From e509996b16728e37d5a909a5c63c1bd64f23b306 Mon Sep 17 00:00:00 2001
From: Eyal Birger <eyal.birger@gmail.com>
Date: Mon, 2 Sep 2024 17:07:09 -0700
Subject: xfrm: extract dst lookup parameters into a struct

Preparation for adding more fields to dst lookup functions without
changing their signatures.

Signed-off-by: Eyal Birger <eyal.birger@gmail.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index b6bfdc6416c7..f3ae50372707 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -349,20 +349,23 @@ struct xfrm_if_cb {
 void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb);
 void xfrm_if_unregister_cb(void);
 
+struct xfrm_dst_lookup_params {
+	struct net *net;
+	int tos;
+	int oif;
+	xfrm_address_t *saddr;
+	xfrm_address_t *daddr;
+	u32 mark;
+};
+
 struct net_device;
 struct xfrm_type;
 struct xfrm_dst;
 struct xfrm_policy_afinfo {
 	struct dst_ops		*dst_ops;
-	struct dst_entry	*(*dst_lookup)(struct net *net,
-					       int tos, int oif,
-					       const xfrm_address_t *saddr,
-					       const xfrm_address_t *daddr,
-					       u32 mark);
-	int			(*get_saddr)(struct net *net, int oif,
-					     xfrm_address_t *saddr,
-					     xfrm_address_t *daddr,
-					     u32 mark);
+	struct dst_entry	*(*dst_lookup)(const struct xfrm_dst_lookup_params *params);
+	int			(*get_saddr)(xfrm_address_t *saddr,
+					     const struct xfrm_dst_lookup_params *params);
 	int			(*fill_dst)(struct xfrm_dst *xdst,
 					    struct net_device *dev,
 					    const struct flowi *fl);
@@ -1764,10 +1767,7 @@ static inline int xfrm_user_policy(struct sock *sk, int optname,
 }
 #endif
 
-struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif,
-				    const xfrm_address_t *saddr,
-				    const xfrm_address_t *daddr,
-				    int family, u32 mark);
+struct dst_entry *__xfrm_dst_lookup(int family, const struct xfrm_dst_lookup_params *params);
 
 struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp);
 
-- 
cgit v1.2.3


From b8469721034300bbb6dec5b4bf32492c95e16a0c Mon Sep 17 00:00:00 2001
From: Eyal Birger <eyal.birger@gmail.com>
Date: Mon, 2 Sep 2024 17:07:10 -0700
Subject: xfrm: respect ip protocols rules criteria when performing dst lookups

The series in the "fixes" tag added the ability to consider L4 attributes
in routing rules.

The dst lookup on the outer packet of encapsulated traffic in the xfrm
code was not adapted to this change, thus routing behavior that relies
on L4 information is not respected.

Pass the ip protocol information when performing dst lookups.

Fixes: a25724b05af0 ("Merge branch 'fib_rules-support-sport-dport-and-proto-match'")
Signed-off-by: Eyal Birger <eyal.birger@gmail.com>
Tested-by: Antony Antony <antony.antony@secunet.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h      |  2 ++
 net/ipv4/xfrm4_policy.c |  2 ++
 net/ipv6/xfrm6_policy.c |  3 +++
 net/xfrm/xfrm_policy.c  | 15 +++++++++++++++
 4 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index f3ae50372707..a0bdd58f401c 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -356,6 +356,8 @@ struct xfrm_dst_lookup_params {
 	xfrm_address_t *saddr;
 	xfrm_address_t *daddr;
 	u32 mark;
+	__u8 ipproto;
+	union flowi_uli uli;
 };
 
 struct net_device;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index ac1a28ef0c56..7e1c2faed1ff 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -30,6 +30,8 @@ static struct dst_entry *__xfrm4_dst_lookup(struct flowi4 *fl4,
 	fl4->flowi4_mark = params->mark;
 	if (params->saddr)
 		fl4->saddr = params->saddr->a4;
+	fl4->flowi4_proto = params->ipproto;
+	fl4->uli = params->uli;
 
 	rt = __ip_route_output_key(params->net, fl4);
 	if (!IS_ERR(rt))
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index fc3f5eec6898..1f19b6f14484 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -37,6 +37,9 @@ static struct dst_entry *xfrm6_dst_lookup(const struct xfrm_dst_lookup_params *p
 	if (params->saddr)
 		memcpy(&fl6.saddr, params->saddr, sizeof(fl6.saddr));
 
+	fl6.flowi4_proto = params->ipproto;
+	fl6.uli = params->uli;
+
 	dst = ip6_route_output(params->net, NULL, &fl6);
 
 	err = dst->error;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index ec8f2fe13a51..55cc9f4cb42b 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -315,6 +315,21 @@ static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x,
 	params.tos = tos;
 	params.oif = oif;
 	params.mark = mark;
+	params.ipproto = x->id.proto;
+	if (x->encap) {
+		switch (x->encap->encap_type) {
+		case UDP_ENCAP_ESPINUDP:
+			params.ipproto = IPPROTO_UDP;
+			params.uli.ports.sport = x->encap->encap_sport;
+			params.uli.ports.dport = x->encap->encap_dport;
+			break;
+		case TCP_ENCAP_ESPINTCP:
+			params.ipproto = IPPROTO_TCP;
+			params.uli.ports.sport = x->encap->encap_sport;
+			params.uli.ports.dport = x->encap->encap_dport;
+			break;
+		}
+	}
 
 	dst = __xfrm_dst_lookup(family, &params);
 
-- 
cgit v1.2.3


From 645546a05b0370391c0eac0f14f5b9ddf8d00731 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 18 Sep 2024 11:12:49 +0200
Subject: xfrm: policy: remove last remnants of pernet inexact list

xfrm_net still contained the no-longer-used inexact policy list heads,
remove them.

Fixes: a54ad727f745 ("xfrm: policy: remove remaining use of inexact list")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/netns/xfrm.h | 1 -
 net/xfrm/xfrm_policy.c   | 3 ---
 2 files changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index d489d9250bff..ae60d6664095 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -51,7 +51,6 @@ struct netns_xfrm {
 	struct hlist_head	*policy_byidx;
 	unsigned int		policy_idx_hmask;
 	unsigned int		idx_generator;
-	struct hlist_head	policy_inexact[XFRM_POLICY_MAX];
 	struct xfrm_policy_hash	policy_bydst[XFRM_POLICY_MAX];
 	unsigned int		policy_count[XFRM_POLICY_MAX * 2];
 	struct work_struct	policy_hash_work;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 55cc9f4cb42b..a2ea9dbac90b 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -4206,7 +4206,6 @@ static int __net_init xfrm_policy_init(struct net *net)
 
 		net->xfrm.policy_count[dir] = 0;
 		net->xfrm.policy_count[XFRM_POLICY_MAX + dir] = 0;
-		INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]);
 
 		htab = &net->xfrm.policy_bydst[dir];
 		htab->table = xfrm_hash_alloc(sz);
@@ -4260,8 +4259,6 @@ static void xfrm_policy_fini(struct net *net)
 	for (dir = 0; dir < XFRM_POLICY_MAX; dir++) {
 		struct xfrm_policy_hash *htab;
 
-		WARN_ON(!hlist_empty(&net->xfrm.policy_inexact[dir]));
-
 		htab = &net->xfrm.policy_bydst[dir];
 		sz = (htab->hmask + 1) * sizeof(struct hlist_head);
 		WARN_ON(!hlist_empty(htab->table));
-- 
cgit v1.2.3


From 796a4049640b54cb1daf9e7fe543292c5ca02c74 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 4 Oct 2024 15:33:58 +0100
Subject: netfs: In readahead, put the folio refs as soon extracted

netfslib currently defers dropping the ref on the folios it obtains during
readahead to after it has started I/O on the basis that we can do it whilst
we wait for the I/O to complete, but this runs the risk of the I/O
collection racing with this in future.

Furthermore, Matthew Wilcox strongly suggests that the refs should be
dropped immediately, as readahead_folio() does (netfslib is using
__readahead_batch() which doesn't drop the refs).

Fixes: ee4cdf7ba857 ("netfs: Speed up buffered reading")
Suggested-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/r/3771538.1728052438@warthog.procyon.org.uk
cc: Jeff Layton <jlayton@kernel.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/buffered_read.c     | 47 +++++++++++++-------------------------------
 fs/netfs/read_collect.c      |  2 ++
 include/trace/events/netfs.h |  1 -
 3 files changed, 16 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
index c40e226053cc..af46a598f4d7 100644
--- a/fs/netfs/buffered_read.c
+++ b/fs/netfs/buffered_read.c
@@ -67,7 +67,8 @@ static int netfs_begin_cache_read(struct netfs_io_request *rreq, struct netfs_in
  * Decant the list of folios to read into a rolling buffer.
  */
 static size_t netfs_load_buffer_from_ra(struct netfs_io_request *rreq,
-					struct folio_queue *folioq)
+					struct folio_queue *folioq,
+					struct folio_batch *put_batch)
 {
 	unsigned int order, nr;
 	size_t size = 0;
@@ -82,6 +83,9 @@ static size_t netfs_load_buffer_from_ra(struct netfs_io_request *rreq,
 		order = folio_order(folio);
 		folioq->orders[i] = order;
 		size += PAGE_SIZE << order;
+
+		if (!folio_batch_add(put_batch, folio))
+			folio_batch_release(put_batch);
 	}
 
 	for (int i = nr; i < folioq_nr_slots(folioq); i++)
@@ -120,6 +124,9 @@ static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq)
 		 * that we will need to release later - but we don't want to do
 		 * that until after we've started the I/O.
 		 */
+		struct folio_batch put_batch;
+
+		folio_batch_init(&put_batch);
 		while (rreq->submitted < subreq->start + rsize) {
 			struct folio_queue *tail = rreq->buffer_tail, *new;
 			size_t added;
@@ -132,10 +139,11 @@ static ssize_t netfs_prepare_read_iterator(struct netfs_io_subrequest *subreq)
 			new->prev = tail;
 			tail->next = new;
 			rreq->buffer_tail = new;
-			added = netfs_load_buffer_from_ra(rreq, new);
+			added = netfs_load_buffer_from_ra(rreq, new, &put_batch);
 			rreq->iter.count += added;
 			rreq->submitted += added;
 		}
+		folio_batch_release(&put_batch);
 	}
 
 	subreq->len = rsize;
@@ -348,6 +356,7 @@ static int netfs_wait_for_read(struct netfs_io_request *rreq)
 static int netfs_prime_buffer(struct netfs_io_request *rreq)
 {
 	struct folio_queue *folioq;
+	struct folio_batch put_batch;
 	size_t added;
 
 	folioq = kmalloc(sizeof(*folioq), GFP_KERNEL);
@@ -360,39 +369,14 @@ static int netfs_prime_buffer(struct netfs_io_request *rreq)
 	rreq->submitted = rreq->start;
 	iov_iter_folio_queue(&rreq->iter, ITER_DEST, folioq, 0, 0, 0);
 
-	added = netfs_load_buffer_from_ra(rreq, folioq);
+	folio_batch_init(&put_batch);
+	added = netfs_load_buffer_from_ra(rreq, folioq, &put_batch);
+	folio_batch_release(&put_batch);
 	rreq->iter.count += added;
 	rreq->submitted += added;
 	return 0;
 }
 
-/*
- * Drop the ref on each folio that we inherited from the VM readahead code.  We
- * still have the folio locks to pin the page until we complete the I/O.
- *
- * Note that we can't just release the batch in each queue struct as we use the
- * occupancy count in other places.
- */
-static void netfs_put_ra_refs(struct folio_queue *folioq)
-{
-	struct folio_batch fbatch;
-
-	folio_batch_init(&fbatch);
-	while (folioq) {
-		for (unsigned int slot = 0; slot < folioq_count(folioq); slot++) {
-			struct folio *folio = folioq_folio(folioq, slot);
-			if (!folio)
-				continue;
-			trace_netfs_folio(folio, netfs_folio_trace_read_put);
-			if (!folio_batch_add(&fbatch, folio))
-				folio_batch_release(&fbatch);
-		}
-		folioq = folioq->next;
-	}
-
-	folio_batch_release(&fbatch);
-}
-
 /**
  * netfs_readahead - Helper to manage a read request
  * @ractl: The description of the readahead request
@@ -436,9 +420,6 @@ void netfs_readahead(struct readahead_control *ractl)
 		goto cleanup_free;
 	netfs_read_to_pagecache(rreq);
 
-	/* Release the folio refs whilst we're waiting for the I/O. */
-	netfs_put_ra_refs(rreq->buffer);
-
 	netfs_put_request(rreq, true, netfs_rreq_trace_put_return);
 	return;
 
diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c
index b18c65ba5580..3cbb289535a8 100644
--- a/fs/netfs/read_collect.c
+++ b/fs/netfs/read_collect.c
@@ -77,6 +77,8 @@ static void netfs_unlock_read_folio(struct netfs_io_subrequest *subreq,
 			folio_unlock(folio);
 		}
 	}
+
+	folioq_clear(folioq, slot);
 }
 
 /*
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 1d7c52821e55..69975c9c6823 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -172,7 +172,6 @@
 	EM(netfs_folio_trace_read,		"read")		\
 	EM(netfs_folio_trace_read_done,		"read-done")	\
 	EM(netfs_folio_trace_read_gaps,		"read-gaps")	\
-	EM(netfs_folio_trace_read_put,		"read-put")	\
 	EM(netfs_folio_trace_read_unlock,	"read-unlock")	\
 	EM(netfs_folio_trace_redirtied,		"redirtied")	\
 	EM(netfs_folio_trace_store,		"store")	\
-- 
cgit v1.2.3


From 6ef6a0e821d3dad6bf8a5d5508762dba9042c84b Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <djwong@kernel.org>
Date: Thu, 3 Oct 2024 08:09:16 -0700
Subject: iomap: share iomap_unshare_iter predicate code with fsdax

The predicate code that iomap_unshare_iter uses to decide if it's really
needs to unshare a file range mapping should be shared with the fsdax
version, because right now they're opencoded and inconsistent.

Note that we simplify the predicate logic a bit -- we no longer allow
unsharing of inline data mappings, but there aren't any filesystems that
allow shared inline data currently.

This is a fix in the sense that it should have been ported to fsdax.

Fixes: b53fdb215d13 ("iomap: improve shared block detection in iomap_unshare_iter")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Link: https://lore.kernel.org/r/172796813294.1131942.15762084021076932620.stgit@frogsfrogsfrogs
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/dax.c               |  3 +--
 fs/iomap/buffered-io.c | 30 ++++++++++++++++--------------
 include/linux/iomap.h  |  1 +
 3 files changed, 18 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/fs/dax.c b/fs/dax.c
index c62acd2812f8..5064eefb1c1e 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1268,8 +1268,7 @@ static s64 dax_unshare_iter(struct iomap_iter *iter)
 	s64 ret = 0;
 	void *daddr = NULL, *saddr = NULL;
 
-	/* don't bother with blocks that are not shared to start with */
-	if (!(iomap->flags & IOMAP_F_SHARED))
+	if (!iomap_want_unshare_iter(iter))
 		return length;
 
 	id = dax_read_lock();
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 78ebd265f425..3899169b2cf7 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1309,19 +1309,12 @@ void iomap_file_buffered_write_punch_delalloc(struct inode *inode,
 }
 EXPORT_SYMBOL_GPL(iomap_file_buffered_write_punch_delalloc);
 
-static loff_t iomap_unshare_iter(struct iomap_iter *iter)
+bool iomap_want_unshare_iter(const struct iomap_iter *iter)
 {
-	struct iomap *iomap = &iter->iomap;
-	loff_t pos = iter->pos;
-	loff_t length = iomap_length(iter);
-	loff_t written = 0;
-
-	/* Don't bother with blocks that are not shared to start with. */
-	if (!(iomap->flags & IOMAP_F_SHARED))
-		return length;
-
 	/*
-	 * Don't bother with delalloc reservations, holes or unwritten extents.
+	 * Don't bother with blocks that are not shared to start with; or
+	 * mappings that cannot be shared, such as inline data, delalloc
+	 * reservations, holes or unwritten extents.
 	 *
 	 * Note that we use srcmap directly instead of iomap_iter_srcmap as
 	 * unsharing requires providing a separate source map, and the presence
@@ -1329,9 +1322,18 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter)
 	 * IOMAP_F_SHARED which can be set for any data that goes into the COW
 	 * fork for XFS.
 	 */
-	if (iter->srcmap.type == IOMAP_HOLE ||
-	    iter->srcmap.type == IOMAP_DELALLOC ||
-	    iter->srcmap.type == IOMAP_UNWRITTEN)
+	return (iter->iomap.flags & IOMAP_F_SHARED) &&
+		iter->srcmap.type == IOMAP_MAPPED;
+}
+
+static loff_t iomap_unshare_iter(struct iomap_iter *iter)
+{
+	struct iomap *iomap = &iter->iomap;
+	loff_t pos = iter->pos;
+	loff_t length = iomap_length(iter);
+	loff_t written = 0;
+
+	if (!iomap_want_unshare_iter(iter))
 		return length;
 
 	do {
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 4ad12a3c8bae..d8a7fc84348c 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -267,6 +267,7 @@ void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len);
 bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio);
 int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 		const struct iomap_ops *ops);
+bool iomap_want_unshare_iter(const struct iomap_iter *iter);
 int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
 		bool *did_zero, const struct iomap_ops *ops);
 int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
-- 
cgit v1.2.3


From 68d0021fe7231eec0fb84cd110cf62a6e782b72d Mon Sep 17 00:00:00 2001
From: Remi Pommarel <repk@triplefau.lt>
Date: Tue, 24 Sep 2024 21:28:04 +0200
Subject: wifi: cfg80211: Add wiphy_delayed_work_pending()

Add wiphy_delayed_work_pending() to check if any delayed work timer is
pending, that can be used to be sure that wiphy_delayed_work_queue()
won't postpone an already pending delayed work.

Signed-off-by: Remi Pommarel <repk@triplefau.lt>
Link: https://patch.msgid.link/20240924192805.13859-2-repk@triplefau.lt
[fix return value kernel-doc]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 44 ++++++++++++++++++++++++++++++++++++++++++++
 net/wireless/core.c    |  7 +++++++
 2 files changed, 51 insertions(+)

(limited to 'include')

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 69ec1eb41a09..941dc62f3027 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -6129,6 +6129,50 @@ void wiphy_delayed_work_cancel(struct wiphy *wiphy,
 void wiphy_delayed_work_flush(struct wiphy *wiphy,
 			      struct wiphy_delayed_work *dwork);
 
+/**
+ * wiphy_delayed_work_pending - Find out whether a wiphy delayable
+ * work item is currently pending.
+ *
+ * @wiphy: the wiphy, for debug purposes
+ * @dwork: the delayed work in question
+ *
+ * Return: true if timer is pending, false otherwise
+ *
+ * How wiphy_delayed_work_queue() works is by setting a timer which
+ * when it expires calls wiphy_work_queue() to queue the wiphy work.
+ * Because wiphy_delayed_work_queue() uses mod_timer(), if it is
+ * called twice and the second call happens before the first call
+ * deadline, the work will rescheduled for the second deadline and
+ * won't run before that.
+ *
+ * wiphy_delayed_work_pending() can be used to detect if calling
+ * wiphy_work_delayed_work_queue() would start a new work schedule
+ * or delayed a previous one. As seen below it cannot be used to
+ * detect precisely if the work has finished to execute nor if it
+ * is currently executing.
+ *
+ *      CPU0                                CPU1
+ * wiphy_delayed_work_queue(wk)
+ *  mod_timer(wk->timer)
+ *                                     wiphy_delayed_work_pending(wk) -> true
+ *
+ * [...]
+ * expire_timers(wk->timer)
+ *  detach_timer(wk->timer)
+ *                                     wiphy_delayed_work_pending(wk) -> false
+ *  wk->timer->function()                          |
+ *   wiphy_work_queue(wk)                          | delayed work pending
+ *    list_add_tail()                              | returns false but
+ *    queue_work(cfg80211_wiphy_work)              | wk->func() has not
+ *                                                 | been run yet
+ * [...]                                           |
+ *  cfg80211_wiphy_work()                          |
+ *   wk->func()                                    V
+ *
+ */
+bool wiphy_delayed_work_pending(struct wiphy *wiphy,
+				struct wiphy_delayed_work *dwork);
+
 /**
  * enum ieee80211_ap_reg_power - regulatory power for an Access Point
  *
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 661adfc77644..8331064de9dd 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1704,6 +1704,13 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy,
 }
 EXPORT_SYMBOL_GPL(wiphy_delayed_work_flush);
 
+bool wiphy_delayed_work_pending(struct wiphy *wiphy,
+				struct wiphy_delayed_work *dwork)
+{
+	return timer_pending(&dwork->timer);
+}
+EXPORT_SYMBOL_GPL(wiphy_delayed_work_pending);
+
 static int __init cfg80211_init(void)
 {
 	int err;
-- 
cgit v1.2.3


From 57be3d3562ca4aa62b8047bc681028cc402af8ce Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Fri, 4 Oct 2024 14:14:44 -0600
Subject: wifi: radiotap: Avoid -Wflex-array-member-not-at-end warnings

-Wflex-array-member-not-at-end was introduced in GCC-14, and we are
getting ready to enable it, globally.

So, in order to avoid ending up with a flexible-array member in the
middle of multiple other structs, we use the `__struct_group()`
helper to create a new tagged `struct ieee80211_radiotap_header_fixed`.
This structure groups together all the members of the flexible
`struct ieee80211_radiotap_header` except the flexible array.

As a result, the array is effectively separated from the rest of the
members without modifying the memory layout of the flexible structure.
We then change the type of the middle struct members currently causing
trouble from `struct ieee80211_radiotap_header` to `struct
ieee80211_radiotap_header_fixed`.

We also want to ensure that in case new members need to be added to the
flexible structure, they are always included within the newly created
tagged struct. For this, we use `static_assert()`. This ensures that the
memory layout for both the flexible structure and the new tagged struct
is the same after any changes.

This approach avoids having to implement `struct ieee80211_radiotap_header_fixed`
as a completely separate structure, thus preventing having to maintain
two independent but basically identical structures, closing the door
to potential bugs in the future.

So, with these changes, fix the following warnings:
drivers/net/wireless/ath/wil6210/txrx.c:309:50: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/ipw2x00/ipw2100.c:2521:50: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/ipw2x00/ipw2200.h:1146:42: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/ipw2x00/libipw.h:595:36: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/marvell/libertas/radiotap.h:34:42: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/marvell/libertas/radiotap.h:5:42: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/microchip/wilc1000/mon.c:10:42: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/microchip/wilc1000/mon.c:15:42: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/virtual/mac80211_hwsim.c:758:42: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/virtual/mac80211_hwsim.c:767:42: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://patch.msgid.link/ZwBMtBZKcrzwU7l4@kspp
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/ath/wil6210/txrx.c          |  2 +-
 drivers/net/wireless/intel/ipw2x00/ipw2100.c     |  2 +-
 drivers/net/wireless/intel/ipw2x00/ipw2200.h     |  2 +-
 drivers/net/wireless/marvell/libertas/radiotap.h |  4 +--
 drivers/net/wireless/microchip/wilc1000/mon.c    |  4 +--
 drivers/net/wireless/virtual/mac80211_hwsim.c    |  4 +--
 include/net/ieee80211_radiotap.h                 | 43 +++++++++++++-----------
 7 files changed, 33 insertions(+), 28 deletions(-)

(limited to 'include')

diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index f29ac6de7139..19702b6f09c3 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -306,7 +306,7 @@ static void wil_rx_add_radiotap_header(struct wil6210_priv *wil,
 				       struct sk_buff *skb)
 {
 	struct wil6210_rtap {
-		struct ieee80211_radiotap_header rthdr;
+		struct ieee80211_radiotap_header_fixed rthdr;
 		/* fields should be in the order of bits in rthdr.it_present */
 		/* flags */
 		u8 flags;
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2100.c b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
index b6636002c7d2..fe75941c584d 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
@@ -2518,7 +2518,7 @@ static void isr_rx_monitor(struct ipw2100_priv *priv, int i,
 	 * to build this manually element by element, we can write it much
 	 * more efficiently than we can parse it. ORDER MATTERS HERE */
 	struct ipw_rt_hdr {
-		struct ieee80211_radiotap_header rt_hdr;
+		struct ieee80211_radiotap_header_fixed rt_hdr;
 		s8 rt_dbmsignal; /* signal in dbM, kluged to signed */
 	} *ipw_rt;
 
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.h b/drivers/net/wireless/intel/ipw2x00/ipw2200.h
index 8ebf09121e17..226286cb7eb8 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2200.h
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.h
@@ -1143,7 +1143,7 @@ struct ipw_prom_priv {
  * structure is provided regardless of any bits unset.
  */
 struct ipw_rt_hdr {
-	struct ieee80211_radiotap_header rt_hdr;
+	struct ieee80211_radiotap_header_fixed rt_hdr;
 	u64 rt_tsf;      /* TSF */	/* XXX */
 	u8 rt_flags;	/* radiotap packet flags */
 	u8 rt_rate;	/* rate in 500kb/s */
diff --git a/drivers/net/wireless/marvell/libertas/radiotap.h b/drivers/net/wireless/marvell/libertas/radiotap.h
index 1ed5608d353f..d543bfe739dc 100644
--- a/drivers/net/wireless/marvell/libertas/radiotap.h
+++ b/drivers/net/wireless/marvell/libertas/radiotap.h
@@ -2,7 +2,7 @@
 #include <net/ieee80211_radiotap.h>
 
 struct tx_radiotap_hdr {
-	struct ieee80211_radiotap_header hdr;
+	struct ieee80211_radiotap_header_fixed hdr;
 	u8 rate;
 	u8 txpower;
 	u8 rts_retries;
@@ -31,7 +31,7 @@ struct tx_radiotap_hdr {
 #define IEEE80211_FC_DSTODS          0x0300
 
 struct rx_radiotap_hdr {
-	struct ieee80211_radiotap_header hdr;
+	struct ieee80211_radiotap_header_fixed hdr;
 	u8 flags;
 	u8 rate;
 	u8 antsignal;
diff --git a/drivers/net/wireless/microchip/wilc1000/mon.c b/drivers/net/wireless/microchip/wilc1000/mon.c
index 03b7229a0ff5..c3d27aaec297 100644
--- a/drivers/net/wireless/microchip/wilc1000/mon.c
+++ b/drivers/net/wireless/microchip/wilc1000/mon.c
@@ -7,12 +7,12 @@
 #include "cfg80211.h"
 
 struct wilc_wfi_radiotap_hdr {
-	struct ieee80211_radiotap_header hdr;
+	struct ieee80211_radiotap_header_fixed hdr;
 	u8 rate;
 } __packed;
 
 struct wilc_wfi_radiotap_cb_hdr {
-	struct ieee80211_radiotap_header hdr;
+	struct ieee80211_radiotap_header_fixed hdr;
 	u8 rate;
 	u8 dump;
 	u16 tx_flags;
diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c
index f0e528abb1b4..3f424f14de4e 100644
--- a/drivers/net/wireless/virtual/mac80211_hwsim.c
+++ b/drivers/net/wireless/virtual/mac80211_hwsim.c
@@ -763,7 +763,7 @@ static const struct rhashtable_params hwsim_rht_params = {
 };
 
 struct hwsim_radiotap_hdr {
-	struct ieee80211_radiotap_header hdr;
+	struct ieee80211_radiotap_header_fixed hdr;
 	__le64 rt_tsft;
 	u8 rt_flags;
 	u8 rt_rate;
@@ -772,7 +772,7 @@ struct hwsim_radiotap_hdr {
 } __packed;
 
 struct hwsim_radiotap_ack_hdr {
-	struct ieee80211_radiotap_header hdr;
+	struct ieee80211_radiotap_header_fixed hdr;
 	u8 rt_flags;
 	u8 pad;
 	__le16 rt_channel;
diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h
index 91762faecc13..1458d3695005 100644
--- a/include/net/ieee80211_radiotap.h
+++ b/include/net/ieee80211_radiotap.h
@@ -24,25 +24,27 @@
  * struct ieee80211_radiotap_header - base radiotap header
  */
 struct ieee80211_radiotap_header {
-	/**
-	 * @it_version: radiotap version, always 0
-	 */
-	uint8_t it_version;
-
-	/**
-	 * @it_pad: padding (or alignment)
-	 */
-	uint8_t it_pad;
-
-	/**
-	 * @it_len: overall radiotap header length
-	 */
-	__le16 it_len;
-
-	/**
-	 * @it_present: (first) present word
-	 */
-	__le32 it_present;
+	__struct_group(ieee80211_radiotap_header_fixed, hdr, __packed,
+		/**
+		 * @it_version: radiotap version, always 0
+		 */
+		uint8_t it_version;
+
+		/**
+		 * @it_pad: padding (or alignment)
+		 */
+		uint8_t it_pad;
+
+		/**
+		 * @it_len: overall radiotap header length
+		 */
+		__le16 it_len;
+
+		/**
+		 * @it_present: (first) present word
+		 */
+		__le32 it_present;
+	);
 
 	/**
 	 * @it_optional: all remaining presence bitmaps
@@ -50,6 +52,9 @@ struct ieee80211_radiotap_header {
 	__le32 it_optional[];
 } __packed;
 
+static_assert(offsetof(struct ieee80211_radiotap_header, it_optional) == sizeof(struct ieee80211_radiotap_header_fixed),
+	      "struct member likely outside of __struct_group()");
+
 /* version is always 0 */
 #define PKTHDR_RADIOTAP_VERSION	0
 
-- 
cgit v1.2.3


From 9eb2142a2ae8c8fdfce2aaa4c110f5a6f6b0b56e Mon Sep 17 00:00:00 2001
From: Amadeusz Sławiński <amadeuszx.slawinski@linux.intel.com>
Date: Wed, 9 Oct 2024 10:12:30 +0200
Subject: ASoC: topology: Bump minimal topology ABI version
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When v4 topology support was removed, minimal topology ABI version
should have been bumped.

Fixes: fe4a07454256 ("ASoC: Drop soc-topology ABI v4 support")
Reviewed-by: Cezary Rojewski <cezary.rojewski@intel.com>
Signed-off-by: Amadeusz Sławiński <amadeuszx.slawinski@linux.intel.com>
Link: https://patch.msgid.link/20241009081230.304918-1-amadeuszx.slawinski@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/uapi/sound/asoc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h
index 99333cbd3114..c117672d4439 100644
--- a/include/uapi/sound/asoc.h
+++ b/include/uapi/sound/asoc.h
@@ -88,7 +88,7 @@
 
 /* ABI version */
 #define SND_SOC_TPLG_ABI_VERSION	0x5	/* current version */
-#define SND_SOC_TPLG_ABI_VERSION_MIN	0x4	/* oldest version supported */
+#define SND_SOC_TPLG_ABI_VERSION_MIN	0x5	/* oldest version supported */
 
 /* Max size of TLV data */
 #define SND_SOC_TPLG_TLV_SIZE		32
-- 
cgit v1.2.3


From bb94f56b9cfa4a946a43492b2a13ecb5b9b571bc Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Tue, 15 Oct 2024 08:53:29 +0200
Subject: fbdev: da8xx: remove the driver

This driver is no longer used on any platform. It has been replaced by
tilcdc on the two DaVinci boards we still support and can be removed.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Acked-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 drivers/video/fbdev/Kconfig    |   13 -
 drivers/video/fbdev/Makefile   |    1 -
 drivers/video/fbdev/da8xx-fb.c | 1665 ----------------------------------------
 include/video/da8xx-fb.h       |   94 ---
 4 files changed, 1773 deletions(-)
 delete mode 100644 drivers/video/fbdev/da8xx-fb.c
 delete mode 100644 include/video/da8xx-fb.h

(limited to 'include')

diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig
index 44a8fdbab6df..77b50579bd09 100644
--- a/drivers/video/fbdev/Kconfig
+++ b/drivers/video/fbdev/Kconfig
@@ -1659,19 +1659,6 @@ config FB_SH7760
 	  and 8, 15 or 16 bpp color; 90 degrees clockwise display rotation for
 	  panels <= 320 pixel horizontal resolution.
 
-config FB_DA8XX
-	tristate "DA8xx/OMAP-L1xx/AM335x Framebuffer support"
-	depends on FB && HAVE_CLK && HAS_IOMEM
-	depends on ARCH_DAVINCI_DA8XX || SOC_AM33XX || COMPILE_TEST
-	select FB_CFB_REV_PIXELS_IN_BYTE
-	select FB_IOMEM_HELPERS
-	select FB_MODE_HELPERS
-	select VIDEOMODE_HELPERS
-	help
-	  This is the frame buffer device driver for the TI LCD controller
-	  found on DA8xx/OMAP-L1xx/AM335x SoCs.
-	  If unsure, say N.
-
 config FB_VIRTUAL
 	tristate "Virtual Frame Buffer support (ONLY FOR TESTING!)"
 	depends on FB
diff --git a/drivers/video/fbdev/Makefile b/drivers/video/fbdev/Makefile
index 3eecd51267fa..b3d12f977c06 100644
--- a/drivers/video/fbdev/Makefile
+++ b/drivers/video/fbdev/Makefile
@@ -121,7 +121,6 @@ obj-$(CONFIG_FB_VESA)             += vesafb.o
 obj-$(CONFIG_FB_EFI)              += efifb.o
 obj-$(CONFIG_FB_VGA16)            += vga16fb.o
 obj-$(CONFIG_FB_OF)               += offb.o
-obj-$(CONFIG_FB_DA8XX)		  += da8xx-fb.o
 obj-$(CONFIG_FB_SSD1307)	  += ssd1307fb.o
 obj-$(CONFIG_FB_SIMPLE)           += simplefb.o
 
diff --git a/drivers/video/fbdev/da8xx-fb.c b/drivers/video/fbdev/da8xx-fb.c
deleted file mode 100644
index fad1e13c6332..000000000000
--- a/drivers/video/fbdev/da8xx-fb.c
+++ /dev/null
@@ -1,1665 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2008-2009 MontaVista Software Inc.
- * Copyright (C) 2008-2009 Texas Instruments Inc
- *
- * Based on the LCD driver for TI Avalanche processors written by
- * Ajay Singh and Shalom Hai.
- */
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/fb.h>
-#include <linux/dma-mapping.h>
-#include <linux/device.h>
-#include <linux/platform_device.h>
-#include <linux/uaccess.h>
-#include <linux/pm_runtime.h>
-#include <linux/interrupt.h>
-#include <linux/wait.h>
-#include <linux/clk.h>
-#include <linux/cpufreq.h>
-#include <linux/console.h>
-#include <linux/regulator/consumer.h>
-#include <linux/spinlock.h>
-#include <linux/slab.h>
-#include <linux/delay.h>
-#include <linux/lcm.h>
-#include <video/da8xx-fb.h>
-#include <asm/div64.h>
-
-#define DRIVER_NAME "da8xx_lcdc"
-
-#define LCD_VERSION_1	1
-#define LCD_VERSION_2	2
-
-/* LCD Status Register */
-#define LCD_END_OF_FRAME1		BIT(9)
-#define LCD_END_OF_FRAME0		BIT(8)
-#define LCD_PL_LOAD_DONE		BIT(6)
-#define LCD_FIFO_UNDERFLOW		BIT(5)
-#define LCD_SYNC_LOST			BIT(2)
-#define LCD_FRAME_DONE			BIT(0)
-
-/* LCD DMA Control Register */
-#define LCD_DMA_BURST_SIZE(x)		((x) << 4)
-#define LCD_DMA_BURST_1			0x0
-#define LCD_DMA_BURST_2			0x1
-#define LCD_DMA_BURST_4			0x2
-#define LCD_DMA_BURST_8			0x3
-#define LCD_DMA_BURST_16		0x4
-#define LCD_V1_END_OF_FRAME_INT_ENA	BIT(2)
-#define LCD_V2_END_OF_FRAME0_INT_ENA	BIT(8)
-#define LCD_V2_END_OF_FRAME1_INT_ENA	BIT(9)
-#define LCD_DUAL_FRAME_BUFFER_ENABLE	BIT(0)
-
-/* LCD Control Register */
-#define LCD_CLK_DIVISOR(x)		((x) << 8)
-#define LCD_RASTER_MODE			0x01
-
-/* LCD Raster Control Register */
-#define LCD_PALETTE_LOAD_MODE(x)	((x) << 20)
-#define PALETTE_AND_DATA		0x00
-#define PALETTE_ONLY			0x01
-#define DATA_ONLY			0x02
-
-#define LCD_MONO_8BIT_MODE		BIT(9)
-#define LCD_RASTER_ORDER		BIT(8)
-#define LCD_TFT_MODE			BIT(7)
-#define LCD_V1_UNDERFLOW_INT_ENA	BIT(6)
-#define LCD_V2_UNDERFLOW_INT_ENA	BIT(5)
-#define LCD_V1_PL_INT_ENA		BIT(4)
-#define LCD_V2_PL_INT_ENA		BIT(6)
-#define LCD_MONOCHROME_MODE		BIT(1)
-#define LCD_RASTER_ENABLE		BIT(0)
-#define LCD_TFT_ALT_ENABLE		BIT(23)
-#define LCD_STN_565_ENABLE		BIT(24)
-#define LCD_V2_DMA_CLK_EN		BIT(2)
-#define LCD_V2_LIDD_CLK_EN		BIT(1)
-#define LCD_V2_CORE_CLK_EN		BIT(0)
-#define LCD_V2_LPP_B10			26
-#define LCD_V2_TFT_24BPP_MODE		BIT(25)
-#define LCD_V2_TFT_24BPP_UNPACK		BIT(26)
-
-/* LCD Raster Timing 2 Register */
-#define LCD_AC_BIAS_TRANSITIONS_PER_INT(x)	((x) << 16)
-#define LCD_AC_BIAS_FREQUENCY(x)		((x) << 8)
-#define LCD_SYNC_CTRL				BIT(25)
-#define LCD_SYNC_EDGE				BIT(24)
-#define LCD_INVERT_PIXEL_CLOCK			BIT(22)
-#define LCD_INVERT_LINE_CLOCK			BIT(21)
-#define LCD_INVERT_FRAME_CLOCK			BIT(20)
-
-/* LCD Block */
-#define  LCD_PID_REG				0x0
-#define  LCD_CTRL_REG				0x4
-#define  LCD_STAT_REG				0x8
-#define  LCD_RASTER_CTRL_REG			0x28
-#define  LCD_RASTER_TIMING_0_REG		0x2C
-#define  LCD_RASTER_TIMING_1_REG		0x30
-#define  LCD_RASTER_TIMING_2_REG		0x34
-#define  LCD_DMA_CTRL_REG			0x40
-#define  LCD_DMA_FRM_BUF_BASE_ADDR_0_REG	0x44
-#define  LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG	0x48
-#define  LCD_DMA_FRM_BUF_BASE_ADDR_1_REG	0x4C
-#define  LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG	0x50
-
-/* Interrupt Registers available only in Version 2 */
-#define  LCD_RAW_STAT_REG			0x58
-#define  LCD_MASKED_STAT_REG			0x5c
-#define  LCD_INT_ENABLE_SET_REG			0x60
-#define  LCD_INT_ENABLE_CLR_REG			0x64
-#define  LCD_END_OF_INT_IND_REG			0x68
-
-/* Clock registers available only on Version 2 */
-#define  LCD_CLK_ENABLE_REG			0x6c
-#define  LCD_CLK_RESET_REG			0x70
-#define  LCD_CLK_MAIN_RESET			BIT(3)
-
-#define LCD_NUM_BUFFERS	2
-
-#define PALETTE_SIZE	256
-
-#define	CLK_MIN_DIV	2
-#define	CLK_MAX_DIV	255
-
-static void __iomem *da8xx_fb_reg_base;
-static unsigned int lcd_revision;
-static irq_handler_t lcdc_irq_handler;
-static wait_queue_head_t frame_done_wq;
-static int frame_done_flag;
-
-static unsigned int lcdc_read(unsigned int addr)
-{
-	return (unsigned int)__raw_readl(da8xx_fb_reg_base + (addr));
-}
-
-static void lcdc_write(unsigned int val, unsigned int addr)
-{
-	__raw_writel(val, da8xx_fb_reg_base + (addr));
-}
-
-struct da8xx_fb_par {
-	struct device		*dev;
-	dma_addr_t		p_palette_base;
-	unsigned char *v_palette_base;
-	dma_addr_t		vram_phys;
-	unsigned long		vram_size;
-	void			*vram_virt;
-	unsigned int		dma_start;
-	unsigned int		dma_end;
-	struct clk *lcdc_clk;
-	int irq;
-	unsigned int palette_sz;
-	int blank;
-	wait_queue_head_t	vsync_wait;
-	int			vsync_flag;
-	int			vsync_timeout;
-	spinlock_t		lock_for_chan_update;
-
-	/*
-	 * LCDC has 2 ping pong DMA channels, channel 0
-	 * and channel 1.
-	 */
-	unsigned int		which_dma_channel_done;
-#ifdef CONFIG_CPU_FREQ
-	struct notifier_block	freq_transition;
-#endif
-	unsigned int		lcdc_clk_rate;
-	struct regulator	*lcd_supply;
-	u32 pseudo_palette[16];
-	struct fb_videomode	mode;
-	struct lcd_ctrl_config	cfg;
-};
-
-static struct fb_var_screeninfo da8xx_fb_var;
-
-static struct fb_fix_screeninfo da8xx_fb_fix = {
-	.id = "DA8xx FB Drv",
-	.type = FB_TYPE_PACKED_PIXELS,
-	.type_aux = 0,
-	.visual = FB_VISUAL_PSEUDOCOLOR,
-	.xpanstep = 0,
-	.ypanstep = 1,
-	.ywrapstep = 0,
-	.accel = FB_ACCEL_NONE
-};
-
-static struct fb_videomode known_lcd_panels[] = {
-	/* Sharp LCD035Q3DG01 */
-	[0] = {
-		.name           = "Sharp_LCD035Q3DG01",
-		.xres           = 320,
-		.yres           = 240,
-		.pixclock       = KHZ2PICOS(4607),
-		.left_margin    = 6,
-		.right_margin   = 8,
-		.upper_margin   = 2,
-		.lower_margin   = 2,
-		.hsync_len      = 0,
-		.vsync_len      = 0,
-		.sync           = FB_SYNC_CLK_INVERT,
-	},
-	/* Sharp LK043T1DG01 */
-	[1] = {
-		.name           = "Sharp_LK043T1DG01",
-		.xres           = 480,
-		.yres           = 272,
-		.pixclock       = KHZ2PICOS(7833),
-		.left_margin    = 2,
-		.right_margin   = 2,
-		.upper_margin   = 2,
-		.lower_margin   = 2,
-		.hsync_len      = 41,
-		.vsync_len      = 10,
-		.sync           = 0,
-		.flag           = 0,
-	},
-	[2] = {
-		/* Hitachi SP10Q010 */
-		.name           = "SP10Q010",
-		.xres           = 320,
-		.yres           = 240,
-		.pixclock       = KHZ2PICOS(7833),
-		.left_margin    = 10,
-		.right_margin   = 10,
-		.upper_margin   = 10,
-		.lower_margin   = 10,
-		.hsync_len      = 10,
-		.vsync_len      = 10,
-		.sync           = 0,
-		.flag           = 0,
-	},
-	[3] = {
-		/* Densitron 84-0023-001T */
-		.name           = "Densitron_84-0023-001T",
-		.xres           = 320,
-		.yres           = 240,
-		.pixclock       = KHZ2PICOS(6400),
-		.left_margin    = 0,
-		.right_margin   = 0,
-		.upper_margin   = 0,
-		.lower_margin   = 0,
-		.hsync_len      = 30,
-		.vsync_len      = 3,
-		.sync           = 0,
-	},
-};
-
-static bool da8xx_fb_is_raster_enabled(void)
-{
-	return !!(lcdc_read(LCD_RASTER_CTRL_REG) & LCD_RASTER_ENABLE);
-}
-
-/* Enable the Raster Engine of the LCD Controller */
-static void lcd_enable_raster(void)
-{
-	u32 reg;
-
-	/* Put LCDC in reset for several cycles */
-	if (lcd_revision == LCD_VERSION_2)
-		/* Write 1 to reset LCDC */
-		lcdc_write(LCD_CLK_MAIN_RESET, LCD_CLK_RESET_REG);
-	mdelay(1);
-
-	/* Bring LCDC out of reset */
-	if (lcd_revision == LCD_VERSION_2)
-		lcdc_write(0, LCD_CLK_RESET_REG);
-	mdelay(1);
-
-	/* Above reset sequence doesnot reset register context */
-	reg = lcdc_read(LCD_RASTER_CTRL_REG);
-	if (!(reg & LCD_RASTER_ENABLE))
-		lcdc_write(reg | LCD_RASTER_ENABLE, LCD_RASTER_CTRL_REG);
-}
-
-/* Disable the Raster Engine of the LCD Controller */
-static void lcd_disable_raster(enum da8xx_frame_complete wait_for_frame_done)
-{
-	u32 reg;
-	int ret;
-
-	reg = lcdc_read(LCD_RASTER_CTRL_REG);
-	if (reg & LCD_RASTER_ENABLE)
-		lcdc_write(reg & ~LCD_RASTER_ENABLE, LCD_RASTER_CTRL_REG);
-	else
-		/* return if already disabled */
-		return;
-
-	if ((wait_for_frame_done == DA8XX_FRAME_WAIT) &&
-			(lcd_revision == LCD_VERSION_2)) {
-		frame_done_flag = 0;
-		ret = wait_event_interruptible_timeout(frame_done_wq,
-				frame_done_flag != 0,
-				msecs_to_jiffies(50));
-		if (ret == 0)
-			pr_err("LCD Controller timed out\n");
-	}
-}
-
-static void lcd_blit(int load_mode, struct da8xx_fb_par *par)
-{
-	u32 start;
-	u32 end;
-	u32 reg_ras;
-	u32 reg_dma;
-	u32 reg_int;
-
-	/* init reg to clear PLM (loading mode) fields */
-	reg_ras = lcdc_read(LCD_RASTER_CTRL_REG);
-	reg_ras &= ~(3 << 20);
-
-	reg_dma  = lcdc_read(LCD_DMA_CTRL_REG);
-
-	if (load_mode == LOAD_DATA) {
-		start    = par->dma_start;
-		end      = par->dma_end;
-
-		reg_ras |= LCD_PALETTE_LOAD_MODE(DATA_ONLY);
-		if (lcd_revision == LCD_VERSION_1) {
-			reg_dma |= LCD_V1_END_OF_FRAME_INT_ENA;
-		} else {
-			reg_int = lcdc_read(LCD_INT_ENABLE_SET_REG) |
-				LCD_V2_END_OF_FRAME0_INT_ENA |
-				LCD_V2_END_OF_FRAME1_INT_ENA |
-				LCD_FRAME_DONE | LCD_SYNC_LOST;
-			lcdc_write(reg_int, LCD_INT_ENABLE_SET_REG);
-		}
-		reg_dma |= LCD_DUAL_FRAME_BUFFER_ENABLE;
-
-		lcdc_write(start, LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
-		lcdc_write(end, LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG);
-		lcdc_write(start, LCD_DMA_FRM_BUF_BASE_ADDR_1_REG);
-		lcdc_write(end, LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG);
-	} else if (load_mode == LOAD_PALETTE) {
-		start    = par->p_palette_base;
-		end      = start + par->palette_sz - 1;
-
-		reg_ras |= LCD_PALETTE_LOAD_MODE(PALETTE_ONLY);
-
-		if (lcd_revision == LCD_VERSION_1) {
-			reg_ras |= LCD_V1_PL_INT_ENA;
-		} else {
-			reg_int = lcdc_read(LCD_INT_ENABLE_SET_REG) |
-				LCD_V2_PL_INT_ENA;
-			lcdc_write(reg_int, LCD_INT_ENABLE_SET_REG);
-		}
-
-		lcdc_write(start, LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
-		lcdc_write(end, LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG);
-	}
-
-	lcdc_write(reg_dma, LCD_DMA_CTRL_REG);
-	lcdc_write(reg_ras, LCD_RASTER_CTRL_REG);
-
-	/*
-	 * The Raster enable bit must be set after all other control fields are
-	 * set.
-	 */
-	lcd_enable_raster();
-}
-
-/* Configure the Burst Size and fifo threhold of DMA */
-static int lcd_cfg_dma(int burst_size, int fifo_th)
-{
-	u32 reg;
-
-	reg = lcdc_read(LCD_DMA_CTRL_REG) & 0x00000001;
-	switch (burst_size) {
-	case 1:
-		reg |= LCD_DMA_BURST_SIZE(LCD_DMA_BURST_1);
-		break;
-	case 2:
-		reg |= LCD_DMA_BURST_SIZE(LCD_DMA_BURST_2);
-		break;
-	case 4:
-		reg |= LCD_DMA_BURST_SIZE(LCD_DMA_BURST_4);
-		break;
-	case 8:
-		reg |= LCD_DMA_BURST_SIZE(LCD_DMA_BURST_8);
-		break;
-	case 16:
-	default:
-		reg |= LCD_DMA_BURST_SIZE(LCD_DMA_BURST_16);
-		break;
-	}
-
-	reg |= (fifo_th << 8);
-
-	lcdc_write(reg, LCD_DMA_CTRL_REG);
-
-	return 0;
-}
-
-static void lcd_cfg_ac_bias(int period, int transitions_per_int)
-{
-	u32 reg;
-
-	/* Set the AC Bias Period and Number of Transisitons per Interrupt */
-	reg = lcdc_read(LCD_RASTER_TIMING_2_REG) & 0xFFF00000;
-	reg |= LCD_AC_BIAS_FREQUENCY(period) |
-		LCD_AC_BIAS_TRANSITIONS_PER_INT(transitions_per_int);
-	lcdc_write(reg, LCD_RASTER_TIMING_2_REG);
-}
-
-static void lcd_cfg_horizontal_sync(int back_porch, int pulse_width,
-		int front_porch)
-{
-	u32 reg;
-
-	reg = lcdc_read(LCD_RASTER_TIMING_0_REG) & 0x3ff;
-	reg |= (((back_porch-1) & 0xff) << 24)
-	    | (((front_porch-1) & 0xff) << 16)
-	    | (((pulse_width-1) & 0x3f) << 10);
-	lcdc_write(reg, LCD_RASTER_TIMING_0_REG);
-
-	/*
-	 * LCDC Version 2 adds some extra bits that increase the allowable
-	 * size of the horizontal timing registers.
-	 * remember that the registers use 0 to represent 1 so all values
-	 * that get set into register need to be decremented by 1
-	 */
-	if (lcd_revision == LCD_VERSION_2) {
-		/* Mask off the bits we want to change */
-		reg = lcdc_read(LCD_RASTER_TIMING_2_REG) & ~0x780000ff;
-		reg |= ((front_porch-1) & 0x300) >> 8;
-		reg |= ((back_porch-1) & 0x300) >> 4;
-		reg |= ((pulse_width-1) & 0x3c0) << 21;
-		lcdc_write(reg, LCD_RASTER_TIMING_2_REG);
-	}
-}
-
-static void lcd_cfg_vertical_sync(int back_porch, int pulse_width,
-		int front_porch)
-{
-	u32 reg;
-
-	reg = lcdc_read(LCD_RASTER_TIMING_1_REG) & 0x3ff;
-	reg |= ((back_porch & 0xff) << 24)
-	    | ((front_porch & 0xff) << 16)
-	    | (((pulse_width-1) & 0x3f) << 10);
-	lcdc_write(reg, LCD_RASTER_TIMING_1_REG);
-}
-
-static int lcd_cfg_display(const struct lcd_ctrl_config *cfg,
-		struct fb_videomode *panel)
-{
-	u32 reg;
-	u32 reg_int;
-
-	reg = lcdc_read(LCD_RASTER_CTRL_REG) & ~(LCD_TFT_MODE |
-						LCD_MONO_8BIT_MODE |
-						LCD_MONOCHROME_MODE);
-
-	switch (cfg->panel_shade) {
-	case MONOCHROME:
-		reg |= LCD_MONOCHROME_MODE;
-		if (cfg->mono_8bit_mode)
-			reg |= LCD_MONO_8BIT_MODE;
-		break;
-	case COLOR_ACTIVE:
-		reg |= LCD_TFT_MODE;
-		if (cfg->tft_alt_mode)
-			reg |= LCD_TFT_ALT_ENABLE;
-		break;
-
-	case COLOR_PASSIVE:
-		/* AC bias applicable only for Pasive panels */
-		lcd_cfg_ac_bias(cfg->ac_bias, cfg->ac_bias_intrpt);
-		if (cfg->bpp == 12 && cfg->stn_565_mode)
-			reg |= LCD_STN_565_ENABLE;
-		break;
-
-	default:
-		return -EINVAL;
-	}
-
-	/* enable additional interrupts here */
-	if (lcd_revision == LCD_VERSION_1) {
-		reg |= LCD_V1_UNDERFLOW_INT_ENA;
-	} else {
-		reg_int = lcdc_read(LCD_INT_ENABLE_SET_REG) |
-			LCD_V2_UNDERFLOW_INT_ENA;
-		lcdc_write(reg_int, LCD_INT_ENABLE_SET_REG);
-	}
-
-	lcdc_write(reg, LCD_RASTER_CTRL_REG);
-
-	reg = lcdc_read(LCD_RASTER_TIMING_2_REG);
-
-	reg |= LCD_SYNC_CTRL;
-
-	if (cfg->sync_edge)
-		reg |= LCD_SYNC_EDGE;
-	else
-		reg &= ~LCD_SYNC_EDGE;
-
-	if ((panel->sync & FB_SYNC_HOR_HIGH_ACT) == 0)
-		reg |= LCD_INVERT_LINE_CLOCK;
-	else
-		reg &= ~LCD_INVERT_LINE_CLOCK;
-
-	if ((panel->sync & FB_SYNC_VERT_HIGH_ACT) == 0)
-		reg |= LCD_INVERT_FRAME_CLOCK;
-	else
-		reg &= ~LCD_INVERT_FRAME_CLOCK;
-
-	lcdc_write(reg, LCD_RASTER_TIMING_2_REG);
-
-	return 0;
-}
-
-static int lcd_cfg_frame_buffer(struct da8xx_fb_par *par, u32 width, u32 height,
-		u32 bpp, u32 raster_order)
-{
-	u32 reg;
-
-	if (bpp > 16 && lcd_revision == LCD_VERSION_1)
-		return -EINVAL;
-
-	/* Set the Panel Width */
-	/* Pixels per line = (PPL + 1)*16 */
-	if (lcd_revision == LCD_VERSION_1) {
-		/*
-		 * 0x3F in bits 4..9 gives max horizontal resolution = 1024
-		 * pixels.
-		 */
-		width &= 0x3f0;
-	} else {
-		/*
-		 * 0x7F in bits 4..10 gives max horizontal resolution = 2048
-		 * pixels.
-		 */
-		width &= 0x7f0;
-	}
-
-	reg = lcdc_read(LCD_RASTER_TIMING_0_REG);
-	reg &= 0xfffffc00;
-	if (lcd_revision == LCD_VERSION_1) {
-		reg |= ((width >> 4) - 1) << 4;
-	} else {
-		width = (width >> 4) - 1;
-		reg |= ((width & 0x3f) << 4) | ((width & 0x40) >> 3);
-	}
-	lcdc_write(reg, LCD_RASTER_TIMING_0_REG);
-
-	/* Set the Panel Height */
-	/* Set bits 9:0 of Lines Per Pixel */
-	reg = lcdc_read(LCD_RASTER_TIMING_1_REG);
-	reg = ((height - 1) & 0x3ff) | (reg & 0xfffffc00);
-	lcdc_write(reg, LCD_RASTER_TIMING_1_REG);
-
-	/* Set bit 10 of Lines Per Pixel */
-	if (lcd_revision == LCD_VERSION_2) {
-		reg = lcdc_read(LCD_RASTER_TIMING_2_REG);
-		reg |= ((height - 1) & 0x400) << 16;
-		lcdc_write(reg, LCD_RASTER_TIMING_2_REG);
-	}
-
-	/* Set the Raster Order of the Frame Buffer */
-	reg = lcdc_read(LCD_RASTER_CTRL_REG) & ~(1 << 8);
-	if (raster_order)
-		reg |= LCD_RASTER_ORDER;
-
-	par->palette_sz = 16 * 2;
-
-	switch (bpp) {
-	case 1:
-	case 2:
-	case 4:
-	case 16:
-		break;
-	case 24:
-		reg |= LCD_V2_TFT_24BPP_MODE;
-		break;
-	case 32:
-		reg |= LCD_V2_TFT_24BPP_MODE;
-		reg |= LCD_V2_TFT_24BPP_UNPACK;
-		break;
-	case 8:
-		par->palette_sz = 256 * 2;
-		break;
-
-	default:
-		return -EINVAL;
-	}
-
-	lcdc_write(reg, LCD_RASTER_CTRL_REG);
-
-	return 0;
-}
-
-#define CNVT_TOHW(val, width) ((((val) << (width)) + 0x7FFF - (val)) >> 16)
-static int fb_setcolreg(unsigned regno, unsigned red, unsigned green,
-			      unsigned blue, unsigned transp,
-			      struct fb_info *info)
-{
-	struct da8xx_fb_par *par = info->par;
-	unsigned short *palette = (unsigned short *) par->v_palette_base;
-	u_short pal;
-	int update_hw = 0;
-
-	if (regno > 255)
-		return 1;
-
-	if (info->fix.visual == FB_VISUAL_DIRECTCOLOR)
-		return 1;
-
-	if (info->var.bits_per_pixel > 16 && lcd_revision == LCD_VERSION_1)
-		return -EINVAL;
-
-	switch (info->fix.visual) {
-	case FB_VISUAL_TRUECOLOR:
-		red = CNVT_TOHW(red, info->var.red.length);
-		green = CNVT_TOHW(green, info->var.green.length);
-		blue = CNVT_TOHW(blue, info->var.blue.length);
-		break;
-	case FB_VISUAL_PSEUDOCOLOR:
-		switch (info->var.bits_per_pixel) {
-		case 4:
-			if (regno > 15)
-				return -EINVAL;
-
-			if (info->var.grayscale) {
-				pal = regno;
-			} else {
-				red >>= 4;
-				green >>= 8;
-				blue >>= 12;
-
-				pal = red & 0x0f00;
-				pal |= green & 0x00f0;
-				pal |= blue & 0x000f;
-			}
-			if (regno == 0)
-				pal |= 0x2000;
-			palette[regno] = pal;
-			break;
-
-		case 8:
-			red >>= 4;
-			green >>= 8;
-			blue >>= 12;
-
-			pal = (red & 0x0f00);
-			pal |= (green & 0x00f0);
-			pal |= (blue & 0x000f);
-
-			if (palette[regno] != pal) {
-				update_hw = 1;
-				palette[regno] = pal;
-			}
-			break;
-		}
-		break;
-	}
-
-	/* Truecolor has hardware independent palette */
-	if (info->fix.visual == FB_VISUAL_TRUECOLOR) {
-		u32 v;
-
-		if (regno > 15)
-			return -EINVAL;
-
-		v = (red << info->var.red.offset) |
-			(green << info->var.green.offset) |
-			(blue << info->var.blue.offset);
-
-		((u32 *) (info->pseudo_palette))[regno] = v;
-		if (palette[0] != 0x4000) {
-			update_hw = 1;
-			palette[0] = 0x4000;
-		}
-	}
-
-	/* Update the palette in the h/w as needed. */
-	if (update_hw)
-		lcd_blit(LOAD_PALETTE, par);
-
-	return 0;
-}
-#undef CNVT_TOHW
-
-static void da8xx_fb_lcd_reset(void)
-{
-	/* DMA has to be disabled */
-	lcdc_write(0, LCD_DMA_CTRL_REG);
-	lcdc_write(0, LCD_RASTER_CTRL_REG);
-
-	if (lcd_revision == LCD_VERSION_2) {
-		lcdc_write(0, LCD_INT_ENABLE_SET_REG);
-		/* Write 1 to reset */
-		lcdc_write(LCD_CLK_MAIN_RESET, LCD_CLK_RESET_REG);
-		lcdc_write(0, LCD_CLK_RESET_REG);
-	}
-}
-
-static int da8xx_fb_config_clk_divider(struct da8xx_fb_par *par,
-					      unsigned lcdc_clk_div,
-					      unsigned lcdc_clk_rate)
-{
-	int ret;
-
-	if (par->lcdc_clk_rate != lcdc_clk_rate) {
-		ret = clk_set_rate(par->lcdc_clk, lcdc_clk_rate);
-		if (ret) {
-			dev_err(par->dev,
-				"unable to set clock rate at %u\n",
-				lcdc_clk_rate);
-			return ret;
-		}
-		par->lcdc_clk_rate = clk_get_rate(par->lcdc_clk);
-	}
-
-	/* Configure the LCD clock divisor. */
-	lcdc_write(LCD_CLK_DIVISOR(lcdc_clk_div) |
-			(LCD_RASTER_MODE & 0x1), LCD_CTRL_REG);
-
-	if (lcd_revision == LCD_VERSION_2)
-		lcdc_write(LCD_V2_DMA_CLK_EN | LCD_V2_LIDD_CLK_EN |
-				LCD_V2_CORE_CLK_EN, LCD_CLK_ENABLE_REG);
-
-	return 0;
-}
-
-static unsigned int da8xx_fb_calc_clk_divider(struct da8xx_fb_par *par,
-					      unsigned pixclock,
-					      unsigned *lcdc_clk_rate)
-{
-	unsigned lcdc_clk_div;
-
-	pixclock = PICOS2KHZ(pixclock) * 1000;
-
-	*lcdc_clk_rate = par->lcdc_clk_rate;
-
-	if (pixclock < (*lcdc_clk_rate / CLK_MAX_DIV)) {
-		*lcdc_clk_rate = clk_round_rate(par->lcdc_clk,
-						pixclock * CLK_MAX_DIV);
-		lcdc_clk_div = CLK_MAX_DIV;
-	} else if (pixclock > (*lcdc_clk_rate / CLK_MIN_DIV)) {
-		*lcdc_clk_rate = clk_round_rate(par->lcdc_clk,
-						pixclock * CLK_MIN_DIV);
-		lcdc_clk_div = CLK_MIN_DIV;
-	} else {
-		lcdc_clk_div = *lcdc_clk_rate / pixclock;
-	}
-
-	return lcdc_clk_div;
-}
-
-static int da8xx_fb_calc_config_clk_divider(struct da8xx_fb_par *par,
-					    struct fb_videomode *mode)
-{
-	unsigned lcdc_clk_rate;
-	unsigned lcdc_clk_div = da8xx_fb_calc_clk_divider(par, mode->pixclock,
-							  &lcdc_clk_rate);
-
-	return da8xx_fb_config_clk_divider(par, lcdc_clk_div, lcdc_clk_rate);
-}
-
-static unsigned da8xx_fb_round_clk(struct da8xx_fb_par *par,
-					  unsigned pixclock)
-{
-	unsigned lcdc_clk_div, lcdc_clk_rate;
-
-	lcdc_clk_div = da8xx_fb_calc_clk_divider(par, pixclock, &lcdc_clk_rate);
-	return KHZ2PICOS(lcdc_clk_rate / (1000 * lcdc_clk_div));
-}
-
-static int lcd_init(struct da8xx_fb_par *par, const struct lcd_ctrl_config *cfg,
-		struct fb_videomode *panel)
-{
-	u32 bpp;
-	int ret = 0;
-
-	ret = da8xx_fb_calc_config_clk_divider(par, panel);
-	if (ret) {
-		dev_err(par->dev, "unable to configure clock\n");
-		return ret;
-	}
-
-	if (panel->sync & FB_SYNC_CLK_INVERT)
-		lcdc_write((lcdc_read(LCD_RASTER_TIMING_2_REG) |
-			LCD_INVERT_PIXEL_CLOCK), LCD_RASTER_TIMING_2_REG);
-	else
-		lcdc_write((lcdc_read(LCD_RASTER_TIMING_2_REG) &
-			~LCD_INVERT_PIXEL_CLOCK), LCD_RASTER_TIMING_2_REG);
-
-	/* Configure the DMA burst size and fifo threshold. */
-	ret = lcd_cfg_dma(cfg->dma_burst_sz, cfg->fifo_th);
-	if (ret < 0)
-		return ret;
-
-	/* Configure the vertical and horizontal sync properties. */
-	lcd_cfg_vertical_sync(panel->upper_margin, panel->vsync_len,
-			panel->lower_margin);
-	lcd_cfg_horizontal_sync(panel->left_margin, panel->hsync_len,
-			panel->right_margin);
-
-	/* Configure for disply */
-	ret = lcd_cfg_display(cfg, panel);
-	if (ret < 0)
-		return ret;
-
-	bpp = cfg->bpp;
-
-	if (bpp == 12)
-		bpp = 16;
-	ret = lcd_cfg_frame_buffer(par, (unsigned int)panel->xres,
-				(unsigned int)panel->yres, bpp,
-				cfg->raster_order);
-	if (ret < 0)
-		return ret;
-
-	/* Configure FDD */
-	lcdc_write((lcdc_read(LCD_RASTER_CTRL_REG) & 0xfff00fff) |
-		       (cfg->fdd << 12), LCD_RASTER_CTRL_REG);
-
-	return 0;
-}
-
-/* IRQ handler for version 2 of LCDC */
-static irqreturn_t lcdc_irq_handler_rev02(int irq, void *arg)
-{
-	struct da8xx_fb_par *par = arg;
-	u32 stat = lcdc_read(LCD_MASKED_STAT_REG);
-
-	if ((stat & LCD_SYNC_LOST) && (stat & LCD_FIFO_UNDERFLOW)) {
-		lcd_disable_raster(DA8XX_FRAME_NOWAIT);
-		lcdc_write(stat, LCD_MASKED_STAT_REG);
-		lcd_enable_raster();
-	} else if (stat & LCD_PL_LOAD_DONE) {
-		/*
-		 * Must disable raster before changing state of any control bit.
-		 * And also must be disabled before clearing the PL loading
-		 * interrupt via the following write to the status register. If
-		 * this is done after then one gets multiple PL done interrupts.
-		 */
-		lcd_disable_raster(DA8XX_FRAME_NOWAIT);
-
-		lcdc_write(stat, LCD_MASKED_STAT_REG);
-
-		/* Disable PL completion interrupt */
-		lcdc_write(LCD_V2_PL_INT_ENA, LCD_INT_ENABLE_CLR_REG);
-
-		/* Setup and start data loading mode */
-		lcd_blit(LOAD_DATA, par);
-	} else {
-		lcdc_write(stat, LCD_MASKED_STAT_REG);
-
-		if (stat & LCD_END_OF_FRAME0) {
-			par->which_dma_channel_done = 0;
-			lcdc_write(par->dma_start,
-				   LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
-			lcdc_write(par->dma_end,
-				   LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG);
-			par->vsync_flag = 1;
-			wake_up_interruptible(&par->vsync_wait);
-		}
-
-		if (stat & LCD_END_OF_FRAME1) {
-			par->which_dma_channel_done = 1;
-			lcdc_write(par->dma_start,
-				   LCD_DMA_FRM_BUF_BASE_ADDR_1_REG);
-			lcdc_write(par->dma_end,
-				   LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG);
-			par->vsync_flag = 1;
-			wake_up_interruptible(&par->vsync_wait);
-		}
-
-		/* Set only when controller is disabled and at the end of
-		 * active frame
-		 */
-		if (stat & BIT(0)) {
-			frame_done_flag = 1;
-			wake_up_interruptible(&frame_done_wq);
-		}
-	}
-
-	lcdc_write(0, LCD_END_OF_INT_IND_REG);
-	return IRQ_HANDLED;
-}
-
-/* IRQ handler for version 1 LCDC */
-static irqreturn_t lcdc_irq_handler_rev01(int irq, void *arg)
-{
-	struct da8xx_fb_par *par = arg;
-	u32 stat = lcdc_read(LCD_STAT_REG);
-	u32 reg_ras;
-
-	if ((stat & LCD_SYNC_LOST) && (stat & LCD_FIFO_UNDERFLOW)) {
-		lcd_disable_raster(DA8XX_FRAME_NOWAIT);
-		lcdc_write(stat, LCD_STAT_REG);
-		lcd_enable_raster();
-	} else if (stat & LCD_PL_LOAD_DONE) {
-		/*
-		 * Must disable raster before changing state of any control bit.
-		 * And also must be disabled before clearing the PL loading
-		 * interrupt via the following write to the status register. If
-		 * this is done after then one gets multiple PL done interrupts.
-		 */
-		lcd_disable_raster(DA8XX_FRAME_NOWAIT);
-
-		lcdc_write(stat, LCD_STAT_REG);
-
-		/* Disable PL completion inerrupt */
-		reg_ras  = lcdc_read(LCD_RASTER_CTRL_REG);
-		reg_ras &= ~LCD_V1_PL_INT_ENA;
-		lcdc_write(reg_ras, LCD_RASTER_CTRL_REG);
-
-		/* Setup and start data loading mode */
-		lcd_blit(LOAD_DATA, par);
-	} else {
-		lcdc_write(stat, LCD_STAT_REG);
-
-		if (stat & LCD_END_OF_FRAME0) {
-			par->which_dma_channel_done = 0;
-			lcdc_write(par->dma_start,
-				   LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
-			lcdc_write(par->dma_end,
-				   LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG);
-			par->vsync_flag = 1;
-			wake_up_interruptible(&par->vsync_wait);
-		}
-
-		if (stat & LCD_END_OF_FRAME1) {
-			par->which_dma_channel_done = 1;
-			lcdc_write(par->dma_start,
-				   LCD_DMA_FRM_BUF_BASE_ADDR_1_REG);
-			lcdc_write(par->dma_end,
-				   LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG);
-			par->vsync_flag = 1;
-			wake_up_interruptible(&par->vsync_wait);
-		}
-	}
-
-	return IRQ_HANDLED;
-}
-
-static int fb_check_var(struct fb_var_screeninfo *var,
-			struct fb_info *info)
-{
-	int err = 0;
-	struct da8xx_fb_par *par = info->par;
-	int bpp = var->bits_per_pixel >> 3;
-	unsigned long line_size = var->xres_virtual * bpp;
-
-	if (var->bits_per_pixel > 16 && lcd_revision == LCD_VERSION_1)
-		return -EINVAL;
-
-	switch (var->bits_per_pixel) {
-	case 1:
-	case 8:
-		var->red.offset = 0;
-		var->red.length = 8;
-		var->green.offset = 0;
-		var->green.length = 8;
-		var->blue.offset = 0;
-		var->blue.length = 8;
-		var->transp.offset = 0;
-		var->transp.length = 0;
-		var->nonstd = 0;
-		break;
-	case 4:
-		var->red.offset = 0;
-		var->red.length = 4;
-		var->green.offset = 0;
-		var->green.length = 4;
-		var->blue.offset = 0;
-		var->blue.length = 4;
-		var->transp.offset = 0;
-		var->transp.length = 0;
-		var->nonstd = FB_NONSTD_REV_PIX_IN_B;
-		break;
-	case 16:		/* RGB 565 */
-		var->red.offset = 11;
-		var->red.length = 5;
-		var->green.offset = 5;
-		var->green.length = 6;
-		var->blue.offset = 0;
-		var->blue.length = 5;
-		var->transp.offset = 0;
-		var->transp.length = 0;
-		var->nonstd = 0;
-		break;
-	case 24:
-		var->red.offset = 16;
-		var->red.length = 8;
-		var->green.offset = 8;
-		var->green.length = 8;
-		var->blue.offset = 0;
-		var->blue.length = 8;
-		var->nonstd = 0;
-		break;
-	case 32:
-		var->transp.offset = 24;
-		var->transp.length = 8;
-		var->red.offset = 16;
-		var->red.length = 8;
-		var->green.offset = 8;
-		var->green.length = 8;
-		var->blue.offset = 0;
-		var->blue.length = 8;
-		var->nonstd = 0;
-		break;
-	default:
-		err = -EINVAL;
-	}
-
-	var->red.msb_right = 0;
-	var->green.msb_right = 0;
-	var->blue.msb_right = 0;
-	var->transp.msb_right = 0;
-
-	if (line_size * var->yres_virtual > par->vram_size)
-		var->yres_virtual = par->vram_size / line_size;
-
-	if (var->yres > var->yres_virtual)
-		var->yres = var->yres_virtual;
-
-	if (var->xres > var->xres_virtual)
-		var->xres = var->xres_virtual;
-
-	if (var->xres + var->xoffset > var->xres_virtual)
-		var->xoffset = var->xres_virtual - var->xres;
-	if (var->yres + var->yoffset > var->yres_virtual)
-		var->yoffset = var->yres_virtual - var->yres;
-
-	var->pixclock = da8xx_fb_round_clk(par, var->pixclock);
-
-	return err;
-}
-
-#ifdef CONFIG_CPU_FREQ
-static int lcd_da8xx_cpufreq_transition(struct notifier_block *nb,
-				     unsigned long val, void *data)
-{
-	struct da8xx_fb_par *par;
-
-	par = container_of(nb, struct da8xx_fb_par, freq_transition);
-	if (val == CPUFREQ_POSTCHANGE) {
-		if (par->lcdc_clk_rate != clk_get_rate(par->lcdc_clk)) {
-			par->lcdc_clk_rate = clk_get_rate(par->lcdc_clk);
-			lcd_disable_raster(DA8XX_FRAME_WAIT);
-			da8xx_fb_calc_config_clk_divider(par, &par->mode);
-			if (par->blank == FB_BLANK_UNBLANK)
-				lcd_enable_raster();
-		}
-	}
-
-	return 0;
-}
-
-static int lcd_da8xx_cpufreq_register(struct da8xx_fb_par *par)
-{
-	par->freq_transition.notifier_call = lcd_da8xx_cpufreq_transition;
-
-	return cpufreq_register_notifier(&par->freq_transition,
-					 CPUFREQ_TRANSITION_NOTIFIER);
-}
-
-static void lcd_da8xx_cpufreq_deregister(struct da8xx_fb_par *par)
-{
-	cpufreq_unregister_notifier(&par->freq_transition,
-				    CPUFREQ_TRANSITION_NOTIFIER);
-}
-#endif
-
-static void fb_remove(struct platform_device *dev)
-{
-	struct fb_info *info = platform_get_drvdata(dev);
-	struct da8xx_fb_par *par = info->par;
-	int ret;
-
-#ifdef CONFIG_CPU_FREQ
-	lcd_da8xx_cpufreq_deregister(par);
-#endif
-	if (par->lcd_supply) {
-		ret = regulator_disable(par->lcd_supply);
-		if (ret)
-			dev_warn(&dev->dev, "Failed to disable regulator (%pe)\n",
-				 ERR_PTR(ret));
-	}
-
-	lcd_disable_raster(DA8XX_FRAME_WAIT);
-	lcdc_write(0, LCD_RASTER_CTRL_REG);
-
-	/* disable DMA  */
-	lcdc_write(0, LCD_DMA_CTRL_REG);
-
-	unregister_framebuffer(info);
-	fb_dealloc_cmap(&info->cmap);
-	pm_runtime_put_sync(&dev->dev);
-	pm_runtime_disable(&dev->dev);
-	framebuffer_release(info);
-}
-
-/*
- * Function to wait for vertical sync which for this LCD peripheral
- * translates into waiting for the current raster frame to complete.
- */
-static int fb_wait_for_vsync(struct fb_info *info)
-{
-	struct da8xx_fb_par *par = info->par;
-	int ret;
-
-	/*
-	 * Set flag to 0 and wait for isr to set to 1. It would seem there is a
-	 * race condition here where the ISR could have occurred just before or
-	 * just after this set. But since we are just coarsely waiting for
-	 * a frame to complete then that's OK. i.e. if the frame completed
-	 * just before this code executed then we have to wait another full
-	 * frame time but there is no way to avoid such a situation. On the
-	 * other hand if the frame completed just after then we don't need
-	 * to wait long at all. Either way we are guaranteed to return to the
-	 * user immediately after a frame completion which is all that is
-	 * required.
-	 */
-	par->vsync_flag = 0;
-	ret = wait_event_interruptible_timeout(par->vsync_wait,
-					       par->vsync_flag != 0,
-					       par->vsync_timeout);
-	if (ret < 0)
-		return ret;
-	if (ret == 0)
-		return -ETIMEDOUT;
-
-	return 0;
-}
-
-static int fb_ioctl(struct fb_info *info, unsigned int cmd,
-			  unsigned long arg)
-{
-	struct lcd_sync_arg sync_arg;
-
-	switch (cmd) {
-	case FBIOGET_CONTRAST:
-	case FBIOPUT_CONTRAST:
-	case FBIGET_BRIGHTNESS:
-	case FBIPUT_BRIGHTNESS:
-	case FBIGET_COLOR:
-	case FBIPUT_COLOR:
-		return -ENOTTY;
-	case FBIPUT_HSYNC:
-		if (copy_from_user(&sync_arg, (char *)arg,
-				sizeof(struct lcd_sync_arg)))
-			return -EFAULT;
-		lcd_cfg_horizontal_sync(sync_arg.back_porch,
-					sync_arg.pulse_width,
-					sync_arg.front_porch);
-		break;
-	case FBIPUT_VSYNC:
-		if (copy_from_user(&sync_arg, (char *)arg,
-				sizeof(struct lcd_sync_arg)))
-			return -EFAULT;
-		lcd_cfg_vertical_sync(sync_arg.back_porch,
-					sync_arg.pulse_width,
-					sync_arg.front_porch);
-		break;
-	case FBIO_WAITFORVSYNC:
-		return fb_wait_for_vsync(info);
-	default:
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static int cfb_blank(int blank, struct fb_info *info)
-{
-	struct da8xx_fb_par *par = info->par;
-	int ret = 0;
-
-	if (par->blank == blank)
-		return 0;
-
-	par->blank = blank;
-	switch (blank) {
-	case FB_BLANK_UNBLANK:
-		lcd_enable_raster();
-
-		if (par->lcd_supply) {
-			ret = regulator_enable(par->lcd_supply);
-			if (ret)
-				return ret;
-		}
-		break;
-	case FB_BLANK_NORMAL:
-	case FB_BLANK_VSYNC_SUSPEND:
-	case FB_BLANK_HSYNC_SUSPEND:
-	case FB_BLANK_POWERDOWN:
-		if (par->lcd_supply) {
-			ret = regulator_disable(par->lcd_supply);
-			if (ret)
-				return ret;
-		}
-
-		lcd_disable_raster(DA8XX_FRAME_WAIT);
-		break;
-	default:
-		ret = -EINVAL;
-	}
-
-	return ret;
-}
-
-/*
- * Set new x,y offsets in the virtual display for the visible area and switch
- * to the new mode.
- */
-static int da8xx_pan_display(struct fb_var_screeninfo *var,
-			     struct fb_info *fbi)
-{
-	int ret = 0;
-	struct fb_var_screeninfo new_var;
-	struct da8xx_fb_par         *par = fbi->par;
-	struct fb_fix_screeninfo    *fix = &fbi->fix;
-	unsigned int end;
-	unsigned int start;
-	unsigned long irq_flags;
-
-	if (var->xoffset != fbi->var.xoffset ||
-			var->yoffset != fbi->var.yoffset) {
-		memcpy(&new_var, &fbi->var, sizeof(new_var));
-		new_var.xoffset = var->xoffset;
-		new_var.yoffset = var->yoffset;
-		if (fb_check_var(&new_var, fbi))
-			ret = -EINVAL;
-		else {
-			memcpy(&fbi->var, &new_var, sizeof(new_var));
-
-			start	= fix->smem_start +
-				new_var.yoffset * fix->line_length +
-				new_var.xoffset * fbi->var.bits_per_pixel / 8;
-			end	= start + fbi->var.yres * fix->line_length - 1;
-			par->dma_start	= start;
-			par->dma_end	= end;
-			spin_lock_irqsave(&par->lock_for_chan_update,
-					irq_flags);
-			if (par->which_dma_channel_done == 0) {
-				lcdc_write(par->dma_start,
-					   LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
-				lcdc_write(par->dma_end,
-					   LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG);
-			} else if (par->which_dma_channel_done == 1) {
-				lcdc_write(par->dma_start,
-					   LCD_DMA_FRM_BUF_BASE_ADDR_1_REG);
-				lcdc_write(par->dma_end,
-					   LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG);
-			}
-			spin_unlock_irqrestore(&par->lock_for_chan_update,
-					irq_flags);
-		}
-	}
-
-	return ret;
-}
-
-static int da8xxfb_set_par(struct fb_info *info)
-{
-	struct da8xx_fb_par *par = info->par;
-	int ret;
-	bool raster = da8xx_fb_is_raster_enabled();
-
-	if (raster)
-		lcd_disable_raster(DA8XX_FRAME_WAIT);
-
-	fb_var_to_videomode(&par->mode, &info->var);
-
-	par->cfg.bpp = info->var.bits_per_pixel;
-
-	info->fix.visual = (par->cfg.bpp <= 8) ?
-				FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_TRUECOLOR;
-	info->fix.line_length = (par->mode.xres * par->cfg.bpp) / 8;
-
-	ret = lcd_init(par, &par->cfg, &par->mode);
-	if (ret < 0) {
-		dev_err(par->dev, "lcd init failed\n");
-		return ret;
-	}
-
-	par->dma_start = info->fix.smem_start +
-			 info->var.yoffset * info->fix.line_length +
-			 info->var.xoffset * info->var.bits_per_pixel / 8;
-	par->dma_end   = par->dma_start +
-			 info->var.yres * info->fix.line_length - 1;
-
-	lcdc_write(par->dma_start, LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
-	lcdc_write(par->dma_end, LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG);
-	lcdc_write(par->dma_start, LCD_DMA_FRM_BUF_BASE_ADDR_1_REG);
-	lcdc_write(par->dma_end, LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG);
-
-	if (raster)
-		lcd_enable_raster();
-
-	return 0;
-}
-
-static const struct fb_ops da8xx_fb_ops = {
-	.owner = THIS_MODULE,
-	FB_DEFAULT_IOMEM_OPS,
-	.fb_check_var = fb_check_var,
-	.fb_set_par = da8xxfb_set_par,
-	.fb_setcolreg = fb_setcolreg,
-	.fb_pan_display = da8xx_pan_display,
-	.fb_ioctl = fb_ioctl,
-	.fb_blank = cfb_blank,
-};
-
-static struct fb_videomode *da8xx_fb_get_videomode(struct platform_device *dev)
-{
-	struct da8xx_lcdc_platform_data *fb_pdata = dev_get_platdata(&dev->dev);
-	struct fb_videomode *lcdc_info;
-	int i;
-
-	for (i = 0, lcdc_info = known_lcd_panels;
-		i < ARRAY_SIZE(known_lcd_panels); i++, lcdc_info++) {
-		if (strcmp(fb_pdata->type, lcdc_info->name) == 0)
-			break;
-	}
-
-	if (i == ARRAY_SIZE(known_lcd_panels)) {
-		dev_err(&dev->dev, "no panel found\n");
-		return NULL;
-	}
-	dev_info(&dev->dev, "found %s panel\n", lcdc_info->name);
-
-	return lcdc_info;
-}
-
-static int fb_probe(struct platform_device *device)
-{
-	struct da8xx_lcdc_platform_data *fb_pdata =
-						dev_get_platdata(&device->dev);
-	struct lcd_ctrl_config *lcd_cfg;
-	struct fb_videomode *lcdc_info;
-	struct fb_info *da8xx_fb_info;
-	struct da8xx_fb_par *par;
-	struct clk *tmp_lcdc_clk;
-	int ret;
-	unsigned long ulcm;
-
-	if (fb_pdata == NULL) {
-		dev_err(&device->dev, "Can not get platform data\n");
-		return -ENOENT;
-	}
-
-	lcdc_info = da8xx_fb_get_videomode(device);
-	if (lcdc_info == NULL)
-		return -ENODEV;
-
-	da8xx_fb_reg_base = devm_platform_ioremap_resource(device, 0);
-	if (IS_ERR(da8xx_fb_reg_base))
-		return PTR_ERR(da8xx_fb_reg_base);
-
-	tmp_lcdc_clk = devm_clk_get(&device->dev, "fck");
-	if (IS_ERR(tmp_lcdc_clk))
-		return dev_err_probe(&device->dev, PTR_ERR(tmp_lcdc_clk),
-				     "Can not get device clock\n");
-
-	pm_runtime_enable(&device->dev);
-	pm_runtime_get_sync(&device->dev);
-
-	/* Determine LCD IP Version */
-	switch (lcdc_read(LCD_PID_REG)) {
-	case 0x4C100102:
-		lcd_revision = LCD_VERSION_1;
-		break;
-	case 0x4F200800:
-	case 0x4F201000:
-		lcd_revision = LCD_VERSION_2;
-		break;
-	default:
-		dev_warn(&device->dev, "Unknown PID Reg value 0x%x, "
-				"defaulting to LCD revision 1\n",
-				lcdc_read(LCD_PID_REG));
-		lcd_revision = LCD_VERSION_1;
-		break;
-	}
-
-	lcd_cfg = (struct lcd_ctrl_config *)fb_pdata->controller_data;
-
-	if (!lcd_cfg) {
-		ret = -EINVAL;
-		goto err_pm_runtime_disable;
-	}
-
-	da8xx_fb_info = framebuffer_alloc(sizeof(struct da8xx_fb_par),
-					&device->dev);
-	if (!da8xx_fb_info) {
-		ret = -ENOMEM;
-		goto err_pm_runtime_disable;
-	}
-
-	par = da8xx_fb_info->par;
-	par->dev = &device->dev;
-	par->lcdc_clk = tmp_lcdc_clk;
-	par->lcdc_clk_rate = clk_get_rate(par->lcdc_clk);
-
-	par->lcd_supply = devm_regulator_get_optional(&device->dev, "lcd");
-	if (IS_ERR(par->lcd_supply)) {
-		if (PTR_ERR(par->lcd_supply) == -EPROBE_DEFER) {
-			ret = -EPROBE_DEFER;
-			goto err_release_fb;
-		}
-
-		par->lcd_supply = NULL;
-	} else {
-		ret = regulator_enable(par->lcd_supply);
-		if (ret)
-			goto err_release_fb;
-	}
-
-	fb_videomode_to_var(&da8xx_fb_var, lcdc_info);
-	par->cfg = *lcd_cfg;
-
-	da8xx_fb_lcd_reset();
-
-	/* allocate frame buffer */
-	par->vram_size = lcdc_info->xres * lcdc_info->yres * lcd_cfg->bpp;
-	ulcm = lcm((lcdc_info->xres * lcd_cfg->bpp)/8, PAGE_SIZE);
-	par->vram_size = roundup(par->vram_size/8, ulcm);
-	par->vram_size = par->vram_size * LCD_NUM_BUFFERS;
-
-	par->vram_virt = dmam_alloc_coherent(par->dev,
-					     par->vram_size,
-					     &par->vram_phys,
-					     GFP_KERNEL | GFP_DMA);
-	if (!par->vram_virt) {
-		dev_err(&device->dev,
-			"GLCD: kmalloc for frame buffer failed\n");
-		ret = -EINVAL;
-		goto err_disable_reg;
-	}
-
-	da8xx_fb_info->screen_base = (char __iomem *) par->vram_virt;
-	da8xx_fb_fix.smem_start    = par->vram_phys;
-	da8xx_fb_fix.smem_len      = par->vram_size;
-	da8xx_fb_fix.line_length   = (lcdc_info->xres * lcd_cfg->bpp) / 8;
-
-	par->dma_start = par->vram_phys;
-	par->dma_end   = par->dma_start + lcdc_info->yres *
-		da8xx_fb_fix.line_length - 1;
-
-	/* allocate palette buffer */
-	par->v_palette_base = dmam_alloc_coherent(par->dev, PALETTE_SIZE,
-						  &par->p_palette_base,
-						  GFP_KERNEL | GFP_DMA);
-	if (!par->v_palette_base) {
-		dev_err(&device->dev,
-			"GLCD: kmalloc for palette buffer failed\n");
-		ret = -EINVAL;
-		goto err_release_fb;
-	}
-
-	par->irq = platform_get_irq(device, 0);
-	if (par->irq < 0) {
-		ret = -ENOENT;
-		goto err_release_fb;
-	}
-
-	da8xx_fb_var.grayscale =
-	    lcd_cfg->panel_shade == MONOCHROME ? 1 : 0;
-	da8xx_fb_var.bits_per_pixel = lcd_cfg->bpp;
-
-	/* Initialize fbinfo */
-	da8xx_fb_info->fix = da8xx_fb_fix;
-	da8xx_fb_info->var = da8xx_fb_var;
-	da8xx_fb_info->fbops = &da8xx_fb_ops;
-	da8xx_fb_info->pseudo_palette = par->pseudo_palette;
-	da8xx_fb_info->fix.visual = (da8xx_fb_info->var.bits_per_pixel <= 8) ?
-				FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_TRUECOLOR;
-
-	ret = fb_alloc_cmap(&da8xx_fb_info->cmap, PALETTE_SIZE, 0);
-	if (ret)
-		goto err_disable_reg;
-	da8xx_fb_info->cmap.len = par->palette_sz;
-
-	/* initialize var_screeninfo */
-	da8xx_fb_var.activate = FB_ACTIVATE_FORCE;
-	fb_set_var(da8xx_fb_info, &da8xx_fb_var);
-
-	platform_set_drvdata(device, da8xx_fb_info);
-
-	/* initialize the vsync wait queue */
-	init_waitqueue_head(&par->vsync_wait);
-	par->vsync_timeout = HZ / 5;
-	par->which_dma_channel_done = -1;
-	spin_lock_init(&par->lock_for_chan_update);
-
-	/* Register the Frame Buffer  */
-	if (register_framebuffer(da8xx_fb_info) < 0) {
-		dev_err(&device->dev,
-			"GLCD: Frame Buffer Registration Failed!\n");
-		ret = -EINVAL;
-		goto err_dealloc_cmap;
-	}
-
-#ifdef CONFIG_CPU_FREQ
-	ret = lcd_da8xx_cpufreq_register(par);
-	if (ret) {
-		dev_err(&device->dev, "failed to register cpufreq\n");
-		goto err_cpu_freq;
-	}
-#endif
-
-	if (lcd_revision == LCD_VERSION_1)
-		lcdc_irq_handler = lcdc_irq_handler_rev01;
-	else {
-		init_waitqueue_head(&frame_done_wq);
-		lcdc_irq_handler = lcdc_irq_handler_rev02;
-	}
-
-	ret = devm_request_irq(&device->dev, par->irq, lcdc_irq_handler, 0,
-			       DRIVER_NAME, par);
-	if (ret)
-		goto irq_freq;
-	return 0;
-
-irq_freq:
-#ifdef CONFIG_CPU_FREQ
-	lcd_da8xx_cpufreq_deregister(par);
-err_cpu_freq:
-#endif
-	unregister_framebuffer(da8xx_fb_info);
-
-err_dealloc_cmap:
-	fb_dealloc_cmap(&da8xx_fb_info->cmap);
-
-err_disable_reg:
-	if (par->lcd_supply)
-		regulator_disable(par->lcd_supply);
-err_release_fb:
-	framebuffer_release(da8xx_fb_info);
-
-err_pm_runtime_disable:
-	pm_runtime_put_sync(&device->dev);
-	pm_runtime_disable(&device->dev);
-
-	return ret;
-}
-
-#ifdef CONFIG_PM_SLEEP
-static struct lcdc_context {
-	u32 clk_enable;
-	u32 ctrl;
-	u32 dma_ctrl;
-	u32 raster_timing_0;
-	u32 raster_timing_1;
-	u32 raster_timing_2;
-	u32 int_enable_set;
-	u32 dma_frm_buf_base_addr_0;
-	u32 dma_frm_buf_ceiling_addr_0;
-	u32 dma_frm_buf_base_addr_1;
-	u32 dma_frm_buf_ceiling_addr_1;
-	u32 raster_ctrl;
-} reg_context;
-
-static void lcd_context_save(void)
-{
-	if (lcd_revision == LCD_VERSION_2) {
-		reg_context.clk_enable = lcdc_read(LCD_CLK_ENABLE_REG);
-		reg_context.int_enable_set = lcdc_read(LCD_INT_ENABLE_SET_REG);
-	}
-
-	reg_context.ctrl = lcdc_read(LCD_CTRL_REG);
-	reg_context.dma_ctrl = lcdc_read(LCD_DMA_CTRL_REG);
-	reg_context.raster_timing_0 = lcdc_read(LCD_RASTER_TIMING_0_REG);
-	reg_context.raster_timing_1 = lcdc_read(LCD_RASTER_TIMING_1_REG);
-	reg_context.raster_timing_2 = lcdc_read(LCD_RASTER_TIMING_2_REG);
-	reg_context.dma_frm_buf_base_addr_0 =
-		lcdc_read(LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
-	reg_context.dma_frm_buf_ceiling_addr_0 =
-		lcdc_read(LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG);
-	reg_context.dma_frm_buf_base_addr_1 =
-		lcdc_read(LCD_DMA_FRM_BUF_BASE_ADDR_1_REG);
-	reg_context.dma_frm_buf_ceiling_addr_1 =
-		lcdc_read(LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG);
-	reg_context.raster_ctrl = lcdc_read(LCD_RASTER_CTRL_REG);
-	return;
-}
-
-static void lcd_context_restore(void)
-{
-	if (lcd_revision == LCD_VERSION_2) {
-		lcdc_write(reg_context.clk_enable, LCD_CLK_ENABLE_REG);
-		lcdc_write(reg_context.int_enable_set, LCD_INT_ENABLE_SET_REG);
-	}
-
-	lcdc_write(reg_context.ctrl, LCD_CTRL_REG);
-	lcdc_write(reg_context.dma_ctrl, LCD_DMA_CTRL_REG);
-	lcdc_write(reg_context.raster_timing_0, LCD_RASTER_TIMING_0_REG);
-	lcdc_write(reg_context.raster_timing_1, LCD_RASTER_TIMING_1_REG);
-	lcdc_write(reg_context.raster_timing_2, LCD_RASTER_TIMING_2_REG);
-	lcdc_write(reg_context.dma_frm_buf_base_addr_0,
-			LCD_DMA_FRM_BUF_BASE_ADDR_0_REG);
-	lcdc_write(reg_context.dma_frm_buf_ceiling_addr_0,
-			LCD_DMA_FRM_BUF_CEILING_ADDR_0_REG);
-	lcdc_write(reg_context.dma_frm_buf_base_addr_1,
-			LCD_DMA_FRM_BUF_BASE_ADDR_1_REG);
-	lcdc_write(reg_context.dma_frm_buf_ceiling_addr_1,
-			LCD_DMA_FRM_BUF_CEILING_ADDR_1_REG);
-	lcdc_write(reg_context.raster_ctrl, LCD_RASTER_CTRL_REG);
-	return;
-}
-
-static int fb_suspend(struct device *dev)
-{
-	struct fb_info *info = dev_get_drvdata(dev);
-	struct da8xx_fb_par *par = info->par;
-	int ret;
-
-	console_lock();
-	if (par->lcd_supply) {
-		ret = regulator_disable(par->lcd_supply);
-		if (ret)
-			return ret;
-	}
-
-	fb_set_suspend(info, 1);
-	lcd_disable_raster(DA8XX_FRAME_WAIT);
-	lcd_context_save();
-	pm_runtime_put_sync(dev);
-	console_unlock();
-
-	return 0;
-}
-static int fb_resume(struct device *dev)
-{
-	struct fb_info *info = dev_get_drvdata(dev);
-	struct da8xx_fb_par *par = info->par;
-	int ret;
-
-	console_lock();
-	pm_runtime_get_sync(dev);
-	lcd_context_restore();
-	if (par->blank == FB_BLANK_UNBLANK) {
-		lcd_enable_raster();
-
-		if (par->lcd_supply) {
-			ret = regulator_enable(par->lcd_supply);
-			if (ret)
-				return ret;
-		}
-	}
-
-	fb_set_suspend(info, 0);
-	console_unlock();
-
-	return 0;
-}
-#endif
-
-static SIMPLE_DEV_PM_OPS(fb_pm_ops, fb_suspend, fb_resume);
-
-static struct platform_driver da8xx_fb_driver = {
-	.probe = fb_probe,
-	.remove = fb_remove,
-	.driver = {
-		   .name = DRIVER_NAME,
-		   .pm	= &fb_pm_ops,
-		   },
-};
-module_platform_driver(da8xx_fb_driver);
-
-MODULE_DESCRIPTION("Framebuffer driver for TI da8xx/omap-l1xx");
-MODULE_AUTHOR("Texas Instruments");
-MODULE_LICENSE("GPL");
diff --git a/include/video/da8xx-fb.h b/include/video/da8xx-fb.h
deleted file mode 100644
index 1d19ae62b844..000000000000
--- a/include/video/da8xx-fb.h
+++ /dev/null
@@ -1,94 +0,0 @@
-/*
- * Header file for TI DA8XX LCD controller platform data.
- *
- * Copyright (C) 2008-2009 MontaVista Software Inc.
- * Copyright (C) 2008-2009 Texas Instruments Inc
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
-
-#ifndef DA8XX_FB_H
-#define DA8XX_FB_H
-
-enum panel_shade {
-	MONOCHROME = 0,
-	COLOR_ACTIVE,
-	COLOR_PASSIVE,
-};
-
-enum raster_load_mode {
-	LOAD_DATA = 1,
-	LOAD_PALETTE,
-};
-
-enum da8xx_frame_complete {
-	DA8XX_FRAME_WAIT,
-	DA8XX_FRAME_NOWAIT,
-};
-
-struct da8xx_lcdc_platform_data {
-	const char manu_name[10];
-	void *controller_data;
-	const char type[25];
-};
-
-struct lcd_ctrl_config {
-	enum panel_shade panel_shade;
-
-	/* AC Bias Pin Frequency */
-	int ac_bias;
-
-	/* AC Bias Pin Transitions per Interrupt */
-	int ac_bias_intrpt;
-
-	/* DMA burst size */
-	int dma_burst_sz;
-
-	/* Bits per pixel */
-	int bpp;
-
-	/* FIFO DMA Request Delay */
-	int fdd;
-
-	/* TFT Alternative Signal Mapping (Only for active) */
-	unsigned char tft_alt_mode;
-
-	/* 12 Bit Per Pixel (5-6-5) Mode (Only for passive) */
-	unsigned char stn_565_mode;
-
-	/* Mono 8-bit Mode: 1=D0-D7 or 0=D0-D3 */
-	unsigned char mono_8bit_mode;
-
-	/* Horizontal and Vertical Sync Edge: 0=rising 1=falling */
-	unsigned char sync_edge;
-
-	/* Raster Data Order Select: 1=Most-to-least 0=Least-to-most */
-	unsigned char raster_order;
-
-	/* DMA FIFO threshold */
-	int fifo_th;
-};
-
-struct lcd_sync_arg {
-	int back_porch;
-	int front_porch;
-	int pulse_width;
-};
-
-/* ioctls */
-#define FBIOGET_CONTRAST	_IOR('F', 1, int)
-#define FBIOPUT_CONTRAST	_IOW('F', 2, int)
-#define FBIGET_BRIGHTNESS	_IOR('F', 3, int)
-#define FBIPUT_BRIGHTNESS	_IOW('F', 3, int)
-#define FBIGET_COLOR		_IOR('F', 5, int)
-#define FBIPUT_COLOR		_IOW('F', 6, int)
-#define FBIPUT_HSYNC		_IOW('F', 9, int)
-#define FBIPUT_VSYNC		_IOW('F', 10, int)
-
-/* Proprietary FB_SYNC_ flags */
-#define FB_SYNC_CLK_INVERT 0x40000000
-
-#endif  /* ifndef DA8XX_FB_H */
-
-- 
cgit v1.2.3


From f03b296e8b516dbd63f57fc9056c1b0da1b9a0ff Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Mon, 14 Oct 2024 21:27:58 +0200
Subject: fs: pass offset and result to backing_file end_write() callback

This is needed for extending fuse inode size after fuse passthrough write.

Suggested-by: Miklos Szeredi <miklos@szeredi.hu>
Link: https://lore.kernel.org/linux-fsdevel/CAJfpegs=cvZ_NYy6Q_D42XhYS=Sjj5poM1b5TzXzOVvX=R36aA@mail.gmail.com/
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/backing-file.c            | 8 ++++----
 fs/fuse/passthrough.c        | 6 +++---
 fs/overlayfs/file.c          | 9 +++++++--
 include/linux/backing-file.h | 2 +-
 4 files changed, 15 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/fs/backing-file.c b/fs/backing-file.c
index 8860dac58c37..09a9be945d45 100644
--- a/fs/backing-file.c
+++ b/fs/backing-file.c
@@ -80,7 +80,7 @@ struct backing_aio {
 	refcount_t ref;
 	struct kiocb *orig_iocb;
 	/* used for aio completion */
-	void (*end_write)(struct file *);
+	void (*end_write)(struct file *, loff_t, ssize_t);
 	struct work_struct work;
 	long res;
 };
@@ -109,7 +109,7 @@ static void backing_aio_cleanup(struct backing_aio *aio, long res)
 	struct kiocb *orig_iocb = aio->orig_iocb;
 
 	if (aio->end_write)
-		aio->end_write(orig_iocb->ki_filp);
+		aio->end_write(orig_iocb->ki_filp, iocb->ki_pos, res);
 
 	orig_iocb->ki_pos = iocb->ki_pos;
 	backing_aio_put(aio);
@@ -239,7 +239,7 @@ ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter,
 
 		ret = vfs_iter_write(file, iter, &iocb->ki_pos, rwf);
 		if (ctx->end_write)
-			ctx->end_write(ctx->user_file);
+			ctx->end_write(ctx->user_file, iocb->ki_pos, ret);
 	} else {
 		struct backing_aio *aio;
 
@@ -317,7 +317,7 @@ ssize_t backing_file_splice_write(struct pipe_inode_info *pipe,
 	revert_creds(old_cred);
 
 	if (ctx->end_write)
-		ctx->end_write(ctx->user_file);
+		ctx->end_write(ctx->user_file, ppos ? *ppos : 0, ret);
 
 	return ret;
 }
diff --git a/fs/fuse/passthrough.c b/fs/fuse/passthrough.c
index 62aee8289d11..e4e92abe1601 100644
--- a/fs/fuse/passthrough.c
+++ b/fs/fuse/passthrough.c
@@ -18,7 +18,7 @@ static void fuse_file_accessed(struct file *file)
 	fuse_invalidate_atime(inode);
 }
 
-static void fuse_file_modified(struct file *file)
+static void fuse_passthrough_end_write(struct file *file, loff_t pos, ssize_t ret)
 {
 	struct inode *inode = file_inode(file);
 
@@ -63,7 +63,7 @@ ssize_t fuse_passthrough_write_iter(struct kiocb *iocb,
 	struct backing_file_ctx ctx = {
 		.cred = ff->cred,
 		.user_file = file,
-		.end_write = fuse_file_modified,
+		.end_write = fuse_passthrough_end_write,
 	};
 
 	pr_debug("%s: backing_file=0x%p, pos=%lld, len=%zu\n", __func__,
@@ -110,7 +110,7 @@ ssize_t fuse_passthrough_splice_write(struct pipe_inode_info *pipe,
 	struct backing_file_ctx ctx = {
 		.cred = ff->cred,
 		.user_file = out,
-		.end_write = fuse_file_modified,
+		.end_write = fuse_passthrough_end_write,
 	};
 
 	pr_debug("%s: backing_file=0x%p, pos=%lld, len=%zu, flags=0x%x\n", __func__,
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index 4504493b20be..4444c78e2e0c 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -231,6 +231,11 @@ static void ovl_file_modified(struct file *file)
 	ovl_copyattr(file_inode(file));
 }
 
+static void ovl_file_end_write(struct file *file, loff_t pos, ssize_t ret)
+{
+	ovl_file_modified(file);
+}
+
 static void ovl_file_accessed(struct file *file)
 {
 	struct inode *inode, *upperinode;
@@ -294,7 +299,7 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	struct backing_file_ctx ctx = {
 		.cred = ovl_creds(inode->i_sb),
 		.user_file = file,
-		.end_write = ovl_file_modified,
+		.end_write = ovl_file_end_write,
 	};
 
 	if (!iov_iter_count(iter))
@@ -364,7 +369,7 @@ static ssize_t ovl_splice_write(struct pipe_inode_info *pipe, struct file *out,
 	struct backing_file_ctx ctx = {
 		.cred = ovl_creds(inode->i_sb),
 		.user_file = out,
-		.end_write = ovl_file_modified,
+		.end_write = ovl_file_end_write,
 	};
 
 	inode_lock(inode);
diff --git a/include/linux/backing-file.h b/include/linux/backing-file.h
index 4b61b0e57720..2eed0ffb5e8f 100644
--- a/include/linux/backing-file.h
+++ b/include/linux/backing-file.h
@@ -16,7 +16,7 @@ struct backing_file_ctx {
 	const struct cred *cred;
 	struct file *user_file;
 	void (*accessed)(struct file *);
-	void (*end_write)(struct file *);
+	void (*end_write)(struct file *, loff_t, ssize_t);
 };
 
 struct file *backing_file_open(const struct path *user_path, int flags,
-- 
cgit v1.2.3


From 88a387cf9e5f7f7665e6dde8c6610f0ea65c5a6b Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Tue, 1 Oct 2024 15:13:53 +0100
Subject: KVM: Remove unused kvm_vcpu_gfn_to_pfn

The last use of kvm_vcpu_gfn_to_pfn was removed by commit
b1624f99aa8f ("KVM: Remove kvm_vcpu_gfn_to_page() and kvm_vcpu_gpa_to_page()")

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Message-ID: <20241001141354.18009-2-linux@treblig.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 include/linux/kvm_host.h | 1 -
 virt/kvm/kvm_main.c      | 6 ------
 2 files changed, 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index db567d26f7b9..b9b2e42e3fa7 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1314,7 +1314,6 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
 struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn);
 kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn);
-kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map);
 void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty);
 unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 05cbb2548d99..f82131e7978b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3047,12 +3047,6 @@ kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn);
 
-kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn)
-{
-	return gfn_to_pfn_memslot(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn);
-}
-EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn);
-
 int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn,
 			    struct page **pages, int nr_pages)
 {
-- 
cgit v1.2.3


From bc07eea2f3b330127242df2e0ec2d6cd16b4f2e8 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Tue, 1 Oct 2024 15:13:54 +0100
Subject: KVM: Remove unused kvm_vcpu_gfn_to_pfn_atomic

The last use of kvm_vcpu_gfn_to_pfn_atomic was removed by commit
1bbc60d0c7e5 ("KVM: x86/mmu: Remove MMU auditing")

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Message-ID: <20241001141354.18009-3-linux@treblig.org>
[Adjust Documentation/virt/kvm/locking.rst. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 Documentation/virt/kvm/locking.rst | 2 +-
 include/linux/kvm_host.h           | 1 -
 virt/kvm/kvm_main.c                | 6 ------
 3 files changed, 1 insertion(+), 8 deletions(-)

(limited to 'include')

diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst
index 20a9a37d1cdd..1bedd56e2fe3 100644
--- a/Documentation/virt/kvm/locking.rst
+++ b/Documentation/virt/kvm/locking.rst
@@ -136,7 +136,7 @@ For direct sp, we can easily avoid it since the spte of direct sp is fixed
 to gfn.  For indirect sp, we disabled fast page fault for simplicity.
 
 A solution for indirect sp could be to pin the gfn, for example via
-kvm_vcpu_gfn_to_pfn_atomic, before the cmpxchg.  After the pinning:
+gfn_to_pfn_memslot_atomic, before the cmpxchg.  After the pinning:
 
 - We have held the refcount of pfn; that means the pfn can not be freed and
   be reused for another gfn.
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b9b2e42e3fa7..45be36e5285f 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1313,7 +1313,6 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
 struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
 struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn);
-kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn);
 int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map);
 void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty);
 unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index f82131e7978b..141db5b79cd4 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3035,12 +3035,6 @@ kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gf
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic);
 
-kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn)
-{
-	return gfn_to_pfn_memslot_atomic(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn);
-}
-EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn_atomic);
-
 kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
 {
 	return gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn);
-- 
cgit v1.2.3


From 95ecba62e2fd201bcdcca636f5d774f1cd4f1458 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 15 Oct 2024 19:41:18 +0000
Subject: net: fix races in netdev_tx_sent_queue()/dev_watchdog()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some workloads hit the infamous dev_watchdog() message:

"NETDEV WATCHDOG: eth0 (xxxx): transmit queue XX timed out"

It seems possible to hit this even for perfectly normal
BQL enabled drivers:

1) Assume a TX queue was idle for more than dev->watchdog_timeo
   (5 seconds unless changed by the driver)

2) Assume a big packet is sent, exceeding current BQL limit.

3) Driver ndo_start_xmit() puts the packet in TX ring,
   and netdev_tx_sent_queue() is called.

4) QUEUE_STATE_STACK_XOFF could be set from netdev_tx_sent_queue()
   before txq->trans_start has been written.

5) txq->trans_start is written later, from netdev_start_xmit()

    if (rc == NETDEV_TX_OK)
          txq_trans_update(txq)

dev_watchdog() running on another cpu could read the old
txq->trans_start, and then see QUEUE_STATE_STACK_XOFF, because 5)
did not happen yet.

To solve the issue, write txq->trans_start right before one XOFF bit
is set :

- _QUEUE_STATE_DRV_XOFF from netif_tx_stop_queue()
- __QUEUE_STATE_STACK_XOFF from netdev_tx_sent_queue()

From dev_watchdog(), we have to read txq->state before txq->trans_start.

Add memory barriers to enforce correct ordering.

In the future, we could avoid writing over txq->trans_start for normal
operations, and rename this field to txq->xoff_start_time.

Fixes: bec251bc8b6a ("net: no longer stop all TX queues in dev_watchdog()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://patch.msgid.link/20241015194118.3951657-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/netdevice.h | 12 ++++++++++++
 net/sched/sch_generic.c   |  8 +++++++-
 2 files changed, 19 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4d20c776a4ff..8896705ccd63 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3325,6 +3325,12 @@ static inline void netif_tx_wake_all_queues(struct net_device *dev)
 
 static __always_inline void netif_tx_stop_queue(struct netdev_queue *dev_queue)
 {
+	/* Paired with READ_ONCE() from dev_watchdog() */
+	WRITE_ONCE(dev_queue->trans_start, jiffies);
+
+	/* This barrier is paired with smp_mb() from dev_watchdog() */
+	smp_mb__before_atomic();
+
 	/* Must be an atomic op see netif_txq_try_stop() */
 	set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
 }
@@ -3451,6 +3457,12 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
 	if (likely(dql_avail(&dev_queue->dql) >= 0))
 		return;
 
+	/* Paired with READ_ONCE() from dev_watchdog() */
+	WRITE_ONCE(dev_queue->trans_start, jiffies);
+
+	/* This barrier is paired with smp_mb() from dev_watchdog() */
+	smp_mb__before_atomic();
+
 	set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state);
 
 	/*
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 2af24547a82c..38ec18f73de4 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -512,9 +512,15 @@ static void dev_watchdog(struct timer_list *t)
 				struct netdev_queue *txq;
 
 				txq = netdev_get_tx_queue(dev, i);
-				trans_start = READ_ONCE(txq->trans_start);
 				if (!netif_xmit_stopped(txq))
 					continue;
+
+				/* Paired with WRITE_ONCE() + smp_mb...() in
+				 * netdev_tx_sent_queue() and netif_tx_stop_queue().
+				 */
+				smp_mb();
+				trans_start = READ_ONCE(txq->trans_start);
+
 				if (time_after(jiffies, trans_start + dev->watchdog_timeo)) {
 					timedout_ms = jiffies_to_msecs(jiffies - trans_start);
 					atomic_long_inc(&txq->trans_timeout);
-- 
cgit v1.2.3


From 4021e685139d567b3fc862f54101ae9dbb15d8b5 Mon Sep 17 00:00:00 2001
From: Gao Xiang <hsiangkao@linux.alibaba.com>
Date: Wed, 9 Oct 2024 11:31:50 +0800
Subject: fs/super.c: introduce get_tree_bdev_flags()

As Allison reported [1], currently get_tree_bdev() will store
"Can't lookup blockdev" error message.  Although it makes sense for
pure bdev-based fses, this message may mislead users who try to use
EROFS file-backed mounts since get_tree_nodev() is used as a fallback
then.

Add get_tree_bdev_flags() to specify extensible flags [2] and
GET_TREE_BDEV_QUIET_LOOKUP to silence "Can't lookup blockdev" message
since it's misleading to EROFS file-backed mounts now.

[1] https://lore.kernel.org/r/CAOYeF9VQ8jKVmpy5Zy9DNhO6xmWSKMB-DO8yvBB0XvBE7=3Ugg@mail.gmail.com
[2] https://lore.kernel.org/r/ZwUkJEtwIpUA4qMz@infradead.org

Suggested-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Gao Xiang <hsiangkao@linux.alibaba.com>
Link: https://lore.kernel.org/r/20241009033151.2334888-1-hsiangkao@linux.alibaba.com
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/super.c                 | 26 ++++++++++++++++++++------
 include/linux/fs_context.h |  6 ++++++
 2 files changed, 26 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/fs/super.c b/fs/super.c
index 1db230432960..c9c7223bc2a2 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1596,13 +1596,14 @@ int setup_bdev_super(struct super_block *sb, int sb_flags,
 EXPORT_SYMBOL_GPL(setup_bdev_super);
 
 /**
- * get_tree_bdev - Get a superblock based on a single block device
+ * get_tree_bdev_flags - Get a superblock based on a single block device
  * @fc: The filesystem context holding the parameters
  * @fill_super: Helper to initialise a new superblock
+ * @flags: GET_TREE_BDEV_* flags
  */
-int get_tree_bdev(struct fs_context *fc,
-		int (*fill_super)(struct super_block *,
-				  struct fs_context *))
+int get_tree_bdev_flags(struct fs_context *fc,
+		int (*fill_super)(struct super_block *sb,
+				  struct fs_context *fc), unsigned int flags)
 {
 	struct super_block *s;
 	int error = 0;
@@ -1613,10 +1614,10 @@ int get_tree_bdev(struct fs_context *fc,
 
 	error = lookup_bdev(fc->source, &dev);
 	if (error) {
-		errorf(fc, "%s: Can't lookup blockdev", fc->source);
+		if (!(flags & GET_TREE_BDEV_QUIET_LOOKUP))
+			errorf(fc, "%s: Can't lookup blockdev", fc->source);
 		return error;
 	}
-
 	fc->sb_flags |= SB_NOSEC;
 	s = sget_dev(fc, dev);
 	if (IS_ERR(s))
@@ -1644,6 +1645,19 @@ int get_tree_bdev(struct fs_context *fc,
 	fc->root = dget(s->s_root);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(get_tree_bdev_flags);
+
+/**
+ * get_tree_bdev - Get a superblock based on a single block device
+ * @fc: The filesystem context holding the parameters
+ * @fill_super: Helper to initialise a new superblock
+ */
+int get_tree_bdev(struct fs_context *fc,
+		int (*fill_super)(struct super_block *,
+				  struct fs_context *))
+{
+	return get_tree_bdev_flags(fc, fill_super, 0);
+}
 EXPORT_SYMBOL(get_tree_bdev);
 
 static int test_bdev_super(struct super_block *s, void *data)
diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h
index c13e99cbbf81..4b4bfef6f053 100644
--- a/include/linux/fs_context.h
+++ b/include/linux/fs_context.h
@@ -160,6 +160,12 @@ extern int get_tree_keyed(struct fs_context *fc,
 
 int setup_bdev_super(struct super_block *sb, int sb_flags,
 		struct fs_context *fc);
+
+#define GET_TREE_BDEV_QUIET_LOOKUP		0x0001
+int get_tree_bdev_flags(struct fs_context *fc,
+		int (*fill_super)(struct super_block *sb,
+				  struct fs_context *fc), unsigned int flags);
+
 extern int get_tree_bdev(struct fs_context *fc,
 			       int (*fill_super)(struct super_block *sb,
 						 struct fs_context *fc));
-- 
cgit v1.2.3


From d2f8671045b41871053dedaf3035a06ad53d2736 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Mon, 21 Oct 2024 22:11:19 +0800
Subject: LoongArch: Set initial pte entry with PAGE_GLOBAL for kernel space

There are two pages in one TLB entry on LoongArch system. For kernel
space, it requires both two pte entries (buddies) with PAGE_GLOBAL bit
set, otherwise HW treats it as non-global tlb, there will be potential
problems if tlb entry for kernel space is not global. Such as fail to
flush kernel tlb with the function local_flush_tlb_kernel_range() which
supposed only flush tlb with global bit.

Kernel address space areas include percpu, vmalloc, vmemmap, fixmap and
kasan areas. For these areas both two consecutive page table entries
should be enabled with PAGE_GLOBAL bit. So with function set_pte() and
pte_clear(), pte buddy entry is checked and set besides its own pte
entry. However it is not atomic operation to set both two pte entries,
there is problem with test_vmalloc test case.

So function kernel_pte_init() is added to init a pte table when it is
created for kernel address space, and the default initial pte value is
PAGE_GLOBAL rather than zero at beginning. Then only its own pte entry
need update with function set_pte() and pte_clear(), nothing to do with
the pte buddy entry.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/include/asm/pgalloc.h | 11 +++++++++++
 arch/loongarch/include/asm/pgtable.h | 35 +++++++----------------------------
 arch/loongarch/mm/init.c             |  2 ++
 arch/loongarch/mm/pgtable.c          | 20 ++++++++++++++++++++
 include/linux/mm.h                   |  3 ++-
 mm/kasan/init.c                      |  8 +++++++-
 mm/sparse-vmemmap.c                  |  5 +++++
 7 files changed, 54 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/arch/loongarch/include/asm/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h
index 4e2d6b7ca2ee..a7b9c9e73593 100644
--- a/arch/loongarch/include/asm/pgalloc.h
+++ b/arch/loongarch/include/asm/pgalloc.h
@@ -10,6 +10,7 @@
 
 #define __HAVE_ARCH_PMD_ALLOC_ONE
 #define __HAVE_ARCH_PUD_ALLOC_ONE
+#define __HAVE_ARCH_PTE_ALLOC_ONE_KERNEL
 #include <asm-generic/pgalloc.h>
 
 static inline void pmd_populate_kernel(struct mm_struct *mm,
@@ -44,6 +45,16 @@ extern void pagetable_init(void);
 
 extern pgd_t *pgd_alloc(struct mm_struct *mm);
 
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
+{
+	pte_t *pte = __pte_alloc_one_kernel(mm);
+
+	if (pte)
+		kernel_pte_init(pte);
+
+	return pte;
+}
+
 #define __pte_free_tlb(tlb, pte, address)			\
 do {								\
 	pagetable_pte_dtor(page_ptdesc(pte));			\
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index 9965f52ef65b..20714b73f14c 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -269,6 +269,7 @@ extern void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pm
 extern void pgd_init(void *addr);
 extern void pud_init(void *addr);
 extern void pmd_init(void *addr);
+extern void kernel_pte_init(void *addr);
 
 /*
  * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that
@@ -325,39 +326,17 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
 {
 	WRITE_ONCE(*ptep, pteval);
 
-	if (pte_val(pteval) & _PAGE_GLOBAL) {
-		pte_t *buddy = ptep_buddy(ptep);
-		/*
-		 * Make sure the buddy is global too (if it's !none,
-		 * it better already be global)
-		 */
-		if (pte_none(ptep_get(buddy))) {
 #ifdef CONFIG_SMP
-			/*
-			 * For SMP, multiple CPUs can race, so we need
-			 * to do this atomically.
-			 */
-			__asm__ __volatile__(
-			__AMOR "$zero, %[global], %[buddy] \n"
-			: [buddy] "+ZB" (buddy->pte)
-			: [global] "r" (_PAGE_GLOBAL)
-			: "memory");
-
-			DBAR(0b11000); /* o_wrw = 0b11000 */
-#else /* !CONFIG_SMP */
-			WRITE_ONCE(*buddy, __pte(pte_val(ptep_get(buddy)) | _PAGE_GLOBAL));
-#endif /* CONFIG_SMP */
-		}
-	}
+	if (pte_val(pteval) & _PAGE_GLOBAL)
+		DBAR(0b11000); /* o_wrw = 0b11000 */
+#endif
 }
 
 static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
-	/* Preserve global status for the pair */
-	if (pte_val(ptep_get(ptep_buddy(ptep))) & _PAGE_GLOBAL)
-		set_pte(ptep, __pte(_PAGE_GLOBAL));
-	else
-		set_pte(ptep, __pte(0));
+	pte_t pte = ptep_get(ptep);
+	pte_val(pte) &= _PAGE_GLOBAL;
+	set_pte(ptep, pte);
 }
 
 #define PGD_T_LOG2	(__builtin_ffs(sizeof(pgd_t)) - 1)
diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c
index 8a87a482c8f4..188b52bbb254 100644
--- a/arch/loongarch/mm/init.c
+++ b/arch/loongarch/mm/init.c
@@ -201,7 +201,9 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
 		pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
 		if (!pte)
 			panic("%s: Failed to allocate memory\n", __func__);
+
 		pmd_populate_kernel(&init_mm, pmd, pte);
+		kernel_pte_init(pte);
 	}
 
 	return pte_offset_kernel(pmd, addr);
diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c
index eb6a29b491a7..3fa69b23ff84 100644
--- a/arch/loongarch/mm/pgtable.c
+++ b/arch/loongarch/mm/pgtable.c
@@ -116,6 +116,26 @@ void pud_init(void *addr)
 EXPORT_SYMBOL_GPL(pud_init);
 #endif
 
+void kernel_pte_init(void *addr)
+{
+	unsigned long *p, *end;
+
+	p = (unsigned long *)addr;
+	end = p + PTRS_PER_PTE;
+
+	do {
+		p[0] = _PAGE_GLOBAL;
+		p[1] = _PAGE_GLOBAL;
+		p[2] = _PAGE_GLOBAL;
+		p[3] = _PAGE_GLOBAL;
+		p[4] = _PAGE_GLOBAL;
+		p += 8;
+		p[-3] = _PAGE_GLOBAL;
+		p[-2] = _PAGE_GLOBAL;
+		p[-1] = _PAGE_GLOBAL;
+	} while (p != end);
+}
+
 pmd_t mk_pmd(struct page *page, pgprot_t prot)
 {
 	pmd_t pmd;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ecf63d2b0582..61fff5d34ed5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3818,8 +3818,9 @@ void *sparse_buffer_alloc(unsigned long size);
 struct page * __populate_section_memmap(unsigned long pfn,
 		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
 		struct dev_pagemap *pgmap);
-void pmd_init(void *addr);
 void pud_init(void *addr);
+void pmd_init(void *addr);
+void kernel_pte_init(void *addr);
 pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
 p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node);
 pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node);
diff --git a/mm/kasan/init.c b/mm/kasan/init.c
index 89895f38f722..ac607c306292 100644
--- a/mm/kasan/init.c
+++ b/mm/kasan/init.c
@@ -106,6 +106,10 @@ static void __ref zero_pte_populate(pmd_t *pmd, unsigned long addr,
 	}
 }
 
+void __weak __meminit kernel_pte_init(void *addr)
+{
+}
+
 static int __ref zero_pmd_populate(pud_t *pud, unsigned long addr,
 				unsigned long end)
 {
@@ -126,8 +130,10 @@ static int __ref zero_pmd_populate(pud_t *pud, unsigned long addr,
 
 			if (slab_is_available())
 				p = pte_alloc_one_kernel(&init_mm);
-			else
+			else {
 				p = early_alloc(PAGE_SIZE, NUMA_NO_NODE);
+				kernel_pte_init(p);
+			}
 			if (!p)
 				return -ENOMEM;
 
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index edcc7a6b0f6f..c0388b2e959d 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -184,6 +184,10 @@ static void * __meminit vmemmap_alloc_block_zero(unsigned long size, int node)
 	return p;
 }
 
+void __weak __meminit kernel_pte_init(void *addr)
+{
+}
+
 pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node)
 {
 	pmd_t *pmd = pmd_offset(pud, addr);
@@ -191,6 +195,7 @@ pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node)
 		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
 		if (!p)
 			return NULL;
+		kernel_pte_init(p);
 		pmd_populate_kernel(&init_mm, pmd, p);
 	}
 	return pmd;
-- 
cgit v1.2.3


From 6db388585e486c0261aeef55f8bc63a9b45756c0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 15 Oct 2024 06:13:50 +0200
Subject: iomap: turn iomap_want_unshare_iter into an inline function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

iomap_want_unshare_iter currently sits in fs/iomap/buffered-io.c, which
depends on CONFIG_BLOCK.  It is also in used in fs/dax.c whіch has no
such dependency.  Given that it is a trivial check turn it into an inline
in include/linux/iomap.h to fix the DAX && !BLOCK build.

Fixes: 6ef6a0e821d3 ("iomap: share iomap_unshare_iter predicate code with fsdax")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20241015041350.118403-1-hch@lst.de
Reviewed-by: Brian Foster <bfoster@redhat.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/buffered-io.c | 17 -----------------
 include/linux/iomap.h  | 20 +++++++++++++++++++-
 2 files changed, 19 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 3899169b2cf7..6db2aaf808d5 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1309,23 +1309,6 @@ void iomap_file_buffered_write_punch_delalloc(struct inode *inode,
 }
 EXPORT_SYMBOL_GPL(iomap_file_buffered_write_punch_delalloc);
 
-bool iomap_want_unshare_iter(const struct iomap_iter *iter)
-{
-	/*
-	 * Don't bother with blocks that are not shared to start with; or
-	 * mappings that cannot be shared, such as inline data, delalloc
-	 * reservations, holes or unwritten extents.
-	 *
-	 * Note that we use srcmap directly instead of iomap_iter_srcmap as
-	 * unsharing requires providing a separate source map, and the presence
-	 * of one is a good indicator that unsharing is needed, unlike
-	 * IOMAP_F_SHARED which can be set for any data that goes into the COW
-	 * fork for XFS.
-	 */
-	return (iter->iomap.flags & IOMAP_F_SHARED) &&
-		iter->srcmap.type == IOMAP_MAPPED;
-}
-
 static loff_t iomap_unshare_iter(struct iomap_iter *iter)
 {
 	struct iomap *iomap = &iter->iomap;
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index d8a7fc84348c..0198f36e521e 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -256,6 +256,25 @@ static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i)
 	return &i->iomap;
 }
 
+/*
+ * Check if the range needs to be unshared for a FALLOC_FL_UNSHARE_RANGE
+ * operation.
+ *
+ * Don't bother with blocks that are not shared to start with; or mappings that
+ * cannot be shared, such as inline data, delalloc reservations, holes or
+ * unwritten extents.
+ *
+ * Note that we use srcmap directly instead of iomap_iter_srcmap as unsharing
+ * requires providing a separate source map, and the presence of one is a good
+ * indicator that unsharing is needed, unlike IOMAP_F_SHARED which can be set
+ * for any data that goes into the COW fork for XFS.
+ */
+static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter)
+{
+	return (iter->iomap.flags & IOMAP_F_SHARED) &&
+		iter->srcmap.type == IOMAP_MAPPED;
+}
+
 ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 		const struct iomap_ops *ops, void *private);
 int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops);
@@ -267,7 +286,6 @@ void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len);
 bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio);
 int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 		const struct iomap_ops *ops);
-bool iomap_want_unshare_iter(const struct iomap_iter *iter);
 int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
 		bool *did_zero, const struct iomap_ops *ops);
 int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
-- 
cgit v1.2.3


From 6fad274f06f038c29660aa53fbad14241c9fd976 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Mon, 21 Oct 2024 17:28:05 +0200
Subject: bpf: Add MEM_WRITE attribute

Add a MEM_WRITE attribute for BPF helper functions which can be used in
bpf_func_proto to annotate an argument type in order to let the verifier
know that the helper writes into the memory passed as an argument. In
the past MEM_UNINIT has been (ab)used for this function, but the latter
merely tells the verifier that the passed memory can be uninitialized.

There have been bugs with overloading the latter but aside from that
there are also cases where the passed memory is read + written which
currently cannot be expressed, see also 4b3786a6c539 ("bpf: Zero former
ARG_PTR_TO_{LONG,INT} args in case of error").

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20241021152809.33343-1-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h      | 14 +++++++++++---
 kernel/bpf/helpers.c     | 10 +++++-----
 kernel/bpf/ringbuf.c     |  2 +-
 kernel/bpf/syscall.c     |  2 +-
 kernel/trace/bpf_trace.c |  4 ++--
 net/core/filter.c        |  4 ++--
 6 files changed, 22 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 19d8ca8ac960..bdadb0bb6cec 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -635,6 +635,7 @@ enum bpf_type_flag {
 	 */
 	PTR_UNTRUSTED		= BIT(6 + BPF_BASE_TYPE_BITS),
 
+	/* MEM can be uninitialized. */
 	MEM_UNINIT		= BIT(7 + BPF_BASE_TYPE_BITS),
 
 	/* DYNPTR points to memory local to the bpf program. */
@@ -700,6 +701,13 @@ enum bpf_type_flag {
 	 */
 	MEM_ALIGNED		= BIT(17 + BPF_BASE_TYPE_BITS),
 
+	/* MEM is being written to, often combined with MEM_UNINIT. Non-presence
+	 * of MEM_WRITE means that MEM is only being read. MEM_WRITE without the
+	 * MEM_UNINIT means that memory needs to be initialized since it is also
+	 * read.
+	 */
+	MEM_WRITE		= BIT(18 + BPF_BASE_TYPE_BITS),
+
 	__BPF_TYPE_FLAG_MAX,
 	__BPF_TYPE_LAST_FLAG	= __BPF_TYPE_FLAG_MAX - 1,
 };
@@ -758,10 +766,10 @@ enum bpf_arg_type {
 	ARG_PTR_TO_SOCKET_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET,
 	ARG_PTR_TO_STACK_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_STACK,
 	ARG_PTR_TO_BTF_ID_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID,
-	/* pointer to memory does not need to be initialized, helper function must fill
-	 * all bytes or clear them in error case.
+	/* Pointer to memory does not need to be initialized, since helper function
+	 * fills all bytes or clears them in error case.
 	 */
-	ARG_PTR_TO_UNINIT_MEM		= MEM_UNINIT | ARG_PTR_TO_MEM,
+	ARG_PTR_TO_UNINIT_MEM		= MEM_UNINIT | MEM_WRITE | ARG_PTR_TO_MEM,
 	/* Pointer to valid memory of size known at compile time. */
 	ARG_PTR_TO_FIXED_SIZE_MEM	= MEM_FIXED_SIZE | ARG_PTR_TO_MEM,
 
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 1a43d06eab28..ca3f0a2e5ed5 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -111,7 +111,7 @@ const struct bpf_func_proto bpf_map_pop_elem_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_MAP_VALUE | MEM_UNINIT,
+	.arg2_type	= ARG_PTR_TO_MAP_VALUE | MEM_UNINIT | MEM_WRITE,
 };
 
 BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value)
@@ -124,7 +124,7 @@ const struct bpf_func_proto bpf_map_peek_elem_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_MAP_VALUE | MEM_UNINIT,
+	.arg2_type	= ARG_PTR_TO_MAP_VALUE | MEM_UNINIT | MEM_WRITE,
 };
 
 BPF_CALL_3(bpf_map_lookup_percpu_elem, struct bpf_map *, map, void *, key, u32, cpu)
@@ -538,7 +538,7 @@ const struct bpf_func_proto bpf_strtol_proto = {
 	.arg1_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg2_type	= ARG_CONST_SIZE,
 	.arg3_type	= ARG_ANYTHING,
-	.arg4_type	= ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
+	.arg4_type	= ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED,
 	.arg4_size	= sizeof(s64),
 };
 
@@ -566,7 +566,7 @@ const struct bpf_func_proto bpf_strtoul_proto = {
 	.arg1_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
 	.arg2_type	= ARG_CONST_SIZE,
 	.arg3_type	= ARG_ANYTHING,
-	.arg4_type	= ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
+	.arg4_type	= ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED,
 	.arg4_size	= sizeof(u64),
 };
 
@@ -1742,7 +1742,7 @@ static const struct bpf_func_proto bpf_dynptr_from_mem_proto = {
 	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
 	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg3_type	= ARG_ANYTHING,
-	.arg4_type	= ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT,
+	.arg4_type	= ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT | MEM_WRITE,
 };
 
 BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern *, src,
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index de3b681d1d13..e1cfe890e0be 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -632,7 +632,7 @@ const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto = {
 	.arg1_type	= ARG_CONST_MAP_PTR,
 	.arg2_type	= ARG_ANYTHING,
 	.arg3_type	= ARG_ANYTHING,
-	.arg4_type	= ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | MEM_UNINIT,
+	.arg4_type	= ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | MEM_UNINIT | MEM_WRITE,
 };
 
 BPF_CALL_2(bpf_ringbuf_submit_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 8cfa7183d2ef..67179529080b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5892,7 +5892,7 @@ static const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = {
 	.arg1_type	= ARG_PTR_TO_MEM,
 	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
 	.arg3_type	= ARG_ANYTHING,
-	.arg4_type	= ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
+	.arg4_type	= ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED,
 	.arg4_size	= sizeof(u64),
 };
 
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 3bd402fa62a4..95b6b3b16bac 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1202,7 +1202,7 @@ static const struct bpf_func_proto bpf_get_func_arg_proto = {
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_CTX,
 	.arg2_type	= ARG_ANYTHING,
-	.arg3_type	= ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
+	.arg3_type	= ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED,
 	.arg3_size	= sizeof(u64),
 };
 
@@ -1219,7 +1219,7 @@ static const struct bpf_func_proto bpf_get_func_ret_proto = {
 	.func		= get_func_ret,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_CTX,
-	.arg2_type	= ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
+	.arg2_type	= ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED,
 	.arg2_size	= sizeof(u64),
 };
 
diff --git a/net/core/filter.c b/net/core/filter.c
index cb272b35d484..16b324d519da 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6368,7 +6368,7 @@ static const struct bpf_func_proto bpf_skb_check_mtu_proto = {
 	.ret_type	= RET_INTEGER,
 	.arg1_type      = ARG_PTR_TO_CTX,
 	.arg2_type      = ARG_ANYTHING,
-	.arg3_type      = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
+	.arg3_type      = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED,
 	.arg3_size	= sizeof(u32),
 	.arg4_type      = ARG_ANYTHING,
 	.arg5_type      = ARG_ANYTHING,
@@ -6380,7 +6380,7 @@ static const struct bpf_func_proto bpf_xdp_check_mtu_proto = {
 	.ret_type	= RET_INTEGER,
 	.arg1_type      = ARG_PTR_TO_CTX,
 	.arg2_type      = ARG_ANYTHING,
-	.arg3_type      = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
+	.arg3_type      = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_WRITE | MEM_ALIGNED,
 	.arg3_size	= sizeof(u32),
 	.arg4_type      = ARG_ANYTHING,
 	.arg5_type      = ARG_ANYTHING,
-- 
cgit v1.2.3


From 1bf4470a3939c678fb822073e9ea77a0560bc6bb Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 22 Oct 2024 12:31:08 -0400
Subject: Bluetooth: SCO: Fix UAF on sco_sock_timeout

conn->sk maybe have been unlinked/freed while waiting for sco_conn_lock
so this checks if the conn->sk is still valid by checking if it part of
sco_sk_list.

Reported-by: syzbot+4c0d0c4cde787116d465@syzkaller.appspotmail.com
Tested-by: syzbot+4c0d0c4cde787116d465@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=4c0d0c4cde787116d465
Fixes: ba316be1b6a0 ("Bluetooth: schedule SCO timeouts with delayed_work")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/bluetooth.h |  1 +
 net/bluetooth/af_bluetooth.c      | 22 ++++++++++++++++++++++
 net/bluetooth/sco.c               | 18 ++++++++++++------
 3 files changed, 35 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 5d655e109b2c..f66bc85c6411 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -403,6 +403,7 @@ int  bt_sock_register(int proto, const struct net_proto_family *ops);
 void bt_sock_unregister(int proto);
 void bt_sock_link(struct bt_sock_list *l, struct sock *s);
 void bt_sock_unlink(struct bt_sock_list *l, struct sock *s);
+bool bt_sock_linked(struct bt_sock_list *l, struct sock *s);
 struct sock *bt_sock_alloc(struct net *net, struct socket *sock,
 			   struct proto *prot, int proto, gfp_t prio, int kern);
 int  bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 67604ccec2f4..bdce9270487d 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -185,6 +185,28 @@ void bt_sock_unlink(struct bt_sock_list *l, struct sock *sk)
 }
 EXPORT_SYMBOL(bt_sock_unlink);
 
+bool bt_sock_linked(struct bt_sock_list *l, struct sock *s)
+{
+	struct sock *sk;
+
+	if (!l || !s)
+		return false;
+
+	read_lock(&l->lock);
+
+	sk_for_each(sk, &l->head) {
+		if (s == sk) {
+			read_unlock(&l->lock);
+			return true;
+		}
+	}
+
+	read_unlock(&l->lock);
+
+	return false;
+}
+EXPORT_SYMBOL(bt_sock_linked);
+
 void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh)
 {
 	const struct cred *old_cred;
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index a5ac160c592e..1c7252a36866 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -76,6 +76,16 @@ struct sco_pinfo {
 #define SCO_CONN_TIMEOUT	(HZ * 40)
 #define SCO_DISCONN_TIMEOUT	(HZ * 2)
 
+static struct sock *sco_sock_hold(struct sco_conn *conn)
+{
+	if (!conn || !bt_sock_linked(&sco_sk_list, conn->sk))
+		return NULL;
+
+	sock_hold(conn->sk);
+
+	return conn->sk;
+}
+
 static void sco_sock_timeout(struct work_struct *work)
 {
 	struct sco_conn *conn = container_of(work, struct sco_conn,
@@ -87,9 +97,7 @@ static void sco_sock_timeout(struct work_struct *work)
 		sco_conn_unlock(conn);
 		return;
 	}
-	sk = conn->sk;
-	if (sk)
-		sock_hold(sk);
+	sk = sco_sock_hold(conn);
 	sco_conn_unlock(conn);
 
 	if (!sk)
@@ -194,9 +202,7 @@ static void sco_conn_del(struct hci_conn *hcon, int err)
 
 	/* Kill socket */
 	sco_conn_lock(conn);
-	sk = conn->sk;
-	if (sk)
-		sock_hold(sk);
+	sk = sco_sock_hold(conn);
 	sco_conn_unlock(conn);
 
 	if (sk) {
-- 
cgit v1.2.3


From 894b00a3350c560990638bdf89bdf1f3d5491950 Mon Sep 17 00:00:00 2001
From: Marco Elver <elver@google.com>
Date: Mon, 21 Oct 2024 14:00:10 +0200
Subject: kasan: Fix Software Tag-Based KASAN with GCC

Per [1], -fsanitize=kernel-hwaddress with GCC currently does not disable
instrumentation in functions with __attribute__((no_sanitize_address)).

However, __attribute__((no_sanitize("hwaddress"))) does correctly
disable instrumentation. Use it instead.

Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117196 [1]
Link: https://lore.kernel.org/r/000000000000f362e80620e27859@google.com
Link: https://lore.kernel.org/r/ZvFGwKfoC4yVjN_X@J2N7QTR9R3
Link: https://bugzilla.kernel.org/show_bug.cgi?id=218854
Reported-by: syzbot+908886656a02769af987@syzkaller.appspotmail.com
Tested-by: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrew Pinski <pinskia@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Marco Elver <elver@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Fixes: 7b861a53e46b ("kasan: Bump required compiler version")
Link: https://lore.kernel.org/r/20241021120013.3209481-1-elver@google.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 include/linux/compiler-gcc.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index f805adaa316e..cd6f9aae311f 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -80,7 +80,11 @@
 #define __noscs __attribute__((__no_sanitize__("shadow-call-stack")))
 #endif
 
+#ifdef __SANITIZE_HWADDRESS__
+#define __no_sanitize_address __attribute__((__no_sanitize__("hwaddress")))
+#else
 #define __no_sanitize_address __attribute__((__no_sanitize_address__))
+#endif
 
 #if defined(__SANITIZE_THREAD__)
 #define __no_sanitize_thread __attribute__((__no_sanitize_thread__))
-- 
cgit v1.2.3


From 247d65fb122ad560be1c8c4d87d7374fb28b0770 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Wed, 23 Oct 2024 11:40:10 +0100
Subject: afs: Fix missing subdir edit when renamed between parent dirs

When rename moves an AFS subdirectory between parent directories, the
subdir also needs a bit of editing: the ".." entry needs updating to point
to the new parent (though I don't make use of the info) and the DV needs
incrementing by 1 to reflect the change of content.  The server also sends
a callback break notification on the subdirectory if we have one, but we
can take care of recovering the promise next time we access the subdir.

This can be triggered by something like:

    mount -t afs %example.com:xfstest.test20 /xfstest.test/
    mkdir /xfstest.test/{aaa,bbb,aaa/ccc}
    touch /xfstest.test/bbb/ccc/d
    mv /xfstest.test/{aaa/ccc,bbb/ccc}
    touch /xfstest.test/bbb/ccc/e

When the pathwalk for the second touch hits "ccc", kafs spots that the DV
is incorrect and downloads it again (so the fix is not critical).

Fix this, if the rename target is a directory and the old and new
parents are different, by:

 (1) Incrementing the DV number of the target locally.

 (2) Editing the ".." entry in the target to refer to its new parent's
     vnode ID and uniquifier.

Link: https://lore.kernel.org/r/3340431.1729680010@warthog.procyon.org.uk
Fixes: 63a4681ff39c ("afs: Locally edit directory data for mkdir/create/unlink/...")
cc: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/afs/dir.c               | 25 +++++++++++++
 fs/afs/dir_edit.c          | 91 +++++++++++++++++++++++++++++++++++++++++++++-
 fs/afs/internal.h          |  2 +
 include/trace/events/afs.h |  7 +++-
 4 files changed, 122 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index f8622ed72e08..ada363af5aab 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -12,6 +12,7 @@
 #include <linux/swap.h>
 #include <linux/ctype.h>
 #include <linux/sched.h>
+#include <linux/iversion.h>
 #include <linux/task_io_accounting_ops.h>
 #include "internal.h"
 #include "afs_fs.h"
@@ -1823,6 +1824,8 @@ error:
 
 static void afs_rename_success(struct afs_operation *op)
 {
+	struct afs_vnode *vnode = AFS_FS_I(d_inode(op->dentry));
+
 	_enter("op=%08x", op->debug_id);
 
 	op->ctime = op->file[0].scb.status.mtime_client;
@@ -1832,6 +1835,22 @@ static void afs_rename_success(struct afs_operation *op)
 		op->ctime = op->file[1].scb.status.mtime_client;
 		afs_vnode_commit_status(op, &op->file[1]);
 	}
+
+	/* If we're moving a subdir between dirs, we need to update
+	 * its DV counter too as the ".." will be altered.
+	 */
+	if (S_ISDIR(vnode->netfs.inode.i_mode) &&
+	    op->file[0].vnode != op->file[1].vnode) {
+		u64 new_dv;
+
+		write_seqlock(&vnode->cb_lock);
+
+		new_dv = vnode->status.data_version + 1;
+		vnode->status.data_version = new_dv;
+		inode_set_iversion_raw(&vnode->netfs.inode, new_dv);
+
+		write_sequnlock(&vnode->cb_lock);
+	}
 }
 
 static void afs_rename_edit_dir(struct afs_operation *op)
@@ -1873,6 +1892,12 @@ static void afs_rename_edit_dir(struct afs_operation *op)
 				 &vnode->fid, afs_edit_dir_for_rename_2);
 	}
 
+	if (S_ISDIR(vnode->netfs.inode.i_mode) &&
+	    new_dvnode != orig_dvnode &&
+	    test_bit(AFS_VNODE_DIR_VALID, &vnode->flags))
+		afs_edit_dir_update_dotdot(vnode, new_dvnode,
+					   afs_edit_dir_for_rename_sub);
+
 	new_inode = d_inode(new_dentry);
 	if (new_inode) {
 		spin_lock(&new_inode->i_lock);
diff --git a/fs/afs/dir_edit.c b/fs/afs/dir_edit.c
index a71bff10496b..fe223fb78111 100644
--- a/fs/afs/dir_edit.c
+++ b/fs/afs/dir_edit.c
@@ -127,10 +127,10 @@ static struct folio *afs_dir_get_folio(struct afs_vnode *vnode, pgoff_t index)
 /*
  * Scan a directory block looking for a dirent of the right name.
  */
-static int afs_dir_scan_block(union afs_xdr_dir_block *block, struct qstr *name,
+static int afs_dir_scan_block(const union afs_xdr_dir_block *block, const struct qstr *name,
 			      unsigned int blocknum)
 {
-	union afs_xdr_dirent *de;
+	const union afs_xdr_dirent *de;
 	u64 bitmap;
 	int d, len, n;
 
@@ -492,3 +492,90 @@ error:
 	clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
 	goto out_unmap;
 }
+
+/*
+ * Edit a subdirectory that has been moved between directories to update the
+ * ".." entry.
+ */
+void afs_edit_dir_update_dotdot(struct afs_vnode *vnode, struct afs_vnode *new_dvnode,
+				enum afs_edit_dir_reason why)
+{
+	union afs_xdr_dir_block *block;
+	union afs_xdr_dirent *de;
+	struct folio *folio;
+	unsigned int nr_blocks, b;
+	pgoff_t index;
+	loff_t i_size;
+	int slot;
+
+	_enter("");
+
+	i_size = i_size_read(&vnode->netfs.inode);
+	if (i_size < AFS_DIR_BLOCK_SIZE) {
+		clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
+		return;
+	}
+	nr_blocks = i_size / AFS_DIR_BLOCK_SIZE;
+
+	/* Find a block that has sufficient slots available.  Each folio
+	 * contains two or more directory blocks.
+	 */
+	for (b = 0; b < nr_blocks; b++) {
+		index = b / AFS_DIR_BLOCKS_PER_PAGE;
+		folio = afs_dir_get_folio(vnode, index);
+		if (!folio)
+			goto error;
+
+		block = kmap_local_folio(folio, b * AFS_DIR_BLOCK_SIZE - folio_pos(folio));
+
+		/* Abandon the edit if we got a callback break. */
+		if (!test_bit(AFS_VNODE_DIR_VALID, &vnode->flags))
+			goto invalidated;
+
+		slot = afs_dir_scan_block(block, &dotdot_name, b);
+		if (slot >= 0)
+			goto found_dirent;
+
+		kunmap_local(block);
+		folio_unlock(folio);
+		folio_put(folio);
+	}
+
+	/* Didn't find the dirent to clobber.  Download the directory again. */
+	trace_afs_edit_dir(vnode, why, afs_edit_dir_update_nodd,
+			   0, 0, 0, 0, "..");
+	clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
+	goto out;
+
+found_dirent:
+	de = &block->dirents[slot];
+	de->u.vnode  = htonl(new_dvnode->fid.vnode);
+	de->u.unique = htonl(new_dvnode->fid.unique);
+
+	trace_afs_edit_dir(vnode, why, afs_edit_dir_update_dd, b, slot,
+			   ntohl(de->u.vnode), ntohl(de->u.unique), "..");
+
+	kunmap_local(block);
+	folio_unlock(folio);
+	folio_put(folio);
+	inode_set_iversion_raw(&vnode->netfs.inode, vnode->status.data_version);
+
+out:
+	_leave("");
+	return;
+
+invalidated:
+	kunmap_local(block);
+	folio_unlock(folio);
+	folio_put(folio);
+	trace_afs_edit_dir(vnode, why, afs_edit_dir_update_inval,
+			   0, 0, 0, 0, "..");
+	clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
+	goto out;
+
+error:
+	trace_afs_edit_dir(vnode, why, afs_edit_dir_update_error,
+			   0, 0, 0, 0, "..");
+	clear_bit(AFS_VNODE_DIR_VALID, &vnode->flags);
+	goto out;
+}
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 6e1d3c4daf72..b306c0980870 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -1072,6 +1072,8 @@ extern void afs_check_for_remote_deletion(struct afs_operation *);
 extern void afs_edit_dir_add(struct afs_vnode *, struct qstr *, struct afs_fid *,
 			     enum afs_edit_dir_reason);
 extern void afs_edit_dir_remove(struct afs_vnode *, struct qstr *, enum afs_edit_dir_reason);
+void afs_edit_dir_update_dotdot(struct afs_vnode *vnode, struct afs_vnode *new_dvnode,
+				enum afs_edit_dir_reason why);
 
 /*
  * dir_silly.c
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 450c44c83a5d..a0aed1a428a1 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -331,7 +331,11 @@ enum yfs_cm_operation {
 	EM(afs_edit_dir_delete,			"delete") \
 	EM(afs_edit_dir_delete_error,		"d_err ") \
 	EM(afs_edit_dir_delete_inval,		"d_invl") \
-	E_(afs_edit_dir_delete_noent,		"d_nent")
+	EM(afs_edit_dir_delete_noent,		"d_nent") \
+	EM(afs_edit_dir_update_dd,		"u_ddot") \
+	EM(afs_edit_dir_update_error,		"u_fail") \
+	EM(afs_edit_dir_update_inval,		"u_invl") \
+	E_(afs_edit_dir_update_nodd,		"u_nodd")
 
 #define afs_edit_dir_reasons				  \
 	EM(afs_edit_dir_for_create,		"Create") \
@@ -340,6 +344,7 @@ enum yfs_cm_operation {
 	EM(afs_edit_dir_for_rename_0,		"Renam0") \
 	EM(afs_edit_dir_for_rename_1,		"Renam1") \
 	EM(afs_edit_dir_for_rename_2,		"Renam2") \
+	EM(afs_edit_dir_for_rename_sub,		"RnmSub") \
 	EM(afs_edit_dir_for_rmdir,		"RmDir ") \
 	EM(afs_edit_dir_for_silly_0,		"S_Ren0") \
 	EM(afs_edit_dir_for_silly_1,		"S_Ren1") \
-- 
cgit v1.2.3


From c2f803052bc7a7feb2e03befccc8e49b6ff1f5f5 Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Thu, 24 Oct 2024 09:35:57 +0800
Subject: bpf: Add the missing BPF_LINK_TYPE invocation for sockmap

There is an out-of-bounds read in bpf_link_show_fdinfo() for the sockmap
link fd. Fix it by adding the missing BPF_LINK_TYPE invocation for
sockmap link

Also add comments for bpf_link_type to prevent missing updates in the
future.

Fixes: 699c23f02c65 ("bpf: Add bpf_link support for sk_msg and sk_skb progs")
Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20241024013558.1135167-2-houtao@huaweicloud.com
---
 include/linux/bpf_types.h      | 1 +
 include/uapi/linux/bpf.h       | 3 +++
 tools/include/uapi/linux/bpf.h | 3 +++
 3 files changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 9f2a6b83b49e..fa78f49d4a9a 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -146,6 +146,7 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp)
 BPF_LINK_TYPE(BPF_LINK_TYPE_NETFILTER, netfilter)
 BPF_LINK_TYPE(BPF_LINK_TYPE_TCX, tcx)
 BPF_LINK_TYPE(BPF_LINK_TYPE_NETKIT, netkit)
+BPF_LINK_TYPE(BPF_LINK_TYPE_SOCKMAP, sockmap)
 #endif
 #ifdef CONFIG_PERF_EVENTS
 BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index e8241b320c6d..4a939c90dc2e 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1121,6 +1121,9 @@ enum bpf_attach_type {
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
+/* Add BPF_LINK_TYPE(type, name) in bpf_types.h to keep bpf_link_type_strs[]
+ * in sync with the definitions below.
+ */
 enum bpf_link_type {
 	BPF_LINK_TYPE_UNSPEC = 0,
 	BPF_LINK_TYPE_RAW_TRACEPOINT = 1,
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index e8241b320c6d..4a939c90dc2e 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1121,6 +1121,9 @@ enum bpf_attach_type {
 
 #define MAX_BPF_ATTACH_TYPE __MAX_BPF_ATTACH_TYPE
 
+/* Add BPF_LINK_TYPE(type, name) in bpf_types.h to keep bpf_link_type_strs[]
+ * in sync with the definitions below.
+ */
 enum bpf_link_type {
 	BPF_LINK_TYPE_UNSPEC = 0,
 	BPF_LINK_TYPE_RAW_TRACEPOINT = 1,
-- 
cgit v1.2.3


From 101c268bd2f37e965a5468353e62d154db38838e Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Tue, 22 Oct 2024 18:43:49 -0700
Subject: cxl/port: Fix use-after-free, permit out-of-order decoder shutdown

In support of investigating an initialization failure report [1],
cxl_test was updated to register mock memory-devices after the mock
root-port/bus device had been registered. That led to cxl_test crashing
with a use-after-free bug with the following signature:

    cxl_port_attach_region: cxl region3: cxl_host_bridge.0:port3 decoder3.0 add: mem0:decoder7.0 @ 0 next: cxl_switch_uport.0 nr_eps: 1 nr_targets: 1
    cxl_port_attach_region: cxl region3: cxl_host_bridge.0:port3 decoder3.0 add: mem4:decoder14.0 @ 1 next: cxl_switch_uport.0 nr_eps: 2 nr_targets: 1
    cxl_port_setup_targets: cxl region3: cxl_switch_uport.0:port6 target[0] = cxl_switch_dport.0 for mem0:decoder7.0 @ 0
1)  cxl_port_setup_targets: cxl region3: cxl_switch_uport.0:port6 target[1] = cxl_switch_dport.4 for mem4:decoder14.0 @ 1
    [..]
    cxld_unregister: cxl decoder14.0:
    cxl_region_decode_reset: cxl_region region3:
    mock_decoder_reset: cxl_port port3: decoder3.0 reset
2)  mock_decoder_reset: cxl_port port3: decoder3.0: out of order reset, expected decoder3.1
    cxl_endpoint_decoder_release: cxl decoder14.0:
    [..]
    cxld_unregister: cxl decoder7.0:
3)  cxl_region_decode_reset: cxl_region region3:
    Oops: general protection fault, probably for non-canonical address 0x6b6b6b6b6b6b6bc3: 0000 [#1] PREEMPT SMP PTI
    [..]
    RIP: 0010:to_cxl_port+0x8/0x60 [cxl_core]
    [..]
    Call Trace:
     <TASK>
     cxl_region_decode_reset+0x69/0x190 [cxl_core]
     cxl_region_detach+0xe8/0x210 [cxl_core]
     cxl_decoder_kill_region+0x27/0x40 [cxl_core]
     cxld_unregister+0x5d/0x60 [cxl_core]

At 1) a region has been established with 2 endpoint decoders (7.0 and
14.0). Those endpoints share a common switch-decoder in the topology
(3.0). At teardown, 2), decoder14.0 is the first to be removed and hits
the "out of order reset case" in the switch decoder. The effect though
is that region3 cleanup is aborted leaving it in-tact and
referencing decoder14.0. At 3) the second attempt to teardown region3
trips over the stale decoder14.0 object which has long since been
deleted.

The fix here is to recognize that the CXL specification places no
mandate on in-order shutdown of switch-decoders, the driver enforces
in-order allocation, and hardware enforces in-order commit. So, rather
than fail and leave objects dangling, always remove them.

In support of making cxl_region_decode_reset() always succeed,
cxl_region_invalidate_memregion() failures are turned into warnings.
Crashing the kernel is ok there since system integrity is at risk if
caches cannot be managed around physical address mutation events like
CXL region destruction.

A new device_for_each_child_reverse_from() is added to cleanup
port->commit_end after all dependent decoders have been disabled. In
other words if decoders are allocated 0->1->2 and disabled 1->2->0 then
port->commit_end only decrements from 2 after 2 has been disabled, and
it decrements all the way to zero since 1 was disabled previously.

Link: http://lore.kernel.org/20241004212504.1246-1-gourry@gourry.net [1]
Cc: stable@vger.kernel.org
Fixes: 176baefb2eb5 ("cxl/hdm: Commit decoder state to hardware")
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Alison Schofield <alison.schofield@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Zijun Hu <quic_zijuhu@quicinc.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Link: https://patch.msgid.link/172964782781.81806.17902885593105284330.stgit@dwillia2-xfh.jf.intel.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
 drivers/base/core.c          | 35 +++++++++++++++++++++++++++++++
 drivers/cxl/core/hdm.c       | 50 +++++++++++++++++++++++++++++++++++++-------
 drivers/cxl/core/region.c    | 48 ++++++++++++------------------------------
 drivers/cxl/cxl.h            |  3 ++-
 include/linux/device.h       |  3 +++
 tools/testing/cxl/test/cxl.c | 14 +++++--------
 6 files changed, 100 insertions(+), 53 deletions(-)

(limited to 'include')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index a4c853411a6b..e42f1ad73078 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -4037,6 +4037,41 @@ int device_for_each_child_reverse(struct device *parent, void *data,
 }
 EXPORT_SYMBOL_GPL(device_for_each_child_reverse);
 
+/**
+ * device_for_each_child_reverse_from - device child iterator in reversed order.
+ * @parent: parent struct device.
+ * @from: optional starting point in child list
+ * @fn: function to be called for each device.
+ * @data: data for the callback.
+ *
+ * Iterate over @parent's child devices, starting at @from, and call @fn
+ * for each, passing it @data. This helper is identical to
+ * device_for_each_child_reverse() when @from is NULL.
+ *
+ * @fn is checked each iteration. If it returns anything other than 0,
+ * iteration stop and that value is returned to the caller of
+ * device_for_each_child_reverse_from();
+ */
+int device_for_each_child_reverse_from(struct device *parent,
+				       struct device *from, const void *data,
+				       int (*fn)(struct device *, const void *))
+{
+	struct klist_iter i;
+	struct device *child;
+	int error = 0;
+
+	if (!parent->p)
+		return 0;
+
+	klist_iter_init_node(&parent->p->klist_children, &i,
+			     (from ? &from->p->knode_parent : NULL));
+	while ((child = prev_device(&i)) && !error)
+		error = fn(child, data);
+	klist_iter_exit(&i);
+	return error;
+}
+EXPORT_SYMBOL_GPL(device_for_each_child_reverse_from);
+
 /**
  * device_find_child - device iterator for locating a particular device.
  * @parent: parent struct device
diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c
index 3df10517a327..223c273c0cd1 100644
--- a/drivers/cxl/core/hdm.c
+++ b/drivers/cxl/core/hdm.c
@@ -712,7 +712,44 @@ static int cxl_decoder_commit(struct cxl_decoder *cxld)
 	return 0;
 }
 
-static int cxl_decoder_reset(struct cxl_decoder *cxld)
+static int commit_reap(struct device *dev, const void *data)
+{
+	struct cxl_port *port = to_cxl_port(dev->parent);
+	struct cxl_decoder *cxld;
+
+	if (!is_switch_decoder(dev) && !is_endpoint_decoder(dev))
+		return 0;
+
+	cxld = to_cxl_decoder(dev);
+	if (port->commit_end == cxld->id &&
+	    ((cxld->flags & CXL_DECODER_F_ENABLE) == 0)) {
+		port->commit_end--;
+		dev_dbg(&port->dev, "reap: %s commit_end: %d\n",
+			dev_name(&cxld->dev), port->commit_end);
+	}
+
+	return 0;
+}
+
+void cxl_port_commit_reap(struct cxl_decoder *cxld)
+{
+	struct cxl_port *port = to_cxl_port(cxld->dev.parent);
+
+	lockdep_assert_held_write(&cxl_region_rwsem);
+
+	/*
+	 * Once the highest committed decoder is disabled, free any other
+	 * decoders that were pinned allocated by out-of-order release.
+	 */
+	port->commit_end--;
+	dev_dbg(&port->dev, "reap: %s commit_end: %d\n", dev_name(&cxld->dev),
+		port->commit_end);
+	device_for_each_child_reverse_from(&port->dev, &cxld->dev, NULL,
+					   commit_reap);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_port_commit_reap, CXL);
+
+static void cxl_decoder_reset(struct cxl_decoder *cxld)
 {
 	struct cxl_port *port = to_cxl_port(cxld->dev.parent);
 	struct cxl_hdm *cxlhdm = dev_get_drvdata(&port->dev);
@@ -721,14 +758,14 @@ static int cxl_decoder_reset(struct cxl_decoder *cxld)
 	u32 ctrl;
 
 	if ((cxld->flags & CXL_DECODER_F_ENABLE) == 0)
-		return 0;
+		return;
 
-	if (port->commit_end != id) {
+	if (port->commit_end == id)
+		cxl_port_commit_reap(cxld);
+	else
 		dev_dbg(&port->dev,
 			"%s: out of order reset, expected decoder%d.%d\n",
 			dev_name(&cxld->dev), port->id, port->commit_end);
-		return -EBUSY;
-	}
 
 	down_read(&cxl_dpa_rwsem);
 	ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(id));
@@ -741,7 +778,6 @@ static int cxl_decoder_reset(struct cxl_decoder *cxld)
 	writel(0, hdm + CXL_HDM_DECODER0_BASE_LOW_OFFSET(id));
 	up_read(&cxl_dpa_rwsem);
 
-	port->commit_end--;
 	cxld->flags &= ~CXL_DECODER_F_ENABLE;
 
 	/* Userspace is now responsible for reconfiguring this decoder */
@@ -751,8 +787,6 @@ static int cxl_decoder_reset(struct cxl_decoder *cxld)
 		cxled = to_cxl_endpoint_decoder(&cxld->dev);
 		cxled->state = CXL_DECODER_STATE_MANUAL;
 	}
-
-	return 0;
 }
 
 static int cxl_setup_hdm_decoder_from_dvsec(
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index e701e4b04032..3478d2058303 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -232,8 +232,8 @@ static int cxl_region_invalidate_memregion(struct cxl_region *cxlr)
 				"Bypassing cpu_cache_invalidate_memregion() for testing!\n");
 			return 0;
 		} else {
-			dev_err(&cxlr->dev,
-				"Failed to synchronize CPU cache state\n");
+			dev_WARN(&cxlr->dev,
+				 "Failed to synchronize CPU cache state\n");
 			return -ENXIO;
 		}
 	}
@@ -242,19 +242,17 @@ static int cxl_region_invalidate_memregion(struct cxl_region *cxlr)
 	return 0;
 }
 
-static int cxl_region_decode_reset(struct cxl_region *cxlr, int count)
+static void cxl_region_decode_reset(struct cxl_region *cxlr, int count)
 {
 	struct cxl_region_params *p = &cxlr->params;
-	int i, rc = 0;
+	int i;
 
 	/*
-	 * Before region teardown attempt to flush, and if the flush
-	 * fails cancel the region teardown for data consistency
-	 * concerns
+	 * Before region teardown attempt to flush, evict any data cached for
+	 * this region, or scream loudly about missing arch / platform support
+	 * for CXL teardown.
 	 */
-	rc = cxl_region_invalidate_memregion(cxlr);
-	if (rc)
-		return rc;
+	cxl_region_invalidate_memregion(cxlr);
 
 	for (i = count - 1; i >= 0; i--) {
 		struct cxl_endpoint_decoder *cxled = p->targets[i];
@@ -277,23 +275,17 @@ static int cxl_region_decode_reset(struct cxl_region *cxlr, int count)
 			cxl_rr = cxl_rr_load(iter, cxlr);
 			cxld = cxl_rr->decoder;
 			if (cxld->reset)
-				rc = cxld->reset(cxld);
-			if (rc)
-				return rc;
+				cxld->reset(cxld);
 			set_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags);
 		}
 
 endpoint_reset:
-		rc = cxled->cxld.reset(&cxled->cxld);
-		if (rc)
-			return rc;
+		cxled->cxld.reset(&cxled->cxld);
 		set_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags);
 	}
 
 	/* all decoders associated with this region have been torn down */
 	clear_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags);
-
-	return 0;
 }
 
 static int commit_decoder(struct cxl_decoder *cxld)
@@ -409,16 +401,8 @@ static ssize_t commit_store(struct device *dev, struct device_attribute *attr,
 		 * still pending.
 		 */
 		if (p->state == CXL_CONFIG_RESET_PENDING) {
-			rc = cxl_region_decode_reset(cxlr, p->interleave_ways);
-			/*
-			 * Revert to committed since there may still be active
-			 * decoders associated with this region, or move forward
-			 * to active to mark the reset successful
-			 */
-			if (rc)
-				p->state = CXL_CONFIG_COMMIT;
-			else
-				p->state = CXL_CONFIG_ACTIVE;
+			cxl_region_decode_reset(cxlr, p->interleave_ways);
+			p->state = CXL_CONFIG_ACTIVE;
 		}
 	}
 
@@ -2054,13 +2038,7 @@ static int cxl_region_detach(struct cxl_endpoint_decoder *cxled)
 	get_device(&cxlr->dev);
 
 	if (p->state > CXL_CONFIG_ACTIVE) {
-		/*
-		 * TODO: tear down all impacted regions if a device is
-		 * removed out of order
-		 */
-		rc = cxl_region_decode_reset(cxlr, p->interleave_ways);
-		if (rc)
-			goto out;
+		cxl_region_decode_reset(cxlr, p->interleave_ways);
 		p->state = CXL_CONFIG_ACTIVE;
 	}
 
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 0d8b810a51f0..5406e3ab3d4a 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -359,7 +359,7 @@ struct cxl_decoder {
 	struct cxl_region *region;
 	unsigned long flags;
 	int (*commit)(struct cxl_decoder *cxld);
-	int (*reset)(struct cxl_decoder *cxld);
+	void (*reset)(struct cxl_decoder *cxld);
 };
 
 /*
@@ -730,6 +730,7 @@ static inline bool is_cxl_root(struct cxl_port *port)
 int cxl_num_decoders_committed(struct cxl_port *port);
 bool is_cxl_port(const struct device *dev);
 struct cxl_port *to_cxl_port(const struct device *dev);
+void cxl_port_commit_reap(struct cxl_decoder *cxld);
 struct pci_bus;
 int devm_cxl_register_pci_bus(struct device *host, struct device *uport_dev,
 			      struct pci_bus *bus);
diff --git a/include/linux/device.h b/include/linux/device.h
index b4bde8d22697..667cb6db9019 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1078,6 +1078,9 @@ int device_for_each_child(struct device *dev, void *data,
 			  int (*fn)(struct device *dev, void *data));
 int device_for_each_child_reverse(struct device *dev, void *data,
 				  int (*fn)(struct device *dev, void *data));
+int device_for_each_child_reverse_from(struct device *parent,
+				       struct device *from, const void *data,
+				       int (*fn)(struct device *, const void *));
 struct device *device_find_child(struct device *dev, void *data,
 				 int (*match)(struct device *dev, void *data));
 struct device *device_find_child_by_name(struct device *parent,
diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c
index 90d5afd52dd0..c5bbd89b3192 100644
--- a/tools/testing/cxl/test/cxl.c
+++ b/tools/testing/cxl/test/cxl.c
@@ -693,26 +693,22 @@ static int mock_decoder_commit(struct cxl_decoder *cxld)
 	return 0;
 }
 
-static int mock_decoder_reset(struct cxl_decoder *cxld)
+static void mock_decoder_reset(struct cxl_decoder *cxld)
 {
 	struct cxl_port *port = to_cxl_port(cxld->dev.parent);
 	int id = cxld->id;
 
 	if ((cxld->flags & CXL_DECODER_F_ENABLE) == 0)
-		return 0;
+		return;
 
 	dev_dbg(&port->dev, "%s reset\n", dev_name(&cxld->dev));
-	if (port->commit_end != id) {
+	if (port->commit_end == id)
+		cxl_port_commit_reap(cxld);
+	else
 		dev_dbg(&port->dev,
 			"%s: out of order reset, expected decoder%d.%d\n",
 			dev_name(&cxld->dev), port->id, port->commit_end);
-		return -EBUSY;
-	}
-
-	port->commit_end--;
 	cxld->flags &= ~CXL_DECODER_F_ENABLE;
-
-	return 0;
 }
 
 static void default_mock_decoder(struct cxl_decoder *cxld)
-- 
cgit v1.2.3


From b5413156bad91dc2995a5c4eab1b05e56914638a Mon Sep 17 00:00:00 2001
From: Benjamin Segall <bsegall@google.com>
Date: Fri, 25 Oct 2024 18:35:35 -0700
Subject: posix-cpu-timers: Clear TICK_DEP_BIT_POSIX_TIMER on clone

When cloning a new thread, its posix_cputimers are not inherited, and
are cleared by posix_cputimers_init(). However, this does not clear the
tick dependency it creates in tsk->tick_dep_mask, and the handler does
not reach the code to clear the dependency if there were no timers to
begin with.

Thus if a thread has a cputimer running before clone/fork, all
descendants will prevent nohz_full unless they create a cputimer of
their own.

Fix this by entirely clearing the tick_dep_mask in copy_process().
(There is currently no inherited state that needs a tick dependency)

Process-wide timers do not have this problem because fork does not copy
signal_struct as a baseline, it creates one from scratch.

Fixes: b78783000d5c ("posix-cpu-timers: Migrate to use new tick dependency mask model")
Signed-off-by: Ben Segall <bsegall@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/all/xm26o737bq8o.fsf@google.com
---
 include/linux/tick.h | 8 ++++++++
 kernel/fork.c        | 2 ++
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/linux/tick.h b/include/linux/tick.h
index 72744638c5b0..99c9c5a7252a 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -251,12 +251,19 @@ static inline void tick_dep_set_task(struct task_struct *tsk,
 	if (tick_nohz_full_enabled())
 		tick_nohz_dep_set_task(tsk, bit);
 }
+
 static inline void tick_dep_clear_task(struct task_struct *tsk,
 				       enum tick_dep_bits bit)
 {
 	if (tick_nohz_full_enabled())
 		tick_nohz_dep_clear_task(tsk, bit);
 }
+
+static inline void tick_dep_init_task(struct task_struct *tsk)
+{
+	atomic_set(&tsk->tick_dep_mask, 0);
+}
+
 static inline void tick_dep_set_signal(struct task_struct *tsk,
 				       enum tick_dep_bits bit)
 {
@@ -290,6 +297,7 @@ static inline void tick_dep_set_task(struct task_struct *tsk,
 				     enum tick_dep_bits bit) { }
 static inline void tick_dep_clear_task(struct task_struct *tsk,
 				       enum tick_dep_bits bit) { }
+static inline void tick_dep_init_task(struct task_struct *tsk) { }
 static inline void tick_dep_set_signal(struct task_struct *tsk,
 				       enum tick_dep_bits bit) { }
 static inline void tick_dep_clear_signal(struct signal_struct *signal,
diff --git a/kernel/fork.c b/kernel/fork.c
index 89ceb4a68af2..6fa9fe62e01e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -105,6 +105,7 @@
 #include <linux/rseq.h>
 #include <uapi/linux/pidfd.h>
 #include <linux/pidfs.h>
+#include <linux/tick.h>
 
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>
@@ -2292,6 +2293,7 @@ __latent_entropy struct task_struct *copy_process(
 	acct_clear_integrals(p);
 
 	posix_cputimers_init(&p->posix_cputimers);
+	tick_dep_init_task(p);
 
 	p->io_context = NULL;
 	audit_set_context(p, NULL);
-- 
cgit v1.2.3


From f64e67e5d3a45a4a04286c47afade4b518acd47b Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Tue, 15 Oct 2024 18:56:05 +0100
Subject: fork: do not invoke uffd on fork if error occurs

Patch series "fork: do not expose incomplete mm on fork".

During fork we may place the virtual memory address space into an
inconsistent state before the fork operation is complete.

In addition, we may encounter an error during the fork operation that
indicates that the virtual memory address space is invalidated.

As a result, we should not be exposing it in any way to external machinery
that might interact with the mm or VMAs, machinery that is not designed to
deal with incomplete state.

We specifically update the fork logic to defer khugepaged and ksm to the
end of the operation and only to be invoked if no error arose, and
disallow uffd from observing fork events should an error have occurred.


This patch (of 2):

Currently on fork we expose the virtual address space of a process to
userland unconditionally if uffd is registered in VMAs, regardless of
whether an error arose in the fork.

This is performed in dup_userfaultfd_complete() which is invoked
unconditionally, and performs two duties - invoking registered handlers
for the UFFD_EVENT_FORK event via dup_fctx(), and clearing down
userfaultfd_fork_ctx objects established in dup_userfaultfd().

This is problematic, because the virtual address space may not yet be
correctly initialised if an error arose.

The change in commit d24062914837 ("fork: use __mt_dup() to duplicate
maple tree in dup_mmap()") makes this more pertinent as we may be in a
state where entries in the maple tree are not yet consistent.

We address this by, on fork error, ensuring that we roll back state that
we would otherwise expect to clean up through the event being handled by
userland and perform the memory freeing duty otherwise performed by
dup_userfaultfd_complete().

We do this by implementing a new function, dup_userfaultfd_fail(), which
performs the same loop, only decrementing reference counts.

Note that we perform mmgrab() on the parent and child mm's, however
userfaultfd_ctx_put() will mmdrop() this once the reference count drops to
zero, so we will avoid memory leaks correctly here.

Link: https://lkml.kernel.org/r/cover.1729014377.git.lorenzo.stoakes@oracle.com
Link: https://lkml.kernel.org/r/d3691d58bb58712b6fb3df2be441d175bd3cdf07.1729014377.git.lorenzo.stoakes@oracle.com
Fixes: d24062914837 ("fork: use __mt_dup() to duplicate maple tree in dup_mmap()")
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reported-by: Jann Horn <jannh@google.com>
Reviewed-by: Jann Horn <jannh@google.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Linus Torvalds <torvalds@linuxfoundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/userfaultfd.c              | 28 ++++++++++++++++++++++++++++
 include/linux/userfaultfd_k.h |  5 +++++
 kernel/fork.c                 |  5 ++++-
 3 files changed, 37 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 68cdd89c97a3..7c0bd0b55f88 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -692,6 +692,34 @@ void dup_userfaultfd_complete(struct list_head *fcs)
 	}
 }
 
+void dup_userfaultfd_fail(struct list_head *fcs)
+{
+	struct userfaultfd_fork_ctx *fctx, *n;
+
+	/*
+	 * An error has occurred on fork, we will tear memory down, but have
+	 * allocated memory for fctx's and raised reference counts for both the
+	 * original and child contexts (and on the mm for each as a result).
+	 *
+	 * These would ordinarily be taken care of by a user handling the event,
+	 * but we are no longer doing so, so manually clean up here.
+	 *
+	 * mm tear down will take care of cleaning up VMA contexts.
+	 */
+	list_for_each_entry_safe(fctx, n, fcs, list) {
+		struct userfaultfd_ctx *octx = fctx->orig;
+		struct userfaultfd_ctx *ctx = fctx->new;
+
+		atomic_dec(&octx->mmap_changing);
+		VM_BUG_ON(atomic_read(&octx->mmap_changing) < 0);
+		userfaultfd_ctx_put(octx);
+		userfaultfd_ctx_put(ctx);
+
+		list_del(&fctx->list);
+		kfree(fctx);
+	}
+}
+
 void mremap_userfaultfd_prep(struct vm_area_struct *vma,
 			     struct vm_userfaultfd_ctx *vm_ctx)
 {
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 9fc6ce15c499..cb40f1a1d081 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -249,6 +249,7 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
 
 extern int dup_userfaultfd(struct vm_area_struct *, struct list_head *);
 extern void dup_userfaultfd_complete(struct list_head *);
+void dup_userfaultfd_fail(struct list_head *);
 
 extern void mremap_userfaultfd_prep(struct vm_area_struct *,
 				    struct vm_userfaultfd_ctx *);
@@ -351,6 +352,10 @@ static inline void dup_userfaultfd_complete(struct list_head *l)
 {
 }
 
+static inline void dup_userfaultfd_fail(struct list_head *l)
+{
+}
+
 static inline void mremap_userfaultfd_prep(struct vm_area_struct *vma,
 					   struct vm_userfaultfd_ctx *ctx)
 {
diff --git a/kernel/fork.c b/kernel/fork.c
index 89ceb4a68af2..597b477dd491 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -775,7 +775,10 @@ out:
 	mmap_write_unlock(mm);
 	flush_tlb_mm(oldmm);
 	mmap_write_unlock(oldmm);
-	dup_userfaultfd_complete(&uf);
+	if (!retval)
+		dup_userfaultfd_complete(&uf);
+	else
+		dup_userfaultfd_fail(&uf);
 fail_uprobe_end:
 	uprobe_end_dup_mmap();
 	return retval;
-- 
cgit v1.2.3


From 985da552a98e27096444508ce5d853244019111f Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Tue, 15 Oct 2024 18:56:06 +0100
Subject: fork: only invoke khugepaged, ksm hooks if no error

There is no reason to invoke these hooks early against an mm that is in an
incomplete state.

The change in commit d24062914837 ("fork: use __mt_dup() to duplicate
maple tree in dup_mmap()") makes this more pertinent as we may be in a
state where entries in the maple tree are not yet consistent.

Their placement early in dup_mmap() only appears to have been meaningful
for early error checking, and since functionally it'd require a very small
allocation to fail (in practice 'too small to fail') that'd only occur in
the most dire circumstances, meaning the fork would fail or be OOM'd in
any case.

Since both khugepaged and KSM tracking are there to provide optimisations
to memory performance rather than critical functionality, it doesn't
really matter all that much if, under such dire memory pressure, we fail
to register an mm with these.

As a result, we follow the example of commit d2081b2bf819 ("mm:
khugepaged: make khugepaged_enter() void function") and make ksm_fork() a
void function also.

We only expose the mm to these functions once we are done with them and
only if no error occurred in the fork operation.

Link: https://lkml.kernel.org/r/e0cb8b840c9d1d5a6e84d4f8eff5f3f2022aa10c.1729014377.git.lorenzo.stoakes@oracle.com
Fixes: d24062914837 ("fork: use __mt_dup() to duplicate maple tree in dup_mmap()")
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reported-by: Jann Horn <jannh@google.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Jann Horn <jannh@google.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Linus Torvalds <torvalds@linuxfoundation.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/ksm.h | 10 ++++------
 kernel/fork.c       |  7 ++-----
 2 files changed, 6 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 11690dacd986..ec9c05044d4f 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -54,12 +54,11 @@ static inline long mm_ksm_zero_pages(struct mm_struct *mm)
 	return atomic_long_read(&mm->ksm_zero_pages);
 }
 
-static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
 {
+	/* Adding mm to ksm is best effort on fork. */
 	if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags))
-		return __ksm_enter(mm);
-
-	return 0;
+		__ksm_enter(mm);
 }
 
 static inline int ksm_execve(struct mm_struct *mm)
@@ -107,9 +106,8 @@ static inline int ksm_disable(struct mm_struct *mm)
 	return 0;
 }
 
-static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
 {
-	return 0;
 }
 
 static inline int ksm_execve(struct mm_struct *mm)
diff --git a/kernel/fork.c b/kernel/fork.c
index 597b477dd491..3bf38d260cb3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -653,11 +653,6 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
 	mm->exec_vm = oldmm->exec_vm;
 	mm->stack_vm = oldmm->stack_vm;
 
-	retval = ksm_fork(mm, oldmm);
-	if (retval)
-		goto out;
-	khugepaged_fork(mm, oldmm);
-
 	/* Use __mt_dup() to efficiently build an identical maple tree. */
 	retval = __mt_dup(&oldmm->mm_mt, &mm->mm_mt, GFP_KERNEL);
 	if (unlikely(retval))
@@ -760,6 +755,8 @@ loop_out:
 	vma_iter_free(&vmi);
 	if (!retval) {
 		mt_set_in_rcu(vmi.mas.tree);
+		ksm_fork(mm, oldmm);
+		khugepaged_fork(mm, oldmm);
 	} else if (mpnt) {
 		/*
 		 * The entire maple tree has already been duplicated. If the
-- 
cgit v1.2.3


From 1c10941e34c5fdc0357e46a25bd130d9cf40b925 Mon Sep 17 00:00:00 2001
From: Pierre Gondois <pierre.gondois@arm.com>
Date: Mon, 28 Oct 2024 13:56:56 +0100
Subject: ACPI: CPPC: Make rmw_lock a raw_spin_lock

The following BUG was triggered:

=============================
[ BUG: Invalid wait context ]
6.12.0-rc2-XXX #406 Not tainted
-----------------------------
kworker/1:1/62 is trying to lock:
ffffff8801593030 (&cpc_ptr->rmw_lock){+.+.}-{3:3}, at: cpc_write+0xcc/0x370
other info that might help us debug this:
context-{5:5}
2 locks held by kworker/1:1/62:
  #0: ffffff897ef5ec98 (&rq->__lock){-.-.}-{2:2}, at: raw_spin_rq_lock_nested+0x2c/0x50
  #1: ffffff880154e238 (&sg_policy->update_lock){....}-{2:2}, at: sugov_update_shared+0x3c/0x280
stack backtrace:
CPU: 1 UID: 0 PID: 62 Comm: kworker/1:1 Not tainted 6.12.0-rc2-g9654bd3e8806 #406
Workqueue:  0x0 (events)
Call trace:
  dump_backtrace+0xa4/0x130
  show_stack+0x20/0x38
  dump_stack_lvl+0x90/0xd0
  dump_stack+0x18/0x28
  __lock_acquire+0x480/0x1ad8
  lock_acquire+0x114/0x310
  _raw_spin_lock+0x50/0x70
  cpc_write+0xcc/0x370
  cppc_set_perf+0xa0/0x3a8
  cppc_cpufreq_fast_switch+0x40/0xc0
  cpufreq_driver_fast_switch+0x4c/0x218
  sugov_update_shared+0x234/0x280
  update_load_avg+0x6ec/0x7b8
  dequeue_entities+0x108/0x830
  dequeue_task_fair+0x58/0x408
  __schedule+0x4f0/0x1070
  schedule+0x54/0x130
  worker_thread+0xc0/0x2e8
  kthread+0x130/0x148
  ret_from_fork+0x10/0x20

sugov_update_shared() locks a raw_spinlock while cpc_write() locks a
spinlock.

To have a correct wait-type order, update rmw_lock to a raw spinlock and
ensure that interrupts will be disabled on the CPU holding it.

Fixes: 60949b7b8054 ("ACPI: CPPC: Fix MASK_VAL() usage")
Signed-off-by: Pierre Gondois <pierre.gondois@arm.com>
Link: https://patch.msgid.link/20241028125657.1271512-1-pierre.gondois@arm.com
[ rjw: Changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/cppc_acpi.c | 9 +++++----
 include/acpi/cppc_acpi.h | 2 +-
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index c3fc2c05d868..1a40f0514eaa 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -867,7 +867,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
 
 	/* Store CPU Logical ID */
 	cpc_ptr->cpu_id = pr->id;
-	spin_lock_init(&cpc_ptr->rmw_lock);
+	raw_spin_lock_init(&cpc_ptr->rmw_lock);
 
 	/* Parse PSD data for this CPU */
 	ret = acpi_get_psd(cpc_ptr, handle);
@@ -1087,6 +1087,7 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val)
 	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
 	struct cpc_reg *reg = &reg_res->cpc_entry.reg;
 	struct cpc_desc *cpc_desc;
+	unsigned long flags;
 
 	size = GET_BIT_WIDTH(reg);
 
@@ -1126,7 +1127,7 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val)
 			return -ENODEV;
 		}
 
-		spin_lock(&cpc_desc->rmw_lock);
+		raw_spin_lock_irqsave(&cpc_desc->rmw_lock, flags);
 		switch (size) {
 		case 8:
 			prev_val = readb_relaxed(vaddr);
@@ -1141,7 +1142,7 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val)
 			prev_val = readq_relaxed(vaddr);
 			break;
 		default:
-			spin_unlock(&cpc_desc->rmw_lock);
+			raw_spin_unlock_irqrestore(&cpc_desc->rmw_lock, flags);
 			return -EFAULT;
 		}
 		val = MASK_VAL_WRITE(reg, prev_val, val);
@@ -1174,7 +1175,7 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val)
 	}
 
 	if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
-		spin_unlock(&cpc_desc->rmw_lock);
+		raw_spin_unlock_irqrestore(&cpc_desc->rmw_lock, flags);
 
 	return ret_val;
 }
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index 76e44e102780..62d368bcd9ec 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -65,7 +65,7 @@ struct cpc_desc {
 	int write_cmd_status;
 	int write_cmd_id;
 	/* Lock used for RMW operations in cpc_write() */
-	spinlock_t rmw_lock;
+	raw_spinlock_t rmw_lock;
 	struct cpc_register_resource cpc_regs[MAX_CPC_REG_ENT];
 	struct acpi_psd_package domain_info;
 	struct kobject kobj;
-- 
cgit v1.2.3


From ad4a3ca6a8e886f6491910a3ae5d53595e40597d Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 22 Oct 2024 09:38:22 +0300
Subject: ipv4: ip_tunnel: Fix suspicious RCU usage warning in
 ip_tunnel_init_flow()

There are code paths from which the function is called without holding
the RCU read lock, resulting in a suspicious RCU usage warning [1].

Fix by using l3mdev_master_upper_ifindex_by_index() which will acquire
the RCU read lock before calling
l3mdev_master_upper_ifindex_by_index_rcu().

[1]
WARNING: suspicious RCU usage
6.12.0-rc3-custom-gac8f72681cf2 #141 Not tainted
-----------------------------
net/core/dev.c:876 RCU-list traversed in non-reader section!!

other info that might help us debug this:

rcu_scheduler_active = 2, debug_locks = 1
1 lock held by ip/361:
 #0: ffffffff86fc7cb0 (rtnl_mutex){+.+.}-{3:3}, at: rtnetlink_rcv_msg+0x377/0xf60

stack backtrace:
CPU: 3 UID: 0 PID: 361 Comm: ip Not tainted 6.12.0-rc3-custom-gac8f72681cf2 #141
Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
Call Trace:
 <TASK>
 dump_stack_lvl+0xba/0x110
 lockdep_rcu_suspicious.cold+0x4f/0xd6
 dev_get_by_index_rcu+0x1d3/0x210
 l3mdev_master_upper_ifindex_by_index_rcu+0x2b/0xf0
 ip_tunnel_bind_dev+0x72f/0xa00
 ip_tunnel_newlink+0x368/0x7a0
 ipgre_newlink+0x14c/0x170
 __rtnl_newlink+0x1173/0x19c0
 rtnl_newlink+0x6c/0xa0
 rtnetlink_rcv_msg+0x3cc/0xf60
 netlink_rcv_skb+0x171/0x450
 netlink_unicast+0x539/0x7f0
 netlink_sendmsg+0x8c1/0xd80
 ____sys_sendmsg+0x8f9/0xc20
 ___sys_sendmsg+0x197/0x1e0
 __sys_sendmsg+0x122/0x1f0
 do_syscall_64+0xbb/0x1d0
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Fixes: db53cd3d88dc ("net: Handle l3mdev in ip_tunnel_init_flow")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20241022063822.462057-1-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip_tunnels.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 6194fbb564c6..6a070478254d 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -354,7 +354,7 @@ static inline void ip_tunnel_init_flow(struct flowi4 *fl4,
 	memset(fl4, 0, sizeof(*fl4));
 
 	if (oif) {
-		fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index_rcu(net, oif);
+		fl4->flowi4_l3mdev = l3mdev_master_upper_ifindex_by_index(net, oif);
 		/* Legacy VRF/l3mdev use case */
 		fl4->flowi4_oif = fl4->flowi4_l3mdev ? 0 : oif;
 	}
-- 
cgit v1.2.3


From 62a898b07b83f6f407003d8a70f0827a5af08a59 Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Wed, 30 Oct 2024 18:05:13 +0800
Subject: bpf: Add bpf_mem_alloc_check_size() helper

Introduce bpf_mem_alloc_check_size() to check whether the allocation
size exceeds the limitation for the kmalloc-equivalent allocator. The
upper limit for percpu allocation is LLIST_NODE_SZ bytes larger than
non-percpu allocation, so a percpu argument is added to the helper.

The helper will be used in the following patch to check whether the size
parameter passed to bpf_mem_alloc() is too big.

Signed-off-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20241030100516.3633640-3-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_mem_alloc.h |  3 +++
 kernel/bpf/memalloc.c         | 14 +++++++++++++-
 2 files changed, 16 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h
index aaf004d94322..e45162ef59bb 100644
--- a/include/linux/bpf_mem_alloc.h
+++ b/include/linux/bpf_mem_alloc.h
@@ -33,6 +33,9 @@ int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg
 int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size);
 void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma);
 
+/* Check the allocation size for kmalloc equivalent allocator */
+int bpf_mem_alloc_check_size(bool percpu, size_t size);
+
 /* kmalloc/kfree equivalent: */
 void *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size);
 void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr);
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index b3858a76e0b3..146f5b57cfb1 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -35,6 +35,8 @@
  */
 #define LLIST_NODE_SZ sizeof(struct llist_node)
 
+#define BPF_MEM_ALLOC_SIZE_MAX 4096
+
 /* similar to kmalloc, but sizeof == 8 bucket is gone */
 static u8 size_index[24] __ro_after_init = {
 	3,	/* 8 */
@@ -65,7 +67,7 @@ static u8 size_index[24] __ro_after_init = {
 
 static int bpf_mem_cache_idx(size_t size)
 {
-	if (!size || size > 4096)
+	if (!size || size > BPF_MEM_ALLOC_SIZE_MAX)
 		return -1;
 
 	if (size <= 192)
@@ -1005,3 +1007,13 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags)
 
 	return !ret ? NULL : ret + LLIST_NODE_SZ;
 }
+
+int bpf_mem_alloc_check_size(bool percpu, size_t size)
+{
+	/* The size of percpu allocation doesn't have LLIST_NODE_SZ overhead */
+	if ((percpu && size > BPF_MEM_ALLOC_SIZE_MAX) ||
+	    (!percpu && size > BPF_MEM_ALLOC_SIZE_MAX - LLIST_NODE_SZ))
+		return -E2BIG;
+
+	return 0;
+}
-- 
cgit v1.2.3


From 0fc810ae3ae110f9e2fcccce80fc8c8d62f97907 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 29 Oct 2024 16:03:31 -1000
Subject: x86/uaccess: Avoid barrier_nospec() in 64-bit copy_from_user()

The barrier_nospec() in 64-bit copy_from_user() is slow. Instead use
pointer masking to force the user pointer to all 1's for an invalid
address.

The kernel test robot reports a 2.6% improvement in the per_thread_ops
benchmark [1].

This is a variation on a patch originally by Josh Poimboeuf [2].

Link: https://lore.kernel.org/202410281344.d02c72a2-oliver.sang@intel.com [1]
Link: https://lore.kernel.org/5b887fe4c580214900e21f6c61095adf9a142735.1730166635.git.jpoimboe@kernel.org [2]
Tested-and-reviewed-by: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/uaccess.h | 21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 39c7cf82b0c2..43844510d5d0 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -38,6 +38,7 @@
 #else
  #define can_do_masked_user_access() 0
  #define masked_user_access_begin(src) NULL
+ #define mask_user_address(src) (src)
 #endif
 
 /*
@@ -159,19 +160,27 @@ _inline_copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	unsigned long res = n;
 	might_fault();
-	if (!should_fail_usercopy() && likely(access_ok(from, n))) {
+	if (should_fail_usercopy())
+		goto fail;
+	if (can_do_masked_user_access())
+		from = mask_user_address(from);
+	else {
+		if (!access_ok(from, n))
+			goto fail;
 		/*
 		 * Ensure that bad access_ok() speculation will not
 		 * lead to nasty side effects *after* the copy is
 		 * finished:
 		 */
 		barrier_nospec();
-		instrument_copy_from_user_before(to, from, n);
-		res = raw_copy_from_user(to, from, n);
-		instrument_copy_from_user_after(to, from, n, res);
 	}
-	if (unlikely(res))
-		memset(to + (n - res), 0, res);
+	instrument_copy_from_user_before(to, from, n);
+	res = raw_copy_from_user(to, from, n);
+	instrument_copy_from_user_after(to, from, n, res);
+	if (likely(!res))
+		return 0;
+fail:
+	memset(to + (n - res), 0, res);
 	return res;
 }
 extern __must_check unsigned long
-- 
cgit v1.2.3


From f4657e16e767105194f97586fe3c03d3f64c4d37 Mon Sep 17 00:00:00 2001
From: Hao Ge <gehao@kylinos.cn>
Date: Sun, 20 Oct 2024 15:08:19 +0800
Subject: mm/codetag: fix null pointer check logic for ref and tag

When we compile and load lib/slub_kunit.c,it will cause a panic.

The root cause is that __kmalloc_cache_noprof was directly called instead
of kmem_cache_alloc,which resulted in no alloc_tag being allocated.This
caused current->alloc_tag to be null,leading to a null pointer dereference
in alloc_tag_ref_set.

Despite the fact that my colleague Pei Xiao will later fix the code in
slub_kunit.c,we still need fix null pointer check logic for ref and tag to
avoid panic caused by a null pointer dereference.

Here is the log for the panic:

[   74.779373][ T2158] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020
[   74.780130][ T2158] Mem abort info:
[   74.780406][ T2158]   ESR = 0x0000000096000004
[   74.780756][ T2158]   EC = 0x25: DABT (current EL), IL = 32 bits
[   74.781225][ T2158]   SET = 0, FnV = 0
[   74.781529][ T2158]   EA = 0, S1PTW = 0
[   74.781836][ T2158]   FSC = 0x04: level 0 translation fault
[   74.782288][ T2158] Data abort info:
[   74.782577][ T2158]   ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
[   74.783068][ T2158]   CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[   74.783533][ T2158]   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[   74.784010][ T2158] user pgtable: 4k pages, 48-bit VAs, pgdp=0000000105f34000
[   74.784586][ T2158] [0000000000000020] pgd=0000000000000000, p4d=0000000000000000
[   74.785293][ T2158] Internal error: Oops: 0000000096000004 [#1] SMP
[   74.785805][ T2158] Modules linked in: slub_kunit kunit ip6t_rpfilter ip6t_REJECT nf_reject_ipv6 ipt_REJECT nf_reject_ipv4 xt_conntrack ebtable_nat ebtable_broute ip6table_nat ip6table_mangle 4
[   74.790661][ T2158] CPU: 0 UID: 0 PID: 2158 Comm: kunit_try_catch Kdump: loaded Tainted: G        W        N 6.12.0-rc3+ #2
[   74.791535][ T2158] Tainted: [W]=WARN, [N]=TEST
[   74.791889][ T2158] Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015
[   74.792479][ T2158] pstate: 40400005 (nZcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[   74.793101][ T2158] pc : alloc_tagging_slab_alloc_hook+0x120/0x270
[   74.793607][ T2158] lr : alloc_tagging_slab_alloc_hook+0x120/0x270
[   74.794095][ T2158] sp : ffff800084d33cd0
[   74.794418][ T2158] x29: ffff800084d33cd0 x28: 0000000000000000 x27: 0000000000000000
[   74.795095][ T2158] x26: 0000000000000000 x25: 0000000000000012 x24: ffff80007b30e314
[   74.795822][ T2158] x23: ffff000390ff6f10 x22: 0000000000000000 x21: 0000000000000088
[   74.796555][ T2158] x20: ffff000390285840 x19: fffffd7fc3ef7830 x18: ffffffffffffffff
[   74.797283][ T2158] x17: ffff8000800e63b4 x16: ffff80007b33afc4 x15: ffff800081654c00
[   74.798011][ T2158] x14: 0000000000000000 x13: 205d383531325420 x12: 5b5d383734363537
[   74.798744][ T2158] x11: ffff800084d337e0 x10: 000000000000005d x9 : 00000000ffffffd0
[   74.799476][ T2158] x8 : 7f7f7f7f7f7f7f7f x7 : ffff80008219d188 x6 : c0000000ffff7fff
[   74.800206][ T2158] x5 : ffff0003fdbc9208 x4 : ffff800081edd188 x3 : 0000000000000001
[   74.800932][ T2158] x2 : 0beaa6dee1ac5a00 x1 : 0beaa6dee1ac5a00 x0 : ffff80037c2cb000
[   74.801656][ T2158] Call trace:
[   74.801954][ T2158]  alloc_tagging_slab_alloc_hook+0x120/0x270
[   74.802494][ T2158]  __kmalloc_cache_noprof+0x148/0x33c
[   74.802976][ T2158]  test_kmalloc_redzone_access+0x4c/0x104 [slub_kunit]
[   74.803607][ T2158]  kunit_try_run_case+0x70/0x17c [kunit]
[   74.804124][ T2158]  kunit_generic_run_threadfn_adapter+0x2c/0x4c [kunit]
[   74.804768][ T2158]  kthread+0x10c/0x118
[   74.805141][ T2158]  ret_from_fork+0x10/0x20
[   74.805540][ T2158] Code: b9400a80 11000400 b9000a80 97ffd858 (f94012d3)
[   74.806176][ T2158] SMP: stopping secondary CPUs
[   74.808130][ T2158] Starting crashdump kernel...

Link: https://lkml.kernel.org/r/20241020070819.307944-1-hao.ge@linux.dev
Fixes: e0a955bf7f61 ("mm/codetag: add pgalloc_tag_copy()")
Signed-off-by: Hao Ge <gehao@kylinos.cn>
Acked-by: Suren Baghdasaryan <surenb@google.com>
Suggested-by: Suren Baghdasaryan <surenb@google.com>
Acked-by: Yu Zhao <yuzhao@google.com>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/alloc_tag.h | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h
index 1f0a9ff23a2c..941deffc590d 100644
--- a/include/linux/alloc_tag.h
+++ b/include/linux/alloc_tag.h
@@ -135,18 +135,21 @@ static inline void alloc_tag_sub_check(union codetag_ref *ref) {}
 #endif
 
 /* Caller should verify both ref and tag to be valid */
-static inline void __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag)
+static inline bool __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag)
 {
 	alloc_tag_add_check(ref, tag);
 	if (!ref || !tag)
-		return;
+		return false;
 
 	ref->ct = &tag->ct;
+	return true;
 }
 
-static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag)
+static inline bool alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag)
 {
-	__alloc_tag_ref_set(ref, tag);
+	if (unlikely(!__alloc_tag_ref_set(ref, tag)))
+		return false;
+
 	/*
 	 * We need in increment the call counter every time we have a new
 	 * allocation or when we split a large allocation into smaller ones.
@@ -154,12 +157,13 @@ static inline void alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *t
 	 * counter because when we free each part the counter will be decremented.
 	 */
 	this_cpu_inc(tag->counters->calls);
+	return true;
 }
 
 static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes)
 {
-	alloc_tag_ref_set(ref, tag);
-	this_cpu_add(tag->counters->bytes, bytes);
+	if (likely(alloc_tag_ref_set(ref, tag)))
+		this_cpu_add(tag->counters->bytes, bytes);
 }
 
 static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes)
-- 
cgit v1.2.3


From 5168a68eb78fa1c67a8b2d31d0642c7fd866cc12 Mon Sep 17 00:00:00 2001
From: Kairui Song <kasong@tencent.com>
Date: Wed, 23 Oct 2024 01:55:12 +0800
Subject: mm, swap: avoid over reclaim of full clusters

When running low on usable slots, cluster allocator will try to reclaim
the full clusters aggressively to reclaim HAS_CACHE slots.  This
guarantees that as long as there are any usable slots, HAS_CACHE or not,
the swap device will be usable and workload won't go OOM early.

Before the cluster allocator, swap allocator fails easily if device is
filled up with reclaimable HAS_CACHE slots.  Which can be easily
reproduced with following simple program:

    #include <stdio.h>
    #include <string.h>
    #include <linux/mman.h>
    #include <sys/mman.h>
    #define SIZE 8192UL * 1024UL * 1024UL
    int main(int argc, char **argv) {
        long tmp;
        char *p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE,
               MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
        memset(p, 0, SIZE);
        madvise(p, SIZE, MADV_PAGEOUT);
        for (unsigned long i = 0; i < SIZE; ++i)
            tmp += p[i];
        getchar(); /* Pause */
        return 0;
    }

Setup an 8G non ramdisk swap, the first run of the program will swapout 8G
ram successfully.  But run same program again after the first run paused,
the second run can't swapout all 8G memory as now half of the swap device
is pinned by HAS_CACHE.  There was a random scan in the old allocator that
may reclaim part of the HAS_CACHE by luck, but it's unreliable.

The new allocator's added reclaim of full clusters when device is low on
usable slots.  But when multiple CPUs are seeing the device is low on
usable slots at the same time, they ran into a thundering herd problem.

This is an observable problem on large machine with mass parallel
workload, as full cluster reclaim is slower on large swap device and
higher number of CPUs will also make things worse.

Testing using a 128G ZRAM on a 48c96t system.  When the swap device is
very close to full (eg.  124G / 128G), running build linux kernel with
make -j96 in a 1G memory cgroup will hung (not a softlockup though)
spinning in full cluster reclaim for about ~5min before go OOM.

To solve this, split the full reclaim into two parts:

- Instead of do a synchronous aggressively reclaim when device is low,
  do only one aggressively reclaim when device is strictly full with a
  kworker. This still ensures in worst case the device won't be unusable
  because of HAS_CACHE slots.

- To avoid allocation (especially higher order) suffer from HAS_CACHE
  filling up clusters and kworker not responsive enough, do one synchronous
  scan every time the free list is drained, and only scan one cluster. This
  is kind of similar to the random reclaim before, keeps the full clusters
  rotated and has a minimal latency. This should provide a fair reclaim
  strategy suitable for most workloads.

Link: https://lkml.kernel.org/r/20241022175512.10398-1-ryncsn@gmail.com
Fixes: 2cacbdfdee65 ("mm: swap: add a adaptive full cluster cache reclaim")
Signed-off-by: Kairui Song <kasong@tencent.com>
Cc: Barry Song <v-songbaohua@oppo.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swap.h |  1 +
 mm/swapfile.c        | 49 ++++++++++++++++++++++++++++++-------------------
 2 files changed, 31 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index ca533b478c21..f3e0ac20c2e8 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -335,6 +335,7 @@ struct swap_info_struct {
 					 * list.
 					 */
 	struct work_struct discard_work; /* discard worker */
+	struct work_struct reclaim_work; /* reclaim worker */
 	struct list_head discard_clusters; /* discard clusters list */
 	struct plist_node avail_lists[]; /*
 					   * entries in swap_avail_heads, one
diff --git a/mm/swapfile.c b/mm/swapfile.c
index b0915f3fab31..46bd4b1a3c07 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -731,15 +731,16 @@ done:
 	return offset;
 }
 
-static void swap_reclaim_full_clusters(struct swap_info_struct *si)
+/* Return true if reclaimed a whole cluster */
+static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force)
 {
 	long to_scan = 1;
 	unsigned long offset, end;
 	struct swap_cluster_info *ci;
 	unsigned char *map = si->swap_map;
-	int nr_reclaim, total_reclaimed = 0;
+	int nr_reclaim;
 
-	if (atomic_long_read(&nr_swap_pages) <= SWAPFILE_CLUSTER)
+	if (force)
 		to_scan = si->inuse_pages / SWAPFILE_CLUSTER;
 
 	while (!list_empty(&si->full_clusters)) {
@@ -749,28 +750,36 @@ static void swap_reclaim_full_clusters(struct swap_info_struct *si)
 		end = min(si->max, offset + SWAPFILE_CLUSTER);
 		to_scan--;
 
+		spin_unlock(&si->lock);
 		while (offset < end) {
 			if (READ_ONCE(map[offset]) == SWAP_HAS_CACHE) {
-				spin_unlock(&si->lock);
 				nr_reclaim = __try_to_reclaim_swap(si, offset,
 								   TTRS_ANYWAY | TTRS_DIRECT);
-				spin_lock(&si->lock);
-				if (nr_reclaim > 0) {
-					offset += nr_reclaim;
-					total_reclaimed += nr_reclaim;
-					continue;
-				} else if (nr_reclaim < 0) {
-					offset += -nr_reclaim;
+				if (nr_reclaim) {
+					offset += abs(nr_reclaim);
 					continue;
 				}
 			}
 			offset++;
 		}
-		if (to_scan <= 0 || total_reclaimed)
+		spin_lock(&si->lock);
+
+		if (to_scan <= 0)
 			break;
 	}
 }
 
+static void swap_reclaim_work(struct work_struct *work)
+{
+	struct swap_info_struct *si;
+
+	si = container_of(work, struct swap_info_struct, reclaim_work);
+
+	spin_lock(&si->lock);
+	swap_reclaim_full_clusters(si, true);
+	spin_unlock(&si->lock);
+}
+
 /*
  * Try to get swap entries with specified order from current cpu's swap entry
  * pool (a cluster). This might involve allocating a new cluster for current CPU
@@ -800,6 +809,10 @@ new_cluster:
 		goto done;
 	}
 
+	/* Try reclaim from full clusters if free clusters list is drained */
+	if (vm_swap_full())
+		swap_reclaim_full_clusters(si, false);
+
 	if (order < PMD_ORDER) {
 		unsigned int frags = 0;
 
@@ -881,13 +894,6 @@ new_cluster:
 	}
 
 done:
-	/* Try reclaim from full clusters if device is nearfull */
-	if (vm_swap_full() && (!found || (si->pages - si->inuse_pages) < SWAPFILE_CLUSTER)) {
-		swap_reclaim_full_clusters(si);
-		if (!found && !order && si->pages != si->inuse_pages)
-			goto new_cluster;
-	}
-
 	cluster->next[order] = offset;
 	return found;
 }
@@ -922,6 +928,9 @@ static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset,
 		si->lowest_bit = si->max;
 		si->highest_bit = 0;
 		del_from_avail_list(si);
+
+		if (vm_swap_full())
+			schedule_work(&si->reclaim_work);
 	}
 }
 
@@ -2816,6 +2825,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	wait_for_completion(&p->comp);
 
 	flush_work(&p->discard_work);
+	flush_work(&p->reclaim_work);
 
 	destroy_swap_extents(p);
 	if (p->flags & SWP_CONTINUED)
@@ -3376,6 +3386,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		return PTR_ERR(si);
 
 	INIT_WORK(&si->discard_work, swap_discard_work);
+	INIT_WORK(&si->reclaim_work, swap_reclaim_work);
 
 	name = getname(specialfile);
 	if (IS_ERR(name)) {
-- 
cgit v1.2.3


From 9d08ec41a0645283d79a2e642205d488feaceacf Mon Sep 17 00:00:00 2001
From: Yu Zhao <yuzhao@google.com>
Date: Sat, 19 Oct 2024 22:22:12 -0600
Subject: mm: allow set/clear page_type again

Some page flags (page->flags) were converted to page types
(page->page_types).  A recent example is PG_hugetlb.

From the exclusive writer's perspective, e.g., a thread doing
__folio_set_hugetlb(), there is a difference between the page flag and
type APIs: the former allows the same non-atomic operation to be repeated
whereas the latter does not.  For example, calling __folio_set_hugetlb()
twice triggers VM_BUG_ON_FOLIO(), since the second call expects the type
(PG_hugetlb) not to be set previously.

Using add_hugetlb_folio() as an example, it calls __folio_set_hugetlb() in
the following error-handling path.  And when that happens, it triggers the
aforementioned VM_BUG_ON_FOLIO().

  if (folio_test_hugetlb(folio)) {
    rc = hugetlb_vmemmap_restore_folio(h, folio);
    if (rc) {
      spin_lock_irq(&hugetlb_lock);
      add_hugetlb_folio(h, folio, false);
      ...

It is possible to make hugeTLB comply with the new requirements from the
page type API.  However, a straightforward fix would be to just allow the
same page type to be set or cleared again inside the API, to avoid any
changes to its callers.

Link: https://lkml.kernel.org/r/20241020042212.296781-1-yuzhao@google.com
Fixes: d99e3140a4d3 ("mm: turn folio_test_hugetlb into a PageType")
Signed-off-by: Yu Zhao <yuzhao@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/page-flags.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 1b3a76710487..cc839e4365c1 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -975,12 +975,16 @@ static __always_inline bool folio_test_##fname(const struct folio *folio) \
 }									\
 static __always_inline void __folio_set_##fname(struct folio *folio)	\
 {									\
+	if (folio_test_##fname(folio))					\
+		return;							\
 	VM_BUG_ON_FOLIO(data_race(folio->page.page_type) != UINT_MAX,	\
 			folio);						\
 	folio->page.page_type = (unsigned int)PGTY_##lname << 24;	\
 }									\
 static __always_inline void __folio_clear_##fname(struct folio *folio)	\
 {									\
+	if (folio->page.page_type == UINT_MAX)				\
+		return;							\
 	VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio);		\
 	folio->page.page_type = UINT_MAX;				\
 }
@@ -993,11 +997,15 @@ static __always_inline int Page##uname(const struct page *page)		\
 }									\
 static __always_inline void __SetPage##uname(struct page *page)		\
 {									\
+	if (Page##uname(page))						\
+		return;							\
 	VM_BUG_ON_PAGE(data_race(page->page_type) != UINT_MAX, page);	\
 	page->page_type = (unsigned int)PGTY_##lname << 24;		\
 }									\
 static __always_inline void __ClearPage##uname(struct page *page)	\
 {									\
+	if (page->page_type == UINT_MAX)				\
+		return;							\
 	VM_BUG_ON_PAGE(!Page##uname(page), page);			\
 	page->page_type = UINT_MAX;					\
 }
-- 
cgit v1.2.3


From 071b24b54d2d05fbf39ddbb27dee08abd1d713f3 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Sun, 27 Oct 2024 22:31:15 -0700
Subject: Input: fix regression when re-registering input handlers

Commit d469647bafd9 ("Input: simplify event handling logic") introduced
code that would set handler->events() method to either
input_handler_events_filter() or input_handler_events_default() or
input_handler_events_null(), depending on the kind of input handler
(a filter or a regular one) we are dealing with. Unfortunately this
breaks cases when we try to re-register the same filter (as is the case
with sysrq handler): after initial registration the handler will have 2
event handling methods defined, and will run afoul of the check in
input_handler_check_methods():

	input: input_handler_check_methods: only one event processing method can be defined (sysrq)
	sysrq: Failed to register input handler, error -22

Fix this by adding handle_events() method to input_handle structure and
setting it up when registering a new input handle according to event
handling methods defined in associated input_handler structure, thus
avoiding modifying the input_handler structure.

Reported-by: "Ned T. Crigler" <crigler@gmail.com>
Reported-by: Christian Heusel <christian@heusel.eu>
Tested-by: "Ned T. Crigler" <crigler@gmail.com>
Tested-by: Peter Seiderer <ps.report@gmx.net>
Fixes: d469647bafd9 ("Input: simplify event handling logic")
Link: https://lore.kernel.org/r/Zx2iQp6csn42PJA7@xavtug
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/input.c | 134 +++++++++++++++++++++++++++-----------------------
 include/linux/input.h |  10 +++-
 2 files changed, 82 insertions(+), 62 deletions(-)

(limited to 'include')

diff --git a/drivers/input/input.c b/drivers/input/input.c
index 3c321671793f..3d2cc13e1f32 100644
--- a/drivers/input/input.c
+++ b/drivers/input/input.c
@@ -119,12 +119,12 @@ static void input_pass_values(struct input_dev *dev,
 
 	handle = rcu_dereference(dev->grab);
 	if (handle) {
-		count = handle->handler->events(handle, vals, count);
+		count = handle->handle_events(handle, vals, count);
 	} else {
 		list_for_each_entry_rcu(handle, &dev->h_list, d_node)
 			if (handle->open) {
-				count = handle->handler->events(handle, vals,
-								count);
+				count = handle->handle_events(handle, vals,
+							      count);
 				if (!count)
 					break;
 			}
@@ -2537,57 +2537,6 @@ static int input_handler_check_methods(const struct input_handler *handler)
 	return 0;
 }
 
-/*
- * An implementation of input_handler's events() method that simply
- * invokes handler->event() method for each event one by one.
- */
-static unsigned int input_handler_events_default(struct input_handle *handle,
-						 struct input_value *vals,
-						 unsigned int count)
-{
-	struct input_handler *handler = handle->handler;
-	struct input_value *v;
-
-	for (v = vals; v != vals + count; v++)
-		handler->event(handle, v->type, v->code, v->value);
-
-	return count;
-}
-
-/*
- * An implementation of input_handler's events() method that invokes
- * handler->filter() method for each event one by one and removes events
- * that were filtered out from the "vals" array.
- */
-static unsigned int input_handler_events_filter(struct input_handle *handle,
-						struct input_value *vals,
-						unsigned int count)
-{
-	struct input_handler *handler = handle->handler;
-	struct input_value *end = vals;
-	struct input_value *v;
-
-	for (v = vals; v != vals + count; v++) {
-		if (handler->filter(handle, v->type, v->code, v->value))
-			continue;
-		if (end != v)
-			*end = *v;
-		end++;
-	}
-
-	return end - vals;
-}
-
-/*
- * An implementation of input_handler's events() method that does nothing.
- */
-static unsigned int input_handler_events_null(struct input_handle *handle,
-					      struct input_value *vals,
-					      unsigned int count)
-{
-	return count;
-}
-
 /**
  * input_register_handler - register a new input handler
  * @handler: handler to be registered
@@ -2607,13 +2556,6 @@ int input_register_handler(struct input_handler *handler)
 
 	INIT_LIST_HEAD(&handler->h_list);
 
-	if (handler->filter)
-		handler->events = input_handler_events_filter;
-	else if (handler->event)
-		handler->events = input_handler_events_default;
-	else if (!handler->events)
-		handler->events = input_handler_events_null;
-
 	error = mutex_lock_interruptible(&input_mutex);
 	if (error)
 		return error;
@@ -2687,6 +2629,75 @@ int input_handler_for_each_handle(struct input_handler *handler, void *data,
 }
 EXPORT_SYMBOL(input_handler_for_each_handle);
 
+/*
+ * An implementation of input_handle's handle_events() method that simply
+ * invokes handler->event() method for each event one by one.
+ */
+static unsigned int input_handle_events_default(struct input_handle *handle,
+						struct input_value *vals,
+						unsigned int count)
+{
+	struct input_handler *handler = handle->handler;
+	struct input_value *v;
+
+	for (v = vals; v != vals + count; v++)
+		handler->event(handle, v->type, v->code, v->value);
+
+	return count;
+}
+
+/*
+ * An implementation of input_handle's handle_events() method that invokes
+ * handler->filter() method for each event one by one and removes events
+ * that were filtered out from the "vals" array.
+ */
+static unsigned int input_handle_events_filter(struct input_handle *handle,
+					       struct input_value *vals,
+					       unsigned int count)
+{
+	struct input_handler *handler = handle->handler;
+	struct input_value *end = vals;
+	struct input_value *v;
+
+	for (v = vals; v != vals + count; v++) {
+		if (handler->filter(handle, v->type, v->code, v->value))
+			continue;
+		if (end != v)
+			*end = *v;
+		end++;
+	}
+
+	return end - vals;
+}
+
+/*
+ * An implementation of input_handle's handle_events() method that does nothing.
+ */
+static unsigned int input_handle_events_null(struct input_handle *handle,
+					     struct input_value *vals,
+					     unsigned int count)
+{
+	return count;
+}
+
+/*
+ * Sets up appropriate handle->event_handler based on the input_handler
+ * associated with the handle.
+ */
+static void input_handle_setup_event_handler(struct input_handle *handle)
+{
+	struct input_handler *handler = handle->handler;
+
+	if (handler->filter)
+		handle->handle_events = input_handle_events_filter;
+	else if (handler->event)
+		handle->handle_events = input_handle_events_default;
+	else if (handler->events)
+		handle->handle_events = handler->events;
+	else
+		handle->handle_events = input_handle_events_null;
+}
+
 /**
  * input_register_handle - register a new input handle
  * @handle: handle to register
@@ -2704,6 +2715,7 @@ int input_register_handle(struct input_handle *handle)
 	struct input_dev *dev = handle->dev;
 	int error;
 
+	input_handle_setup_event_handler(handle);
 	/*
 	 * We take dev->mutex here to prevent race with
 	 * input_release_device().
diff --git a/include/linux/input.h b/include/linux/input.h
index 89a0be6ee0e2..cd866b020a01 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -339,12 +339,16 @@ struct input_handler {
  * @name: name given to the handle by handler that created it
  * @dev: input device the handle is attached to
  * @handler: handler that works with the device through this handle
+ * @handle_events: event sequence handler. It is set up by the input core
+ *	according to event handling method specified in the @handler. See
+ *	input_handle_setup_event_handler().
+ *	This method is being called by the input core with interrupts disabled
+ *	and dev->event_lock spinlock held and so it may not sleep.
  * @d_node: used to put the handle on device's list of attached handles
  * @h_node: used to put the handle on handler's list of handles from which
  *	it gets events
  */
 struct input_handle {
-
 	void *private;
 
 	int open;
@@ -353,6 +357,10 @@ struct input_handle {
 	struct input_dev *dev;
 	struct input_handler *handler;
 
+	unsigned int (*handle_events)(struct input_handle *handle,
+				      struct input_value *vals,
+				      unsigned int count);
+
 	struct list_head	d_node;
 	struct list_head	h_node;
 };
-- 
cgit v1.2.3


From ddd6d8e975b171ea3f63a011a75820883ff0d479 Mon Sep 17 00:00:00 2001
From: Yu Zhao <yuzhao@google.com>
Date: Sat, 19 Oct 2024 01:29:38 +0000
Subject: mm: multi-gen LRU: remove MM_LEAF_OLD and MM_NONLEAF_TOTAL stats

Patch series "mm: multi-gen LRU: Have secondary MMUs participate in
MM_WALK".

Today, the MM_WALK capability causes MGLRU to clear the young bit from
PMDs and PTEs during the page table walk before eviction, but MGLRU does
not call the clear_young() MMU notifier in this case.  By not calling this
notifier, the MM walk takes less time/CPU, but it causes pages that are
accessed mostly through KVM / secondary MMUs to appear younger than they
should be.

We do call the clear_young() notifier today, but only when attempting to
evict the page, so we end up clearing young/accessed information less
frequently for secondary MMUs than for mm PTEs, and therefore they appear
younger and are less likely to be evicted.  Therefore, memory that is
*not* being accessed mostly by KVM will be evicted *more* frequently,
worsening performance.

ChromeOS observed a tab-open latency regression when enabling MGLRU with a
setup that involved running a VM:

		Tab-open latency histogram (ms)
Version		p50	mean	p95	p99	max
base		1315	1198	2347	3454	10319
mglru		2559	1311	7399	12060	43758
fix		1119	926	2470	4211	6947

This series replaces the final non-selftest patchs from this series[1],
which introduced a similar change (and a new MMU notifier) with KVM
optimizations.  I'll send a separate series (to Sean and Paolo) for the
KVM optimizations.

This series also makes proactive reclaim with MGLRU possible for KVM
memory.  I have verified that this functions correctly with the selftest
from [1], but given that that test is a KVM selftest, I'll send it with
the rest of the KVM optimizations later.  Andrew, let me know if you'd
like to take the test now anyway.

[1]: https://lore.kernel.org/linux-mm/20240926013506.860253-18-jthoughton@google.com/


This patch (of 2):

The removed stats, MM_LEAF_OLD and MM_NONLEAF_TOTAL, are not very helpful
and become more complicated to properly compute when adding
test/clear_young() notifiers in MGLRU's mm walk.

Link: https://lkml.kernel.org/r/20241019012940.3656292-1-jthoughton@google.com
Link: https://lkml.kernel.org/r/20241019012940.3656292-2-jthoughton@google.com
Fixes: bd74fdaea146 ("mm: multi-gen LRU: support page table walks")
Signed-off-by: Yu Zhao <yuzhao@google.com>
Signed-off-by: James Houghton <jthoughton@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Matlack <dmatlack@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: David Stevens <stevensd@google.com>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Wei Xu <weixugc@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mmzone.h |  2 --
 mm/vmscan.c            | 14 +++++---------
 2 files changed, 5 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 17506e4a2835..9342e5692dab 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -458,9 +458,7 @@ struct lru_gen_folio {
 
 enum {
 	MM_LEAF_TOTAL,		/* total leaf entries */
-	MM_LEAF_OLD,		/* old leaf entries */
 	MM_LEAF_YOUNG,		/* young leaf entries */
-	MM_NONLEAF_TOTAL,	/* total non-leaf entries */
 	MM_NONLEAF_FOUND,	/* non-leaf entries found in Bloom filters */
 	MM_NONLEAF_ADDED,	/* non-leaf entries added to Bloom filters */
 	NR_MM_STATS
diff --git a/mm/vmscan.c b/mm/vmscan.c
index eb4e8440c507..4f1d33e4b360 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3399,7 +3399,6 @@ restart:
 			continue;
 
 		if (!pte_young(ptent)) {
-			walk->mm_stats[MM_LEAF_OLD]++;
 			continue;
 		}
 
@@ -3552,7 +3551,6 @@ restart:
 			walk->mm_stats[MM_LEAF_TOTAL]++;
 
 			if (!pmd_young(val)) {
-				walk->mm_stats[MM_LEAF_OLD]++;
 				continue;
 			}
 
@@ -3564,8 +3562,6 @@ restart:
 			continue;
 		}
 
-		walk->mm_stats[MM_NONLEAF_TOTAL]++;
-
 		if (!walk->force_scan && should_clear_pmd_young()) {
 			if (!pmd_young(val))
 				continue;
@@ -5254,11 +5250,11 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
 	for (tier = 0; tier < MAX_NR_TIERS; tier++) {
 		seq_printf(m, "            %10d", tier);
 		for (type = 0; type < ANON_AND_FILE; type++) {
-			const char *s = "   ";
+			const char *s = "xxx";
 			unsigned long n[3] = {};
 
 			if (seq == max_seq) {
-				s = "RT ";
+				s = "RTx";
 				n[0] = READ_ONCE(lrugen->avg_refaulted[type][tier]);
 				n[1] = READ_ONCE(lrugen->avg_total[type][tier]);
 			} else if (seq == min_seq[type] || NR_HIST_GENS > 1) {
@@ -5280,14 +5276,14 @@ static void lru_gen_seq_show_full(struct seq_file *m, struct lruvec *lruvec,
 
 	seq_puts(m, "                      ");
 	for (i = 0; i < NR_MM_STATS; i++) {
-		const char *s = "      ";
+		const char *s = "xxxx";
 		unsigned long n = 0;
 
 		if (seq == max_seq && NR_HIST_GENS == 1) {
-			s = "LOYNFA";
+			s = "TYFA";
 			n = READ_ONCE(mm_state->stats[hist][i]);
 		} else if (seq != max_seq && NR_HIST_GENS > 1) {
-			s = "loynfa";
+			s = "tyfa";
 			n = READ_ONCE(mm_state->stats[hist][i]);
 		}
 
-- 
cgit v1.2.3


From 1d4832becdc2cdb2cffe2a6050c9d9fd8ff1c58c Mon Sep 17 00:00:00 2001
From: Yu Zhao <yuzhao@google.com>
Date: Sat, 19 Oct 2024 01:29:39 +0000
Subject: mm: multi-gen LRU: use {ptep,pmdp}_clear_young_notify()

When the MM_WALK capability is enabled, memory that is mostly accessed by
a VM appears younger than it really is, therefore this memory will be less
likely to be evicted.  Therefore, the presence of a running VM can
significantly increase swap-outs for non-VM memory, regressing the
performance for the rest of the system.

Fix this regression by always calling {ptep,pmdp}_clear_young_notify()
whenever we clear the young bits on PMDs/PTEs.

[jthoughton@google.com: fix link-time error]
Link: https://lkml.kernel.org/r/20241019012940.3656292-3-jthoughton@google.com
Fixes: bd74fdaea146 ("mm: multi-gen LRU: support page table walks")
Signed-off-by: Yu Zhao <yuzhao@google.com>
Signed-off-by: James Houghton <jthoughton@google.com>
Reported-by: David Stevens <stevensd@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: David Matlack <dmatlack@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: Wei Xu <weixugc@google.com>
Cc: <stable@vger.kernel.org>
Cc: kernel test robot <lkp@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mmzone.h |  5 +--
 mm/rmap.c              |  9 ++----
 mm/vmscan.c            | 88 ++++++++++++++++++++++++++++----------------------
 3 files changed, 55 insertions(+), 47 deletions(-)

(limited to 'include')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 9342e5692dab..5b1c984daf45 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -555,7 +555,7 @@ struct lru_gen_memcg {
 
 void lru_gen_init_pgdat(struct pglist_data *pgdat);
 void lru_gen_init_lruvec(struct lruvec *lruvec);
-void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
+bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
 
 void lru_gen_init_memcg(struct mem_cgroup *memcg);
 void lru_gen_exit_memcg(struct mem_cgroup *memcg);
@@ -574,8 +574,9 @@ static inline void lru_gen_init_lruvec(struct lruvec *lruvec)
 {
 }
 
-static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 {
+	return false;
 }
 
 static inline void lru_gen_init_memcg(struct mem_cgroup *memcg)
diff --git a/mm/rmap.c b/mm/rmap.c
index a8797d1b3d49..73d5998677d4 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -885,13 +885,10 @@ static bool folio_referenced_one(struct folio *folio,
 			return false;
 		}
 
-		if (pvmw.pte) {
-			if (lru_gen_enabled() &&
-			    pte_young(ptep_get(pvmw.pte))) {
-				lru_gen_look_around(&pvmw);
+		if (lru_gen_enabled() && pvmw.pte) {
+			if (lru_gen_look_around(&pvmw))
 				referenced++;
-			}
-
+		} else if (pvmw.pte) {
 			if (ptep_clear_flush_young_notify(vma, address,
 						pvmw.pte))
 				referenced++;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4f1d33e4b360..ddaaff67642e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -56,6 +56,7 @@
 #include <linux/khugepaged.h>
 #include <linux/rculist_nulls.h>
 #include <linux/random.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -3294,7 +3295,8 @@ static bool get_next_vma(unsigned long mask, unsigned long size, struct mm_walk
 	return false;
 }
 
-static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr)
+static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned long addr,
+				 struct pglist_data *pgdat)
 {
 	unsigned long pfn = pte_pfn(pte);
 
@@ -3306,13 +3308,20 @@ static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned
 	if (WARN_ON_ONCE(pte_devmap(pte) || pte_special(pte)))
 		return -1;
 
+	if (!pte_young(pte) && !mm_has_notifiers(vma->vm_mm))
+		return -1;
+
 	if (WARN_ON_ONCE(!pfn_valid(pfn)))
 		return -1;
 
+	if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
+		return -1;
+
 	return pfn;
 }
 
-static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr)
+static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned long addr,
+				 struct pglist_data *pgdat)
 {
 	unsigned long pfn = pmd_pfn(pmd);
 
@@ -3324,9 +3333,15 @@ static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned
 	if (WARN_ON_ONCE(pmd_devmap(pmd)))
 		return -1;
 
+	if (!pmd_young(pmd) && !mm_has_notifiers(vma->vm_mm))
+		return -1;
+
 	if (WARN_ON_ONCE(!pfn_valid(pfn)))
 		return -1;
 
+	if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
+		return -1;
+
 	return pfn;
 }
 
@@ -3335,10 +3350,6 @@ static struct folio *get_pfn_folio(unsigned long pfn, struct mem_cgroup *memcg,
 {
 	struct folio *folio;
 
-	/* try to avoid unnecessary memory loads */
-	if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
-		return NULL;
-
 	folio = pfn_folio(pfn);
 	if (folio_nid(folio) != pgdat->node_id)
 		return NULL;
@@ -3394,20 +3405,16 @@ restart:
 		total++;
 		walk->mm_stats[MM_LEAF_TOTAL]++;
 
-		pfn = get_pte_pfn(ptent, args->vma, addr);
+		pfn = get_pte_pfn(ptent, args->vma, addr, pgdat);
 		if (pfn == -1)
 			continue;
 
-		if (!pte_young(ptent)) {
-			continue;
-		}
-
 		folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap);
 		if (!folio)
 			continue;
 
-		if (!ptep_test_and_clear_young(args->vma, addr, pte + i))
-			VM_WARN_ON_ONCE(true);
+		if (!ptep_clear_young_notify(args->vma, addr, pte + i))
+			continue;
 
 		young++;
 		walk->mm_stats[MM_LEAF_YOUNG]++;
@@ -3473,21 +3480,25 @@ static void walk_pmd_range_locked(pud_t *pud, unsigned long addr, struct vm_area
 		/* don't round down the first address */
 		addr = i ? (*first & PMD_MASK) + i * PMD_SIZE : *first;
 
-		pfn = get_pmd_pfn(pmd[i], vma, addr);
-		if (pfn == -1)
+		if (!pmd_present(pmd[i]))
 			goto next;
 
 		if (!pmd_trans_huge(pmd[i])) {
-			if (!walk->force_scan && should_clear_pmd_young())
+			if (!walk->force_scan && should_clear_pmd_young() &&
+			    !mm_has_notifiers(args->mm))
 				pmdp_test_and_clear_young(vma, addr, pmd + i);
 			goto next;
 		}
 
+		pfn = get_pmd_pfn(pmd[i], vma, addr, pgdat);
+		if (pfn == -1)
+			goto next;
+
 		folio = get_pfn_folio(pfn, memcg, pgdat, walk->can_swap);
 		if (!folio)
 			goto next;
 
-		if (!pmdp_test_and_clear_young(vma, addr, pmd + i))
+		if (!pmdp_clear_young_notify(vma, addr, pmd + i))
 			goto next;
 
 		walk->mm_stats[MM_LEAF_YOUNG]++;
@@ -3545,24 +3556,18 @@ restart:
 		}
 
 		if (pmd_trans_huge(val)) {
-			unsigned long pfn = pmd_pfn(val);
 			struct pglist_data *pgdat = lruvec_pgdat(walk->lruvec);
+			unsigned long pfn = get_pmd_pfn(val, vma, addr, pgdat);
 
 			walk->mm_stats[MM_LEAF_TOTAL]++;
 
-			if (!pmd_young(val)) {
-				continue;
-			}
-
-			/* try to avoid unnecessary memory loads */
-			if (pfn < pgdat->node_start_pfn || pfn >= pgdat_end_pfn(pgdat))
-				continue;
-
-			walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first);
+			if (pfn != -1)
+				walk_pmd_range_locked(pud, addr, vma, args, bitmap, &first);
 			continue;
 		}
 
-		if (!walk->force_scan && should_clear_pmd_young()) {
+		if (!walk->force_scan && should_clear_pmd_young() &&
+		    !mm_has_notifiers(args->mm)) {
 			if (!pmd_young(val))
 				continue;
 
@@ -4036,13 +4041,13 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
  * the PTE table to the Bloom filter. This forms a feedback loop between the
  * eviction and the aging.
  */
-void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 {
 	int i;
 	unsigned long start;
 	unsigned long end;
 	struct lru_gen_mm_walk *walk;
-	int young = 0;
+	int young = 1;
 	pte_t *pte = pvmw->pte;
 	unsigned long addr = pvmw->address;
 	struct vm_area_struct *vma = pvmw->vma;
@@ -4058,12 +4063,15 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 	lockdep_assert_held(pvmw->ptl);
 	VM_WARN_ON_ONCE_FOLIO(folio_test_lru(folio), folio);
 
+	if (!ptep_clear_young_notify(vma, addr, pte))
+		return false;
+
 	if (spin_is_contended(pvmw->ptl))
-		return;
+		return true;
 
 	/* exclude special VMAs containing anon pages from COW */
 	if (vma->vm_flags & VM_SPECIAL)
-		return;
+		return true;
 
 	/* avoid taking the LRU lock under the PTL when possible */
 	walk = current->reclaim_state ? current->reclaim_state->mm_walk : NULL;
@@ -4071,6 +4079,9 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 	start = max(addr & PMD_MASK, vma->vm_start);
 	end = min(addr | ~PMD_MASK, vma->vm_end - 1) + 1;
 
+	if (end - start == PAGE_SIZE)
+		return true;
+
 	if (end - start > MIN_LRU_BATCH * PAGE_SIZE) {
 		if (addr - start < MIN_LRU_BATCH * PAGE_SIZE / 2)
 			end = start + MIN_LRU_BATCH * PAGE_SIZE;
@@ -4084,7 +4095,7 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 
 	/* folio_update_gen() requires stable folio_memcg() */
 	if (!mem_cgroup_trylock_pages(memcg))
-		return;
+		return true;
 
 	arch_enter_lazy_mmu_mode();
 
@@ -4094,19 +4105,16 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 		unsigned long pfn;
 		pte_t ptent = ptep_get(pte + i);
 
-		pfn = get_pte_pfn(ptent, vma, addr);
+		pfn = get_pte_pfn(ptent, vma, addr, pgdat);
 		if (pfn == -1)
 			continue;
 
-		if (!pte_young(ptent))
-			continue;
-
 		folio = get_pfn_folio(pfn, memcg, pgdat, can_swap);
 		if (!folio)
 			continue;
 
-		if (!ptep_test_and_clear_young(vma, addr, pte + i))
-			VM_WARN_ON_ONCE(true);
+		if (!ptep_clear_young_notify(vma, addr, pte + i))
+			continue;
 
 		young++;
 
@@ -4136,6 +4144,8 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 	/* feedback from rmap walkers to page table walkers */
 	if (mm_state && suitable_to_scan(i, young))
 		update_bloom_filter(mm_state, max_seq, pvmw->pmd);
+
+	return true;
 }
 
 /******************************************************************************
-- 
cgit v1.2.3