26 files changed, 410 insertions, 45 deletions

diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h
index 04f3ace5787b..8fc1aed64113 100644
--- a/include/linux/ceph/decode.h
+++ b/include/linux/ceph/decode.h
@@ -6,7 +6,7 @@
 #include <linux/bug.h>
 #include <linux/slab.h>
 #include <linux/time.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 
 #include <linux/ceph/types.h>
 
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 4497d0a6772c..15fb566d3f46 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -4,7 +4,7 @@
 
 #include <linux/ceph/ceph_debug.h>
 
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 #include <linux/backing-dev.h>
 #include <linux/completion.h>
 #include <linux/exportfs.h>
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index e0e19d9c1323..7fe0981a7e46 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -1107,10 +1107,9 @@ static inline int parse_perf_domain(int cpu, const char *list_name,
 				    const char *cell_name,
 				    struct of_phandle_args *args)
 {
-	struct device_node *cpu_np;
 	int ret;
 
-	cpu_np = of_cpu_device_node_get(cpu);
+	struct device_node *cpu_np __free(device_node) = of_cpu_device_node_get(cpu);
 	if (!cpu_np)
 		return -ENODEV;
 
@@ -1118,9 +1117,6 @@ static inline int parse_perf_domain(int cpu, const char *list_name,
 					 args);
 	if (ret < 0)
 		return ret;
-
-	of_node_put(cpu_np);
-
 	return 0;
 }
 
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 2361ed4d2b15..61d9a66d1807 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -227,6 +227,7 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_ARM_APM_XGENE_ONLINE,
 	CPUHP_AP_PERF_ARM_CAVIUM_TX2_UNCORE_ONLINE,
 	CPUHP_AP_PERF_ARM_MARVELL_CN10K_DDR_ONLINE,
+	CPUHP_AP_PERF_ARM_MRVL_PEM_ONLINE,
 	CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE,
 	CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE,
 	CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE,
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 30114c25ad12..ecf203f01034 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -21,7 +21,7 @@
 #include <linux/netdevice.h>
 #include <linux/random.h>
 #include <linux/crc32.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 #include <asm/bitsperlong.h>
 
 #ifdef __KERNEL__
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index 2944d4aa413b..b1c5722f2b3c 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -22,7 +22,6 @@
  * as this is the granularity returned by copy_fdset().
  */
 #define NR_OPEN_DEFAULT BITS_PER_LONG
-#define NR_OPEN_MAX ~0U
 
 struct fdtable {
 	unsigned int max_fds;
@@ -106,7 +105,10 @@ struct task_struct;
 
 void put_files_struct(struct files_struct *fs);
 int unshare_files(void);
-struct files_struct *dup_fd(struct files_struct *, unsigned, int *) __latent_entropy;
+struct fd_range {
+	unsigned int from, to;
+};
+struct files_struct *dup_fd(struct files_struct *, struct fd_range *) __latent_entropy;
 void do_close_on_exec(struct files_struct *);
 int iterate_fd(struct files_struct *, unsigned,
 		int (*)(const void *, struct file *, unsigned),
@@ -115,8 +117,6 @@ int iterate_fd(struct files_struct *, unsigned,
 extern int close_fd(unsigned int fd);
 extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags);
 extern struct file *file_close_fd(unsigned int fd);
-extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
-		      struct files_struct **new_fdp);
 
 extern struct kmem_cache *files_cachep;
 
diff --git a/include/linux/folio_queue.h b/include/linux/folio_queue.h
index 955680c3bb5f..3abe614ef5f0 100644
--- a/include/linux/folio_queue.h
+++ b/include/linux/folio_queue.h
@@ -3,6 +3,12 @@
  *
  * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
+ *
+ * See:
+ *
+ *	Documentation/core-api/folio_queue.rst
+ *
+ * for a description of the API.
  */
 
 #ifndef _LINUX_FOLIO_QUEUE_H
@@ -33,6 +39,13 @@ struct folio_queue {
 #endif
 };
 
+/**
+ * folioq_init - Initialise a folio queue segment
+ * @folioq: The segment to initialise
+ *
+ * Initialise a folio queue segment.  Note that the folio pointers are
+ * left uninitialised.
+ */
 static inline void folioq_init(struct folio_queue *folioq)
 {
 	folio_batch_init(&folioq->vec);
@@ -43,62 +56,155 @@ static inline void folioq_init(struct folio_queue *folioq)
 	folioq->marks3 = 0;
 }
 
+/**
+ * folioq_nr_slots: Query the capacity of a folio queue segment
+ * @folioq: The segment to query
+ *
+ * Query the number of folios that a particular folio queue segment might hold.
+ * [!] NOTE: This must not be assumed to be the same for every segment!
+ */
 static inline unsigned int folioq_nr_slots(const struct folio_queue *folioq)
 {
 	return PAGEVEC_SIZE;
 }
 
+/**
+ * folioq_count: Query the occupancy of a folio queue segment
+ * @folioq: The segment to query
+ *
+ * Query the number of folios that have been added to a folio queue segment.
+ * Note that this is not decreased as folios are removed from a segment.
+ */
 static inline unsigned int folioq_count(struct folio_queue *folioq)
 {
 	return folio_batch_count(&folioq->vec);
 }
 
+/**
+ * folioq_full: Query if a folio queue segment is full
+ * @folioq: The segment to query
+ *
+ * Query if a folio queue segment is fully occupied.  Note that this does not
+ * change if folios are removed from a segment.
+ */
 static inline bool folioq_full(struct folio_queue *folioq)
 {
 	//return !folio_batch_space(&folioq->vec);
 	return folioq_count(folioq) >= folioq_nr_slots(folioq);
 }
 
+/**
+ * folioq_is_marked: Check first folio mark in a folio queue segment
+ * @folioq: The segment to query
+ * @slot: The slot number of the folio to query
+ *
+ * Determine if the first mark is set for the folio in the specified slot in a
+ * folio queue segment.
+ */
 static inline bool folioq_is_marked(const struct folio_queue *folioq, unsigned int slot)
 {
 	return test_bit(slot, &folioq->marks);
 }
 
+/**
+ * folioq_mark: Set the first mark on a folio in a folio queue segment
+ * @folioq: The segment to modify
+ * @slot: The slot number of the folio to modify
+ *
+ * Set the first mark for the folio in the specified slot in a folio queue
+ * segment.
+ */
 static inline void folioq_mark(struct folio_queue *folioq, unsigned int slot)
 {
 	set_bit(slot, &folioq->marks);
 }
 
+/**
+ * folioq_unmark: Clear the first mark on a folio in a folio queue segment
+ * @folioq: The segment to modify
+ * @slot: The slot number of the folio to modify
+ *
+ * Clear the first mark for the folio in the specified slot in a folio queue
+ * segment.
+ */
 static inline void folioq_unmark(struct folio_queue *folioq, unsigned int slot)
 {
 	clear_bit(slot, &folioq->marks);
 }
 
+/**
+ * folioq_is_marked2: Check second folio mark in a folio queue segment
+ * @folioq: The segment to query
+ * @slot: The slot number of the folio to query
+ *
+ * Determine if the second mark is set for the folio in the specified slot in a
+ * folio queue segment.
+ */
 static inline bool folioq_is_marked2(const struct folio_queue *folioq, unsigned int slot)
 {
 	return test_bit(slot, &folioq->marks2);
 }
 
+/**
+ * folioq_mark2: Set the second mark on a folio in a folio queue segment
+ * @folioq: The segment to modify
+ * @slot: The slot number of the folio to modify
+ *
+ * Set the second mark for the folio in the specified slot in a folio queue
+ * segment.
+ */
 static inline void folioq_mark2(struct folio_queue *folioq, unsigned int slot)
 {
 	set_bit(slot, &folioq->marks2);
 }
 
+/**
+ * folioq_unmark2: Clear the second mark on a folio in a folio queue segment
+ * @folioq: The segment to modify
+ * @slot: The slot number of the folio to modify
+ *
+ * Clear the second mark for the folio in the specified slot in a folio queue
+ * segment.
+ */
 static inline void folioq_unmark2(struct folio_queue *folioq, unsigned int slot)
 {
 	clear_bit(slot, &folioq->marks2);
 }
 
+/**
+ * folioq_is_marked3: Check third folio mark in a folio queue segment
+ * @folioq: The segment to query
+ * @slot: The slot number of the folio to query
+ *
+ * Determine if the third mark is set for the folio in the specified slot in a
+ * folio queue segment.
+ */
 static inline bool folioq_is_marked3(const struct folio_queue *folioq, unsigned int slot)
 {
 	return test_bit(slot, &folioq->marks3);
 }
 
+/**
+ * folioq_mark3: Set the third mark on a folio in a folio queue segment
+ * @folioq: The segment to modify
+ * @slot: The slot number of the folio to modify
+ *
+ * Set the third mark for the folio in the specified slot in a folio queue
+ * segment.
+ */
 static inline void folioq_mark3(struct folio_queue *folioq, unsigned int slot)
 {
 	set_bit(slot, &folioq->marks3);
 }
 
+/**
+ * folioq_unmark3: Clear the third mark on a folio in a folio queue segment
+ * @folioq: The segment to modify
+ * @slot: The slot number of the folio to modify
+ *
+ * Clear the third mark for the folio in the specified slot in a folio queue
+ * segment.
+ */
 static inline void folioq_unmark3(struct folio_queue *folioq, unsigned int slot)
 {
 	clear_bit(slot, &folioq->marks3);
@@ -111,6 +217,19 @@ static inline unsigned int __folio_order(struct folio *folio)
 	return folio->_flags_1 & 0xff;
 }
 
+/**
+ * folioq_append: Add a folio to a folio queue segment
+ * @folioq: The segment to add to
+ * @folio: The folio to add
+ *
+ * Add a folio to the tail of the sequence in a folio queue segment, increasing
+ * the occupancy count and returning the slot number for the folio just added.
+ * The folio size is extracted and stored in the queue and the marks are left
+ * unmodified.
+ *
+ * Note that it's left up to the caller to check that the segment capacity will
+ * not be exceeded and to extend the queue.
+ */
 static inline unsigned int folioq_append(struct folio_queue *folioq, struct folio *folio)
 {
 	unsigned int slot = folioq->vec.nr++;
@@ -120,6 +239,19 @@ static inline unsigned int folioq_append(struct folio_queue *folioq, struct foli
 	return slot;
 }
 
+/**
+ * folioq_append_mark: Add a folio to a folio queue segment
+ * @folioq: The segment to add to
+ * @folio: The folio to add
+ *
+ * Add a folio to the tail of the sequence in a folio queue segment, increasing
+ * the occupancy count and returning the slot number for the folio just added.
+ * The folio size is extracted and stored in the queue, the first mark is set
+ * and and the second and third marks are left unmodified.
+ *
+ * Note that it's left up to the caller to check that the segment capacity will
+ * not be exceeded and to extend the queue.
+ */
 static inline unsigned int folioq_append_mark(struct folio_queue *folioq, struct folio *folio)
 {
 	unsigned int slot = folioq->vec.nr++;
@@ -130,21 +262,57 @@ static inline unsigned int folioq_append_mark(struct folio_queue *folioq, struct
 	return slot;
 }
 
+/**
+ * folioq_folio: Get a folio from a folio queue segment
+ * @folioq: The segment to access
+ * @slot: The folio slot to access
+ *
+ * Retrieve the folio in the specified slot from a folio queue segment.  Note
+ * that no bounds check is made and if the slot hasn't been added into yet, the
+ * pointer will be undefined.  If the slot has been cleared, NULL will be
+ * returned.
+ */
 static inline struct folio *folioq_folio(const struct folio_queue *folioq, unsigned int slot)
 {
 	return folioq->vec.folios[slot];
 }
 
+/**
+ * folioq_folio_order: Get the order of a folio from a folio queue segment
+ * @folioq: The segment to access
+ * @slot: The folio slot to access
+ *
+ * Retrieve the order of the folio in the specified slot from a folio queue
+ * segment.  Note that no bounds check is made and if the slot hasn't been
+ * added into yet, the order returned will be 0.
+ */
 static inline unsigned int folioq_folio_order(const struct folio_queue *folioq, unsigned int slot)
 {
 	return folioq->orders[slot];
 }
 
+/**
+ * folioq_folio_size: Get the size of a folio from a folio queue segment
+ * @folioq: The segment to access
+ * @slot: The folio slot to access
+ *
+ * Retrieve the size of the folio in the specified slot from a folio queue
+ * segment.  Note that no bounds check is made and if the slot hasn't been
+ * added into yet, the size returned will be PAGE_SIZE.
+ */
 static inline size_t folioq_folio_size(const struct folio_queue *folioq, unsigned int slot)
 {
 	return PAGE_SIZE << folioq_folio_order(folioq, slot);
 }
 
+/**
+ * folioq_clear: Clear a folio from a folio queue segment
+ * @folioq: The segment to clear
+ * @slot: The folio slot to clear
+ *
+ * Clear a folio from a sequence in a folio queue segment and clear its marks.
+ * The occupancy count is left unchanged.
+ */
 static inline void folioq_clear(struct folio_queue *folioq, unsigned int slot)
 {
 	folioq->vec.folios[slot] = NULL;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e3c603d01337..3559446279c1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3082,7 +3082,12 @@ extern loff_t default_llseek(struct file *file, loff_t offset, int whence);
 
 extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence);
 
-extern int inode_init_always(struct super_block *, struct inode *);
+extern int inode_init_always_gfp(struct super_block *, struct inode *, gfp_t);
+static inline int inode_init_always(struct super_block *sb, struct inode *inode)
+{
+	return inode_init_always_gfp(sb, inode, GFP_NOFS);
+}
+
 extern void inode_init_once(struct inode *);
 extern void address_space_init_once(struct address_space *mapping);
 extern struct inode * igrab(struct inode *);
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 8be029bc50b1..3ecf7768e577 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -217,7 +217,6 @@ struct fsnotify_group {
 
 #define FSNOTIFY_GROUP_USER	0x01 /* user allocated group */
 #define FSNOTIFY_GROUP_DUPS	0x02 /* allow multiple marks per object */
-#define FSNOTIFY_GROUP_NOFS	0x04 /* group lock is not direct reclaim safe */
 	int flags;
 	unsigned int owner_flags;	/* stored flags of mark_mutex owner */
 
@@ -268,22 +267,19 @@ struct fsnotify_group {
 static inline void fsnotify_group_lock(struct fsnotify_group *group)
 {
 	mutex_lock(&group->mark_mutex);
-	if (group->flags & FSNOTIFY_GROUP_NOFS)
-		group->owner_flags = memalloc_nofs_save();
+	group->owner_flags = memalloc_nofs_save();
 }
 
 static inline void fsnotify_group_unlock(struct fsnotify_group *group)
 {
-	if (group->flags & FSNOTIFY_GROUP_NOFS)
-		memalloc_nofs_restore(group->owner_flags);
+	memalloc_nofs_restore(group->owner_flags);
 	mutex_unlock(&group->mark_mutex);
 }
 
 static inline void fsnotify_group_assert_locked(struct fsnotify_group *group)
 {
 	WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex));
-	if (group->flags & FSNOTIFY_GROUP_NOFS)
-		WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS));
+	WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS));
 }
 
 /* When calling fsnotify tell it if the data is a path or inode */
diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h
index 3bb87bf6bc65..455f855bc084 100644
--- a/include/linux/hdmi.h
+++ b/include/linux/hdmi.h
@@ -59,6 +59,15 @@ enum hdmi_infoframe_type {
 #define HDMI_DRM_INFOFRAME_SIZE    26
 #define HDMI_VENDOR_INFOFRAME_SIZE  4
 
+/*
+ * HDMI 1.3a table 5-14 states that the largest InfoFrame_length is 27,
+ * not including the packet header or checksum byte. We include the
+ * checksum byte in HDMI_INFOFRAME_HEADER_SIZE, so this should allow
+ * HDMI_INFOFRAME_SIZE(MAX) to be the largest buffer we could ever need
+ * for any HDMI infoframe.
+ */
+#define HDMI_MAX_INFOFRAME_SIZE    27
+
 #define HDMI_INFOFRAME_SIZE(type)	\
 	(HDMI_INFOFRAME_HEADER_SIZE + HDMI_ ## type ## _INFOFRAME_SIZE)
 
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 30cef3b940eb..456bca45ff05 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -20,7 +20,7 @@
 #include <linux/etherdevice.h>
 #include <linux/bitfield.h>
 #include <asm/byteorder.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 
 /*
  * DS bit usage
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 97f6de69f616..96d369112bfa 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -2138,7 +2138,7 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8	   ts_cqe_metadata_size2wqe_counter[0x5];
 	u8	   reserved_at_250[0x10];
 
-	u8	   reserved_at_260[0x120];
+	u8	   reserved_at_260[0x20];
 
 	u8	   format_select_dw_gtpu_dw_0[0x8];
 	u8	   format_select_dw_gtpu_dw_1[0x8];
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ecf63d2b0582..8852c39c7695 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -329,12 +329,14 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_HIGH_ARCH_BIT_3	35	/* bit only usable on 64-bit architectures */
 #define VM_HIGH_ARCH_BIT_4	36	/* bit only usable on 64-bit architectures */
 #define VM_HIGH_ARCH_BIT_5	37	/* bit only usable on 64-bit architectures */
+#define VM_HIGH_ARCH_BIT_6	38	/* bit only usable on 64-bit architectures */
 #define VM_HIGH_ARCH_0	BIT(VM_HIGH_ARCH_BIT_0)
 #define VM_HIGH_ARCH_1	BIT(VM_HIGH_ARCH_BIT_1)
 #define VM_HIGH_ARCH_2	BIT(VM_HIGH_ARCH_BIT_2)
 #define VM_HIGH_ARCH_3	BIT(VM_HIGH_ARCH_BIT_3)
 #define VM_HIGH_ARCH_4	BIT(VM_HIGH_ARCH_BIT_4)
 #define VM_HIGH_ARCH_5	BIT(VM_HIGH_ARCH_BIT_5)
+#define VM_HIGH_ARCH_6	BIT(VM_HIGH_ARCH_BIT_6)
 #endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */
 
 #ifdef CONFIG_ARCH_HAS_PKEYS
@@ -365,7 +367,17 @@ extern unsigned int kobjsize(const void *objp);
  * for more details on the guard size.
  */
 # define VM_SHADOW_STACK	VM_HIGH_ARCH_5
-#else
+#endif
+
+#if defined(CONFIG_ARM64_GCS)
+/*
+ * arm64's Guarded Control Stack implements similar functionality and
+ * has similar constraints to shadow stacks.
+ */
+# define VM_SHADOW_STACK	VM_HIGH_ARCH_6
+#endif
+
+#ifndef VM_SHADOW_STACK
 # define VM_SHADOW_STACK	VM_NONE
 #endif
 
@@ -4219,4 +4231,8 @@ static inline void pgalloc_tag_copy(struct folio *new, struct folio *old)
 }
 #endif /* CONFIG_MEM_ALLOC_PROFILING */
 
+int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status);
+int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status);
+int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status);
+
 #endif /* _LINUX_MM_H */
diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h
index b4fa92a6e44b..1b56796f6cb3 100644
--- a/include/linux/mtd/map.h
+++ b/include/linux/mtd/map.h
@@ -15,7 +15,7 @@
 #include <linux/kernel.h>
 #include <linux/io.h>
 
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 #include <asm/barrier.h>
 
 #ifdef CONFIG_MTD_MAP_BANK_WIDTH_1
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e87b5e488325..4d20c776a4ff 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -5029,6 +5029,24 @@ void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs);
 void netif_inherit_tso_max(struct net_device *to,
 			   const struct net_device *from);
 
+static inline unsigned int
+netif_get_gro_max_size(const struct net_device *dev, const struct sk_buff *skb)
+{
+	/* pairs with WRITE_ONCE() in netif_set_gro(_ipv4)_max_size() */
+	return skb->protocol == htons(ETH_P_IPV6) ?
+	       READ_ONCE(dev->gro_max_size) :
+	       READ_ONCE(dev->gro_ipv4_max_size);
+}
+
+static inline unsigned int
+netif_get_gso_max_size(const struct net_device *dev, const struct sk_buff *skb)
+{
+	/* pairs with WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */
+	return skb->protocol == htons(ETH_P_IPV6) ?
+	       READ_ONCE(dev->gso_max_size) :
+	       READ_ONCE(dev->gso_ipv4_max_size);
+}
+
 static inline bool netif_is_macsec(const struct net_device *dev)
 {
 	return dev->priv_flags & IFF_MACSEC;
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 853df3fcd4c2..b804346a9741 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -249,6 +249,7 @@ struct nfs_server {
 	struct list_head	layouts;
 	struct list_head	delegations;
 	struct list_head	ss_copies;
+	struct list_head	ss_src_copies;
 
 	unsigned long		delegation_gen;
 	unsigned long		mig_gen;
diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h
index b353abe00357..b0dd9b1eef4f 100644
--- a/include/linux/nfslocalio.h
+++ b/include/linux/nfslocalio.h
@@ -65,10 +65,25 @@ struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *,
 		   struct rpc_clnt *, const struct cred *,
 		   const struct nfs_fh *, const fmode_t);
 
+static inline void nfs_to_nfsd_file_put_local(struct nfsd_file *localio)
+{
+	/*
+	 * Once reference to nfsd_serv is dropped, NFSD could be
+	 * unloaded, so ensure safe return from nfsd_file_put_local()
+	 * by always taking RCU.
+	 */
+	rcu_read_lock();
+	nfs_to->nfsd_file_put_local(localio);
+	rcu_read_unlock();
+}
+
 #else   /* CONFIG_NFS_LOCALIO */
 static inline void nfsd_localio_ops_init(void)
 {
 }
+static inline void nfs_to_nfsd_file_put_local(struct nfsd_file *localio)
+{
+}
 #endif  /* CONFIG_NFS_LOCALIO */
 
 #endif  /* __LINUX_NFSLOCALIO_H */
diff --git a/include/linux/perf/arm_pmuv3.h b/include/linux/perf/arm_pmuv3.h
index 3372c1b56486..d698efba28a2 100644
--- a/include/linux/perf/arm_pmuv3.h
+++ b/include/linux/perf/arm_pmuv3.h
@@ -257,6 +257,7 @@
 #define ARMV8_PMU_USERENR_SW	(1 << 1) /* PMSWINC can be written at EL0 */
 #define ARMV8_PMU_USERENR_CR	(1 << 2) /* Cycle counter can be read at EL0 */
 #define ARMV8_PMU_USERENR_ER	(1 << 3) /* Event counter can be read at EL0 */
+#define ARMV8_PMU_USERENR_UEN	(1 << 4) /* Fine grained per counter access at EL0 */
 /* Mask for writable bits */
 #define ARMV8_PMU_USERENR_MASK	(ARMV8_PMU_USERENR_EN | ARMV8_PMU_USERENR_SW | \
 				 ARMV8_PMU_USERENR_CR | ARMV8_PMU_USERENR_ER)
diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h
index 1b5a953c6bbc..3a74f69e0b59 100644
--- a/include/linux/ptp_classify.h
+++ b/include/linux/ptp_classify.h
@@ -10,7 +10,7 @@
 #ifndef _PTP_CLASSIFY_H_
 #define _PTP_CLASSIFY_H_
 
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 #include <linux/ip.h>
 #include <linux/ktime.h>
 #include <linux/skbuff.h>
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e6ee4258169a..449dd64ed9ac 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1681,8 +1681,8 @@ extern struct pid *cad_pid;
 						 * I am cleaning dirty pages from some other bdi. */
 #define PF_KTHREAD		0x00200000	/* I am a kernel thread */
 #define PF_RANDOMIZE		0x00400000	/* Randomize virtual address space */
-#define PF_MEMALLOC_NORECLAIM	0x00800000	/* All allocation requests will clear __GFP_DIRECT_RECLAIM */
-#define PF_MEMALLOC_NOWARN	0x01000000	/* All allocation requests will inherit __GFP_NOWARN */
+#define PF__HOLE__00800000	0x00800000
+#define PF__HOLE__01000000	0x01000000
 #define PF__HOLE__02000000	0x02000000
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
 #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 07bb8d4181d7..928a626725e6 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -251,25 +251,16 @@ static inline gfp_t current_gfp_context(gfp_t flags)
 {
 	unsigned int pflags = READ_ONCE(current->flags);
 
-	if (unlikely(pflags & (PF_MEMALLOC_NOIO |
-			       PF_MEMALLOC_NOFS |
-			       PF_MEMALLOC_NORECLAIM |
-			       PF_MEMALLOC_NOWARN |
-			       PF_MEMALLOC_PIN))) {
+	if (unlikely(pflags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_PIN))) {
 		/*
-		 * Stronger flags before weaker flags:
-		 * NORECLAIM implies NOIO, which in turn implies NOFS
+		 * NOIO implies both NOIO and NOFS and it is a weaker context
+		 * so always make sure it makes precedence
 		 */
-		if (pflags & PF_MEMALLOC_NORECLAIM)
-			flags &= ~__GFP_DIRECT_RECLAIM;
-		else if (pflags & PF_MEMALLOC_NOIO)
+		if (pflags & PF_MEMALLOC_NOIO)
 			flags &= ~(__GFP_IO | __GFP_FS);
 		else if (pflags & PF_MEMALLOC_NOFS)
 			flags &= ~__GFP_FS;
 
-		if (pflags & PF_MEMALLOC_NOWARN)
-			flags |= __GFP_NOWARN;
-
 		if (pflags & PF_MEMALLOC_PIN)
 			flags &= ~__GFP_MOVABLE;
 	}
diff --git a/include/linux/security.h b/include/linux/security.h
index b86ec2afc691..2ec8f3014757 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -348,7 +348,7 @@ int security_dentry_create_files_as(struct dentry *dentry, int mode,
 					struct cred *new);
 int security_path_notify(const struct path *path, u64 mask,
 					unsigned int obj_type);
-int security_inode_alloc(struct inode *inode);
+int security_inode_alloc(struct inode *inode, gfp_t gfp);
 void security_inode_free(struct inode *inode);
 int security_inode_init_security(struct inode *inode, struct inode *dir,
 				 const struct qstr *qstr,
@@ -789,7 +789,7 @@ static inline int security_path_notify(const struct path *path, u64 mask,
 	return 0;
 }
 
-static inline int security_inode_alloc(struct inode *inode)
+static inline int security_inode_alloc(struct inode *inode, gfp_t gfp)
 {
 	return 0;
 }
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 2f8dc47f1eb0..5f775e104f9a 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -13,7 +13,7 @@
 
 #include <linux/uio.h>
 #include <asm/byteorder.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 #include <linux/scatterlist.h>
 
 struct bio_vec;
diff --git a/include/linux/tpm.h b/include/linux/tpm.h
index e93ee8d936a9..587b96b4418e 100644
--- a/include/linux/tpm.h
+++ b/include/linux/tpm.h
@@ -537,7 +537,7 @@ int tpm_buf_check_hmac_response(struct tpm_chip *chip, struct tpm_buf *buf,
 				int rc);
 void tpm2_end_auth_session(struct tpm_chip *chip);
 #else
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 
 static inline int tpm2_start_auth_session(struct tpm_chip *chip)
 {
diff --git a/include/linux/unaligned.h b/include/linux/unaligned.h
new file mode 100644
index 000000000000..4a9651017e3c
--- /dev/null
+++ b/include/linux/unaligned.h
@@ -0,0 +1,146 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_UNALIGNED_H
+#define __LINUX_UNALIGNED_H
+
+/*
+ * This is the most generic implementation of unaligned accesses
+ * and should work almost anywhere.
+ */
+#include <linux/unaligned/packed_struct.h>
+#include <asm/byteorder.h>
+#include <vdso/unaligned.h>
+
+#define get_unaligned(ptr)	__get_unaligned_t(typeof(*(ptr)), (ptr))
+#define put_unaligned(val, ptr) __put_unaligned_t(typeof(*(ptr)), (val), (ptr))
+
+static inline u16 get_unaligned_le16(const void *p)
+{
+	return le16_to_cpu(__get_unaligned_t(__le16, p));
+}
+
+static inline u32 get_unaligned_le32(const void *p)
+{
+	return le32_to_cpu(__get_unaligned_t(__le32, p));
+}
+
+static inline u64 get_unaligned_le64(const void *p)
+{
+	return le64_to_cpu(__get_unaligned_t(__le64, p));
+}
+
+static inline void put_unaligned_le16(u16 val, void *p)
+{
+	__put_unaligned_t(__le16, cpu_to_le16(val), p);
+}
+
+static inline void put_unaligned_le32(u32 val, void *p)
+{
+	__put_unaligned_t(__le32, cpu_to_le32(val), p);
+}
+
+static inline void put_unaligned_le64(u64 val, void *p)
+{
+	__put_unaligned_t(__le64, cpu_to_le64(val), p);
+}
+
+static inline u16 get_unaligned_be16(const void *p)
+{
+	return be16_to_cpu(__get_unaligned_t(__be16, p));
+}
+
+static inline u32 get_unaligned_be32(const void *p)
+{
+	return be32_to_cpu(__get_unaligned_t(__be32, p));
+}
+
+static inline u64 get_unaligned_be64(const void *p)
+{
+	return be64_to_cpu(__get_unaligned_t(__be64, p));
+}
+
+static inline void put_unaligned_be16(u16 val, void *p)
+{
+	__put_unaligned_t(__be16, cpu_to_be16(val), p);
+}
+
+static inline void put_unaligned_be32(u32 val, void *p)
+{
+	__put_unaligned_t(__be32, cpu_to_be32(val), p);
+}
+
+static inline void put_unaligned_be64(u64 val, void *p)
+{
+	__put_unaligned_t(__be64, cpu_to_be64(val), p);
+}
+
+static inline u32 __get_unaligned_be24(const u8 *p)
+{
+	return p[0] << 16 | p[1] << 8 | p[2];
+}
+
+static inline u32 get_unaligned_be24(const void *p)
+{
+	return __get_unaligned_be24(p);
+}
+
+static inline u32 __get_unaligned_le24(const u8 *p)
+{
+	return p[0] | p[1] << 8 | p[2] << 16;
+}
+
+static inline u32 get_unaligned_le24(const void *p)
+{
+	return __get_unaligned_le24(p);
+}
+
+static inline void __put_unaligned_be24(const u32 val, u8 *p)
+{
+	*p++ = (val >> 16) & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = val & 0xff;
+}
+
+static inline void put_unaligned_be24(const u32 val, void *p)
+{
+	__put_unaligned_be24(val, p);
+}
+
+static inline void __put_unaligned_le24(const u32 val, u8 *p)
+{
+	*p++ = val & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = (val >> 16) & 0xff;
+}
+
+static inline void put_unaligned_le24(const u32 val, void *p)
+{
+	__put_unaligned_le24(val, p);
+}
+
+static inline void __put_unaligned_be48(const u64 val, u8 *p)
+{
+	*p++ = (val >> 40) & 0xff;
+	*p++ = (val >> 32) & 0xff;
+	*p++ = (val >> 24) & 0xff;
+	*p++ = (val >> 16) & 0xff;
+	*p++ = (val >> 8) & 0xff;
+	*p++ = val & 0xff;
+}
+
+static inline void put_unaligned_be48(const u64 val, void *p)
+{
+	__put_unaligned_be48(val, p);
+}
+
+static inline u64 __get_unaligned_be48(const u8 *p)
+{
+	return (u64)p[0] << 40 | (u64)p[1] << 32 | (u64)p[2] << 24 |
+		p[3] << 16 | p[4] << 8 | p[5];
+}
+
+static inline u64 get_unaligned_be48(const void *p)
+{
+	return __get_unaligned_be48(p);
+}
+
+#endif /* __LINUX_UNALIGNED_H */
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 276ca543ef44..02a9f4dc594d 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -103,8 +103,10 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 
 		if (!skb_partial_csum_set(skb, start, off))
 			return -EINVAL;
+		if (skb_transport_offset(skb) < nh_min_len)
+			return -EINVAL;
 
-		nh_min_len = max_t(u32, nh_min_len, skb_transport_offset(skb));
+		nh_min_len = skb_transport_offset(skb);
 		p_off = nh_min_len + thlen;
 		if (!pskb_may_pull(skb, p_off))
 			return -EINVAL;