the lock, but spinning until RT throttling happens for the lock as the lock was taken by CFS task.

This patch attempts to fix the above issue by disabling preemption until owner is set for the lock. While at it also fix the issues at the places where rwsem_{set,clear}_owner() are called.

This also adds lockdep annotation of preemption disable in rwsem_{set,clear}_owner() on Peter Z. suggestion.

---
 kernel/locking/rwsem.c |   14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)
kernel/locking/rwsem.c +12 -2
@@ -133,14 +133,19 @@
  * the owner value concurrently without lock. Read from owner, however,
  * may not need READ_ONCE() as long as the pointer value is only used
  * for comparison and isn't being dereferenced.
+ *
+ * Both rwsem_{set,clear}_owner() functions should be in the same
+ * preempt disable section as the atomic op that changes sem->count.
  */
 static inline void rwsem_set_owner(struct rw_semaphore *sem)
 {
+	lockdep_assert_preemption_disabled();
 	atomic_long_set(&sem->owner, (long)current);
 }
 
 static inline void rwsem_clear_owner(struct rw_semaphore *sem)
 {
+	lockdep_assert_preemption_disabled();
 	atomic_long_set(&sem->owner, 0);
 }
 
@@ -251,13 +256,16 @@ static inline bool rwsem_read_trylock(st
 static inline bool rwsem_write_trylock(struct rw_semaphore *sem)
 {
 	long tmp = RWSEM_UNLOCKED_VALUE;
+	bool ret = false;
 
+	preempt_disable();
 	if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp, RWSEM_WRITER_LOCKED)) {
 		rwsem_set_owner(sem);
-		return true;
+		ret = true;
 	}
 
-	return false;
+	preempt_enable();
+	return ret;
 }
 
 /*
@@ -1341,8 +1349,10 @@ static inline void __up_write(struct rw_
 	DEBUG_RWSEMS_WARN_ON((rwsem_owner(sem) != current) &&
 			    !rwsem_test_oflags(sem, RWSEM_NONSPINNABLE), sem);
 
+	preempt_disable();
 	rwsem_clear_owner(sem);
 	tmp = atomic_long_fetch_add_release(-RWSEM_WRITER_LOCKED, &sem->count);
+	preempt_enable();
 	if (unlikely(tmp & RWSEM_FLAG_WAITERS))
 		rwsem_wake(sem);
 }
author maintainer
#634 lore raw

PATCH 630/690 io_uring: ensure 0 is returned on file registration success

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jens Axboe <[email protected]>

A previous backport mistakenly removed code that cleared 'ret' to zero, as the SCM logging was performed. Fix up the return value so we don't return an errant error on fixed file registration.

Fixes d909d381c315 ("io_uring: drop any code related to SCM_RIGHTS")
---
 io_uring/io_uring.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
io_uring/io_uring.c +1 -1
@@ -8422,7 +8422,7 @@ static int io_sqe_files_register(struct
 	}
 
 	io_rsrc_node_switch(ctx, NULL);
-	return ret;
+	return 0;
 out_fput:
 	for (i = 0; i < ctx->nr_user_files; i++) {
 		file = io_file_from_index(ctx, i);
author maintainer
#635 lore raw

PATCH 631/690 Revert "x86/mm/ident_map: Use gbpages only where full GB page should be mapped."

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ingo Molnar <[email protected]>

commit c567f2948f57bdc03ed03403ae0234085f376b7d upstream.

This reverts commit d794734c9bbfe22f86686dc2909c25f5ffe1a572.

While the original change tries to fix a bug, it also unintentionally broke existing systems, see the regressions reported at:

https://lore.kernel.org/all/[email protected]/

Since d794734c9bbf was also marked for -stable, let's back it out before causing more damage.

Note that due to another upstream change the revert was not 100% automatic:

0a845e0f6348 mm/treewide: replace pud_large() with pud_leaf()

Cc Russ Anderson <[email protected]>
Cc Steve Wahl <[email protected]>
Cc Dave Hansen <[email protected]>
Fixes d794734c9bbf ("x86/mm/ident_map: Use gbpages only where full GB page should be mapped.")
---
 arch/x86/mm/ident_map.c |   23 +++++------------------
 1 file changed, 5 insertions(+), 18 deletions(-)
arch/x86/mm/ident_map.c +5 -18
@@ -26,31 +26,18 @@ static int ident_pud_init(struct x86_map
 	for (; addr < end; addr = next) {
 		pud_t *pud = pud_page + pud_index(addr);
 		pmd_t *pmd;
-		bool use_gbpage;
 
 		next = (addr & PUD_MASK) + PUD_SIZE;
 		if (next > end)
 			next = end;
 
-		/* if this is already a gbpage, this portion is already mapped */
-		if (pud_large(*pud))
-			continue;
-
-		/* Is using a gbpage allowed? */
-		use_gbpage = info->direct_gbpages;
-
-		/* Don't use gbpage if it maps more than the requested region. */
-		/* at the begining: */
-		use_gbpage &= ((addr & ~PUD_MASK) == 0);
-		/* ... or at the end: */
-		use_gbpage &= ((next & ~PUD_MASK) == 0);
-
-		/* Never overwrite existing mappings */
-		use_gbpage &= !pud_present(*pud);
-
-		if (use_gbpage) {
+		if (info->direct_gbpages) {
 			pud_t pudval;
 
+			if (pud_present(*pud))
+				continue;
+
+			addr &= PUD_MASK;
 			pudval = __pud((addr - info->offset) | info->page_flag);
 			set_pud(pud, pudval);
 			continue;
author maintainer
#636 lore raw

PATCH 632/690 mm, vmscan: prevent infinite loop for costly GFP_NOIO | __GFP_RETRY_MAYFAIL allocations

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Vlastimil Babka <[email protected]>

commit 803de9000f334b771afacb6ff3e78622916668b0 upstream.

Sven reports an infinite loop in __alloc_pages_slowpath() for costly order __GFP_RETRY_MAYFAIL allocations that are also GFP_NOIO. Such combination can happen in a suspend/resume context where a GFP_KERNEL allocation can have __GFP_IO masked out via gfp_allowed_mask.

Quoting Sven:

1. try to do a "costly" allocation (order > PAGE_ALLOC_COSTLY_ORDER) with __GFP_RETRY_MAYFAIL set.

2. page alloc's __alloc_pages_slowpath tries to get a page from the freelist. This fails because there is nothing free of that costly order.

3. page alloc tries to reclaim by calling __alloc_pages_direct_reclaim, which bails out because a zone is ready to be compacted; it pretends to have made a single page of progress.

4. page alloc tries to compact, but this always bails out early because __GFP_IO is not set (it's not passed by the snd allocator, and even if it were, we are suspending so the __GFP_IO flag would be cleared anyway).

5. page alloc believes reclaim progress was made (because of the pretense in item 3) and so it checks whether it should retry compaction. The compaction retry logic thinks it should try again, because:
a) reclaim is needed because of the early bail-out in item 4
b) a zonelist is suitable for compaction

6. goto 2. indefinite stall.

(end quote)

The immediate root cause is confusing the COMPACT_SKIPPED returned from __alloc_pages_direct_compact() (step 4) due to lack of __GFP_IO to be indicating a lack of order-0 pages, and in step 5 evaluating that in should_compact_retry() as a reason to retry, before incrementing and limiting the number of retries. There are however other places that wrongly assume that compaction can happen while we lack __GFP_IO.

To fix this, introduce gfp_compaction_allowed() to abstract the __GFP_IO evaluation and switch the open-coded test in try_to_compact_pages() to use it.

Also use the new helper in:
- compaction_ready(), which will make reclaim not bail out in step 3, so there's at least one attempt to actually reclaim, even if chances are small for a costly order
- in_reclaim_compaction() which will make should_continue_reclaim() return false and we don't over-reclaim unnecessarily
- in __alloc_pages_slowpath() to set a local variable can_compact, which is then used to avoid retrying reclaim/compaction for costly allocations (step 5) if we can't compact and also to skip the early compaction attempt that we do in some cases

---
 include/linux/gfp.h |    9 +++++++++
 mm/compaction.c     |    7 +------
 mm/page_alloc.c     |   10 ++++++----
 mm/vmscan.c         |    5 ++++-
 4 files changed, 20 insertions(+), 11 deletions(-)
include/linux/gfp.h +9 -0
@@ -660,6 +660,15 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_ma
 extern void pm_restrict_gfp_mask(void);
 extern void pm_restore_gfp_mask(void);
 
+/*
+ * Check if the gfp flags allow compaction - GFP_NOIO is a really
+ * tricky context because the migration might require IO.
+ */
+static inline bool gfp_compaction_allowed(gfp_t gfp_mask)
+{
+	return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO);
+}
+
 extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma);
 
 #ifdef CONFIG_PM_SLEEP
mm/compaction.c +1 -6
@@ -2582,16 +2582,11 @@ enum compact_result try_to_compact_pages
 		unsigned int alloc_flags, const struct alloc_context *ac,
 		enum compact_priority prio, struct page **capture)
 {
-	int may_perform_io = gfp_mask & __GFP_IO;
 	struct zoneref *z;
 	struct zone *zone;
 	enum compact_result rc = COMPACT_SKIPPED;
 
-	/*
-	 * Check if the GFP flags allow compaction - GFP_NOIO is really
-	 * tricky context because the migration might require IO
-	 */
-	if (!may_perform_io)
+	if (!gfp_compaction_allowed(gfp_mask))
 		return COMPACT_SKIPPED;
 
 	trace_mm_compaction_try_to_compact_pages(order, gfp_mask, prio);
mm/page_alloc.c +6 -4
@@ -4903,6 +4903,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, u
 						struct alloc_context *ac)
 {
 	bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM;
+	bool can_compact = gfp_compaction_allowed(gfp_mask);
 	const bool costly_order = order > PAGE_ALLOC_COSTLY_ORDER;
 	struct page *page = NULL;
 	unsigned int alloc_flags;
@@ -4968,7 +4969,7 @@ restart:
 	 * Don't try this for allocations that are allowed to ignore
 	 * watermarks, as the ALLOC_NO_WATERMARKS attempt didn't yet happen.
 	 */
-	if (can_direct_reclaim &&
+	if (can_direct_reclaim && can_compact &&
 			(costly_order ||
 			   (order > 0 && ac->migratetype != MIGRATE_MOVABLE))
 			&& !gfp_pfmemalloc_allowed(gfp_mask)) {
@@ -5065,9 +5066,10 @@ retry:
 
 	/*
 	 * Do not retry costly high order allocations unless they are
-	 * __GFP_RETRY_MAYFAIL
+	 * __GFP_RETRY_MAYFAIL and we can compact
 	 */
-	if (costly_order && !(gfp_mask & __GFP_RETRY_MAYFAIL))
+	if (costly_order && (!can_compact ||
+			     !(gfp_mask & __GFP_RETRY_MAYFAIL)))
 		goto nopage;
 
 	if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,
@@ -5080,7 +5082,7 @@ retry:
 	 * implementation of the compaction depends on the sufficient amount
 	 * of free memory (see __compaction_suitable)
 	 */
-	if (did_some_progress > 0 &&
+	if (did_some_progress > 0 && can_compact &&
 			should_compact_retry(ac, order, alloc_flags,
 				compact_result, &compact_priority,
 				&compaction_retries))
mm/vmscan.c +4 -1
@@ -2834,7 +2834,7 @@ static void shrink_lruvec(struct lruvec
 /* Use reclaim/compaction for costly allocs or under memory pressure */
 static bool in_reclaim_compaction(struct scan_control *sc)
 {
-	if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
+	if (gfp_compaction_allowed(sc->gfp_mask) && sc->order &&
 			(sc->order > PAGE_ALLOC_COSTLY_ORDER ||
 			 sc->priority < DEF_PRIORITY - 2))
 		return true;
@@ -3167,6 +3167,9 @@ static inline bool compaction_ready(stru
 	unsigned long watermark;
 	enum compact_result suitable;
 
+	if (!gfp_compaction_allowed(sc->gfp_mask))
+		return false;
+
 	suitable = compaction_suitable(zone, sc->order, 0, sc->reclaim_idx);
 	if (suitable == COMPACT_SUCCESS)
 		/* Allocation should succeed already. Don't reclaim. */
author maintainer
#637 lore raw

PATCH 633/690 thermal: devfreq_cooling: Fix perf state when calculate dfc res_util

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ye Zhang <[email protected]>

commit a26de34b3c77ae3a969654d94be49e433c947e3b upstream.

The issue occurs when the devfreq cooling device uses the EM power model and the get_real_power() callback is provided by the driver.

The EM power table is sorted ascending,can't index the table by cooling device state,so convert cooling state to performance state by dfc->max_state - dfc->capped_state.

Fixes 615510fe13bd ("thermal: devfreq_cooling: remove old power model and use EM")
Cc 5.11+ <[email protected]> # 5.11+
---
 drivers/thermal/devfreq_cooling.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/thermal/devfreq_cooling.c +1 -1
@@ -199,7 +199,7 @@ static int devfreq_cooling_get_requested
 
 		res = dfc->power_ops->get_real_power(df, power, freq, voltage);
 		if (!res) {
-			state = dfc->capped_state;
+			state = dfc->max_state - dfc->capped_state;
 			dfc->res_util = dfc->em_pd->table[state].power;
 			dfc->res_util *= SCALE_ERROR_MITIGATION;
 
author maintainer
#638 lore raw

PATCH 634/690 KVM: x86: Bail to userspace if emulation of atomic user access faults

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sean Christopherson <[email protected]>

commit 5d6c7de6446e9ab3fb41d6f7d82770e50998f3de upstream.

Exit to userspace when emulating an atomic guest access if the CMPXCHG on the userspace address faults. Emulating the access as a write and thus likely treating it as emulated MMIO is wrong, as KVM has already confirmed there is a valid, writable memslot.

Message-Id: <[email protected]>

---
 arch/x86/kvm/x86.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/kvm/x86.c +1 -1
@@ -7108,7 +7108,7 @@ static int emulator_cmpxchg_emulated(str
 	}
 
 	if (r < 0)
-		goto emul_write;
+		return X86EMUL_UNHANDLEABLE;
 	if (r)
 		return X86EMUL_CMPXCHG_FAILED;
 
author maintainer
#639 lore raw

PATCH 635/690 KVM: x86: Mark target gfn of emulated atomic instruction as dirty

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sean Christopherson <[email protected]>

commit 910c57dfa4d113aae6571c2a8b9ae8c430975902 upstream.

When emulating an atomic access on behalf of the guest, mark the target gfn dirty if the CMPXCHG by KVM is attempted and doesn't fault. This fixes a bug where KVM effectively corrupts guest memory during live migration by writing to guest memory without informing userspace that the page is dirty.

Marking the page dirty got unintentionally dropped when KVM's emulated CMPXCHG was converted to do a user access. Before that, KVM explicitly mapped the guest page into kernel memory, and marked the page dirty during the unmap phase.

Mark the page dirty even if the CMPXCHG fails, as the old data is written back on failure, i.e. the page is still written. The value written is guaranteed to be the same because the operation is atomic, but KVM's ABI is that all writes are dirty logged regardless of the value written. And more importantly, that's what KVM did before the buggy commit.

Huge kudos to the folks on the Cc list (and many others), who did all the actual work of triaging and debugging.

Fixes 1c2361f667f3 ("KVM: x86: Use __try_cmpxchg_user() to emulate atomic accesses")
Cc David Matlack <[email protected]>
Cc Pasha Tatashin <[email protected]>
Cc Michael Krebs <[email protected]>

base-commit: 6769ea8da8a93ed4630f1ce64df6aafcaabfce64

---
 arch/x86/kvm/x86.c |   10 ++++++++++
 1 file changed, 10 insertions(+)
arch/x86/kvm/x86.c +10 -0
@@ -7109,6 +7109,16 @@ static int emulator_cmpxchg_emulated(str
 
 	if (r < 0)
 		return X86EMUL_UNHANDLEABLE;
+
+	/*
+	 * Mark the page dirty _before_ checking whether or not the CMPXCHG was
+	 * successful, as the old value is written back on failure.  Note, for
+	 * live migration, this is unnecessarily conservative as CMPXCHG writes
+	 * back the original value and the access is atomic, but KVM's ABI is
+	 * that all writes are dirty logged, regardless of the value written.
+	 */
+	kvm_vcpu_mark_page_dirty(vcpu, gpa_to_gfn(gpa));
+
 	if (r)
 		return X86EMUL_CMPXCHG_FAILED;
 
author maintainer
#640 lore raw

PATCH 636/690 netfilter: nf_tables: reject new basechain after table flag update

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pablo Neira Ayuso <[email protected]>

commit 994209ddf4f430946f6247616b2e33d179243769 upstream.

When dormant flag is toggled, hooks are disabled in the commit phase by iterating over current chains in table (existing and new).

The following configuration allows for an inconsistent state:

add table x
add chain x y { type filter hook input priority 0; } add table x { flags dormant; }
add chain x w { type filter hook input priority 1; }

which triggers the following warning when trying to unregister chain w which is already unregistered.

[  127.322252] WARNING: CPU: 7 PID: 1211 at net/netfilter/core.c:50                                                                     1 __nf_unregister_net_hook+0x21a/0x260
[...]
[  127.322519] Call Trace:
[  127.322521]  <TASK>
[  127.322524]  ? __warn+0x9f/0x1a0
[  127.322531]  ? __nf_unregister_net_hook+0x21a/0x260
[  127.322537]  ? report_bug+0x1b1/0x1e0
[  127.322545]  ? handle_bug+0x3c/0x70
[  127.322552]  ? exc_invalid_op+0x17/0x40
[  127.322556]  ? asm_exc_invalid_op+0x1a/0x20
[  127.322563]  ? kasan_save_free_info+0x3b/0x60
[  127.322570]  ? __nf_unregister_net_hook+0x6a/0x260
[  127.322577]  ? __nf_unregister_net_hook+0x21a/0x260
[  127.322583]  ? __nf_unregister_net_hook+0x6a/0x260
[  127.322590]  ? __nf_tables_unregister_hook+0x8a/0xe0 [nf_tables]
[  127.322655]  nft_table_disable+0x75/0xf0 [nf_tables]
[  127.322717]  nf_tables_commit+0x2571/0x2620 [nf_tables]
Fixes 179d9ba5559a ("netfilter: nf_tables: fix table flag updates")
---
 net/netfilter/nf_tables_api.c |    3 +++
 1 file changed, 3 insertions(+)
net/netfilter/nf_tables_api.c +3 -0
@@ -2303,6 +2303,9 @@ static int nf_tables_addchain(struct nft
 		struct nft_stats __percpu *stats = NULL;
 		struct nft_chain_hook hook;
 
+		if (table->flags & __NFT_TABLE_F_UPDATE)
+			return -EINVAL;
+
 		if (flags & NFT_CHAIN_BINDING)
 			return -EOPNOTSUPP;
 
author maintainer
#641 lore raw

PATCH 637/690 netfilter: nf_tables: flush pending destroy work before exit_net release

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Pablo Neira Ayuso <[email protected]>

commit 24cea9677025e0de419989ecb692acd4bb34cac2 upstream.

Similar to 2c9f0293280e ("netfilter: nf_tables: flush pending destroy work before netlink notifier") to address a race between exit_net and the destroy workqueue.

The trace below shows an element to be released via destroy workqueue while exit_net path (triggered via module removal) has already released the set that is used in such transaction.

[ 1360.547789] BUG: KASAN: slab-use-after-free in nf_tables_trans_destroy_work+0x3f5/0x590 [nf_tables]
[ 1360.547861] Read of size 8 at addr ffff888140500cc0 by task kworker/4:1/152465
[ 1360.547870] CPU: 4 PID: 152465 Comm: kworker/4:1 Not tainted 6.8.0+ #359
[ 1360.547882] Workqueue: events nf_tables_trans_destroy_work [nf_tables]
[ 1360.547984] Call Trace:
[ 1360.547991]  <TASK>
[ 1360.547998]  dump_stack_lvl+0x53/0x70
[ 1360.548014]  print_report+0xc4/0x610
[ 1360.548026]  ? __virt_addr_valid+0xba/0x160
[ 1360.548040]  ? __pfx__raw_spin_lock_irqsave+0x10/0x10
[ 1360.548054]  ? nf_tables_trans_destroy_work+0x3f5/0x590 [nf_tables]
[ 1360.548176]  kasan_report+0xae/0xe0
[ 1360.548189]  ? nf_tables_trans_destroy_work+0x3f5/0x590 [nf_tables]
[ 1360.548312]  nf_tables_trans_destroy_work+0x3f5/0x590 [nf_tables]
[ 1360.548447]  ? __pfx_nf_tables_trans_destroy_work+0x10/0x10 [nf_tables]
[ 1360.548577]  ? _raw_spin_unlock_irq+0x18/0x30
[ 1360.548591]  process_one_work+0x2f1/0x670
[ 1360.548610]  worker_thread+0x4d3/0x760
[ 1360.548627]  ? __pfx_worker_thread+0x10/0x10
[ 1360.548640]  kthread+0x16b/0x1b0
[ 1360.548653]  ? __pfx_kthread+0x10/0x10
[ 1360.548665]  ret_from_fork+0x2f/0x50
[ 1360.548679]  ? __pfx_kthread+0x10/0x10
[ 1360.548690]  ret_from_fork_asm+0x1a/0x30
[ 1360.548707]  </TASK>
[ 1360.548719] Allocated by task 192061:
[ 1360.548726]  kasan_save_stack+0x20/0x40
[ 1360.548739]  kasan_save_track+0x14/0x30
[ 1360.548750]  __kasan_kmalloc+0x8f/0xa0
[ 1360.548760]  __kmalloc_node+0x1f1/0x450
[ 1360.548771]  nf_tables_newset+0x10c7/0x1b50 [nf_tables]
[ 1360.548883]  nfnetlink_rcv_batch+0xbc4/0xdc0 [nfnetlink]
[ 1360.548909]  nfnetlink_rcv+0x1a8/0x1e0 [nfnetlink]
[ 1360.548927]  netlink_unicast+0x367/0x4f0
[ 1360.548935]  netlink_sendmsg+0x34b/0x610
[ 1360.548944]  ____sys_sendmsg+0x4d4/0x510
[ 1360.548953]  ___sys_sendmsg+0xc9/0x120
[ 1360.548961]  __sys_sendmsg+0xbe/0x140
[ 1360.548971]  do_syscall_64+0x55/0x120
[ 1360.548982]  entry_SYSCALL_64_after_hwframe+0x55/0x5d
[ 1360.548994] Freed by task 192222:
[ 1360.548999]  kasan_save_stack+0x20/0x40
[ 1360.549009]  kasan_save_track+0x14/0x30
[ 1360.549019]  kasan_save_free_info+0x3b/0x60
[ 1360.549028]  poison_slab_object+0x100/0x180
[ 1360.549036]  __kasan_slab_free+0x14/0x30
[ 1360.549042]  kfree+0xb6/0x260
[ 1360.549049]  __nft_release_table+0x473/0x6a0 [nf_tables]
[ 1360.549131]  nf_tables_exit_net+0x170/0x240 [nf_tables]
[ 1360.549221]  ops_exit_list+0x50/0xa0
[ 1360.549229]  free_exit_list+0x101/0x140
[ 1360.549236]  unregister_pernet_operations+0x107/0x160
[ 1360.549245]  unregister_pernet_subsys+0x1c/0x30
[ 1360.549254]  nf_tables_module_exit+0x43/0x80 [nf_tables]
[ 1360.549345]  __do_sys_delete_module+0x253/0x370
[ 1360.549352]  do_syscall_64+0x55/0x120
[ 1360.549360]  entry_SYSCALL_64_after_hwframe+0x55/0x5d

(gdb) list *__nft_release_table+0x473
0x1e033 is in __nft_release_table (net/netfilter/nf_tables_api.c:11354).
11349 list_for_each_entry_safe(flowtable, nf, &table->flowtables, list) {

11350                   list_del(&flowtable->list);
11351                   nft_use_dec(&table->use);
11352                   nf_tables_flowtable_destroy(flowtable);
11353           }
11354           list_for_each_entry_safe(set, ns, &table->sets, list) {
11355                   list_del(&set->list);
11356                   nft_use_dec(&table->use);
11357                   if (set->flags & (NFT_SET_MAP | NFT_SET_OBJECT))

11358 nft_map_deactivate(&ctx, set);
(gdb)

[ 1360.549372] Last potentially related work creation:
[ 1360.549376]  kasan_save_stack+0x20/0x40
[ 1360.549384]  __kasan_record_aux_stack+0x9b/0xb0
[ 1360.549392]  __queue_work+0x3fb/0x780
[ 1360.549399]  queue_work_on+0x4f/0x60
[ 1360.549407]  nft_rhash_remove+0x33b/0x340 [nf_tables]
[ 1360.549516]  nf_tables_commit+0x1c6a/0x2620 [nf_tables]
[ 1360.549625]  nfnetlink_rcv_batch+0x728/0xdc0 [nfnetlink]
[ 1360.549647]  nfnetlink_rcv+0x1a8/0x1e0 [nfnetlink]
[ 1360.549671]  netlink_unicast+0x367/0x4f0
[ 1360.549680]  netlink_sendmsg+0x34b/0x610
[ 1360.549690]  ____sys_sendmsg+0x4d4/0x510
[ 1360.549697]  ___sys_sendmsg+0xc9/0x120
[ 1360.549706]  __sys_sendmsg+0xbe/0x140
[ 1360.549715]  do_syscall_64+0x55/0x120
[ 1360.549725]  entry_SYSCALL_64_after_hwframe+0x55/0x5d
Fixes 0935d5588400 ("netfilter: nf_tables: asynchronous release")
---
 net/netfilter/nf_tables_api.c |    1 +
 1 file changed, 1 insertion(+)
net/netfilter/nf_tables_api.c +1 -0
@@ -10784,6 +10784,7 @@ static void __exit nf_tables_module_exit
 	unregister_netdevice_notifier(&nf_tables_flowtable_notifier);
 	nft_chain_filter_fini();
 	nft_chain_route_fini();
+	nf_tables_trans_destroy_flush_work();
 	unregister_pernet_subsys(&nf_tables_net_ops);
 	cancel_work_sync(&trans_gc_work);
 	cancel_work_sync(&trans_destroy_work);
author maintainer
#642 lore raw

PATCH 638/690 netfilter: nf_tables: Fix potential data-race in __nft_flowtable_type_get()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ziyang Xuan <[email protected]>

commit 24225011d81b471acc0e1e315b7d9905459a6304 upstream.

nft_unregister_flowtable_type() within nf_flow_inet_module_exit() can concurrent with __nft_flowtable_type_get() within nf_tables_newflowtable(). And thhere is not any protection when iterate over nf_tables_flowtables list in __nft_flowtable_type_get(). Therefore, there is pertential data-race of nf_tables_flowtables list entry.

Use list_for_each_entry_rcu() to iterate over nf_tables_flowtables list in __nft_flowtable_type_get(), and use rcu_read_lock() in the caller nft_flowtable_type_get() to protect the entire type query process.

Fixes 3b49e2e94e6e ("netfilter: nf_tables: add flow table netlink frontend")
---
 net/netfilter/nf_tables_api.c |    9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)
net/netfilter/nf_tables_api.c +7 -2
@@ -7693,11 +7693,12 @@ static int nft_flowtable_parse_hook(cons
 	return err;
 }
 
+/* call under rcu_read_lock */
 static const struct nf_flowtable_type *__nft_flowtable_type_get(u8 family)
 {
 	const struct nf_flowtable_type *type;
 
-	list_for_each_entry(type, &nf_tables_flowtables, list) {
+	list_for_each_entry_rcu(type, &nf_tables_flowtables, list) {
 		if (family == type->family)
 			return type;
 	}
@@ -7709,9 +7710,13 @@ nft_flowtable_type_get(struct net *net,
 {
 	const struct nf_flowtable_type *type;
 
+	rcu_read_lock();
 	type = __nft_flowtable_type_get(family);
-	if (type != NULL && try_module_get(type->owner))
+	if (type != NULL && try_module_get(type->owner)) {
+		rcu_read_unlock();
 		return type;
+	}
+	rcu_read_unlock();
 
 	lockdep_nfnl_nft_mutex_not_held();
 #ifdef CONFIG_MODULES
author maintainer
#643 lore raw

PATCH 639/690 netfilter: validate user input for expected length

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

commit 0c83842df40f86e529db6842231154772c20edcc upstream.

I got multiple syzbot reports showing old bugs exposed by BPF after commit 20f2505fb436 ("bpf: Try to avoid kzalloc in cgroup/{s,g}etsockopt")

setsockopt() @optlen argument should be taken into account before copying data.

 BUG: KASAN: slab-out-of-bounds in copy_from_sockptr_offset include/linux/sockptr.h:49 [inline]
 BUG: KASAN: slab-out-of-bounds in copy_from_sockptr include/linux/sockptr.h:55 [inline]
 BUG: KASAN: slab-out-of-bounds in do_replace net/ipv4/netfilter/ip_tables.c:1111 [inline]
 BUG: KASAN: slab-out-of-bounds in do_ipt_set_ctl+0x902/0x3dd0 net/ipv4/netfilter/ip_tables.c:1627
Read of size 96 at addr ffff88802cd73da0 by task syz-executor.4/7238

CPU: 1 PID: 7238 Comm: syz-executor.4 Not tainted 6.9.0-rc2-next-20240403-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/27/2024
Call Trace:
 <TASK>
  __dump_stack lib/dump_stack.c:88 [inline]
  dump_stack_lvl+0x241/0x360 lib/dump_stack.c:114
  print_address_description mm/kasan/report.c:377 [inline]
  print_report+0x169/0x550 mm/kasan/report.c:488
  kasan_report+0x143/0x180 mm/kasan/report.c:601
  kasan_check_range+0x282/0x290 mm/kasan/generic.c:189
  __asan_memcpy+0x29/0x70 mm/kasan/shadow.c:105
  copy_from_sockptr_offset include/linux/sockptr.h:49 [inline]
  copy_from_sockptr include/linux/sockptr.h:55 [inline]
  do_replace net/ipv4/netfilter/ip_tables.c:1111 [inline]
  do_ipt_set_ctl+0x902/0x3dd0 net/ipv4/netfilter/ip_tables.c:1627
  nf_setsockopt+0x295/0x2c0 net/netfilter/nf_sockopt.c:101
  do_sock_setsockopt+0x3af/0x720 net/socket.c:2311
  __sys_setsockopt+0x1ae/0x250 net/socket.c:2334
  __do_sys_setsockopt net/socket.c:2343 [inline]
  __se_sys_setsockopt net/socket.c:2340 [inline]
  __x64_sys_setsockopt+0xb5/0xd0 net/socket.c:2340
 do_syscall_64+0xfb/0x240
 entry_SYSCALL_64_after_hwframe+0x72/0x7a
RIP: 0033:0x7fd22067dde9
Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 20 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b0 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007fd21f9ff0c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 00007fd2207abf80 RCX: 00007fd22067dde9
RDX: 0000000000000040 RSI: 0000000000000000 RDI: 0000000000000003
RBP: 00007fd2206ca47a R08: 0000000000000001 R09: 0000000000000000
R10: 0000000020000880 R11: 0000000000000246 R12: 0000000000000000
R13: 000000000000000b R14: 00007fd2207abf80 R15: 00007ffd2d0170d8
 </TASK>

Allocated by task 7238:
  kasan_save_stack mm/kasan/common.c:47 [inline]
  kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
  poison_kmalloc_redzone mm/kasan/common.c:370 [inline]
  __kasan_kmalloc+0x98/0xb0 mm/kasan/common.c:387
  kasan_kmalloc include/linux/kasan.h:211 [inline]
  __do_kmalloc_node mm/slub.c:4069 [inline]
  __kmalloc_noprof+0x200/0x410 mm/slub.c:4082
  kmalloc_noprof include/linux/slab.h:664 [inline]
  __cgroup_bpf_run_filter_setsockopt+0xd47/0x1050 kernel/bpf/cgroup.c:1869
  do_sock_setsockopt+0x6b4/0x720 net/socket.c:2293
  __sys_setsockopt+0x1ae/0x250 net/socket.c:2334
  __do_sys_setsockopt net/socket.c:2343 [inline]
  __se_sys_setsockopt net/socket.c:2340 [inline]
  __x64_sys_setsockopt+0xb5/0xd0 net/socket.c:2340
 do_syscall_64+0xfb/0x240
 entry_SYSCALL_64_after_hwframe+0x72/0x7a

The buggy address belongs to the object at ffff88802cd73da0
 which belongs to the cache kmalloc-8 of size 8

The buggy address is located 0 bytes inside of
allocated 1-byte region [ffff88802cd73da0, ffff88802cd73da1)

The buggy address belongs to the physical page:
page: refcount:1 mapcount:0 mapping:0000000000000000 index:0xffff88802cd73020 pfn:0x2cd73
flags: 0xfff80000000000(node=0|zone=1|lastcpupid=0xfff)
page_type: 0xffffefff(slab)
raw: 00fff80000000000 ffff888015041280 dead000000000100 dead000000000122
raw: ffff88802cd73020 000000008080007f 00000001ffffefff 0000000000000000
page dumped because: kasan: bad access detected
page_owner tracks the page as allocated
page last allocated via order 0, migratetype Unmovable, gfp_mask 0x12cc0(GFP_KERNEL|__GFP_NOWARN|__GFP_NORETRY), pid 5103, tgid 2119833701 (syz-executor.4), ts 5103, free_ts 70804600828
  set_page_owner include/linux/page_owner.h:32 [inline]
  post_alloc_hook+0x1f3/0x230 mm/page_alloc.c:1490
  prep_new_page mm/page_alloc.c:1498 [inline]
  get_page_from_freelist+0x2e7e/0x2f40 mm/page_alloc.c:3454
  __alloc_pages_noprof+0x256/0x6c0 mm/page_alloc.c:4712
  __alloc_pages_node_noprof include/linux/gfp.h:244 [inline]
  alloc_pages_node_noprof include/linux/gfp.h:271 [inline]
  alloc_slab_page+0x5f/0x120 mm/slub.c:2249
  allocate_slab+0x5a/0x2e0 mm/slub.c:2412
  new_slab mm/slub.c:2465 [inline]
  ___slab_alloc+0xcd1/0x14b0 mm/slub.c:3615
  __slab_alloc+0x58/0xa0 mm/slub.c:3705
  __slab_alloc_node mm/slub.c:3758 [inline]
  slab_alloc_node mm/slub.c:3936 [inline]
  __do_kmalloc_node mm/slub.c:4068 [inline]
  kmalloc_node_track_caller_noprof+0x286/0x450 mm/slub.c:4089
  kstrdup+0x3a/0x80 mm/util.c:62
  device_rename+0xb5/0x1b0 drivers/base/core.c:4558
  dev_change_name+0x275/0x860 net/core/dev.c:1232
  do_setlink+0xa4b/0x41f0 net/core/rtnetlink.c:2864
  __rtnl_newlink net/core/rtnetlink.c:3680 [inline]
  rtnl_newlink+0x180b/0x20a0 net/core/rtnetlink.c:3727
  rtnetlink_rcv_msg+0x89b/0x10d0 net/core/rtnetlink.c:6594
  netlink_rcv_skb+0x1e3/0x430 net/netlink/af_netlink.c:2559
  netlink_unicast_kernel net/netlink/af_netlink.c:1335 [inline]
  netlink_unicast+0x7ea/0x980 net/netlink/af_netlink.c:1361
page last free pid 5146 tgid 5146 stack trace:
  reset_page_owner include/linux/page_owner.h:25 [inline]
  free_pages_prepare mm/page_alloc.c:1110 [inline]
  free_unref_page+0xd3c/0xec0 mm/page_alloc.c:2617
  discard_slab mm/slub.c:2511 [inline]
  __put_partials+0xeb/0x130 mm/slub.c:2980
  put_cpu_partial+0x17c/0x250 mm/slub.c:3055
  __slab_free+0x2ea/0x3d0 mm/slub.c:4254
  qlink_free mm/kasan/quarantine.c:163 [inline]
  qlist_free_all+0x9e/0x140 mm/kasan/quarantine.c:179
  kasan_quarantine_reduce+0x14f/0x170 mm/kasan/quarantine.c:286
  __kasan_slab_alloc+0x23/0x80 mm/kasan/common.c:322
  kasan_slab_alloc include/linux/kasan.h:201 [inline]
  slab_post_alloc_hook mm/slub.c:3888 [inline]
  slab_alloc_node mm/slub.c:3948 [inline]
  __do_kmalloc_node mm/slub.c:4068 [inline]
  __kmalloc_node_noprof+0x1d7/0x450 mm/slub.c:4076
  kmalloc_node_noprof include/linux/slab.h:681 [inline]
  kvmalloc_node_noprof+0x72/0x190 mm/util.c:634
  bucket_table_alloc lib/rhashtable.c:186 [inline]
  rhashtable_rehash_alloc+0x9e/0x290 lib/rhashtable.c:367
  rht_deferred_worker+0x4e1/0x2440 lib/rhashtable.c:427
  process_one_work kernel/workqueue.c:3218 [inline]
  process_scheduled_works+0xa2c/0x1830 kernel/workqueue.c:3299
  worker_thread+0x86d/0xd70 kernel/workqueue.c:3380
  kthread+0x2f0/0x390 kernel/kthread.c:388
  ret_from_fork+0x4b/0x80 arch/x86/kernel/process.c:147
  ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:243

Memory state around the buggy address:
 ffff88802cd73c80: 07 fc fc fc 05 fc fc fc 05 fc fc fc fa fc fc fc
 ffff88802cd73d00: fa fc fc fc fa fc fc fc fa fc fc fc fa fc fc fc
>ffff88802cd73d80: fa fc fc fc 01 fc fc fc fa fc fc fc fa fc fc fc
                               ^
 ffff88802cd73e00: fa fc fc fc fa fc fc fc 05 fc fc fc 07 fc fc fc
 ffff88802cd73e80: 07 fc fc fc 07 fc fc fc 07 fc fc fc 07 fc fc fc
---
 net/bridge/netfilter/ebtables.c |    6 ++++++
 net/ipv4/netfilter/arp_tables.c |    4 ++++
 net/ipv4/netfilter/ip_tables.c  |    4 ++++
 net/ipv6/netfilter/ip6_tables.c |    4 ++++
 4 files changed, 18 insertions(+)
net/bridge/netfilter/ebtables.c +6 -0
@@ -1111,6 +1111,8 @@ static int do_replace(struct net *net, s
 	struct ebt_table_info *newinfo;
 	struct ebt_replace tmp;
 
+	if (len < sizeof(tmp))
+		return -EINVAL;
 	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
 		return -EFAULT;
 
@@ -1422,6 +1424,8 @@ static int update_counters(struct net *n
 {
 	struct ebt_replace hlp;
 
+	if (len < sizeof(hlp))
+		return -EINVAL;
 	if (copy_from_sockptr(&hlp, arg, sizeof(hlp)))
 		return -EFAULT;
 
@@ -2351,6 +2355,8 @@ static int compat_update_counters(struct
 {
 	struct compat_ebt_replace hlp;
 
+	if (len < sizeof(hlp))
+		return -EINVAL;
 	if (copy_from_sockptr(&hlp, arg, sizeof(hlp)))
 		return -EFAULT;
 
net/ipv4/netfilter/arp_tables.c +4 -0
@@ -955,6 +955,8 @@ static int do_replace(struct net *net, s
 	void *loc_cpu_entry;
 	struct arpt_entry *iter;
 
+	if (len < sizeof(tmp))
+		return -EINVAL;
 	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
 		return -EFAULT;
 
@@ -1253,6 +1255,8 @@ static int compat_do_replace(struct net
 	void *loc_cpu_entry;
 	struct arpt_entry *iter;
 
+	if (len < sizeof(tmp))
+		return -EINVAL;
 	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
 		return -EFAULT;
 
net/ipv4/netfilter/ip_tables.c +4 -0
@@ -1109,6 +1109,8 @@ do_replace(struct net *net, sockptr_t ar
 	void *loc_cpu_entry;
 	struct ipt_entry *iter;
 
+	if (len < sizeof(tmp))
+		return -EINVAL;
 	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
 		return -EFAULT;
 
@@ -1493,6 +1495,8 @@ compat_do_replace(struct net *net, sockp
 	void *loc_cpu_entry;
 	struct ipt_entry *iter;
 
+	if (len < sizeof(tmp))
+		return -EINVAL;
 	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
 		return -EFAULT;
 
net/ipv6/netfilter/ip6_tables.c +4 -0
@@ -1127,6 +1127,8 @@ do_replace(struct net *net, sockptr_t ar
 	void *loc_cpu_entry;
 	struct ip6t_entry *iter;
 
+	if (len < sizeof(tmp))
+		return -EINVAL;
 	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
 		return -EFAULT;
 
@@ -1503,6 +1505,8 @@ compat_do_replace(struct net *net, sockp
 	void *loc_cpu_entry;
 	struct ip6t_entry *iter;
 
+	if (len < sizeof(tmp))
+		return -EINVAL;
 	if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0)
 		return -EFAULT;
 
author maintainer
#644 lore raw

PATCH 640/690 vboxsf: Avoid an spurious warning if load_nls_xxx() fails

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christophe JAILLET <[email protected]>

commit de3f64b738af57e2732b91a0774facc675b75b54 upstream.

If an load_nls_xxx() function fails a few lines above, the 'sbi->bdi_id' is still 0.
So, in the error handling path, we will call ida_simple_remove(..., 0) which is not allocated yet.

In order to prevent a spurious "ida_free called for id=0 which is not allocated." message, tweak the error handling path and add a new label.

---
 fs/vboxsf/super.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
fs/vboxsf/super.c +2 -1
@@ -151,7 +151,7 @@ static int vboxsf_fill_super(struct supe
 		if (!sbi->nls) {
 			vbg_err("vboxsf: Count not load '%s' nls\n", nls_name);
 			err = -EINVAL;
-			goto fail_free;
+			goto fail_destroy_idr;
 		}
 	}
 
@@ -224,6 +224,7 @@ fail_free:
 		ida_simple_remove(&vboxsf_bdi_ida, sbi->bdi_id);
 	if (sbi->nls)
 		unload_nls(sbi->nls);
+fail_destroy_idr:
 	idr_destroy(&sbi->ino_idr);
 	kfree(sbi);
 	return err;
author maintainer
#645 lore raw

PATCH 641/690 bpf, sockmap: Prevent lock inversion deadlock in map delete elem

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jakub Sitnicki <[email protected]>

commit ff91059932401894e6c86341915615c5eb0eca48 upstream.

syzkaller started using corpuses where a BPF tracing program deletes elements from a sockmap/sockhash map. Because BPF tracing programs can be invoked from any interrupt context, locks taken during a map_delete_elem operation must be hardirq-safe. Otherwise a deadlock due to lock inversion is possible, as reported by lockdep:

       CPU0                    CPU1
       ----                    ----
  lock(&htab->buckets[i].lock);
                               local_irq_disable();
                               lock(&host->lock);
                               lock(&htab->buckets[i].lock);
  <Interrupt>
    lock(&host->lock);

Locks in sockmap are hardirq-unsafe by design. We expects elements to be deleted from sockmap/sockhash only in task (normal) context with interrupts enabled, or in softirq context.

Detect when map_delete_elem operation is invoked from a context which is _not_ hardirq-unsafe, that is interrupts are disabled, and bail out with an error.

Note that map updates are not affected by this issue. BPF verifier does not allow updating sockmap/sockhash from a BPF tracing program today.

---
 net/core/sock_map.c |    6 ++++++
 1 file changed, 6 insertions(+)
net/core/sock_map.c +6 -0
@@ -413,6 +413,9 @@ static int __sock_map_delete(struct bpf_
 	struct sock *sk;
 	int err = 0;
 
+	if (irqs_disabled())
+		return -EOPNOTSUPP; /* locks here are hardirq-unsafe */
+
 	raw_spin_lock_bh(&stab->lock);
 	sk = *psk;
 	if (!sk_test || sk_test == sk)
@@ -931,6 +934,9 @@ static int sock_hash_delete_elem(struct
 	struct bpf_shtab_elem *elem;
 	int ret = -ENOENT;
 
+	if (irqs_disabled())
+		return -EOPNOTSUPP; /* locks here are hardirq-unsafe */
+
 	hash = sock_hash_bucket_hash(key, key_size);
 	bucket = sock_hash_select_bucket(htab, hash);
 
author maintainer
#646 lore raw

PATCH 642/690 net/sched: act_skbmod: prevent kernel-infoleak

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

commit d313eb8b77557a6d5855f42d2234bd592c7b50dd upstream.

syzbot found that tcf_skbmod_dump() was copying four bytes from kernel stack to user space [1].

The issue here is that 'struct tc_skbmod' has a four bytes hole.

We need to clear the structure before filling fields.

[1]

BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:114 [inline]
 BUG: KMSAN: kernel-infoleak in copy_to_user_iter lib/iov_iter.c:24 [inline]
 BUG: KMSAN: kernel-infoleak in iterate_ubuf include/linux/iov_iter.h:29 [inline]
 BUG: KMSAN: kernel-infoleak in iterate_and_advance2 include/linux/iov_iter.h:245 [inline]
 BUG: KMSAN: kernel-infoleak in iterate_and_advance include/linux/iov_iter.h:271 [inline]
 BUG: KMSAN: kernel-infoleak in _copy_to_iter+0x366/0x2520 lib/iov_iter.c:185
  instrument_copy_to_user include/linux/instrumented.h:114 [inline]
  copy_to_user_iter lib/iov_iter.c:24 [inline]
  iterate_ubuf include/linux/iov_iter.h:29 [inline]
  iterate_and_advance2 include/linux/iov_iter.h:245 [inline]
  iterate_and_advance include/linux/iov_iter.h:271 [inline]
  _copy_to_iter+0x366/0x2520 lib/iov_iter.c:185
  copy_to_iter include/linux/uio.h:196 [inline]
  simple_copy_to_iter net/core/datagram.c:532 [inline]
  __skb_datagram_iter+0x185/0x1000 net/core/datagram.c:420
  skb_copy_datagram_iter+0x5c/0x200 net/core/datagram.c:546
  skb_copy_datagram_msg include/linux/skbuff.h:4050 [inline]
  netlink_recvmsg+0x432/0x1610 net/netlink/af_netlink.c:1962
  sock_recvmsg_nosec net/socket.c:1046 [inline]
  sock_recvmsg+0x2c4/0x340 net/socket.c:1068
  __sys_recvfrom+0x35a/0x5f0 net/socket.c:2242
  __do_sys_recvfrom net/socket.c:2260 [inline]
  __se_sys_recvfrom net/socket.c:2256 [inline]
  __x64_sys_recvfrom+0x126/0x1d0 net/socket.c:2256
 do_syscall_64+0xd5/0x1f0
 entry_SYSCALL_64_after_hwframe+0x6d/0x75

Uninit was stored to memory at:

  pskb_expand_head+0x30f/0x19d0 net/core/skbuff.c:2253
  netlink_trim+0x2c2/0x330 net/netlink/af_netlink.c:1317
  netlink_unicast+0x9f/0x1260 net/netlink/af_netlink.c:1351
  nlmsg_unicast include/net/netlink.h:1144 [inline]
  nlmsg_notify+0x21d/0x2f0 net/netlink/af_netlink.c:2610
  rtnetlink_send+0x73/0x90 net/core/rtnetlink.c:741
  rtnetlink_maybe_send include/linux/rtnetlink.h:17 [inline]
  tcf_add_notify net/sched/act_api.c:2048 [inline]
  tcf_action_add net/sched/act_api.c:2071 [inline]
  tc_ctl_action+0x146e/0x19d0 net/sched/act_api.c:2119
  rtnetlink_rcv_msg+0x1737/0x1900 net/core/rtnetlink.c:6595
  netlink_rcv_skb+0x375/0x650 net/netlink/af_netlink.c:2559
  rtnetlink_rcv+0x34/0x40 net/core/rtnetlink.c:6613
  netlink_unicast_kernel net/netlink/af_netlink.c:1335 [inline]
  netlink_unicast+0xf4c/0x1260 net/netlink/af_netlink.c:1361
  netlink_sendmsg+0x10df/0x11f0 net/netlink/af_netlink.c:1905
  sock_sendmsg_nosec net/socket.c:730 [inline]
  __sock_sendmsg+0x30f/0x380 net/socket.c:745
  ____sys_sendmsg+0x877/0xb60 net/socket.c:2584
  ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2638
  __sys_sendmsg net/socket.c:2667 [inline]
  __do_sys_sendmsg net/socket.c:2676 [inline]
  __se_sys_sendmsg net/socket.c:2674 [inline]
  __x64_sys_sendmsg+0x307/0x4a0 net/socket.c:2674
 do_syscall_64+0xd5/0x1f0
 entry_SYSCALL_64_after_hwframe+0x6d/0x75

Uninit was stored to memory at:

  __nla_put lib/nlattr.c:1041 [inline]
  nla_put+0x1c6/0x230 lib/nlattr.c:1099
  tcf_skbmod_dump+0x23f/0xc20 net/sched/act_skbmod.c:256
  tcf_action_dump_old net/sched/act_api.c:1191 [inline]
  tcf_action_dump_1+0x85e/0x970 net/sched/act_api.c:1227
  tcf_action_dump+0x1fd/0x460 net/sched/act_api.c:1251
  tca_get_fill+0x519/0x7a0 net/sched/act_api.c:1628
  tcf_add_notify_msg net/sched/act_api.c:2023 [inline]
  tcf_add_notify net/sched/act_api.c:2042 [inline]
  tcf_action_add net/sched/act_api.c:2071 [inline]
  tc_ctl_action+0x1365/0x19d0 net/sched/act_api.c:2119
  rtnetlink_rcv_msg+0x1737/0x1900 net/core/rtnetlink.c:6595
  netlink_rcv_skb+0x375/0x650 net/netlink/af_netlink.c:2559
  rtnetlink_rcv+0x34/0x40 net/core/rtnetlink.c:6613
  netlink_unicast_kernel net/netlink/af_netlink.c:1335 [inline]
  netlink_unicast+0xf4c/0x1260 net/netlink/af_netlink.c:1361
  netlink_sendmsg+0x10df/0x11f0 net/netlink/af_netlink.c:1905
  sock_sendmsg_nosec net/socket.c:730 [inline]
  __sock_sendmsg+0x30f/0x380 net/socket.c:745
  ____sys_sendmsg+0x877/0xb60 net/socket.c:2584
  ___sys_sendmsg+0x28d/0x3c0 net/socket.c:2638
  __sys_sendmsg net/socket.c:2667 [inline]
  __do_sys_sendmsg net/socket.c:2676 [inline]
  __se_sys_sendmsg net/socket.c:2674 [inline]
  __x64_sys_sendmsg+0x307/0x4a0 net/socket.c:2674
 do_syscall_64+0xd5/0x1f0
 entry_SYSCALL_64_after_hwframe+0x6d/0x75

Local variable opt created at:

  tcf_skbmod_dump+0x9d/0xc20 net/sched/act_skbmod.c:244
  tcf_action_dump_old net/sched/act_api.c:1191 [inline]
  tcf_action_dump_1+0x85e/0x970 net/sched/act_api.c:1227

Bytes 188-191 of 248 are uninitialized Memory access of size 248 starts at ffff888117697680 Data copied to user address 00007ffe56d855f0

---
 net/sched/act_skbmod.c |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)
net/sched/act_skbmod.c +5 -5
@@ -240,13 +240,13 @@ static int tcf_skbmod_dump(struct sk_buf
 	struct tcf_skbmod *d = to_skbmod(a);
 	unsigned char *b = skb_tail_pointer(skb);
 	struct tcf_skbmod_params  *p;
-	struct tc_skbmod opt = {
-		.index   = d->tcf_index,
-		.refcnt  = refcount_read(&d->tcf_refcnt) - ref,
-		.bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
-	};
+	struct tc_skbmod opt;
 	struct tcf_t t;
 
+	memset(&opt, 0, sizeof(opt));
+	opt.index   = d->tcf_index;
+	opt.refcnt  = refcount_read(&d->tcf_refcnt) - ref,
+	opt.bindcnt = atomic_read(&d->tcf_bindcnt) - bind;
 	spin_lock_bh(&d->tcf_lock);
 	opt.action = d->tcf_action;
 	p = rcu_dereference_protected(d->skbmod_p,
author maintainer
#647 lore raw

PATCH 643/690 net: stmmac: fix rx queue priority assignment

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Piotr Wejman <[email protected]>

commit b3da86d432b7cd65b025a11f68613e333d2483db upstream.

The driver should ensure that same priority is not mapped to multiple rx queues. From DesignWare Cores Ethernet Quality-of-Service Databook, section 17.1.29 MAC_RxQ_Ctrl2:
"[...]The software must ensure that the content of this field is mutually exclusive to the PSRQ fields for other queues, that is, the same priority is not mapped to multiple Rx queues[...]"

Previously rx_queue_priority() function was:
- clearing all priorities from a queue
- adding new priorities to that queue
After this patch it will:
- first assign new priorities to a queue
- then remove those priorities from all other queues
- keep other priorities previously assigned to that queue

Fixes a8f5102af2a7 ("net: stmmac: TX and RX queue priority configuration")
Fixes 2142754f8b9c ("net: stmmac: Add MAC related callbacks for XGMAC2")
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c   |   40 +++++++++++++++-----
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c |   38 +++++++++++++++----
 2 files changed, 62 insertions(+), 16 deletions(-)
drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +31 -9
@@ -88,19 +88,41 @@ static void dwmac4_rx_queue_priority(str
 				     u32 prio, u32 queue)
 {
 	void __iomem *ioaddr = hw->pcsr;
-	u32 base_register;
-	u32 value;
+	u32 clear_mask = 0;
+	u32 ctrl2, ctrl3;
+	int i;
 
-	base_register = (queue < 4) ? GMAC_RXQ_CTRL2 : GMAC_RXQ_CTRL3;
-	if (queue >= 4)
-		queue -= 4;
+	ctrl2 = readl(ioaddr + GMAC_RXQ_CTRL2);
+	ctrl3 = readl(ioaddr + GMAC_RXQ_CTRL3);
+
+	/* The software must ensure that the same priority
+	 * is not mapped to multiple Rx queues
+	 */
+	for (i = 0; i < 4; i++)
+		clear_mask |= ((prio << GMAC_RXQCTRL_PSRQX_SHIFT(i)) &
+						GMAC_RXQCTRL_PSRQX_MASK(i));
 
-	value = readl(ioaddr + base_register);
+	ctrl2 &= ~clear_mask;
+	ctrl3 &= ~clear_mask;
 
-	value &= ~GMAC_RXQCTRL_PSRQX_MASK(queue);
-	value |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) &
+	/* First assign new priorities to a queue, then
+	 * clear them from others queues
+	 */
+	if (queue < 4) {
+		ctrl2 |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) &
 						GMAC_RXQCTRL_PSRQX_MASK(queue);
-	writel(value, ioaddr + base_register);
+
+		writel(ctrl2, ioaddr + GMAC_RXQ_CTRL2);
+		writel(ctrl3, ioaddr + GMAC_RXQ_CTRL3);
+	} else {
+		queue -= 4;
+
+		ctrl3 |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) &
+						GMAC_RXQCTRL_PSRQX_MASK(queue);
+
+		writel(ctrl3, ioaddr + GMAC_RXQ_CTRL3);
+		writel(ctrl2, ioaddr + GMAC_RXQ_CTRL2);
+	}
 }
 
 static void dwmac4_tx_queue_priority(struct mac_device_info *hw,
drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +31 -7
@@ -97,17 +97,41 @@ static void dwxgmac2_rx_queue_prio(struc
 				   u32 queue)
 {
 	void __iomem *ioaddr = hw->pcsr;
-	u32 value, reg;
+	u32 clear_mask = 0;
+	u32 ctrl2, ctrl3;
+	int i;
 
-	reg = (queue < 4) ? XGMAC_RXQ_CTRL2 : XGMAC_RXQ_CTRL3;
-	if (queue >= 4)
+	ctrl2 = readl(ioaddr + XGMAC_RXQ_CTRL2);
+	ctrl3 = readl(ioaddr + XGMAC_RXQ_CTRL3);
+
+	/* The software must ensure that the same priority
+	 * is not mapped to multiple Rx queues
+	 */
+	for (i = 0; i < 4; i++)
+		clear_mask |= ((prio << XGMAC_PSRQ_SHIFT(i)) &
+						XGMAC_PSRQ(i));
+
+	ctrl2 &= ~clear_mask;
+	ctrl3 &= ~clear_mask;
+
+	/* First assign new priorities to a queue, then
+	 * clear them from others queues
+	 */
+	if (queue < 4) {
+		ctrl2 |= (prio << XGMAC_PSRQ_SHIFT(queue)) &
+						XGMAC_PSRQ(queue);
+
+		writel(ctrl2, ioaddr + XGMAC_RXQ_CTRL2);
+		writel(ctrl3, ioaddr + XGMAC_RXQ_CTRL3);
+	} else {
 		queue -= 4;
 
-	value = readl(ioaddr + reg);
-	value &= ~XGMAC_PSRQ(queue);
-	value |= (prio << XGMAC_PSRQ_SHIFT(queue)) & XGMAC_PSRQ(queue);
+		ctrl3 |= (prio << XGMAC_PSRQ_SHIFT(queue)) &
+						XGMAC_PSRQ(queue);
 
-	writel(value, ioaddr + reg);
+		writel(ctrl3, ioaddr + XGMAC_RXQ_CTRL3);
+		writel(ctrl2, ioaddr + XGMAC_RXQ_CTRL2);
+	}
 }
 
 static void dwxgmac2_tx_queue_prio(struct mac_device_info *hw, u32 prio,
author maintainer
#648 lore raw

PATCH 644/690 selftests: net: gro fwd: update vxlan GRO test expectations

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Antoine Tenart <[email protected]>

commit 0fb101be97ca27850c5ecdbd1269423ce4d1f607 upstream.

UDP tunnel packets can't be GRO in-between their endpoints as this causes different issues. The UDP GRO fwd vxlan tests were relying on this and their expectations have to be fixed.

We keep both vxlan tests and expected no GRO from happening. The vxlan UDP GRO bench test was removed as it's not providing any valuable information now.

Fixes a062260a9d5f ("selftests: net: add UDP GRO forwarding self-tests")
---
 tools/testing/selftests/net/udpgro_fwd.sh |   10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)
tools/testing/selftests/net/udpgro_fwd.sh +2 -8
@@ -238,7 +238,7 @@ for family in 4 6; do
 
 	create_vxlan_pair
 	ip netns exec $NS_DST ethtool -K veth$DST rx-gro-list on
-	run_test "GRO frag list over UDP tunnel" $OL_NET$DST 1 1
+	run_test "GRO frag list over UDP tunnel" $OL_NET$DST 10 10
 	cleanup
 
 	# use NAT to circumvent GRO FWD check
@@ -251,13 +251,7 @@ for family in 4 6; do
 	# load arp cache before running the test to reduce the amount of
 	# stray traffic on top of the UDP tunnel
 	ip netns exec $NS_SRC $PING -q -c 1 $OL_NET$DST_NAT >/dev/null
-	run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 1 1 $OL_NET$DST
-	cleanup
-
-	create_vxlan_pair
-	run_bench "UDP tunnel fwd perf" $OL_NET$DST
-	ip netns exec $NS_DST ethtool -K veth$DST rx-udp-gro-forwarding on
-	run_bench "UDP tunnel GRO fwd perf" $OL_NET$DST
+	run_test "GRO fwd over UDP tunnel" $OL_NET$DST_NAT 10 10 $OL_NET$DST
 	cleanup
 done
 
author maintainer
#649 lore raw

PATCH 645/690 erspan: make sure erspan_base_hdr is present in skb->head

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet <[email protected]>

commit 17af420545a750f763025149fa7b833a4fc8b8f0 upstream.

syzbot reported a problem in ip6erspan_rcv() [1]

Issue is that ip6erspan_rcv() (and erspan_rcv()) no longer make sure erspan_base_hdr is present in skb linear part (skb->head) before getting @ver field from it.

Add the missing pskb_may_pull() calls.

v2: Reload iph pointer in erspan_rcv() after pskb_may_pull()

    because skb->head might have changed.

[1]

 BUG: KMSAN: uninit-value in pskb_may_pull_reason include/linux/skbuff.h:2742 [inline]
 BUG: KMSAN: uninit-value in pskb_may_pull include/linux/skbuff.h:2756 [inline]
 BUG: KMSAN: uninit-value in ip6erspan_rcv net/ipv6/ip6_gre.c:541 [inline]
 BUG: KMSAN: uninit-value in gre_rcv+0x11f8/0x1930 net/ipv6/ip6_gre.c:610
  pskb_may_pull_reason include/linux/skbuff.h:2742 [inline]
  pskb_may_pull include/linux/skbuff.h:2756 [inline]
  ip6erspan_rcv net/ipv6/ip6_gre.c:541 [inline]
  gre_rcv+0x11f8/0x1930 net/ipv6/ip6_gre.c:610
  ip6_protocol_deliver_rcu+0x1d4c/0x2ca0 net/ipv6/ip6_input.c:438
  ip6_input_finish net/ipv6/ip6_input.c:483 [inline]
  NF_HOOK include/linux/netfilter.h:314 [inline]
  ip6_input+0x15d/0x430 net/ipv6/ip6_input.c:492
  ip6_mc_input+0xa7e/0xc80 net/ipv6/ip6_input.c:586
  dst_input include/net/dst.h:460 [inline]
  ip6_rcv_finish+0x955/0x970 net/ipv6/ip6_input.c:79
  NF_HOOK include/linux/netfilter.h:314 [inline]
  ipv6_rcv+0xde/0x390 net/ipv6/ip6_input.c:310
  __netif_receive_skb_one_core net/core/dev.c:5538 [inline]
  __netif_receive_skb+0x1da/0xa00 net/core/dev.c:5652
  netif_receive_skb_internal net/core/dev.c:5738 [inline]
  netif_receive_skb+0x58/0x660 net/core/dev.c:5798
  tun_rx_batched+0x3ee/0x980 drivers/net/tun.c:1549
  tun_get_user+0x5566/0x69e0 drivers/net/tun.c:2002
  tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048
  call_write_iter include/linux/fs.h:2108 [inline]
  new_sync_write fs/read_write.c:497 [inline]
  vfs_write+0xb63/0x1520 fs/read_write.c:590
  ksys_write+0x20f/0x4c0 fs/read_write.c:643
  __do_sys_write fs/read_write.c:655 [inline]
  __se_sys_write fs/read_write.c:652 [inline]
  __x64_sys_write+0x93/0xe0 fs/read_write.c:652
 do_syscall_64+0xd5/0x1f0
 entry_SYSCALL_64_after_hwframe+0x6d/0x75

Uninit was created at:

  slab_post_alloc_hook mm/slub.c:3804 [inline]
  slab_alloc_node mm/slub.c:3845 [inline]
  kmem_cache_alloc_node+0x613/0xc50 mm/slub.c:3888
  kmalloc_reserve+0x13d/0x4a0 net/core/skbuff.c:577
  __alloc_skb+0x35b/0x7a0 net/core/skbuff.c:668
  alloc_skb include/linux/skbuff.h:1318 [inline]
  alloc_skb_with_frags+0xc8/0xbf0 net/core/skbuff.c:6504
  sock_alloc_send_pskb+0xa81/0xbf0 net/core/sock.c:2795
  tun_alloc_skb drivers/net/tun.c:1525 [inline]
  tun_get_user+0x209a/0x69e0 drivers/net/tun.c:1846
  tun_chr_write_iter+0x3af/0x5d0 drivers/net/tun.c:2048
  call_write_iter include/linux/fs.h:2108 [inline]
  new_sync_write fs/read_write.c:497 [inline]
  vfs_write+0xb63/0x1520 fs/read_write.c:590
  ksys_write+0x20f/0x4c0 fs/read_write.c:643
  __do_sys_write fs/read_write.c:655 [inline]
  __se_sys_write fs/read_write.c:652 [inline]
  __x64_sys_write+0x93/0xe0 fs/read_write.c:652
 do_syscall_64+0xd5/0x1f0
 entry_SYSCALL_64_after_hwframe+0x6d/0x75

CPU: 1 PID: 5045 Comm: syz-executor114 Not tainted 6.9.0-rc1-syzkaller-00021-g962490525cff #0
---
 net/ipv4/ip_gre.c  |    5 +++++
 net/ipv6/ip6_gre.c |    3 +++
 2 files changed, 8 insertions(+)
net/ipv4/ip_gre.c +5 -0
@@ -280,8 +280,13 @@ static int erspan_rcv(struct sk_buff *sk
 					  tpi->flags | TUNNEL_NO_KEY,
 					  iph->saddr, iph->daddr, 0);
 	} else {
+		if (unlikely(!pskb_may_pull(skb,
+					    gre_hdr_len + sizeof(*ershdr))))
+			return PACKET_REJECT;
+
 		ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len);
 		ver = ershdr->ver;
+		iph = ip_hdr(skb);
 		tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex,
 					  tpi->flags | TUNNEL_KEY,
 					  iph->saddr, iph->daddr, tpi->key);
net/ipv6/ip6_gre.c +3 -0
@@ -533,6 +533,9 @@ static int ip6erspan_rcv(struct sk_buff
 	struct ip6_tnl *tunnel;
 	u8 ver;
 
+	if (unlikely(!pskb_may_pull(skb, sizeof(*ershdr))))
+		return PACKET_REJECT;
+
 	ipv6h = ipv6_hdr(skb);
 	ershdr = (struct erspan_base_hdr *)skb->data;
 	ver = ershdr->ver;
author maintainer
#650 lore raw

PATCH 646/690 selftests: reuseaddr_conflict: add missing new line at the end of the output

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Jakub Kicinski <[email protected]>

commit 31974122cfdeaf56abc18d8ab740d580d9833e90 upstream.

The netdev CI runs in a VM and captures serial, so stdout and stderr get combined. Because there's a missing new line in stderr the test ends up corrupting KTAP:

# Successok 1 selftests: net: reuseaddr_conflict

which should have been:

# Success
ok 1 selftests: net: reuseaddr_conflict

---
 tools/testing/selftests/net/reuseaddr_conflict.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
tools/testing/selftests/net/reuseaddr_conflict.c +1 -1
@@ -109,6 +109,6 @@ int main(void)
 	fd1 = open_port(0, 1);
 	if (fd1 >= 0)
 		error(1, 0, "Was allowed to create an ipv4 reuseport on an already bound non-reuseport socket with no ipv6");
-	fprintf(stderr, "Success");
+	fprintf(stderr, "Success\n");
 	return 0;
 }
author maintainer
#651 lore raw

PATCH 647/690 ipv6: Fix infinite recursion in fib6_dump_done().

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kuniyuki Iwashima <[email protected]>

commit d21d40605bca7bd5fc23ef03d4c1ca1f48bc2cae upstream.

syzkaller reported infinite recursive calls of fib6_dump_done() during netlink socket destruction. [1]

Quoted 1 line

From the log, syzkaller sent an AF_UNSPEC RTM_GETROUTE message, and then

the response was generated. The following recvmmsg() resumed the dump for IPv6, but the first call of inet6_dump_fib() failed at kzalloc() due to the fault injection. [0]

12:01:34 executing program 3:
r0 = socket$nl_route(0x10, 0x3, 0x0)
sendmsg$nl_route(r0, ... snip ...)
recvmmsg(r0, ... snip ...) (fail_nth: 8)

Here, fib6_dump_done() was set to nlk_sk(sk)->cb.done, and the next call of inet6_dump_fib() set it to nlk_sk(sk)->cb.args[3]. syzkaller stopped receiving the response halfway through, and finally netlink_sock_destruct() called nlk_sk(sk)->cb.done().

fib6_dump_done() calls fib6_dump_end() and nlk_sk(sk)->cb.done() if it is still not NULL. fib6_dump_end() rewrites nlk_sk(sk)->cb.done() by nlk_sk(sk)->cb.args[3], but it has the same function, not NULL, calling itself recursively and hitting the stack guard page.

To avoid the issue, let's set the destructor after kzalloc().

[0]:
FAULT_INJECTION: forcing a failure.
name failslab, interval 1, probability 0, space 0, times 0

CPU: 1 PID: 432110 Comm: syz-executor.3 Not tainted 6.8.0-12821-g537c2e91d354-dirty #11
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
Call Trace:
 <TASK>
 dump_stack_lvl (lib/dump_stack.c:117)
 should_fail_ex (lib/fault-inject.c:52 lib/fault-inject.c:153)
 should_failslab (mm/slub.c:3733)
 kmalloc_trace (mm/slub.c:3748 mm/slub.c:3827 mm/slub.c:3992)
 inet6_dump_fib (./include/linux/slab.h:628 ./include/linux/slab.h:749 net/ipv6/ip6_fib.c:662)
 rtnl_dump_all (net/core/rtnetlink.c:4029)
 netlink_dump (net/netlink/af_netlink.c:2269)
 netlink_recvmsg (net/netlink/af_netlink.c:1988)
 ____sys_recvmsg (net/socket.c:1046 net/socket.c:2801)
 ___sys_recvmsg (net/socket.c:2846)
 do_recvmmsg (net/socket.c:2943)
 __x64_sys_recvmmsg (net/socket.c:3041 net/socket.c:3034 net/socket.c:3034)

[1]:

BUG: TASK stack guard page was hit at 00000000f2fa9af1 (stack is 00000000b7912430..000000009a436beb)
stack guard page: 0000 [#1] PREEMPT SMP KASAN
CPU: 1 PID: 223719 Comm: kworker/1:3 Not tainted 6.8.0-12821-g537c2e91d354-dirty #11
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
Workqueue: events netlink_sock_destruct_work
RIP: 0010:fib6_dump_done (net/ipv6/ip6_fib.c:570)
Code: 3c 24 e8 f3 e9 51 fd e9 28 fd ff ff 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 f3 0f 1e fa 41 57 41 56 41 55 41 54 55 48 89 fd <53> 48 8d 5d 60 e8 b6 4d 07 fd 48 89 da 48 b8 00 00 00 00 00 fc ff
RSP: 0018:ffffc9000d980000 EFLAGS: 00010293
RAX: 0000000000000000 RBX: ffffffff84405990 RCX: ffffffff844059d3
RDX: ffff8881028e0000 RSI: ffffffff84405ac2 RDI: ffff88810c02f358
RBP: ffff88810c02f358 R08: 0000000000000007 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000224 R12: 0000000000000000
R13: ffff888007c82c78 R14: ffff888007c82c68 R15: ffff888007c82c68
FS:  0000000000000000(0000) GS:ffff88811b100000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffc9000d97fff8 CR3: 0000000102309002 CR4: 0000000000770ef0
PKRU: 55555554
Call Trace:
 <#DF>
 </#DF>
 <TASK>
 fib6_dump_done (net/ipv6/ip6_fib.c:572 (discriminator 1))
 fib6_dump_done (net/ipv6/ip6_fib.c:572 (discriminator 1))
 ...
 fib6_dump_done (net/ipv6/ip6_fib.c:572 (discriminator 1))
 fib6_dump_done (net/ipv6/ip6_fib.c:572 (discriminator 1))
 netlink_sock_destruct (net/netlink/af_netlink.c:401)
 __sk_destruct (net/core/sock.c:2177 (discriminator 2))
 sk_destruct (net/core/sock.c:2224)
 __sk_free (net/core/sock.c:2235)
 sk_free (net/core/sock.c:2246)
 process_one_work (kernel/workqueue.c:3259)
 worker_thread (kernel/workqueue.c:3329 kernel/workqueue.c:3416)
 kthread (kernel/kthread.c:388)
 ret_from_fork (arch/x86/kernel/process.c:153)
 ret_from_fork_asm (arch/x86/entry/entry_64.S:256)
Modules linked in:
---
 net/ipv6/ip6_fib.c |   14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)
net/ipv6/ip6_fib.c +7 -7
@@ -645,19 +645,19 @@ static int inet6_dump_fib(struct sk_buff
 	if (!w) {
 		/* New dump:
 		 *
-		 * 1. hook callback destructor.
-		 */
-		cb->args[3] = (long)cb->done;
-		cb->done = fib6_dump_done;
-
-		/*
-		 * 2. allocate and initialize walker.
+		 * 1. allocate and initialize walker.
 		 */
 		w = kzalloc(sizeof(*w), GFP_ATOMIC);
 		if (!w)
 			return -ENOMEM;
 		w->func = fib6_dump_node;
 		cb->args[2] = (long)w;
+
+		/* 2. hook callback destructor.
+		 */
+		cb->args[3] = (long)cb->done;
+		cb->done = fib6_dump_done;
+
 	}
 
 	arg.skb = skb;
author maintainer
#652 lore raw

PATCH 648/690 mlxbf_gige: stop interface during shutdown

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: David Thompson <[email protected]>

commit 09ba28e1cd3cf715daab1fca6e1623e22fd754a6 upstream.

The mlxbf_gige driver intermittantly encounters a NULL pointer exception while the system is shutting down via "reboot" command. The mlxbf_driver will experience an exception right after executing its shutdown() method. One example of this exception is:

Unable to handle kernel NULL pointer dereference at virtual address 0000000000000070

Mem abort info:
ESR = 0x0000000096000004
EC = 0x25: DABT (current EL), IL = 32 bits
SET = 0, FnV = 0
EA = 0, S1PTW = 0
FSC = 0x04: level 0 translation fault
Data abort info:
ISV = 0, ISS = 0x00000004
CM = 0, WnR = 0
user pgtable: 4k pages, 48-bit VAs, pgdp=000000011d373000 [0000000000000070] pgd=0000000000000000, p4d=0000000000000000

Internal error: Oops: 96000004 [#1] SMP
CPU: 0 PID: 13 Comm: ksoftirqd/0 Tainted: G S         OE     5.15.0-bf.6.gef6992a #1
Hardware name: https://www.mellanox.com BlueField SoC/BlueField SoC, BIOS 4.0.2.12669 Apr 21 2023
pstate: 20400009 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : mlxbf_gige_handle_tx_complete+0xc8/0x170 [mlxbf_gige]
lr : mlxbf_gige_poll+0x54/0x160 [mlxbf_gige]

sp : ffff8000080d3c10
x29: ffff8000080d3c10 x28: ffffcce72cbb7000 x27: ffff8000080d3d58
x26: ffff0000814e7340 x25: ffff331cd1a05000 x24: ffffcce72c4ea008
x23: ffff0000814e4b40 x22: ffff0000814e4d10 x21: ffff0000814e4128
x20: 0000000000000000 x19: ffff0000814e4a80 x18: ffffffffffffffff
x17: 000000000000001c x16: ffffcce72b4553f4 x15: ffff80008805b8a7
x14: 0000000000000000 x13: 0000000000000030 x12: 0101010101010101
x11: 7f7f7f7f7f7f7f7f x10: c2ac898b17576267 x9 : ffffcce720fa5404 x8 : ffff000080812138 x7 : 0000000000002e9a x6 : 0000000000000080 x5 : ffff00008de3b000 x4 : 0000000000000000 x3 : 0000000000000001 x2 : 0000000000000000 x1 : 0000000000000000 x0 : 0000000000000000

Call trace:
 mlxbf_gige_handle_tx_complete+0xc8/0x170 [mlxbf_gige]
 mlxbf_gige_poll+0x54/0x160 [mlxbf_gige]
 __napi_poll+0x40/0x1c8
 net_rx_action+0x314/0x3a0
 __do_softirq+0x128/0x334
 run_ksoftirqd+0x54/0x6c
 smpboot_thread_fn+0x14c/0x190
 kthread+0x10c/0x110
 ret_from_fork+0x10/0x20
Code: 8b070000 f9000ea0 f95056c0 f86178a1 (b9407002)
---[ end trace 7cc3941aa0d8e6a4 ]---
Kernel panic - not syncing: Oops: Fatal exception in interrupt

Kernel Offset: 0x4ce722520000 from 0xffff800008000000
PHYS_OFFSET: 0x80000000
CPU features: 0x000005c1,a3330e5a
Memory Limit: none

---[ end Kernel panic - not syncing: Oops: Fatal exception in interrupt ]---

During system shutdown, the mlxbf_gige driver's shutdown() is always executed. However, the driver's stop() method will only execute if networking interface configuration logic within the Linux distribution has been setup to do so.

If shutdown() executes but stop() does not execute, NAPI remains enabled and this can lead to an exception if NAPI is scheduled while the hardware interface has only been partially deinitialized.

The networking interface managed by the mlxbf_gige driver must be properly stopped during system shutdown so that IFF_UP is cleared, the hardware interface is put into a clean state, and NAPI is fully deinitialized.

Fixes f92e1869d74e ("Add Mellanox BlueField Gigabit Ethernet driver")
---
 drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c |   10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)
drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +8 -2
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/phy.h>
 #include <linux/platform_device.h>
+#include <linux/rtnetlink.h>
 #include <linux/skbuff.h>
 
 #include "mlxbf_gige.h"
@@ -419,8 +420,13 @@ static void mlxbf_gige_shutdown(struct p
 {
 	struct mlxbf_gige *priv = platform_get_drvdata(pdev);
 
-	writeq(0, priv->base + MLXBF_GIGE_INT_EN);
-	mlxbf_gige_clean_port(priv);
+	rtnl_lock();
+	netif_device_detach(priv->netdev);
+
+	if (netif_running(priv->netdev))
+		dev_close(priv->netdev);
+
+	rtnl_unlock();
 }
 
 static const struct acpi_device_id __maybe_unused mlxbf_gige_acpi_match[] = {
author maintainer
#653 lore raw

PATCH 649/690 udp: do not accept non-tunnel GSO skbs landing in a tunnel

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Antoine Tenart <[email protected]>

commit 3d010c8031e39f5fa1e8b13ada77e0321091011f upstream.

When rx-udp-gro-forwarding is enabled UDP packets might be GROed when being forwarded. If such packets might land in a tunnel this can cause various issues and udp_gro_receive makes sure this isn't the case by looking for a matching socket. This is performed in udp4/6_gro_lookup_skb but only in the current netns. This is an issue with tunneled packets when the endpoint is in another netns. In such cases the packets will be GROed at the UDP level, which leads to various issues later on. The same thing can happen with rx-gro-list.

We saw this with geneve packets being GROed at the UDP level. In such case gso_size is set; later the packet goes through the geneve rx path, the geneve header is pulled, the offset are adjusted and frag_list skbs are not adjusted with regard to geneve. When those skbs hit skb_fragment, it will misbehave. Different outcomes are possible depending on what the GROed skbs look like; from corrupted packets to kernel crashes.

One example is a BUG_ON[1] triggered in skb_segment while processing the frag_list. Because gso_size is wrong (geneve header was pulled) skb_segment thinks there is "geneve header size" of data in frag_list, although it's in fact the next packet. The BUG_ON itself has nothing to do with the issue. This is only one of the potential issues.

Looking up for a matching socket in udp_gro_receive is fragile: the lookup could be extended to all netns (not speaking about performances) but nothing prevents those packets from being modified in between and we could still not find a matching socket. It's OK to keep the current logic there as it should cover most cases but we also need to make sure we handle tunnel packets being GROed too early.

This is done by extending the checks in udp_unexpected_gso: GSO packets lacking the SKB_GSO_UDP_TUNNEL/_CSUM bits and landing in a tunnel must be segmented.

[1] kernel BUG at net/core/skbuff.c:4408!

    RIP: 0010:skb_segment+0xd2a/0xf70
    __udp_gso_segment+0xaa/0x560
Fixes 9fd1ff5d2ac7 ("udp: Support UDP fraglist GRO/GSO.")
Fixes 36707061d6ba ("udp: allow forwarding of plain (non-fraglisted) UDP GRO packets")
---
 include/linux/udp.h    |   28 ++++++++++++++++++++++++++++
 net/ipv4/udp.c         |    7 +++++++
 net/ipv4/udp_offload.c |    6 ++++--
 net/ipv6/udp.c         |    2 +-
 4 files changed, 40 insertions(+), 3 deletions(-)
include/linux/udp.h +28 -0
@@ -132,6 +132,24 @@ static inline void udp_cmsg_recv(struct
 	}
 }
 
+DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key);
+#if IS_ENABLED(CONFIG_IPV6)
+DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
+#endif
+
+static inline bool udp_encap_needed(void)
+{
+	if (static_branch_unlikely(&udp_encap_needed_key))
+		return true;
+
+#if IS_ENABLED(CONFIG_IPV6)
+	if (static_branch_unlikely(&udpv6_encap_needed_key))
+		return true;
+#endif
+
+	return false;
+}
+
 static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb)
 {
 	if (!skb_is_gso(skb))
@@ -143,6 +161,16 @@ static inline bool udp_unexpected_gso(st
 	if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST && !udp_sk(sk)->accept_udp_fraglist)
 		return true;
 
+	/* GSO packets lacking the SKB_GSO_UDP_TUNNEL/_CSUM bits might still
+	 * land in a tunnel as the socket check in udp_gro_receive cannot be
+	 * foolproof.
+	 */
+	if (udp_encap_needed() &&
+	    READ_ONCE(udp_sk(sk)->encap_rcv) &&
+	    !(skb_shinfo(skb)->gso_type &
+	      (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM)))
+		return true;
+
 	return false;
 }
 
net/ipv4/udp.c +7 -0
@@ -601,6 +601,13 @@ static inline bool __udp_is_mcast_sock(s
 }
 
 DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key);
+EXPORT_SYMBOL(udp_encap_needed_key);
+
+#if IS_ENABLED(CONFIG_IPV6)
+DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
+EXPORT_SYMBOL(udpv6_encap_needed_key);
+#endif
+
 void udp_encap_enable(void)
 {
 	static_branch_inc(&udp_encap_needed_key);
net/ipv4/udp_offload.c +4 -2
@@ -515,8 +515,10 @@ struct sk_buff *udp_gro_receive(struct l
 	unsigned int off = skb_gro_offset(skb);
 	int flush = 1;
 
-	/* we can do L4 aggregation only if the packet can't land in a tunnel
-	 * otherwise we could corrupt the inner stream
+	/* We can do L4 aggregation only if the packet can't land in a tunnel
+	 * otherwise we could corrupt the inner stream. Detecting such packets
+	 * cannot be foolproof and the aggregation might still happen in some
+	 * cases. Such packets should be caught in udp_unexpected_gso later.
 	 */
 	NAPI_GRO_CB(skb)->is_flist = 0;
 	if (!sk || !udp_sk(sk)->gro_receive) {
net/ipv6/udp.c +1 -1
@@ -473,7 +473,7 @@ csum_copy_err:
 	goto try_again;
 }
 
-DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
+DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
 void udpv6_encap_enable(void)
 {
 	static_branch_inc(&udpv6_encap_needed_key);
author maintainer
#654 lore raw

PATCH 650/690 udp: do not transition UDP GRO fraglist partial checksums to unnecessary

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Antoine Tenart <[email protected]>

commit f0b8c30345565344df2e33a8417a27503589247d upstream.

UDP GRO validates checksums and in udp4/6_gro_complete fraglist packets are converted to CHECKSUM_UNNECESSARY to avoid later checks. However this is an issue for CHECKSUM_PARTIAL packets as they can be looped in an egress path and then their partial checksums are not fixed.

Different issues can be observed, from invalid checksum on packets to traces like:

gen01: hw csum failure
skb len=3008 headroom=160 headlen=1376 tailroom=0 mac=(106,14) net=(120,40) trans=160 shinfo(txflags=0 nr_frags=0 gso(size=0 type=0 segs=0)) csum(0xffff232e ip_summed=2 complete_sw=0 valid=0 level=0) hash(0x77e3d716 sw=1 l4=1) proto=0x86dd pkttype=0 iif=12
...

Fix this by only converting CHECKSUM_NONE packets to CHECKSUM_UNNECESSARY by reusing __skb_incr_checksum_unnecessary. All other checksum types are kept as-is, including CHECKSUM_COMPLETE as fraglist packets being segmented back would have their skb->csum valid.

Fixes 9fd1ff5d2ac7 ("udp: Support UDP fraglist GRO/GSO.")
---
 net/ipv4/udp_offload.c |    8 +-------
 net/ipv6/udp_offload.c |    8 +-------
 2 files changed, 2 insertions(+), 14 deletions(-)
net/ipv4/udp_offload.c +1 -7
@@ -685,13 +685,7 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_com
 		skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4);
 		skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
 
-		if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
-			if (skb->csum_level < SKB_MAX_CSUM_LEVEL)
-				skb->csum_level++;
-		} else {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			skb->csum_level = 0;
-		}
+		__skb_incr_checksum_unnecessary(skb);
 
 		return 0;
 	}
net/ipv6/udp_offload.c +1 -7
@@ -170,13 +170,7 @@ INDIRECT_CALLABLE_SCOPE int udp6_gro_com
 		skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4);
 		skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
 
-		if (skb->ip_summed == CHECKSUM_UNNECESSARY) {
-			if (skb->csum_level < SKB_MAX_CSUM_LEVEL)
-				skb->csum_level++;
-		} else {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			skb->csum_level = 0;
-		}
+		__skb_incr_checksum_unnecessary(skb);
 
 		return 0;
 	}
author maintainer
#655 lore raw

PATCH 651/690 udp: prevent local UDP tunnel packets from being GROed

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Antoine Tenart <[email protected]>

commit 64235eabc4b5b18c507c08a1f16cdac6c5661220 upstream.

GRO has a fundamental issue with UDP tunnel packets as it can't detect those in a foolproof way and GRO could happen before they reach the tunnel endpoint. Previous commits have fixed issues when UDP tunnel packets come from a remote host, but if those packets are issued locally they could run into checksum issues.

If the inner packet has a partial checksum the information will be lost in the GRO logic, either in udp4/6_gro_complete or in udp_gro_complete_segment and packets will have an invalid checksum when leaving the host.

Prevent local UDP tunnel packets from ever being GROed at the outer UDP level.

Due to skb->encapsulation being wrongly used in some drivers this is actually only preventing UDP tunnel packets with a partial checksum to be GROed (see iptunnel_handle_offloads) but those were also the packets triggering issues so in practice this should be sufficient.

Fixes 9fd1ff5d2ac7 ("udp: Support UDP fraglist GRO/GSO.")
Fixes 36707061d6ba ("udp: allow forwarding of plain (non-fraglisted) UDP GRO packets")
---
 net/ipv4/udp_offload.c |    6 ++++++
 1 file changed, 6 insertions(+)
net/ipv4/udp_offload.c +6 -0
@@ -522,6 +522,12 @@ struct sk_buff *udp_gro_receive(struct l
 	 */
 	NAPI_GRO_CB(skb)->is_flist = 0;
 	if (!sk || !udp_sk(sk)->gro_receive) {
+		/* If the packet was locally encapsulated in a UDP tunnel that
+		 * wasn't detected above, do not GRO.
+		 */
+		if (skb->encapsulation)
+			goto out;
+
 		if (skb->dev->features & NETIF_F_GRO_FRAGLIST)
 			NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled : 1;
 
author maintainer
#656 lore raw

PATCH 652/690 octeontx2-af: Fix issue with loading coalesced KPU profiles

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Hariprasad Kelam <[email protected]>

commit 0ba80d96585662299d4ea4624043759ce9015421 upstream.

The current implementation for loading coalesced KPU profiles has a limitation. The "offset" field, which is used to locate profiles within the profile is restricted to a u16.

This restricts the number of profiles that can be loaded. This patch addresses this limitation by increasing the size of the "offset" field.

Fixes 11c730bfbf5b ("octeontx2-af: support for coalescing KPU profiles")
---
 drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +1 -1
@@ -1622,7 +1622,7 @@ static int npc_fwdb_detect_load_prfl_img
 	struct npc_coalesced_kpu_prfl *img_data = NULL;
 	int i = 0, rc = -EINVAL;
 	void __iomem *kpu_prfl_addr;
-	u16 offset;
+	u32 offset;
 
 	img_data = (struct npc_coalesced_kpu_prfl __force *)rvu->kpu_prfl_addr;
 	if (le64_to_cpu(img_data->signature) == KPU_SIGN &&
author maintainer
#657 lore raw

PATCH 653/690 octeontx2-pf: check negative error code in otx2_open()

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Su Hui <[email protected]>

commit e709acbd84fb6ef32736331b0147f027a3ef4c20 upstream.

otx2_rxtx_enable() return negative error code such as -EIO, check -EIO rather than EIO to fix this problem.

---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +1 -1
@@ -1795,7 +1795,7 @@ int otx2_open(struct net_device *netdev)
 	 * mcam entries are enabled to receive the packets. Hence disable the
 	 * packet I/O.
 	 */
-	if (err == EIO)
+	if (err == -EIO)
 		goto err_disable_rxtx;
 	else if (err)
 		goto err_tx_stop_queues;
author maintainer
#658 lore raw

PATCH 654/690 i40e: fix i40e_count_filters() to count only active/new filters

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Aleksandr Loktionov <[email protected]>

commit eb58c598ce45b7e787568fe27016260417c3d807 upstream.

The bug usually affects untrusted VFs, because they are limited to 18 MACs, it affects them badly, not letting to create MAC all filters. Not stable to reproduce, it happens when VF user creates MAC filters when other MACVLAN operations are happened in parallel.
But consequence is that VF can't receive desired traffic.

Fix counter to be bumped only for new or active filters.

Fixes 621650cabee5 ("i40e: Refactoring VF MAC filters counting to make more reliable")
---
 drivers/net/ethernet/intel/i40e/i40e_main.c |    7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)
drivers/net/ethernet/intel/i40e/i40e_main.c +5 -2
@@ -1231,8 +1231,11 @@ int i40e_count_filters(struct i40e_vsi *
 	int bkt;
 	int cnt = 0;
 
-	hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist)
-		++cnt;
+	hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
+		if (f->state == I40E_FILTER_NEW ||
+		    f->state == I40E_FILTER_ACTIVE)
+			++cnt;
+	}
 
 	return cnt;
 }
author maintainer
#659 lore raw

PATCH 655/690 i40e: fix vf may be used uninitialized in this function warning

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Aleksandr Loktionov <[email protected]>

commit f37c4eac99c258111d414d31b740437e1925b8e8 upstream.

To fix the regression introduced by commit 52424f974bc5, which causes servers hang in very hard to reproduce conditions with resets races. Using two sources for the information is the root cause.
In this function before the fix bumping v didn't mean bumping vf pointer. But the code used this variables interchangeably, so stale vf could point to different/not intended vf.

Remove redundant "v" variable and iterate via single VF pointer across whole function instead to guarantee VF pointer validity.

---
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c |   34 +++++++++------------
 1 file changed, 16 insertions(+), 18 deletions(-)
drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +16 -18
@@ -1626,8 +1626,8 @@ bool i40e_reset_all_vfs(struct i40e_pf *
 {
 	struct i40e_hw *hw = &pf->hw;
 	struct i40e_vf *vf;
-	int i, v;
 	u32 reg;
+	int i;
 
 	/* If we don't have any VFs, then there is nothing to reset */
 	if (!pf->num_alloc_vfs)
@@ -1638,11 +1638,10 @@ bool i40e_reset_all_vfs(struct i40e_pf *
 		return false;
 
 	/* Begin reset on all VFs at once */
-	for (v = 0; v < pf->num_alloc_vfs; v++) {
-		vf = &pf->vf[v];
+	for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) {
 		/* If VF is being reset no need to trigger reset again */
 		if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
-			i40e_trigger_vf_reset(&pf->vf[v], flr);
+			i40e_trigger_vf_reset(vf, flr);
 	}
 
 	/* HW requires some time to make sure it can flush the FIFO for a VF
@@ -1651,14 +1650,13 @@ bool i40e_reset_all_vfs(struct i40e_pf *
 	 * the VFs using a simple iterator that increments once that VF has
 	 * finished resetting.
 	 */
-	for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) {
+	for (i = 0, vf = &pf->vf[0]; i < 10 && vf < &pf->vf[pf->num_alloc_vfs]; ++i) {
 		usleep_range(10000, 20000);
 
 		/* Check each VF in sequence, beginning with the VF to fail
 		 * the previous check.
 		 */
-		while (v < pf->num_alloc_vfs) {
-			vf = &pf->vf[v];
+		while (vf < &pf->vf[pf->num_alloc_vfs]) {
 			if (!test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states)) {
 				reg = rd32(hw, I40E_VPGEN_VFRSTAT(vf->vf_id));
 				if (!(reg & I40E_VPGEN_VFRSTAT_VFRD_MASK))
@@ -1668,7 +1666,7 @@ bool i40e_reset_all_vfs(struct i40e_pf *
 			/* If the current VF has finished resetting, move on
 			 * to the next VF in sequence.
 			 */
-			v++;
+			++vf;
 		}
 	}
 
@@ -1678,39 +1676,39 @@ bool i40e_reset_all_vfs(struct i40e_pf *
 	/* Display a warning if at least one VF didn't manage to reset in
 	 * time, but continue on with the operation.
 	 */
-	if (v < pf->num_alloc_vfs)
+	if (vf < &pf->vf[pf->num_alloc_vfs])
 		dev_err(&pf->pdev->dev, "VF reset check timeout on VF %d\n",
-			pf->vf[v].vf_id);
+			vf->vf_id);
 	usleep_range(10000, 20000);
 
 	/* Begin disabling all the rings associated with VFs, but do not wait
 	 * between each VF.
 	 */
-	for (v = 0; v < pf->num_alloc_vfs; v++) {
+	for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) {
 		/* On initial reset, we don't have any queues to disable */
-		if (pf->vf[v].lan_vsi_idx == 0)
+		if (vf->lan_vsi_idx == 0)
 			continue;
 
 		/* If VF is reset in another thread just continue */
 		if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
 			continue;
 
-		i40e_vsi_stop_rings_no_wait(pf->vsi[pf->vf[v].lan_vsi_idx]);
+		i40e_vsi_stop_rings_no_wait(pf->vsi[vf->lan_vsi_idx]);
 	}
 
 	/* Now that we've notified HW to disable all of the VF rings, wait
 	 * until they finish.
 	 */
-	for (v = 0; v < pf->num_alloc_vfs; v++) {
+	for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) {
 		/* On initial reset, we don't have any queues to disable */
-		if (pf->vf[v].lan_vsi_idx == 0)
+		if (vf->lan_vsi_idx == 0)
 			continue;
 
 		/* If VF is reset in another thread just continue */
 		if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
 			continue;
 
-		i40e_vsi_wait_queues_disabled(pf->vsi[pf->vf[v].lan_vsi_idx]);
+		i40e_vsi_wait_queues_disabled(pf->vsi[vf->lan_vsi_idx]);
 	}
 
 	/* Hw may need up to 50ms to finish disabling the RX queues. We
@@ -1719,12 +1717,12 @@ bool i40e_reset_all_vfs(struct i40e_pf *
 	mdelay(50);
 
 	/* Finish the reset on each VF */
-	for (v = 0; v < pf->num_alloc_vfs; v++) {
+	for (vf = &pf->vf[0]; vf < &pf->vf[pf->num_alloc_vfs]; ++vf) {
 		/* If VF is reset in another thread just continue */
 		if (test_bit(I40E_VF_STATE_RESETTING, &vf->vf_states))
 			continue;
 
-		i40e_cleanup_reset_vf(&pf->vf[v]);
+		i40e_cleanup_reset_vf(vf);
 	}
 
 	i40e_flush(hw);
author maintainer
#660 lore raw

PATCH 656/690 scsi: qla2xxx: Update manufacturer details

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bikash Hazarika <[email protected]>

[ Upstream commit 1ccad27716ecad1fd58c35e579bedb81fa5e1ad5 ]

Update manufacturer details to indicate Marvell Semiconductors.

Stable-dep-of: 688fa069fda6 ("scsi: qla2xxx: Update manufacturer detail")

---
 drivers/scsi/qla2xxx/qla_def.h | 2 +-
 drivers/scsi/qla2xxx/qla_gs.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)
drivers/scsi/qla2xxx/qla_def.h +1 -1
index 3c876967e8b16..bab890f1110a1 100644
@@ -78,7 +78,7 @@ typedef union {
 #include "qla_nvme.h"
 #define QLA2XXX_DRIVER_NAME	"qla2xxx"
 #define QLA2XXX_APIDEV		"ql2xapidev"
-#define QLA2XXX_MANUFACTURER	"QLogic Corporation"
+#define QLA2XXX_MANUFACTURER	"Marvell Semiconductor, Inc."
 
 /*
  * We have MAILBOX_REGISTER_COUNT sized arrays in a few places,
drivers/scsi/qla2xxx/qla_gs.c +1 -1
index d3742a83d2fd7..b0f3bf42c3405 100644
@@ -1615,7 +1615,7 @@ qla2x00_hba_attributes(scsi_qla_host_t *vha, void *entries,
 	eiter->type = cpu_to_be16(FDMI_HBA_MANUFACTURER);
 	alen = scnprintf(
 		eiter->a.manufacturer, sizeof(eiter->a.manufacturer),
-		"%s", "QLogic Corporation");
+		"%s", QLA2XXX_MANUFACTURER);
 	alen += FDMI_ATTR_ALIGNMENT(alen);
 	alen += FDMI_ATTR_TYPELEN(eiter);
 	eiter->len = cpu_to_be16(alen);
Signature · 1 line
2.43.0
author maintainer
#661 lore raw

PATCH 657/690 scsi: qla2xxx: Update manufacturer detail

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Bikash Hazarika <[email protected]>

[ Upstream commit 688fa069fda6fce24d243cddfe0c7024428acb74 ]

Update manufacturer detail from "Marvell Semiconductor, Inc." to "Marvell".

---
 drivers/scsi/qla2xxx/qla_def.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/scsi/qla2xxx/qla_def.h +1 -1
index bab890f1110a1..87ada9b447170 100644
@@ -78,7 +78,7 @@ typedef union {
 #include "qla_nvme.h"
 #define QLA2XXX_DRIVER_NAME	"qla2xxx"
 #define QLA2XXX_APIDEV		"ql2xapidev"
-#define QLA2XXX_MANUFACTURER	"Marvell Semiconductor, Inc."
+#define QLA2XXX_MANUFACTURER	"Marvell"
 
 /*
  * We have MAILBOX_REGISTER_COUNT sized arrays in a few places,
Signature · 1 line
2.43.0
author maintainer
#662 lore raw

PATCH 658/690 Revert "usb: phy: generic: Get the vbus supply"

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alexander Stein <[email protected]>

[ Upstream commit fdada0db0b2ae2addef4ccafe50937874dbeeebe ]

This reverts commit 75fd6485cccef269ac9eb3b71cf56753341195ef. This patch was applied twice by accident, causing probe failures. Revert the accident.

---
 drivers/usb/phy/phy-generic.c | 7 -------
 1 file changed, 7 deletions(-)
drivers/usb/phy/phy-generic.c +0 -7
index 34b9f81401871..661a229c105dd 100644
@@ -268,13 +268,6 @@ int usb_phy_gen_create_phy(struct device *dev, struct usb_phy_generic *nop)
 			return -EPROBE_DEFER;
 	}
 
-	nop->vbus_draw = devm_regulator_get_exclusive(dev, "vbus");
-	if (PTR_ERR(nop->vbus_draw) == -ENODEV)
-		nop->vbus_draw = NULL;
-	if (IS_ERR(nop->vbus_draw))
-		return dev_err_probe(dev, PTR_ERR(nop->vbus_draw),
-				     "could not get vbus regulator\n");
-
 	nop->dev		= dev;
 	nop->phy.dev		= nop->dev;
 	nop->phy.label		= "nop-xceiv";
Signature · 1 line
2.43.0
author maintainer
#663 lore raw

PATCH 659/690 usb: typec: ucsi: Check for notifications after init

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Christian A. Ehrhardt <[email protected]>

[ Upstream commit 808a8b9e0b87bbc72bcc1f7ddfe5d04746e7ce56 ]

The completion notification for the final SET_NOTIFICATION_ENABLE command during initialization can include a connector change notification. However, at the time this completion notification is processed, the ucsi struct is not ready to handle this notification. As a result the notification is ignored and the controller never sends an interrupt again.

Re-check CCI for a pending connector state change after initialization is complete. Adjust the corresponding debug message accordingly.

---
 drivers/usb/typec/ucsi/ucsi.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)
drivers/usb/typec/ucsi/ucsi.c +9 -1
index 985e512c0e659..df7c42df9ea0d 100644
@@ -854,7 +854,7 @@ void ucsi_connector_change(struct ucsi *ucsi, u8 num)
 	struct ucsi_connector *con = &ucsi->connector[num - 1];
 
 	if (!(ucsi->ntfy & UCSI_ENABLE_NTFY_CONNECTOR_CHANGE)) {
-		dev_dbg(ucsi->dev, "Bogus connector change event\n");
+		dev_dbg(ucsi->dev, "Early connector change event\n");
 		return;
 	}
 
@@ -1241,6 +1241,7 @@ static int ucsi_init(struct ucsi *ucsi)
 {
 	struct ucsi_connector *con;
 	u64 command, ntfy;
+	u32 cci;
 	int ret;
 	int i;
 
@@ -1292,6 +1293,13 @@ static int ucsi_init(struct ucsi *ucsi)
 		goto err_unregister;
 
 	ucsi->ntfy = ntfy;
+
+	ret = ucsi->ops->read(ucsi, UCSI_CCI, &cci, sizeof(cci));
+	if (ret)
+		return ret;
+	if (UCSI_CCI_CONNECTOR(READ_ONCE(cci)))
+		ucsi_connector_change(ucsi, cci);
+
 	return 0;
 
 err_unregister:
Signature · 1 line
2.43.0
author maintainer
#664 lore raw

PATCH 660/690 i40e: Store the irq number in i40e_q_vector

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Joe Damato <[email protected]>

[ Upstream commit 6b85a4f39ff7177b2428d4deab1151a31754e391 ]

Make it easy to figure out the IRQ number for a particular i40e_q_vector by storing the assigned IRQ in the structure itself.

Stable-dep-of: ea558de7238b ("i40e: Enforce software interrupt during busy-poll exit")

---
 drivers/net/ethernet/intel/i40e/i40e.h      | 1 +
 drivers/net/ethernet/intel/i40e/i40e_main.c | 1 +
 2 files changed, 2 insertions(+)
drivers/net/ethernet/intel/i40e/i40e.h +1 -0
index 453a85410634e..7282dfba4122e 100644
@@ -973,6 +973,7 @@ struct i40e_q_vector {
 	struct rcu_head rcu;	/* to avoid race with update stats on free */
 	char name[I40E_INT_NAME_STR_LEN];
 	bool arm_wb_state;
+	int irq_num;		/* IRQ assigned to this q_vector */
 } ____cacheline_internodealigned_in_smp;
 
 /* lan device */
drivers/net/ethernet/intel/i40e/i40e_main.c +1 -0
index a98b1251b561e..d204c33409c68 100644
@@ -4133,6 +4133,7 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename)
 		}
 
 		/* register for affinity change notifications */
+		q_vector->irq_num = irq_num;
 		q_vector->affinity_notify.notify = i40e_irq_affinity_notify;
 		q_vector->affinity_notify.release = i40e_irq_affinity_release;
 		irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify);
Signature · 1 line
2.43.0
author maintainer
#665 lore raw

PATCH 661/690 i40e: Remove _t suffix from enum type names

In reply to Greg Kroah-Hartman

5.15-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ivan Vecera <[email protected]>

[ Upstream commit addca9175e5f74cf29e8ad918c38c09b8663b5b8 ]

Enum type names should not be suffixed by '_t'. Either to use 'typedef enum name name_t' to so plain 'name_t var' instead of 'enum name_t var'.

Stable-dep-of: ea558de7238b ("i40e: Enforce software interrupt during busy-poll exit")

---
 drivers/net/ethernet/intel/i40e/i40e.h      | 4 ++--
 drivers/net/ethernet/intel/i40e/i40e_ptp.c  | 6 +++---
 drivers/net/ethernet/intel/i40e/i40e_txrx.h | 4 ++--
 3 files changed, 7 insertions(+), 7 deletions(-)
drivers/net/ethernet/intel/i40e/i40e.h +2 -2
index 7282dfba4122e..1580f9c2a3209 100644
@@ -108,7 +108,7 @@
 #define I40E_MAX_BW_INACTIVE_ACCUM	4 /* accumulate 4 credits max */
 
 /* driver state flags */
-enum i40e_state_t {
+enum i40e_state {
 	__I40E_TESTING,
 	__I40E_CONFIG_BUSY,
 	__I40E_CONFIG_DONE,
@@ -156,7 +156,7 @@ enum i40e_state_t {
 	BIT_ULL(__I40E_PF_RESET_AND_REBUILD_REQUESTED)
 
 /* VSI state flags */
-enum i40e_vsi_state_t {
+enum i40e_vsi_state {
 	__I40E_VSI_DOWN,
 	__I40E_VSI_NEEDS_RESTART,
 	__I40E_VSI_SYNCING_FILTERS,
drivers/net/ethernet/intel/i40e/i40e_ptp.c +3 -3
index 09b1d5aed1c9f..38942d3f7819b 100644
@@ -35,7 +35,7 @@ enum i40e_ptp_pin {
 	GPIO_4
 };
 
-enum i40e_can_set_pins_t {
+enum i40e_can_set_pins {
 	CANT_DO_PINS = -1,
 	CAN_SET_PINS,
 	CAN_DO_PINS
@@ -193,7 +193,7 @@ static bool i40e_is_ptp_pin_dev(struct i40e_hw *hw)
  * return CAN_DO_PINS if pins can be manipulated within a NIC or
  * return CANT_DO_PINS otherwise.
  **/
-static enum i40e_can_set_pins_t i40e_can_set_pins(struct i40e_pf *pf)
+static enum i40e_can_set_pins i40e_can_set_pins(struct i40e_pf *pf)
 {
 	if (!i40e_is_ptp_pin_dev(&pf->hw)) {
 		dev_warn(&pf->pdev->dev,
@@ -1089,7 +1089,7 @@ static void i40e_ptp_set_pins_hw(struct i40e_pf *pf)
 static int i40e_ptp_set_pins(struct i40e_pf *pf,
 			     struct i40e_ptp_pins_settings *pins)
 {
-	enum i40e_can_set_pins_t pin_caps = i40e_can_set_pins(pf);
+	enum i40e_can_set_pins pin_caps = i40e_can_set_pins(pf);
 	int i = 0;
 
 	if (pin_caps == CANT_DO_PINS)
drivers/net/ethernet/intel/i40e/i40e_txrx.h +2 -2
index f3b0b81517096..a4f38ab0ecca9 100644
@@ -57,7 +57,7 @@ static inline u16 i40e_intrl_usec_to_reg(int intrl)
  * mentioning ITR_INDX, ITR_NONE cannot be used as an index 'n' into any
  * register but instead is a special value meaning "don't update" ITR0/1/2.
  */
-enum i40e_dyn_idx_t {
+enum i40e_dyn_idx {
 	I40E_IDX_ITR0 = 0,
 	I40E_IDX_ITR1 = 1,
 	I40E_IDX_ITR2 = 2,
@@ -301,7 +301,7 @@ struct i40e_rx_queue_stats {
 	u64 realloc_count;
 };
 
-enum i40e_ring_state_t {
+enum i40e_ring_state {
 	__I40E_TX_FDIR_INIT_DONE,
 	__I40E_TX_XPS_INIT_DONE,
 	__I40E_RING_STATE_NBITS /* must be last */
Signature · 1 line
2.43.0