spi: fsl-lpspi: fix DMA termination issues

Carlos Song (OSS) <carlos.song@oss.nxp.com> says:

This series fixes two issues in the fsl-lpspi DMA transfer error paths.

Patch 1 replaces the deprecated dmaengine_terminate_all() with
dmaengine_terminate_sync() across all error paths in
fsl_lpspi_dma_transfer().

Patch 2 fixes a missing RX DMA channel termination when TX descriptor
preparation fails. Since the RX channel is already submitted and issued
before the TX descriptor is prepared, returning -EINVAL without
terminating the RX channel leaves it running against buffers that the
SPI core will unmap, potentially causing memory corruption.

Link: https://patch.msgid.link/20260525062357.3191349-1-carlos.song@oss.nxp.com

29 files changed, 428 insertions, 64 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 01e203964892..cd191c5fdb0a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2917,7 +2917,13 @@ int bpf_check_uarg_tail_zero(bpfptr_t uaddr, size_t expected_size,
 int bpf_check(struct bpf_prog **fp, union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size);
 
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
-void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
+int bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
+s32 bpf_call_args_imm(s16 idx);
+#else
+static inline s32 bpf_call_args_imm(s16 idx)
+{
+	return 0;
+}
 #endif
 
 struct btf *bpf_get_btf_vmlinux(void);
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index b148f816f25b..185b2aa43a42 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -729,6 +729,7 @@ struct bpf_subprog_info {
 	 */
 	s16 fastcall_stack_off;
 	bool has_tail_call: 1;
+	bool might_throw: 1;
 	bool tail_call_reachable: 1;
 	bool has_ld_abs: 1;
 	bool is_cb: 1;
@@ -1308,6 +1309,7 @@ void bpf_fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask);
 bool bpf_subprog_is_global(const struct bpf_verifier_env *env, int subprog);
 
 int bpf_find_subprog(struct bpf_verifier_env *env, int off);
+bool bpf_is_throw_kfunc(struct bpf_insn *insn);
 int bpf_compute_const_regs(struct bpf_verifier_env *env);
 int bpf_prune_dead_branches(struct bpf_verifier_env *env);
 int bpf_check_cfg(struct bpf_verifier_env *env);
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index f6d037a30fd8..c5648fcf74e2 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -777,6 +777,7 @@ static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen)
 /*
  * cgroup scalable recursive statistics.
  */
+void __css_rstat_updated(struct cgroup_subsys_state *css, int cpu);
 void css_rstat_updated(struct cgroup_subsys_state *css, int cpu);
 void css_rstat_flush(struct cgroup_subsys_state *css);
 
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 56cebaff0c91..8da0a15c95f4 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -72,6 +72,10 @@
 	__diag_push();								\
 	__diag_ignore(GCC, 8, "-Wattribute-alias",				\
 		      "Type aliasing is used to sanitize syscall arguments");\
+	__diag_ignore(clang, 23, "-Wunknown-warning-option",			\
+		      "Avoid breaking versions without -Wattribute-alias");	\
+	__diag_ignore(clang, 23, "-Wattribute-alias",				\
+		      "Type aliasing is used to sanitize syscall arguments");	\
 	asmlinkage long compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))	\
 		__attribute__((alias(__stringify(__se_compat_sys##name))));	\
 	ALLOW_ERROR_INJECTION(compat_sys##name, ERRNO);				\
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index e1123dd28486..527e4e136020 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -131,6 +131,12 @@
 #define __diag_str(s)		__diag_str1(s)
 #define __diag(s)		_Pragma(__diag_str(clang diagnostic s))
 
+#if CONFIG_CLANG_VERSION >= 230000
+#define __diag_clang_23(s)	__diag(s)
+#else
+#define __diag_clang_23(s)
+#endif
+
 #define __diag_clang_13(s)	__diag(s)
 
 #define __diag_ignore_all(option, comment) \
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index c16d4199bf92..836a50f5917a 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -397,6 +397,17 @@
 #endif
 
 /*
+ * Optional: not supported by clang
+ *
+ *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Attributes.html#index-noipa
+ */
+#if __has_attribute(noipa)
+# define __noipa __attribute__((noipa))
+#else
+# define __noipa
+#endif
+
+/*
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-weak-function-attribute
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-weak-variable-attribute
  */
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index e8fd77593b68..369966598a2c 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -711,6 +711,10 @@ struct ftrace_likely_data {
 #define __diag_GCC(version, severity, string)
 #endif
 
+#ifndef __diag_clang
+#define __diag_clang(version, severity, string)
+#endif
+
 #define __diag_push()	__diag(push)
 #define __diag_pop()	__diag(pop)
 
diff --git a/include/linux/dpll.h b/include/linux/dpll.h
index f8037f1ab20b..2dbe8567eafc 100644
--- a/include/linux/dpll.h
+++ b/include/linux/dpll.h
@@ -284,6 +284,7 @@ void dpll_pin_on_pin_unregister(struct dpll_pin *parent, struct dpll_pin *pin,
 int dpll_pin_ref_sync_pair_add(struct dpll_pin *pin,
 			       struct dpll_pin *ref_sync_pin);
 
+int __dpll_device_change_ntf(struct dpll_device *dpll);
 int dpll_device_change_ntf(struct dpll_device *dpll);
 
 int __dpll_pin_change_ntf(struct dpll_pin *pin);
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 72e76ec54641..ccbc35479684 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -61,7 +61,7 @@ typedef void *efi_handle_t;
 
 /*
  * The UEFI spec and EDK2 reference implementation both define EFI_GUID as
- * struct { u32 a; u16; b; u16 c; u8 d[8]; }; and so the implied alignment
+ * struct { u32 a; u16 b; u16 c; u8 d[8]; }; and so the implied alignment
  * is 32 bits not 8 bits like our guid_t. In some cases (i.e., on 32-bit ARM),
  * this means that firmware services invoked by the kernel may assume that
  * efi_guid_t* arguments are 32-bit aligned, and use memory accessors that
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 1ec6d5ba64cc..88a241aac36a 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1151,9 +1151,6 @@ bool sk_filter_charge(struct sock *sk, struct sk_filter *fp);
 void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp);
 
 u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
-#define __bpf_call_base_args \
-	((u64 (*)(u64, u64, u64, u64, u64, const struct bpf_insn *)) \
-	 (void *)__bpf_call_base)
 
 struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog);
 void bpf_jit_compile(struct bpf_prog *prog);
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 80b38fbf2121..31df7608737e 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -208,6 +208,7 @@ struct fwnode_operations {
 static inline void fwnode_init(struct fwnode_handle *fwnode,
 			       const struct fwnode_operations *ops)
 {
+	fwnode->secondary = NULL;
 	fwnode->ops = ops;
 	INIT_LIST_HEAD(&fwnode->consumers);
 	INIT_LIST_HEAD(&fwnode->suppliers);
diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h
index 6c75df30a281..cd4972a7c97c 100644
--- a/include/linux/gfp_types.h
+++ b/include/linux/gfp_types.h
@@ -273,11 +273,11 @@ enum {
  *
  * %__GFP_ZERO returns a zeroed page on success.
  *
- * %__GFP_ZEROTAGS zeroes memory tags at allocation time if the memory itself
- * is being zeroed (either via __GFP_ZERO or via init_on_alloc, provided that
- * __GFP_SKIP_ZERO is not set). This flag is intended for optimization: setting
- * memory tags at the same time as zeroing memory has minimal additional
- * performance impact.
+ * %__GFP_ZEROTAGS zeroes memory tags at allocation time. Setting memory tags at
+ * the same time as zeroing memory (e.g., with __GFP_ZERO) has minimal
+ * additional performance impact. However, __GFP_ZEROTAGS also zeroes the tags
+ * even if memory is not getting zeroed at allocation time (e.g.,
+ * with init_on_free).
  *
  * %__GFP_SKIP_KASAN makes KASAN skip unpoisoning on page allocation.
  * Used for userspace and vmalloc pages; the latter are unpoisoned by
diff --git a/include/linux/hid.h b/include/linux/hid.h
index bfb9859f391e..47dc0bc89fa4 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -1316,8 +1316,6 @@ void hid_quirks_exit(__u16 bus);
 	dev_notice(&(hid)->dev, fmt, ##__VA_ARGS__)
 #define hid_warn(hid, fmt, ...)				\
 	dev_warn(&(hid)->dev, fmt, ##__VA_ARGS__)
-#define hid_warn_ratelimited(hid, fmt, ...)				\
-	dev_warn_ratelimited(&(hid)->dev, fmt, ##__VA_ARGS__)
 #define hid_info(hid, fmt, ...)				\
 	dev_info(&(hid)->dev, fmt, ##__VA_ARGS__)
 #define hid_dbg(hid, fmt, ...)				\
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index af03db851a1d..d7aac9de1c8a 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -347,10 +347,11 @@ static inline void clear_highpage_kasan_tagged(struct page *page)
 
 #ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGES
 
-/* Return false to let people know we did not initialize the pages */
-static inline bool tag_clear_highpages(struct page *page, int numpages)
+/* Returns true if the caller has to initialize the pages */
+static inline bool tag_clear_highpages(struct page *page, int numpages,
+		bool clear_pages)
 {
-	return false;
+	return clear_pages;
 }
 
 #endif
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 93418625d3c5..5957bc25efa8 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -148,7 +148,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
 			     struct folio **foliop);
 #endif /* CONFIG_USERFAULTFD */
 long hugetlb_reserve_pages(struct inode *inode, long from, long to,
-			   struct vm_area_desc *desc, vma_flags_t vma_flags);
+			   struct vm_area_struct *vma, vma_flags_t vma_flags);
 long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
 						long freed);
 bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list);
@@ -276,7 +276,6 @@ long hugetlb_change_protection(struct vm_area_struct *vma,
 void hugetlb_unshare_all_pmds(struct vm_area_struct *vma);
 void fixup_hugetlb_reservations(struct vm_area_struct *vma);
 void hugetlb_split(struct vm_area_struct *vma, unsigned long addr);
-int hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
 
 unsigned int arch_hugetlb_cma_order(void);
 
@@ -469,11 +468,6 @@ static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma)
 
 static inline void hugetlb_split(struct vm_area_struct *vma, unsigned long addr) {}
 
-static inline int hugetlb_vma_lock_alloc(struct vm_area_struct *vma)
-{
-	return 0;
-}
-
 #endif /* !CONFIG_HUGETLB_PAGE */
 
 #ifndef pgd_write
diff --git a/include/linux/hugetlb_inline.h b/include/linux/hugetlb_inline.h
index 565b473fd135..5c29cd3223a1 100644
--- a/include/linux/hugetlb_inline.h
+++ b/include/linux/hugetlb_inline.h
@@ -6,23 +6,13 @@
 
 #ifdef CONFIG_HUGETLB_PAGE
 
-static inline bool is_vm_hugetlb_flags(vm_flags_t vm_flags)
-{
-	return !!(vm_flags & VM_HUGETLB);
-}
-
 static inline bool is_vma_hugetlb_flags(const vma_flags_t *flags)
 {
-	return vma_flags_test_any(flags, VMA_HUGETLB_BIT);
+	return vma_flags_test(flags, VMA_HUGETLB_BIT);
 }
 
 #else
 
-static inline bool is_vm_hugetlb_flags(vm_flags_t vm_flags)
-{
-	return false;
-}
-
 static inline bool is_vma_hugetlb_flags(const vma_flags_t *flags)
 {
 	return false;
@@ -32,7 +22,7 @@ static inline bool is_vma_hugetlb_flags(const vma_flags_t *flags)
 
 static inline bool is_vm_hugetlb_page(const struct vm_area_struct *vma)
 {
-	return is_vm_hugetlb_flags(vma->vm_flags);
+	return is_vma_hugetlb_flags(&vma->flags);
 }
 
 #endif
diff --git a/include/linux/kho/abi/kexec_handover.h b/include/linux/kho/abi/kexec_handover.h
index 7e847a2339b0..db9bda6dd310 100644
--- a/include/linux/kho/abi/kexec_handover.h
+++ b/include/linux/kho/abi/kexec_handover.h
@@ -274,7 +274,7 @@ enum kho_radix_consts {
 	 * and 1 bitmap level.
 	 */
 	KHO_TREE_MAX_DEPTH =
-		DIV_ROUND_UP(KHO_ORDER_0_LOG2 - KHO_BITMAP_SIZE_LOG2,
+		DIV_ROUND_UP(KHO_ORDER_0_LOG2 - KHO_BITMAP_SIZE_LOG2 + 1,
 			     KHO_TABLE_SIZE_LOG2) + 1,
 };
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 5c085ef4eda7..127229fbd1a6 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -371,6 +371,7 @@ enum {
 	/* return values for ->qc_defer */
 	ATA_DEFER_LINK		= 1,
 	ATA_DEFER_PORT		= 2,
+	ATA_DEFER_LINK_EXCL	= 3,
 
 	/* desc_len for ata_eh_info and context */
 	ATA_EH_DESC_LEN		= 80,
@@ -854,6 +855,9 @@ struct ata_link {
 	unsigned int		sata_spd;	/* current SATA PHY speed */
 	enum ata_lpm_policy	lpm_policy;
 
+	struct work_struct	deferred_qc_work;
+	struct ata_queued_cmd	*deferred_qc;
+
 	/* record runtime error info, protected by host_set lock */
 	struct ata_eh_info	eh_info;
 	/* EH context */
@@ -899,9 +903,6 @@ struct ata_port {
 	u64			qc_active;
 	int			nr_active_links; /* #links with active qcs */
 
-	struct work_struct	deferred_qc_work;
-	struct ata_queued_cmd	*deferred_qc;
-
 	struct ata_link		link;		/* host default link */
 	struct ata_link		*slave_link;	/* see ata_slave_link_init() */
 
diff --git a/include/linux/list.h b/include/linux/list.h
index 00ea8e5fb88b..09d979976b3b 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -191,6 +191,29 @@ static inline void list_add_tail(struct list_head *new, struct list_head *head)
 	__list_add(new, head->prev, head);
 }
 
+/**
+ * list_add_tail_release - add a new entry with release barrier
+ * @new: new entry to be added
+ * @head: list head to add it before
+ *
+ * Insert a new entry before the specified head, using a release barrier to set
+ * the ->next pointer that points to it.  This is useful for implementing
+ * queues, in particular one that the elements will be walked through forwards
+ * locklessly.
+ */
+static inline void list_add_tail_release(struct list_head *new,
+					 struct list_head *head)
+{
+	struct list_head *prev = head->prev;
+
+	if (__list_add_valid(new, prev, head)) {
+		new->next = head;
+		new->prev = prev;
+		head->prev = new;
+		smp_store_release(&prev->next, new);
+	}
+}
+
 /*
  * Delete a list entry by making the prev/next entries
  * point to each other.
@@ -645,6 +668,20 @@ static inline void list_splice_tail_init(struct list_head *list,
 })
 
 /**
+ * list_first_entry_or_null_acquire - get the first element from a list with barrier
+ * @ptr:	the list head to take the element from.
+ * @type:	the type of the struct this is embedded in.
+ * @member:	the name of the list_head within the struct.
+ *
+ * Note that if the list is empty, it returns NULL.
+ */
+#define list_first_entry_or_null_acquire(ptr, type, member) ({ \
+	struct list_head *head__ = (ptr); \
+	struct list_head *pos__ = smp_load_acquire(&head__->next); \
+	pos__ != head__ ? list_entry(pos__, type, member) : NULL; \
+})
+
+/**
  * list_last_entry_or_null - get the last element from a list
  * @ptr:	the list head to take the element from.
  * @type:	the type of the struct this is embedded in.
diff --git a/include/linux/mm.h b/include/linux/mm.h
index af23453e9dbd..06bbe9eba636 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -5174,9 +5174,10 @@ int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status);
  * DMA mapping IDs for page_pool
  *
  * When DMA-mapping a page, page_pool allocates an ID (from an xarray) and
- * stashes it in the upper bits of page->pp_magic. Non-PP pages can have
- * arbitrary kernel pointers stored in the same field as pp_magic (since
- * it overlaps with page->lru.next), so we must ensure that we cannot
+ * stashes it in the upper bits of page->pp_magic. We always want to be able to
+ * unambiguously identify page pool pages (using page_pool_page_is_pp()). Non-PP
+ * pages can have arbitrary kernel pointers stored in the same field as pp_magic
+ * (since it overlaps with page->lru.next), so we must ensure that we cannot
  * mistake a valid kernel pointer with any of the values we write into this
  * field.
  *
@@ -5211,6 +5212,26 @@ int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status);
 #define PP_DMA_INDEX_MASK GENMASK(PP_DMA_INDEX_BITS + PP_DMA_INDEX_SHIFT - 1, \
 				  PP_DMA_INDEX_SHIFT)
 
+/* Mask used for checking in page_pool_page_is_pp() below. page->pp_magic is
+ * OR'ed with PP_SIGNATURE after the allocation in order to preserve bit 0 for
+ * the head page of compound page and bit 1 for pfmemalloc page, as well as the
+ * bits used for the DMA index. page_is_pfmemalloc() is checked in
+ * __page_pool_put_page() to avoid recycling the pfmemalloc page.
+ */
+#define PP_MAGIC_MASK ~(PP_DMA_INDEX_MASK | 0x3UL)
+
+#ifdef CONFIG_PAGE_POOL
+static inline bool page_pool_page_is_pp(const struct page *page)
+{
+	return (page->pp_magic & PP_MAGIC_MASK) == PP_SIGNATURE;
+}
+#else
+static inline bool page_pool_page_is_pp(const struct page *page)
+{
+	return false;
+}
+#endif
+
 #define PAGE_SNAPSHOT_FAITHFUL (1 << 0)
 #define PAGE_SNAPSHOT_PG_BUDDY (1 << 1)
 #define PAGE_SNAPSHOT_PG_IDLE  (1 << 2)
diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h
index 9ee7014400e8..ad5563f0f864 100644
--- a/include/linux/netfilter/nf_conntrack_proto_gre.h
+++ b/include/linux/netfilter/nf_conntrack_proto_gre.h
@@ -18,9 +18,10 @@ struct nf_ct_gre_keymap {
 	struct rcu_head rcu;
 };
 
-/* add new tuple->key_reply pair to keymap */
-int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir,
-			 struct nf_conntrack_tuple *t);
+/* add tuple->key_reply pairs to keymap */
+bool nf_ct_gre_keymap_add(struct nf_conn *ct,
+			  const struct nf_conntrack_tuple *orig,
+			  const struct nf_conntrack_tuple *repl);
 
 /* delete keymap entries */
 void nf_ct_gre_keymap_destroy(struct nf_conn *ct);
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index ba17ac5bf356..243c0f737938 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -62,8 +62,8 @@ struct netfs_inode {
 	struct fscache_cookie	*cache;
 #endif
 	struct mutex		wb_lock;	/* Writeback serialisation */
-	loff_t			remote_i_size;	/* Size of the remote file */
-	loff_t			zero_point;	/* Size after which we assume there's no data
+	loff_t			_remote_i_size;	/* Size of the remote file */
+	loff_t			_zero_point;	/* Size after which we assume there's no data
 						 * on the server */
 	atomic_t		io_count;	/* Number of outstanding reqs */
 	unsigned long		flags;
@@ -252,7 +252,7 @@ struct netfs_io_request {
 	unsigned long long	collected_to;	/* Point we've collected to */
 	unsigned long long	cleaned_to;	/* Position we've cleaned folios to */
 	unsigned long long	abandon_to;	/* Position to abandon folios to */
-	pgoff_t			no_unlock_folio; /* Don't unlock this folio after read */
+	const struct folio	*no_unlock_folio; /* Don't unlock this folio after read */
 	unsigned int		direct_bv_count; /* Number of elements in direct_bv[] */
 	unsigned int		debug_id;
 	unsigned int		rsize;		/* Maximum read size (0 for none) */
@@ -475,6 +475,254 @@ static inline struct netfs_inode *netfs_inode(struct inode *inode)
 }
 
 /**
+ * netfs_read_remote_i_size - Read remote_i_size safely
+ * @inode: The inode to access
+ *
+ * Read remote_i_size safely without the potential for tearing on 32-bit
+ * arches.
+ *
+ * NOTE: in a 32bit arch with a preemptable kernel and an UP compile the
+ * i_size_read/write must be atomic with respect to the local cpu (unlike with
+ * preempt disabled), but they don't need to be atomic with respect to other
+ * cpus like in true SMP (so they need either to either locally disable irq
+ * around the read or for example on x86 they can be still implemented as a
+ * cmpxchg8b without the need of the lock prefix).  For SMP compiles and 64bit
+ * archs it makes no difference if preempt is enabled or not.
+ */
+static inline unsigned long long netfs_read_remote_i_size(const struct inode *inode)
+{
+	const struct netfs_inode *ictx = container_of(inode, struct netfs_inode, inode);
+	unsigned long long remote_i_size;
+
+#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
+	unsigned int seq;
+
+	do {
+		seq = read_seqcount_begin(&inode->i_size_seqcount);
+		remote_i_size = ictx->_remote_i_size;
+	} while (read_seqcount_retry(&inode->i_size_seqcount, seq));
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
+	preempt_disable();
+	remote_i_size = ictx->_remote_i_size;
+	preempt_enable();
+#else
+	/* Pairs with smp_store_release() in netfs_write_remote_i_size() */
+	remote_i_size = smp_load_acquire(&ictx->_remote_i_size);
+#endif
+	return remote_i_size;
+}
+
+/*
+ * netfs_write_remote_i_size - Set remote_i_size safely
+ * @inode: The inode to access
+ * @remote_i_size: The new value for the size of the file on the server
+ *
+ * Set remote_i_size safely without the potential for tearing on 32-bit arches.
+ *
+ * Context: The caller must hold inode->i_lock.
+ *
+ * NOTE: unlike netfs_read_remote_i_size(), netfs_write_remote_i_size() does
+ * need locking around it (normally i_rwsem), otherwise on 32bit/SMP an update
+ * of i_size_seqcount can be lost, resulting in subsequent i_size_read() calls
+ * spinning forever.
+ */
+static inline void netfs_write_remote_i_size(struct inode *inode,
+					     unsigned long long remote_i_size)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+
+#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
+	write_seqcount_begin(&inode->i_size_seqcount);
+	ictx->_remote_i_size = remote_i_size;
+	write_seqcount_end(&inode->i_size_seqcount);
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
+	preempt_disable();
+	ictx->_remote_i_size = remote_i_size;
+	preempt_enable();
+#else
+	/*
+	 * Pairs with smp_load_acquire() in netfs_read_remote_i_size() to
+	 * ensure changes related to inode size (such as page contents) are
+	 * visible before we see the changed inode size.
+	 */
+	smp_store_release(&ictx->_remote_i_size, remote_i_size);
+#endif
+}
+
+/**
+ * netfs_read_zero_point - Read zero_point safely
+ * @inode: The inode to access
+ *
+ * Read zero_point safely without the potential for tearing on 32-bit
+ * arches.
+ *
+ * NOTE: in a 32bit arch with a preemptable kernel and an UP compile the
+ * i_size_read/write must be atomic with respect to the local cpu (unlike with
+ * preempt disabled), but they don't need to be atomic with respect to other
+ * cpus like in true SMP (so they need either to either locally disable irq
+ * around the read or for example on x86 they can be still implemented as a
+ * cmpxchg8b without the need of the lock prefix).  For SMP compiles and 64bit
+ * archs it makes no difference if preempt is enabled or not.
+ */
+static inline unsigned long long netfs_read_zero_point(const struct inode *inode)
+{
+	struct netfs_inode *ictx = container_of(inode, struct netfs_inode, inode);
+	unsigned long long zero_point;
+
+#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
+	unsigned int seq;
+
+	do {
+		seq = read_seqcount_begin(&inode->i_size_seqcount);
+		zero_point = ictx->_zero_point;
+	} while (read_seqcount_retry(&inode->i_size_seqcount, seq));
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
+	preempt_disable();
+	zero_point = ictx->_zero_point;
+	preempt_enable();
+#else
+	/* Pairs with smp_store_release() in netfs_write_zero_point() */
+	zero_point = smp_load_acquire(&ictx->_zero_point);
+#endif
+	return zero_point;
+}
+
+/*
+ * netfs_write_zero_point - Set zero_point safely
+ * @inode: The inode to access
+ * @zero_point: The new value for the point beyond which the server has no data
+ *
+ * Set zero_point safely without the potential for tearing on 32-bit arches.
+ *
+ * Context: The caller must hold inode->i_lock.
+ *
+ * NOTE: unlike netfs_read_zero_point(), netfs_write_zero_point() does need
+ * locking around it (normally i_rwsem), otherwise on 32bit/SMP an update of
+ * i_size_seqcount can be lost, resulting in subsequent read calls spinning
+ * forever.
+ */
+static inline void netfs_write_zero_point(struct inode *inode,
+					  unsigned long long zero_point)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+
+#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
+	write_seqcount_begin(&inode->i_size_seqcount);
+	ictx->_zero_point = zero_point;
+	write_seqcount_end(&inode->i_size_seqcount);
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
+	preempt_disable();
+	ictx->_zero_point = zero_point;
+	preempt_enable();
+#else
+	/*
+	 * Pairs with smp_load_acquire() in netfs_read_zero_point() to
+	 * ensure changes related to inode size (such as page contents) are
+	 * visible before we see the changed inode size.
+	 */
+	smp_store_release(&ictx->_zero_point, zero_point);
+#endif
+}
+
+/**
+ * netfs_read_sizes - Read remote_i_size and zero_point safely
+ * @inode: The inode to access
+ * @i_size: Where to return the local file size.
+ * @remote_i_size: Where to return the size of the file on the server
+ * @zero_point: Where to return the the point beyond which the server has no data
+ *
+ * Read remote_i_size and zero_point safely without the potential for tearing
+ * on 32-bit arches.
+ *
+ * NOTE: in a 32bit arch with a preemptable kernel and an UP compile the
+ * i_size_read/write must be atomic with respect to the local cpu (unlike with
+ * preempt disabled), but they don't need to be atomic with respect to other
+ * cpus like in true SMP (so they need either to either locally disable irq
+ * around the read or for example on x86 they can be still implemented as a
+ * cmpxchg8b without the need of the lock prefix).  For SMP compiles and 64bit
+ * archs it makes no difference if preempt is enabled or not.
+ */
+static inline void netfs_read_sizes(const struct inode *inode,
+				    unsigned long long *i_size,
+				    unsigned long long *remote_i_size,
+				    unsigned long long *zero_point)
+{
+	const struct netfs_inode *ictx = container_of(inode, struct netfs_inode, inode);
+#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
+	unsigned int seq;
+
+	do {
+		seq = read_seqcount_begin(&inode->i_size_seqcount);
+		*i_size = inode->i_size;
+		*remote_i_size = ictx->_remote_i_size;
+		*zero_point = ictx->_zero_point;
+	} while (read_seqcount_retry(&inode->i_size_seqcount, seq));
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
+	preempt_disable();
+	*i_size = inode->i_size;
+	*remote_i_size = ictx->_remote_i_size;
+	*zero_point = ictx->_zero_point;
+	preempt_enable();
+#else
+	/* Pairs with smp_store_release() in i_size_write() */
+	*i_size = smp_load_acquire(&inode->i_size);
+	/* Pairs with smp_store_release() in netfs_write_remote_i_size() */
+	*remote_i_size = smp_load_acquire(&ictx->_remote_i_size);
+	/* Pairs with smp_store_release() in netfs_write_zero_point() */
+	*zero_point = smp_load_acquire(&ictx->_zero_point);
+#endif
+}
+
+/*
+ * netfs_write_sizes - Set i_size, remote_i_size and zero_point safely
+ * @inode: The inode to access
+ * @i_size: The new value for the local size of the file
+ * @re