Merge tag 'v6.1-rc8' into rdma.git for-next

For dependencies in following patches

Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

45 files changed, 263 insertions, 125 deletions

diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h
index aeb257ad3d1a..8392caea398f 100644
--- a/include/asm-generic/compat.h
+++ b/include/asm-generic/compat.h
@@ -15,7 +15,7 @@
 #endif
 
 #ifndef compat_arg_u64
-#ifdef CONFIG_CPU_BIG_ENDIAN
+#ifndef CONFIG_CPU_BIG_ENDIAN
 #define compat_arg_u64(name)		u32  name##_lo, u32  name##_hi
 #define compat_arg_u64_dual(name)	u32, name##_lo, u32, name##_hi
 #else
diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h
index fdce7a4cfc6f..b17c6eeb9afa 100644
--- a/include/asm-generic/hyperv-tlfs.h
+++ b/include/asm-generic/hyperv-tlfs.h
@@ -102,6 +102,15 @@ struct ms_hyperv_tsc_page {
 	volatile s64 tsc_offset;
 } __packed;
 
+union hv_reference_tsc_msr {
+	u64 as_uint64;
+	struct {
+		u64 enable:1;
+		u64 reserved:11;
+		u64 pfn:52;
+	} __packed;
+};
+
 /*
  * The guest OS needs to register the guest ID with the hypervisor.
  * The guest ID is a 64 bit entity and the structure of this ID is
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 492dce43236e..cab7cfebf40b 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -222,12 +222,16 @@ extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 #define tlb_needs_table_invalidate() (true)
 #endif
 
+void tlb_remove_table_sync_one(void);
+
 #else
 
 #ifdef tlb_needs_table_invalidate
 #error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE
 #endif
 
+static inline void tlb_remove_table_sync_one(void) { }
+
 #endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */
 
 
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index d06ada2341cb..3dc5824141cd 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -347,6 +347,7 @@
 #define DATA_DATA							\
 	*(.xiptext)							\
 	*(DATA_MAIN)							\
+	*(.data..decrypted)						\
 	*(.ref.data)							\
 	*(.data..shared_aligned) /* percpu related */			\
 	MEM_KEEP(init.data*)						\
@@ -995,7 +996,6 @@
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 #define PERCPU_DECRYPTED_SECTION					\
 	. = ALIGN(PAGE_SIZE);						\
-	*(.data..decrypted)						\
 	*(.data..percpu..decrypted)					\
 	. = ALIGN(PAGE_SIZE);
 #else
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 50e358a19d98..891f8cbcd043 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -311,6 +311,13 @@ struct queue_limits {
 	unsigned char		discard_misaligned;
 	unsigned char		raid_partial_stripes_expensive;
 	enum blk_zoned_model	zoned;
+
+	/*
+	 * Drivers that set dma_alignment to less than 511 must be prepared to
+	 * handle individual bvec's that are not a multiple of a SECTOR_SIZE
+	 * due to possible offsets.
+	 */
+	unsigned int		dma_alignment;
 };
 
 typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
@@ -456,12 +463,6 @@ struct request_queue {
 	unsigned long		nr_requests;	/* Max # of requests */
 
 	unsigned int		dma_pad_mask;
-	/*
-	 * Drivers that set dma_alignment to less than 511 must be prepared to
-	 * handle individual bvec's that are not a multiple of a SECTOR_SIZE
-	 * due to possible offsets.
-	 */
-	unsigned int		dma_alignment;
 
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 	struct blk_crypto_profile *crypto_profile;
@@ -944,7 +945,6 @@ extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
 extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt);
 extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt);
 extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth);
-extern void blk_set_default_limits(struct queue_limits *lim);
 extern void blk_set_stacking_limits(struct queue_limits *lim);
 extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 			    sector_t offset);
@@ -1324,7 +1324,7 @@ static inline sector_t bdev_zone_sectors(struct block_device *bdev)
 
 static inline int queue_dma_alignment(const struct request_queue *q)
 {
-	return q ? q->dma_alignment : 511;
+	return q ? q->limits.dma_alignment : 511;
 }
 
 static inline unsigned int bdev_dma_alignment(struct block_device *bdev)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 0566705c1d4e..c1bd1bd10506 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -27,7 +27,7 @@
 #include <linux/bpfptr.h>
 #include <linux/btf.h>
 #include <linux/rcupdate_trace.h>
-#include <linux/init.h>
+#include <linux/static_call.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -315,7 +315,7 @@ static inline void __copy_map_value(struct bpf_map *map, void *dst, void *src, b
 		u32 next_off = map->off_arr->field_off[i];
 
 		memcpy(dst + curr_off, src + curr_off, next_off - curr_off);
-		curr_off += map->off_arr->field_sz[i];
+		curr_off = next_off + map->off_arr->field_sz[i];
 	}
 	memcpy(dst + curr_off, src + curr_off, map->value_size - curr_off);
 }
@@ -344,7 +344,7 @@ static inline void zero_map_value(struct bpf_map *map, void *dst)
 		u32 next_off = map->off_arr->field_off[i];
 
 		memset(dst + curr_off, 0, next_off - curr_off);
-		curr_off += map->off_arr->field_sz[i];
+		curr_off = next_off + map->off_arr->field_sz[i];
 	}
 	memset(dst + curr_off, 0, map->value_size - curr_off);
 }
@@ -954,6 +954,10 @@ struct bpf_dispatcher {
 	void *rw_image;
 	u32 image_off;
 	struct bpf_ksym ksym;
+#ifdef CONFIG_HAVE_STATIC_CALL
+	struct static_call_key *sc_key;
+	void *sc_tramp;
+#endif
 };
 
 static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func(
@@ -971,7 +975,33 @@ struct bpf_trampoline *bpf_trampoline_get(u64 key,
 					  struct bpf_attach_target_info *tgt_info);
 void bpf_trampoline_put(struct bpf_trampoline *tr);
 int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_funcs);
-int __init bpf_arch_init_dispatcher_early(void *ip);
+
+/*
+ * When the architecture supports STATIC_CALL replace the bpf_dispatcher_fn
+ * indirection with a direct call to the bpf program. If the architecture does
+ * not have STATIC_CALL, avoid a double-indirection.
+ */
+#ifdef CONFIG_HAVE_STATIC_CALL
+
+#define __BPF_DISPATCHER_SC_INIT(_name)				\
+	.sc_key = &STATIC_CALL_KEY(_name),			\
+	.sc_tramp = STATIC_CALL_TRAMP_ADDR(_name),
+
+#define __BPF_DISPATCHER_SC(name)				\
+	DEFINE_STATIC_CALL(bpf_dispatcher_##name##_call, bpf_dispatcher_nop_func)
+
+#define __BPF_DISPATCHER_CALL(name)				\
+	static_call(bpf_dispatcher_##name##_call)(ctx, insnsi, bpf_func)
+
+#define __BPF_DISPATCHER_UPDATE(_d, _new)			\
+	__static_call_update((_d)->sc_key, (_d)->sc_tramp, (_new))
+
+#else
+#define __BPF_DISPATCHER_SC_INIT(name)
+#define __BPF_DISPATCHER_SC(name)
+#define __BPF_DISPATCHER_CALL(name)		bpf_func(ctx, insnsi)
+#define __BPF_DISPATCHER_UPDATE(_d, _new)
+#endif
 
 #define BPF_DISPATCHER_INIT(_name) {				\
 	.mutex = __MUTEX_INITIALIZER(_name.mutex),		\
@@ -984,34 +1014,21 @@ int __init bpf_arch_init_dispatcher_early(void *ip);
 		.name  = #_name,				\
 		.lnode = LIST_HEAD_INIT(_name.ksym.lnode),	\
 	},							\
+	__BPF_DISPATCHER_SC_INIT(_name##_call)			\
 }
 
-#define BPF_DISPATCHER_INIT_CALL(_name)					\
-	static int __init _name##_init(void)				\
-	{								\
-		return bpf_arch_init_dispatcher_early(_name##_func);	\
-	}								\
-	early_initcall(_name##_init)
-
-#ifdef CONFIG_X86_64
-#define BPF_DISPATCHER_ATTRIBUTES __attribute__((patchable_function_entry(5)))
-#else
-#define BPF_DISPATCHER_ATTRIBUTES
-#endif
-
 #define DEFINE_BPF_DISPATCHER(name)					\
-	notrace BPF_DISPATCHER_ATTRIBUTES				\
+	__BPF_DISPATCHER_SC(name);					\
 	noinline __nocfi unsigned int bpf_dispatcher_##name##_func(	\
 		const void *ctx,					\
 		const struct bpf_insn *insnsi,				\
 		bpf_func_t bpf_func)					\
 	{								\
-		return bpf_func(ctx, insnsi);				\
+		return __BPF_DISPATCHER_CALL(name);			\
 	}								\
 	EXPORT_SYMBOL(bpf_dispatcher_##name##_func);			\
 	struct bpf_dispatcher bpf_dispatcher_##name =			\
-		BPF_DISPATCHER_INIT(bpf_dispatcher_##name);		\
-	BPF_DISPATCHER_INIT_CALL(bpf_dispatcher_##name);
+		BPF_DISPATCHER_INIT(bpf_dispatcher_##name);
 
 #define DECLARE_BPF_DISPATCHER(name)					\
 	unsigned int bpf_dispatcher_##name##_func(			\
@@ -1019,6 +1036,7 @@ int __init bpf_arch_init_dispatcher_early(void *ip);
 		const struct bpf_insn *insnsi,				\
 		bpf_func_t bpf_func);					\
 	extern struct bpf_dispatcher bpf_dispatcher_##name;
+
 #define BPF_DISPATCHER_FUNC(name) bpf_dispatcher_##name##_func
 #define BPF_DISPATCHER_PTR(name) (&bpf_dispatcher_##name)
 void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 58f5431a5559..982ba245eb41 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -152,6 +152,22 @@ static inline bool can_is_canxl_dev_mtu(unsigned int mtu)
 	return (mtu >= CANXL_MIN_MTU && mtu <= CANXL_MAX_MTU);
 }
 
+/* drop skb if it does not contain a valid CAN frame for sending */
+static inline bool can_dev_dropped_skb(struct net_device *dev, struct sk_buff *skb)
+{
+	struct can_priv *priv = netdev_priv(dev);
+
+	if (priv->ctrlmode & CAN_CTRLMODE_LISTENONLY) {
+		netdev_info_once(dev,
+				 "interface in listen only mode, dropping skb\n");
+		kfree_skb(skb);
+		dev->stats.tx_dropped++;
+		return true;
+	}
+
+	return can_dropped_invalid_skb(dev, skb);
+}
+
 void can_setup(struct net_device *dev);
 
 struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max,
diff --git a/include/linux/can/platform/sja1000.h b/include/linux/can/platform/sja1000.h
index 5755ae5a4712..6a869682c120 100644
--- a/include/linux/can/platform/sja1000.h
+++ b/include/linux/can/platform/sja1000.h
@@ -14,7 +14,7 @@
 #define OCR_MODE_TEST     0x01
 #define OCR_MODE_NORMAL   0x02
 #define OCR_MODE_CLOCK    0x03
-#define OCR_MODE_MASK     0x07
+#define OCR_MODE_MASK     0x03
 #define OCR_TX0_INVERT    0x04
 #define OCR_TX0_PULLDOWN  0x08
 #define OCR_TX0_PULLUP    0x10
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 80f3c1c7827d..7603fc58c47c 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -389,6 +389,7 @@ void efi_native_runtime_setup(void);
 #define EFI_LOAD_FILE2_PROTOCOL_GUID		EFI_GUID(0x4006c0c1, 0xfcb3, 0x403e,  0x99, 0x6d, 0x4a, 0x6c, 0x87, 0x24, 0xe0, 0x6d)
 #define EFI_RT_PROPERTIES_TABLE_GUID		EFI_GUID(0xeb66918a, 0x7eef, 0x402a,  0x84, 0x2e, 0x93, 0x1d, 0x21, 0xc3, 0x8a, 0xe9)
 #define EFI_DXE_SERVICES_TABLE_GUID		EFI_GUID(0x05ad34ba, 0x6f02, 0x4214,  0x95, 0x2e, 0x4d, 0xa0, 0x39, 0x8e, 0x2b, 0xb9)
+#define EFI_SMBIOS_PROTOCOL_GUID		EFI_GUID(0x03583ff6, 0xcb36, 0x4940,  0x94, 0x7e, 0xb9, 0xb3, 0x9f, 0x4a, 0xfa, 0xf7)
 
 #define EFI_IMAGE_SECURITY_DATABASE_GUID	EFI_GUID(0xd719b2cb, 0x3d3a, 0x4596,  0xa3, 0xbc, 0xda, 0xd0, 0x0e, 0x67, 0x65, 0x6f)
 #define EFI_SHIM_LOCK_GUID			EFI_GUID(0x605dab50, 0xe046, 0x4300,  0xab, 0xb6, 0x3d, 0xd8, 0x10, 0xdd, 0x8b, 0x23)
@@ -1222,7 +1223,7 @@ efi_status_t efi_random_get_seed(void);
 	arch_efi_call_virt_teardown();					\
 })
 
-#define EFI_RANDOM_SEED_SIZE		64U
+#define EFI_RANDOM_SEED_SIZE		32U // BLAKE2S_HASH_SIZE
 
 struct linux_efi_random_seed {
 	u32	size;
diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h
index 9f6e25467844..444236dadcf0 100644
--- a/include/linux/fault-inject.h
+++ b/include/linux/fault-inject.h
@@ -20,7 +20,6 @@ struct fault_attr {
 	atomic_t space;
 	unsigned long verbose;
 	bool task_filter;
-	bool no_warn;
 	unsigned long stacktrace_depth;
 	unsigned long require_start;
 	unsigned long require_end;
@@ -32,6 +31,10 @@ struct fault_attr {
 	struct dentry *dname;
 };
 
+enum fault_flags {
+	FAULT_NOWARN =	1 << 0,
+};
+
 #define FAULT_ATTR_INITIALIZER {					\
 		.interval = 1,						\
 		.times = ATOMIC_INIT(1),				\
@@ -40,11 +43,11 @@ struct fault_attr {
 		.ratelimit_state = RATELIMIT_STATE_INIT_DISABLED,	\
 		.verbose = 2,						\
 		.dname = NULL,						\
-		.no_warn = false,					\
 	}
 
 #define DECLARE_FAULT_ATTR(name) struct fault_attr name = FAULT_ATTR_INITIALIZER
 int setup_fault_attr(struct fault_attr *attr, char *str);
+bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags);
 bool should_fail(struct fault_attr *attr, ssize_t size);
 
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h
index 18a31b125f9d..1067a8450826 100644
--- a/include/linux/fortify-string.h
+++ b/include/linux/fortify-string.h
@@ -454,13 +454,18 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size,
 
 #define __fortify_memcpy_chk(p, q, size, p_size, q_size,		\
 			     p_size_field, q_size_field, op) ({		\
-	size_t __fortify_size = (size_t)(size);				\
-	WARN_ONCE(fortify_memcpy_chk(__fortify_size, p_size, q_size,	\
-				     p_size_field, q_size_field, #op),	\
+	const size_t __fortify_size = (size_t)(size);			\
+	const size_t __p_size = (p_size);				\
+	const size_t __q_size = (q_size);				\
+	const size_t __p_size_field = (p_size_field);			\
+	const size_t __q_size_field = (q_size_field);			\
+	WARN_ONCE(fortify_memcpy_chk(__fortify_size, __p_size,		\
+				     __q_size, __p_size_field,		\
+				     __q_size_field, #op),		\
 		  #op ": detected field-spanning write (size %zu) of single %s (size %zu)\n", \
 		  __fortify_size,					\
 		  "field \"" #p "\" at " __FILE__ ":" __stringify(__LINE__), \
-		  p_size_field);					\
+		  __p_size_field);					\
 	__underlying_##op(p, q, __fortify_size);			\
 })
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e654435f1651..59ae95ddb679 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2089,6 +2089,14 @@ struct dir_context {
  */
 #define REMAP_FILE_ADVISORY		(REMAP_FILE_CAN_SHORTEN)
 
+/*
+ * These flags control the behavior of vfs_copy_file_range().
+ * They are not available to the user via syscall.
+ *
+ * COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops
+ */
+#define COPY_FILE_SPLICE		(1 << 0)
+
 struct iov_iter;
 struct io_uring_cmd;
 
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
index 36e5dd84cf59..8e312c8323a8 100644
--- a/include/linux/fscache.h
+++ b/include/linux/fscache.h
@@ -75,7 +75,7 @@ struct fscache_volume {
 	atomic_t			n_accesses;	/* Number of cache accesses in progress */
 	unsigned int			debug_id;
 	unsigned int			key_hash;	/* Hash of key string */
-	char				*key;		/* Volume ID, eg. "afs@example.com@1234" */
+	u8				*key;		/* Volume ID, eg. "afs@example.com@1234" */
 	struct list_head		proc_link;	/* Link in /proc/fs/fscache/volumes */
 	struct hlist_bl_node		hash_link;	/* Link in hash table */
 	struct work_struct		work;
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index ef4aea3b356e..65a78773dcca 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -210,6 +210,20 @@ alloc_pages_bulk_array_node(gfp_t gfp, int nid, unsigned long nr_pages, struct p
 	return __alloc_pages_bulk(gfp, nid, NULL, nr_pages, NULL, page_array);
 }
 
+static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask)
+{
+	gfp_t warn_gfp = gfp_mask & (__GFP_THISNODE|__GFP_NOWARN);
+
+	if (warn_gfp != (__GFP_THISNODE|__GFP_NOWARN))
+		return;
+
+	if (node_online(this_node))
+		return;
+
+	pr_warn("%pGg allocation from offline node %d\n", &gfp_mask, this_node);
+	dump_stack();
+}
+
 /*
  * Allocate pages, preferring the node given as nid. The node must be valid and
  * online. For more general interface, see alloc_pages_node().
@@ -218,7 +232,7 @@ static inline struct page *
 __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
 {
 	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
-	VM_WARN_ON((gfp_mask & __GFP_THISNODE) && !node_online(nid));
+	warn_if_node_offline(nid, gfp_mask);
 
 	return __alloc_pages(gfp_mask, order, nid, NULL);
 }
@@ -227,7 +241,7 @@ static inline
 struct folio *__folio_alloc_node(gfp_t gfp, unsigned int order, int nid)
 {
 	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
-	VM_WARN_ON((gfp & __GFP_THISNODE) && !node_online(nid));
+	warn_if_node_offline(nid, gfp);
 
 	return __folio_alloc(gfp, order, nid, NULL);
 }
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 43bc8a2edccf..0ded9e271523 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -16,6 +16,9 @@ enum io_uring_cmd_flags {
 	IO_URING_F_SQE128		= 4,
 	IO_URING_F_CQE32		= 8,
 	IO_URING_F_IOPOLL		= 16,
+
+	/* the request is executed from poll, it should not be freed */
+	IO_URING_F_MULTISHOT		= 32,
 };
 
 struct io_uring_cmd {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 00c3448ba7f8..637a60607c7d 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -776,6 +776,7 @@ struct kvm {
 	struct srcu_struct srcu;
 	struct srcu_struct irq_srcu;
 	pid_t userspace_pid;
+	bool override_halt_poll_ns;
 	unsigned int max_halt_poll_ns;
 	u32 dirty_ring_size;
 	bool vm_bugged;
@@ -1240,8 +1241,18 @@ int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data,
 void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn);
 
 /**
- * kvm_gfn_to_pfn_cache_init - prepare a cached kernel mapping and HPA for a
- *                             given guest physical address.
+ * kvm_gpc_init - initialize gfn_to_pfn_cache.
+ *
+ * @gpc:	   struct gfn_to_pfn_cache object.
+ *
+ * This sets up a gfn_to_pfn_cache by initializing locks.  Note, the cache must
+ * be zero-allocated (or zeroed by the caller before init).
+ */
+void kvm_gpc_init(struct gfn_to_pfn_cache *gpc);
+
+/**
+ * kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest
+ *                    physical address.
  *
  * @kvm:	   pointer to kvm instance.
  * @gpc:	   struct gfn_to_pfn_cache object.
@@ -1265,9 +1276,9 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn);
  * kvm_gfn_to_pfn_cache_check() to ensure that the cache is valid before
  * accessing the target page.
  */
-int kvm_gfn_to_pfn_cache_init(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
-			      struct kvm_vcpu *vcpu, enum pfn_cache_usage usage,
-			      gpa_t gpa, unsigned long len);
+int kvm_gpc_activate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
+		     struct kvm_vcpu *vcpu, enum pfn_cache_usage usage,
+		     gpa_t gpa, unsigned long len);
 
 /**
  * kvm_gfn_to_pfn_cache_check - check validity of a gfn_to_pfn_cache.
@@ -1324,7 +1335,7 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
 void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc);
 
 /**
- * kvm_gfn_to_pfn_cache_destroy - destroy and unlink a gfn_to_pfn_cache.
+ * kvm_gpc_deactivate - deactivate and unlink a gfn_to_pfn_cache.
  *
  * @kvm:	   pointer to kvm instance.
  * @gpc:	   struct gfn_to_pfn_cache object.
@@ -1332,7 +1343,7 @@ void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc);
  * This removes a cache from the @kvm's list to be processed on MMU notifier
  * invocation.
  */
-void kvm_gfn_to_pfn_cache_destroy(struct kvm *kvm, struct gfn_to_pfn_cache *gpc);
+void kvm_gpc_deactivate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc);
 
 void kvm_sigset_activate(struct kvm_vcpu *vcpu);
 void kvm_sigset_deactivate(struct kvm_vcpu *vcpu);
diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h
index 2effab72add1..e594db58a0f1 100644
--- a/include/linux/maple_tree.h
+++ b/include/linux/maple_tree.h
@@ -638,6 +638,12 @@ static inline void mt_set_in_rcu(struct maple_tree *mt)
 	}
 }
 
+static inline unsigned int mt_height(const struct maple_tree *mt)
+
+{
+	return (mt->ma_flags & MT_FLAGS_HEIGHT_MASK) >> MT_FLAGS_HEIGHT_OFFSET;
+}
+
 void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max);
 void *mt_find_after(struct maple_tree *mt, unsigned long *index,
 		    unsigned long max);
@@ -664,6 +670,7 @@ extern atomic_t maple_tree_tests_passed;
 
 void mt_dump(const struct maple_tree *mt);
 void mt_validate(struct maple_tree *mt);
+void mt_cache_shrink(void);
 #define MT_BUG_ON(__tree, __x) do {					\
 	atomic_inc(&maple_tree_tests_run);				\
 	if (__x) {							\
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index af2ceb4160bc..06cbad166225 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -981,6 +981,7 @@ struct mlx5_async_work {
 	struct mlx5_async_ctx *ctx;
 	mlx5_async_cbk_t user_callback;
 	u16 opcode; /* cmd opcode */
+	u16 op_mod; /* cmd op_mod */
 	void *out; /* pointer to the cmd output buffer */
 };
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8bbcccbc5565..974ccca609d2 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1852,6 +1852,25 @@ static void __maybe_unused show_free_areas(unsigned int flags, nodemask_t *nodem
 	__show_free_areas(flags, nodemask, MAX_NR_ZONES - 1);
 }
 
+/*
+ * Parameter block passed down to zap_pte_range in exceptional cases.
+ */
+struct zap_details {
+	struct folio *single_folio;	/* Locked folio to be unmapped */
+	bool even_cows;			/* Zap COWed private pages too? */
+	zap_flags_t zap_flags;		/* Extra flags for zapping */
+};
+
+/*
+ * Whether to drop the pte markers, for example, the uffd-wp information for
+ * file-backed memory.  This should only be specified when we will completely
+ * drop the page in the mm, either by truncation or unmapping of the vma.  By
+ * default, the flag is not set.
+ */
+#define  ZAP_FLAG_DROP_MARKER        ((__force zap_flags_t) BIT(0))
+/* Set in unmap_vmas() to indicate a final unmap call.  Only used by hugetlb */
+#define  ZAP_FLAG_UNMAP              ((__force zap_flags_t) BIT(1))
+
 #ifdef CONFIG_MMU
 extern bool can_do_mlock(void);
 #else
@@ -1869,6 +1888,8 @@ void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
 		  unsigned long size);
 void zap_page_range(struct vm_area_struct *vma, unsigned long address,
 		    unsigned long size);
+void zap_page_range_single(struct vm_area_struct *vma, unsigned long address,
+			   unsigned long size, struct zap_details *details);
 void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
 		struct vm_area_struct *start_vma, unsigned long start,
 		unsigned long end);
@@ -3467,12 +3488,4 @@ madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
 }
 #endif
 
-/*
- * Whether to drop the pte markers, for example, the uffd-wp information for
- * file-backed memory.  This should only be specified when we will completely
- * drop the page in the mm, either by truncation or unmapping of the vma.  By
- * default, the flag is not set.
- */
-#define  ZAP_FLAG_DROP_MARKER        ((__force zap_flags_t) BIT(0))
-
 #endif /* _LINUX_MM_H */
diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h
index 9c50bc40f8ff..6f7993803ee7 100644
--- a/include/linux/mmc/mmc.h
+++ b/include/linux/mmc/mmc.h
@@ -451,7 +451,7 @@ static inline bool mmc_ready_for_data(u32 status)
 #define MMC_SECURE_TRIM1_ARG		0x80000001
 #define MMC