6.18.38-rc1 review

index 0bd0cb8992c9fd..541e199feb9981 100644
@@ -2453,13 +2453,15 @@ static struct kvm_mmu_page *kvm_mmu_get_child_sp(struct kvm_vcpu *vcpu,
 						 u64 *sptep, gfn_t gfn,
 						 bool direct, unsigned int access)
 {
-	union kvm_mmu_page_role role;
+	union kvm_mmu_page_role role = kvm_mmu_child_role(sptep, direct, access);
 
-	if (is_shadow_present_pte(*sptep) && !is_large_pte(*sptep) &&
-	    spte_to_child_sp(*sptep) && spte_to_child_sp(*sptep)->gfn == gfn)
+	if (is_shadow_present_pte(*sptep) &&
+	    !is_large_pte(*sptep) &&
+	    spte_to_child_sp(*sptep) &&
+	    spte_to_child_sp(*sptep)->gfn == gfn &&
+	    spte_to_child_sp(*sptep)->role.word == role.word)
 		return ERR_PTR(-EEXIST);
 
-	role = kvm_mmu_child_role(sptep, direct, access);
 	return kvm_mmu_get_shadow_page(vcpu, gfn, role);
 }
 

index 15a7f80310848d..e049a627d78fb9 100644
@@ -12,6 +12,7 @@
 #include <linux/backing-file.h>
 #include <linux/splice.h>
 #include <linux/mm.h>
+#include <linux/security.h>
 
 #include "internal.h"
 

@@ -29,14 +30,15 @@
  * returned file into a container structure that also stores the stacked
  * file's path, which can be retrieved using backing_file_user_path().
  */
-struct file *backing_file_open(const struct path *user_path, int flags,
+struct file *backing_file_open(const struct file *user_file, int flags,
 			       const struct path *real_path,
 			       const struct cred *cred)
 {
+	const struct path *user_path = &user_file->f_path;
 	struct file *f;
 	int error;
 
-	f = alloc_empty_backing_file(flags, cred);
+	f = alloc_empty_backing_file(flags, cred, user_file);
 	if (IS_ERR(f))
 		return f;
 

@@ -52,15 +54,16 @@ struct file *backing_file_open(const struct path *user_path, int flags,
 }
 EXPORT_SYMBOL_GPL(backing_file_open);
 
-struct file *backing_tmpfile_open(const struct path *user_path, int flags,
+struct file *backing_tmpfile_open(const struct file *user_file, int flags,
 				  const struct path *real_parentpath,
 				  umode_t mode, const struct cred *cred)
 {
 	struct mnt_idmap *real_idmap = mnt_idmap(real_parentpath->mnt);
+	const struct path *user_path = &user_file->f_path;
 	struct file *f;
 	int error;
 
-	f = alloc_empty_backing_file(flags, cred);
+	f = alloc_empty_backing_file(flags, cred, user_file);
 	if (IS_ERR(f))
 		return f;
 

@@ -339,6 +342,12 @@ int backing_file_mmap(struct file *file, struct vm_area_struct *vma,
 	vma_set_file(vma, file);
 
 	old_cred = override_creds(ctx->cred);
+	ret = security_mmap_backing_file(vma, file, user_file);
+	if (ret) {
+		revert_creds(old_cred);
+		return ret;
+	}
+
 	ret = vfs_mmap(vma->vm_file, vma);
 	revert_creds(old_cred);
 

index 762f03dcbcd778..987e01da993894 100644
@@ -50,6 +50,9 @@ struct backing_file {
 		struct path user_path;
 		freeptr_t bf_freeptr;
 	};
+#ifdef CONFIG_SECURITY
+	void *security;
+#endif
 };
 
 #define backing_file(f) container_of(f, struct backing_file, file)

@@ -66,8 +69,21 @@ void backing_file_set_user_path(struct file *f, const struct path *path)
 }
 EXPORT_SYMBOL_GPL(backing_file_set_user_path);
 
+#ifdef CONFIG_SECURITY
+void *backing_file_security(const struct file *f)
+{
+	return backing_file(f)->security;
+}
+
+void backing_file_set_security(struct file *f, void *security)
+{
+	backing_file(f)->security = security;
+}
+#endif /* CONFIG_SECURITY */
+
 static inline void backing_file_free(struct backing_file *ff)
 {
+	security_backing_file_free(&ff->file);
 	path_put(&ff->user_path);
 	kmem_cache_free(bfilp_cachep, ff);
 }

@@ -288,10 +304,12 @@ struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred)
 	return f;
 }
 
-static int init_backing_file(struct backing_file *ff)
+static int init_backing_file(struct backing_file *ff,
+			     const struct file *user_file)
 {
 	memset(&ff->user_path, 0, sizeof(ff->user_path));
-	return 0;
+	backing_file_set_security(&ff->file, NULL);
+	return security_backing_file_alloc(&ff->file, user_file);
 }
 
 /*

@@ -301,7 +319,8 @@ static int init_backing_file(struct backing_file *ff)
  * This is only for kernel internal use, and the allocate file must not be
  * installed into file tables or such.
  */
-struct file *alloc_empty_backing_file(int flags, const struct cred *cred)
+struct file *alloc_empty_backing_file(int flags, const struct cred *cred,
+				      const struct file *user_file)
 {
 	struct backing_file *ff;
 	int error;

@@ -318,7 +337,7 @@ struct file *alloc_empty_backing_file(int flags, const struct cred *cred)
 
 	/* The f_mode flags must be set before fput(). */
 	ff->file.f_mode |= FMODE_BACKING | FMODE_NOACCOUNT;
-	error = init_backing_file(ff);
+	error = init_backing_file(ff, user_file);
 	if (unlikely(error)) {
 		fput(&ff->file);
 		return ERR_PTR(error);

index 72de97c03d0eeb..f2d08ac2459b7e 100644
@@ -167,7 +167,7 @@ struct fuse_backing *fuse_passthrough_open(struct file *file, int backing_id)
 		goto out;
 
 	/* Allocate backing file per fuse file to store fuse path */
-	backing_file = backing_file_open(&file->f_path, file->f_flags,
+	backing_file = backing_file_open(file, file->f_flags,
 					 &fb->file->f_path, fb->cred);
 	err = PTR_ERR(backing_file);
 	if (IS_ERR(backing_file)) {

index 9b2b4d11688023..51107fd515145b 100644
@@ -100,7 +100,8 @@ extern void chroot_fs_refs(const struct path *, const struct path *);
  */
 struct file *alloc_empty_file(int flags, const struct cred *cred);
 struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred);
-struct file *alloc_empty_backing_file(int flags, const struct cred *cred);
+struct file *alloc_empty_backing_file(int flags, const struct cred *cred,
+				      const struct file *user_file);
 void backing_file_set_user_path(struct file *f, const struct path *path);
 
 static inline void file_put_write_access(struct file *file)

index a5e9ddf3023b39..e924321b64025e 100644
@@ -1355,7 +1355,7 @@ static int ovl_create_tmpfile(struct file *file, struct dentry *dentry,
 	}
 
 	ovl_path_upper(dentry->d_parent, &realparentpath);
-	realfile = backing_tmpfile_open(&file->f_path, flags, &realparentpath,
+	realfile = backing_tmpfile_open(file, flags, &realparentpath,
 					mode, current_cred());
 	err = PTR_ERR_OR_ZERO(realfile);
 	pr_debug("tmpfile/open(%pd2, 0%o) = %i\n", realparentpath.dentry, mode, err);

index 7ab2c9daffd017..3fedfdddfa7584 100644
@@ -48,7 +48,7 @@ static struct file *ovl_open_realfile(const struct file *file,
 		if (!inode_owner_or_capable(real_idmap, realinode))
 			flags &= ~O_NOATIME;
 
-		realfile = backing_file_open(file_user_path(file),
+		realfile = backing_file_open(file,
 					     flags, realpath, current_cred());
 	}
 	ovl_revert_creds(old_cred);

index 1476a6ed1bfd77..c939cd222730c4 100644
@@ -18,10 +18,10 @@ struct backing_file_ctx {
 	void (*end_write)(struct kiocb *iocb, ssize_t);
 };
 
-struct file *backing_file_open(const struct path *user_path, int flags,
+struct file *backing_file_open(const struct file *user_file, int flags,
 			       const struct path *real_path,
 			       const struct cred *cred);
-struct file *backing_tmpfile_open(const struct path *user_path, int flags,
+struct file *backing_tmpfile_open(const struct file *user_file, int flags,
 				  const struct path *real_parentpath,
 				  umode_t mode, const struct cred *cred);
 ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter,

index 014cb04eefbe6c..f3e798184a58e8 100644
@@ -2890,6 +2890,19 @@ struct file *dentry_create(const struct path *path, int flags, umode_t mode,
 			   const struct cred *cred);
 const struct path *backing_file_user_path(const struct file *f);
 
+#ifdef CONFIG_SECURITY
+void *backing_file_security(const struct file *f);
+void backing_file_set_security(struct file *f, void *security);
+#else
+static inline void *backing_file_security(const struct file *f)
+{
+	return NULL;
+}
+static inline void backing_file_set_security(struct file *f, void *security)
+{
+}
+#endif /* CONFIG_SECURITY */
+
 /*
  * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file
  * stored in ->vm_file is a backing file whose f_inode is on the underlying

index 382c56a97bba1d..584db296e43b20 100644
@@ -94,7 +94,7 @@ struct common_audit_data {
 #endif
 		char *kmod_name;
 		struct lsm_ioctlop_audit *op;
-		struct file *file;
+		const struct file *file;
 		struct lsm_ibpkey_audit *ibpkey;
 		struct lsm_ibendport_audit *ibendport;
 		int reason;

index 8c42b4bde09c07..b4958167e38196 100644
@@ -191,6 +191,9 @@ LSM_HOOK(int, 0, file_permission, struct file *file, int mask)
 LSM_HOOK(int, 0, file_alloc_security, struct file *file)
 LSM_HOOK(void, LSM_RET_VOID, file_release, struct file *file)
 LSM_HOOK(void, LSM_RET_VOID, file_free_security, struct file *file)
+LSM_HOOK(int, 0, backing_file_alloc, struct file *backing_file,
+	 const struct file *user_file)
+LSM_HOOK(void, LSM_RET_VOID, backing_file_free, struct file *backing_file)
 LSM_HOOK(int, 0, file_ioctl, struct file *file, unsigned int cmd,
 	 unsigned long arg)
 LSM_HOOK(int, 0, file_ioctl_compat, struct file *file, unsigned int cmd,

@@ -198,6 +201,8 @@ LSM_HOOK(int, 0, file_ioctl_compat, struct file *file, unsigned int cmd,
 LSM_HOOK(int, 0, mmap_addr, unsigned long addr)
 LSM_HOOK(int, 0, mmap_file, struct file *file, unsigned long reqprot,
 	 unsigned long prot, unsigned long flags)
+LSM_HOOK(int, 0, mmap_backing_file, struct vm_area_struct *vma,
+	 struct file *backing_file, struct file *user_file)
 LSM_HOOK(int, 0, file_mprotect, struct vm_area_struct *vma,
 	 unsigned long reqprot, unsigned long prot)
 LSM_HOOK(int, 0, file_lock, struct file *file, unsigned int cmd)

index 79ec5a2bdcca7a..ea4b0f5ca7f0ff 100644
@@ -104,6 +104,7 @@ struct security_hook_list {
 struct lsm_blob_sizes {
 	int lbs_cred;
 	int lbs_file;
+	int lbs_backing_file;
 	int lbs_ib;
 	int lbs_inode;
 	int lbs_sock;

index b64598e5d65d75..e540253624268d 100644
@@ -473,11 +473,17 @@ int security_file_permission(struct file *file, int mask);
 int security_file_alloc(struct file *file);
 void security_file_release(struct file *file);
 void security_file_free(struct file *file);
+int security_backing_file_alloc(struct file *backing_file,
+				const struct file *user_file);
+void security_backing_file_free(struct file *backing_file);
 int security_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 int security_file_ioctl_compat(struct file *file, unsigned int cmd,
 			       unsigned long arg);
 int security_mmap_file(struct file *file, unsigned long prot,
 			unsigned long flags);
+int security_mmap_backing_file(struct vm_area_struct *vma,
+			       struct file *backing_file,
+			       struct file *user_file);
 int security_mmap_addr(unsigned long addr);
 int security_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot,
 			   unsigned long prot);

@@ -1142,6 +1148,15 @@ static inline void security_file_release(struct file *file)
 static inline void security_file_free(struct file *file)
 { }
 
+static inline int security_backing_file_alloc(struct file *backing_file,
+					      const struct file *user_file)
+{
+	return 0;
+}
+
+static inline void security_backing_file_free(struct file *backing_file)
+{ }
+
 static inline int security_file_ioctl(struct file *file, unsigned int cmd,
 				      unsigned long arg)
 {

@@ -1161,6 +1176,13 @@ static inline int security_mmap_file(struct file *file, unsigned long prot,
 	return 0;
 }
 
+static inline int security_mmap_backing_file(struct vm_area_struct *vma,
+					     struct file *backing_file,
+					     struct file *user_file)
+{
+	return 0;
+}
+
 static inline int security_mmap_addr(unsigned long addr)
 {
 	return cap_mmap_addr(addr);

151 lines not on this page · raw message

index 3da3017ad2ca06..f96ee8f372e3b2 100644
@@ -1739,49 +1739,72 @@ static inline int file_path_has_perm(const struct cred *cred,
 static int bpf_fd_pass(const struct file *file, u32 sid);
 #endif
 
-/* Check whether a task can use an open file descriptor to
-   access an inode in a given way.  Check access to the
-   descriptor itself, and then use dentry_has_perm to
-   check a particular permission to the file.
-   Access to the descriptor is implicitly granted if it
-   has the same SID as the process.  If av is zero, then
-   access to the file is not checked, e.g. for cases
-   where only the descriptor is affected like seek. */
-static int file_has_perm(const struct cred *cred,
-			 struct file *file,
-			 u32 av)
+static int __file_has_perm(const struct cred *cred, const struct file *file,
+			   u32 av, bool bf_user_file)
+
 {
-	struct file_security_struct *fsec = selinux_file(file);
-	struct inode *inode = file_inode(file);
 	struct common_audit_data ad;
-	u32 sid = cred_sid(cred);
+	struct inode *inode;
+	u32 ssid = cred_sid(cred);
+	u32 tsid_fd;
 	int rc;
 
-	ad.type = LSM_AUDIT_DATA_FILE;
-	ad.u.file = file;
+	if (bf_user_file) {
+		struct backing_file_security_struct *bfsec;
+		const struct path *path;
 
-	if (sid != fsec->sid) {
-		rc = avc_has_perm(sid, fsec->sid,
-				  SECCLASS_FD,
-				  FD__USE,
-				  &ad);
+		if (WARN_ON(!(file->f_mode & FMODE_BACKING)))
+			return -EIO;
+
+		bfsec = selinux_backing_file(file);
+		path = backing_file_user_path(file);
+		tsid_fd = bfsec->uf_sid;
+		inode = d_inode(path->dentry);
+
+		ad.type = LSM_AUDIT_DATA_PATH;
+		ad.u.path = *path;
+	} else {
+		struct file_security_struct *fsec = selinux_file(file);
+
+		tsid_fd = fsec->sid;
+		inode = file_inode(file);
+
+		ad.type = LSM_AUDIT_DATA_FILE;
+		ad.u.file = file;
+	}
+
+	if (ssid != tsid_fd) {
+		rc = avc_has_perm(ssid, tsid_fd, SECCLASS_FD, FD__USE, &ad);
 		if (rc)
-			goto out;
+			return rc;
 	}
 
 #ifdef CONFIG_BPF_SYSCALL
-	rc = bpf_fd_pass(file, cred_sid(cred));
+	/* regardless of backing vs user file, use the underlying file here */
+	rc = bpf_fd_pass(file, ssid);
 	if (rc)
 		return rc;
 #endif
 
 	/* av is zero if only checking access to the descriptor. */
-	rc = 0;
 	if (av)
-		rc = inode_has_perm(cred, inode, av, &ad);
+		return inode_has_perm(cred, inode, av, &ad);
 
-out:
-	return rc;
+	return 0;
+}
+
+/* Check whether a task can use an open file descriptor to
+   access an inode in a given way.  Check access to the
+   descriptor itself, and then use dentry_has_perm to
+   check a particular permission to the file.
+   Access to the descriptor is implicitly granted if it
+   has the same SID as the process.  If av is zero, then
+   access to the file is not checked, e.g. for cases
+   where only the descriptor is affected like seek. */
+static inline int file_has_perm(const struct cred *cred,
+				const struct file *file, u32 av)
+{
+	return __file_has_perm(cred, file, av, false);
 }
 
 /*

@@ -3799,6 +3822,17 @@ static int selinux_file_alloc_security(struct file *file)
 	return 0;
 }
 
+static int selinux_backing_file_alloc(struct file *backing_file,
+				      const struct file *user_file)
+{
+	struct backing_file_security_struct *bfsec;
+
+	bfsec = selinux_backing_file(backing_file);
+	bfsec->uf_sid = selinux_file(user_file)->sid;
+
+	return 0;
+}
+
 /*
  * Check whether a task has the ioctl permission and cmd
  * operation to an inode.

@@ -3916,42 +3950,55 @@ static int selinux_file_ioctl_compat(struct file *file, unsigned int cmd,
 
 static int default_noexec __ro_after_init;
 
-static int file_map_prot_check(struct file *file, unsigned long prot, int shared)
+static int __file_map_prot_check(const struct cred *cred,
+				 const struct file *file, unsigned long prot,
+				 bool shared, bool bf_user_file)
 {
-	const struct cred *cred = current_cred();
-	u32 sid = cred_sid(cred);
-	int rc = 0;
+	struct inode *inode = NULL;
+	bool prot_exec = prot & PROT_EXEC;
+	bool prot_write = prot & PROT_WRITE;
+
+	if (file) {
+		if (bf_user_file)
+			inode = d_inode(backing_file_user_path(file)->dentry);
+		else
+			inode = file_inode(file);
+	}
+
+	if (default_noexec && prot_exec &&
+	    (!file || IS_PRIVATE(inode) || (!shared && prot_write))) {
+		int rc;
+		u32 sid = cred_sid(cred);
 
-	if (default_noexec &&
-	    (prot & PROT_EXEC) && (!file || IS_PRIVATE(file_inode(file)) ||
-				   (!shared && (prot & PROT_WRITE)))) {
 		/*
-		 * We are making executable an anonymous mapping or a
-		 * private file mapping that will also be writable.
-		 * This has an additional check.
+		 * We are making executable an anonymous mapping or a private
+		 * file mapping that will also be writable.
 		 */
-		rc = avc_has_perm(sid, sid, SECCLASS_PROCESS,
-				  PROCESS__EXECMEM, NULL);
+		rc = avc_has_perm(sid, sid, SECCLASS_PROCESS, PROCESS__EXECMEM,
+				  NULL);
 		if (rc)
-			goto error;
+			return rc;
 	}
 
 	if (file) {
-		/* read access is always possible with a mapping */
+		/* "read" always possible, "write" only if shared */
 		u32 av = FILE__READ;
-
-		/* write access only matters if the mapping is shared */
-		if (shared && (prot & PROT_WRITE))
+		if (shared && prot_write)
 			av |= FILE__WRITE;
-
-		if (prot & PROT_EXEC)
+		if (prot_exec)
 			av |= FILE__EXECUTE;
 
-		return file_has_perm(cred, file, av);
+		return __file_has_perm(cred, file, av, bf_user_file);
 	}
 
-error:
-	return rc;
+	return 0;
+}
+
+static inline int file_map_prot_check(const struct cred *cred,
+				      const struct file *file,
+				      unsigned long prot, bool shared)
+{
+	return __file_map_prot_check(cred, file, prot, shared, false);
 }
 
 static int selinux_mmap_addr(unsigned long addr)

@@ -3967,36 +4014,80 @@ static int selinux_mmap_addr(unsigned long addr)
 	return rc;
 }
 
-static int selinux_mmap_file(struct file *file,
-			     unsigned long reqprot __always_unused,
-			     unsigned long prot, unsigned long flags)
+static int selinux_mmap_file_common(const struct cred *cred, struct file *file,
+				    unsigned long prot, bool shared)
 {
-	struct common_audit_data ad;
-	int rc;
-
 	if (file) {
+		int rc;
+		struct common_audit_data ad;
+
 		ad.type = LSM_AUDIT_DATA_FILE;
 		ad.u.file = file;
-		rc = inode_has_perm(current_cred(), file_inode(file),
-				    FILE__MAP, &ad);
+		rc = inode_has_perm(cred, file_inode(file), FILE__MAP, &ad);
 		if (rc)
 			return rc;
 	}
 
-	return file_map_prot_check(file, prot,
-				   (flags & MAP_TYPE) == MAP_SHARED);
+	return file_map_prot_check(cred, file, prot, shared);
+}
+
+static int selinux_mmap_file(struct file *file,
+			     unsigned long reqprot __always_unused,
+			     unsigned long prot, unsigned long flags)
+{
+	return selinux_mmap_file_common(current_cred(), file, prot,
+					(flags & MAP_TYPE) == MAP_SHARED);
+}
+
+/**
+ * selinux_mmap_backing_file - Check mmap permissions on a backing file
+ * @vma: memory region
+ * @backing_file: stacked filesystem backing file
+ * @user_file: user visible file
+ *
+ * This is called after selinux_mmap_file() on stacked filesystems, and it
+ * is this function's responsibility to verify access to @backing_file and
+ * setup the SELinux state for possible later use in the mprotect() code path.
+ *
+ * By the time this function is called, mmap() access to @user_file has already
+ * been authorized and @vma->vm_file has been set to point to @backing_file.
+ *
+ * Return zero on success, negative values otherwise.
+ */
+static int selinux_mmap_backing_file(struct vm_area_struct *vma,
+				     struct file *backing_file,
+				     struct file *user_file __always_unused)
+{
+	unsigned long prot = 0;
+
+	/* translate vma->vm_flags perms into PROT perms */
+	if (vma->vm_flags & VM_READ)
+		prot |= PROT_READ;
+	if (vma->vm_flags & VM_WRITE)
+		prot |= PROT_WRITE;
+	if (vma->vm_flags & VM_EXEC)
+		prot |= PROT_EXEC;
+
+	return selinux_mmap_file_common(backing_file->f_cred, backing_file,
+					prot, vma->vm_flags & VM_SHARED);
 }
 
 static int selinux_file_mprotect(struct vm_area_struct *vma,
 				 unsigned long reqprot __always_unused,
 				 unsigned long prot)
 {
+	int rc;
 	const struct cred *cred = current_cred();
 	u32 sid = cred_sid(cred);
+	const struct file *file = vma->vm_file;
+	bool backing_file;
+	bool shared = vma->vm_flags & VM_SHARED;
+
+	/* check if we need to trigger the "backing files are awful" mode */
+	backing_file = file && (file->f_mode & FMODE_BACKING);
 
 	if (default_noexec &&
 	    (prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) {
-		int rc = 0;
 		/*
 		 * We don't use the vma_is_initial_heap() helper as it has
 		 * a history of problems and is currently broken on systems

@@ -4010,11 +4101,15 @@ static int selinux_file_mprotect(struct vm_area_struct *vma,
 		    vma->vm_end <= vma->vm_mm->brk) {
 			rc = avc_has_perm(sid, sid, SECCLASS_PROCESS,
 					  PROCESS__EXECHEAP, NULL);
-		} else if (!vma->vm_file && (vma_is_initial_stack(vma) ||
+			if (rc)
+				return rc;
+		} else if (!file && (vma_is_initial_stack(vma) ||
 			    vma_is_stack_for_current(vma))) {
 			rc = avc_has_perm(sid, sid, SECCLASS_PROCESS,
 					  PROCESS__EXECSTACK, NULL);
-		} else if (vma->vm_file && vma->anon_vma) {
+			if (rc)
+				return rc;
+		} else if (file && vma->anon_vma) {
 			/*
 			 * We are making executable a file mapping that has
 			 * had some COW done. Since pages might have been

@@ -4022,13 +4117,29 @@ static int selinux_file_mprotect(struct vm_area_struct *vma,
 			 * modified content.  This typically should only
 			 * occur for text relocations.
 			 */
-			rc = file_has_perm(cred, vma->vm_file, FILE__EXECMOD);
+			rc = __file_has_perm(cred, file, FILE__EXECMOD,
+					     backing_file);
+			if (rc)
+				return rc;
+			if (backing_file) {
+				rc = file_has_perm(file->f_cred, file,
+						   FILE__EXECMOD);
+				if (rc)
+					return rc;
+			}
 		}
+	}
+
+	rc = __file_map_prot_check(cred, file, prot, shared, backing_file);
+	if (rc)
+		return rc;
+	if (backing_file) {
+		rc = file_map_prot_check(file->f_cred, file, prot, shared);
 		if (rc)
 			return rc;
 	}
 
-	return file_map_prot_check(vma->vm_file, prot, vma->vm_flags&VM_SHARED);
+	return 0;
 }
 
 static int selinux_file_lock(struct file *file, unsigned int cmd)

@@ -7140,6 +7251,7 @@ struct lsm_blob_sizes selinux_blob_sizes __ro_after_init = {
 	.lbs_cred = sizeof(struct cred_security_struct),
 	.lbs_task = sizeof(struct task_security_struct),
 	.lbs_file = sizeof(struct file_security_struct),
+	.lbs_backing_file = sizeof(struct backing_file_security_struct),
 	.lbs_inode = sizeof(struct inode_security_struct),
 	.lbs_ipc = sizeof(struct ipc_security_struct),
 	.lbs_key = sizeof(struct key_security_struct),

@@ -7363,9 +7475,11 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = {
 
 	LSM_HOOK_INIT(file_permission, selinux_file_permission),
 	LSM_HOOK_INIT(file_alloc_security, selinux_file_alloc_security),
+	LSM_HOOK_INIT(backing_file_alloc, selinux_backing_file_alloc),
 	LSM_HOOK_INIT(file_ioctl, selinux_file_ioctl),
 	LSM_HOOK_INIT(file_ioctl_compat, selinux_file_ioctl_compat),
 	LSM_HOOK_INIT(mmap_file, selinux_mmap_file),
+	LSM_HOOK_INIT(mmap_backing_file, selinux_mmap_backing_file),
 	LSM_HOOK_INIT(mmap_addr, selinux_mmap_addr),
 	LSM_HOOK_INIT(file_mprotect, selinux_file_mprotect),
 	LSM_HOOK_INIT(file_lock, selinux_file_lock),

index 816fde5a5896c1..fcb46793898f5e 100644
@@ -86,6 +86,10 @@ struct file_security_struct {
 	u32 pseqno; /* Policy seqno at the time of file open */
 };
 
+struct backing_file_security_struct {
+	u32 uf_sid; /* associated user file fsec->sid */
+};
+
 struct superblock_security_struct {
 	u32 sid; /* SID of file system superblock */
 	u32 def_sid; /* default SID for labeling */

@@ -190,6 +194,13 @@ static inline struct file_security_struct *selinux_file(const struct file *file)
 	return file->f_security + selinux_blob_sizes.lbs_file;
 }
 
+static inline struct backing_file_security_struct *
+selinux_backing_file(const struct file *backing_file)
+{
+	void *blob = backing_file_security(backing_file);
+	return blob + selinux_blob_sizes.lbs_backing_file;
+}
+
 static inline struct inode_security_struct *
 selinux_inode(const struct inode *inode)
 {

index 43555ad9e5dcf5..789cc0e3c10da9 100644
@@ -341,20 +341,15 @@ static void qcom_pcie_clear_aspm_l0s(struct dw_pcie *pci)
 	dw_pcie_dbi_ro_wr_dis(pci);
 }
 
-static void qcom_pcie_set_slot_nccs(struct dw_pcie *pci)
+static void qcom_pcie_clear_hpc(struct dw_pcie *pci)
 {
 	u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
 	u32 val;
 
 	dw_pcie_dbi_ro_wr_en(pci);
 
-	/*
-	 * Qcom PCIe Root Ports do not support generating command completion
-	 * notifications for the Hot-Plug commands. So set the NCCS field to
-	 * avoid waiting for the completions.
-	 */
 	val = readl(pci->dbi_base + offset + PCI_EXP_SLTCAP);
-	val |= PCI_EXP_SLTCAP_NCCS;
+	val &= ~PCI_EXP_SLTCAP_HPC;
 	writel(val, pci->dbi_base + offset + PCI_EXP_SLTCAP);
 
 	dw_pcie_dbi_ro_wr_dis(pci);

@@ -554,7 +549,7 @@ static int qcom_pcie_post_init_2_1_0(struct qcom_pcie *pcie)
 	writel(CFG_BRIDGE_SB_INIT,
 	       pci->dbi_base + AXI_MSTR_RESP_COMP_CTRL1);
 
-	qcom_pcie_set_slot_nccs(pcie->pci);
+	qcom_pcie_clear_hpc(pcie->pci);
 
 	return 0;
 }

@@ -634,7 +629,7 @@ static int qcom_pcie_post_init_1_0_0(struct qcom_pcie *pcie)
 		writel(val, pcie->parf + PARF_AXI_MSTR_WR_ADDR_HALT);
 	}
 
-	qcom_pcie_set_slot_nccs(pcie->pci);
+	qcom_pcie_clear_hpc(pcie->pci);
 
 	return 0;
 }

@@ -727,7 +722,7 @@ static int qcom_pcie_post_init_2_3_2(struct qcom_pcie *pcie)
 	val |= EN;
 	writel(val, pcie->parf + PARF_AXI_MSTR_WR_ADDR_HALT_V2);
 
-	qcom_pcie_set_slot_nccs(pcie->pci);
+	qcom_pcie_clear_hpc(pcie->pci);
 
 	return 0;
 }

@@ -1033,7 +1028,7 @@ static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie)
 		writel(WR_NO_SNOOP_OVERRIDE_EN | RD_NO_SNOOP_OVERRIDE_EN,
 				pcie->parf + PARF_NO_SNOOP_OVERRIDE);
 
-	qcom_pcie_set_slot_nccs(pcie->pci);
+	qcom_pcie_clear_hpc(pcie->pci);
 
 	return 0;
 }

index 4b6f18d977343d..75e020a8bfd072 100644
@@ -26,6 +26,8 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
 	struct nlm_host		*host = NULL;
 	struct nlm_file		*file = NULL;
 	struct nlm_lock		*lock = &argp->lock;
+	bool			is_test = (rqstp->rq_proc == NLMPROC_TEST ||
+					   rqstp->rq_proc == NLMPROC_TEST_MSG);
 	__be32			error = 0;
 
 	/* nfsd callbacks must have been installed for this procedure */

@@ -46,15 +48,20 @@ nlm4svc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
 	if (filp != NULL) {
 		int mode = lock_to_openmode(&lock->fl);
 
+		if (is_test)
+			mode = O_RDWR;
+
 		lock->fl.c.flc_flags = FL_POSIX;
 
-		error = nlm_lookup_file(rqstp, &file, lock);
+		error = nlm_lookup_file(rqstp, &file, lock, mode);
 		if (error)
 			goto no_locks;
 		*filp = file;
-
 		/* Set up the missing parts of the file_lock structure */
-		lock->fl.c.flc_file = file->f_file[mode];
+		if (is_test)
+			lock->fl.c.flc_file = nlmsvc_file_file(file);
+		else
+			lock->fl.c.flc_file = file->f_file[mode];
 		lock->fl.c.flc_pid = current->tgid;
 		lock->fl.fl_start = (loff_t)lock->lock_start;
 		lock->fl.fl_end = lock->lock_len ?

index d66e8285159996..c35ffa1b4b89d4 100644
@@ -611,7 +611,6 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 		struct nlm_lock *conflock)
 {
 	int			error;
-	int			mode;
 	__be32			ret;
 
 	dprintk("lockd: nlmsvc_testlock(%s/%ld, ty=%d, %Ld-%Ld)\n",

@@ -626,14 +625,13 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
 		goto out;
 	}
 
-	mode = lock_to_openmode(&lock->fl);
 	locks_init_lock(&conflock->fl);
 	/* vfs_test_lock only uses start, end, and owner, but tests flc_file */
 	conflock->fl.c.flc_file = lock->fl.c.flc_file;
 	conflock->fl.fl_start = lock->fl.fl_start;
 	conflock->fl.fl_end = lock->fl.fl_end;
 	conflock->fl.c.flc_owner = lock->fl.c.flc_owner;
-	error = vfs_test_lock(file->f_file[mode], &conflock->fl);
+	error = vfs_test_lock(lock->fl.c.flc_file, &conflock->fl);
 	if (error) {
 		/* We can't currently deal with deferred test requests */
 		if (error == FILE_LOCK_DEFERRED)

index 5817ef272332d9..d98e8d684376b7 100644
@@ -55,6 +55,8 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
 	struct nlm_host		*host = NULL;
 	struct nlm_file		*file = NULL;
 	struct nlm_lock		*lock = &argp->lock;
+	bool			is_test = (rqstp->rq_proc == NLMPROC_TEST ||
+					   rqstp->rq_proc == NLMPROC_TEST_MSG);
 	int			mode;
 	__be32			error = 0;
 

@@ -70,15 +72,22 @@ nlmsvc_retrieve_args(struct svc_rqst *rqstp, struct nlm_args *argp,
 
 	/* Obtain file pointer. Not used by FREE_ALL call. */
 	if (filp != NULL) {
-		error = cast_status(nlm_lookup_file(rqstp, &file, lock));
+		mode = lock_to_openmode(&lock->fl);
+
+		if (is_test)
+			mode = O_RDWR;
+
+		error = cast_status(nlm_lookup_file(rqstp, &file, lock, mode));
 		if (error != 0)
 			goto no_locks;
 		*filp = file;
 
 		/* Set up the missing parts of the file_lock structure */
-		mode = lock_to_openmode(&lock->fl);
 		lock->fl.c.flc_flags = FL_POSIX;
-		lock->fl.c.flc_file  = file->f_file[mode];
+		if (is_test)
+			lock->fl.c.flc_file = nlmsvc_file_file(file);
+		else
+			lock->fl.c.flc_file = file->f_file[mode];
 		lock->fl.c.flc_pid = current->tgid;
 		lock->fl.fl_lmops = &nlmsvc_lock_operations;
 		nlmsvc_locks_init_private(&lock->fl, host, (pid_t)lock->svid);

index 9103896164f688..7ea204eadfcace 100644
@@ -82,18 +82,35 @@ int lock_to_openmode(struct file_lock *lock)
  *
  * We have to make sure we have the right credential to open
  * the file.
+ *
+ * mode can be O_RDONLY(0), O_WRONLY(1) or O_RDWR(2). The latter
+ * means success can be achieved with EITHER O_RDONLY or O_WRONLY.
+ * It does NOT mean both read and write are required.
  */
 static __be32 nlm_do_fopen(struct svc_rqst *rqstp,
 			   struct nlm_file *file, int mode)
 {
-	struct file **fp = &file->f_file[mode];
-	__be32	nfserr;
+	__be32 nfserr = nlm_lck_denied_nolocks;
+	__be32 deferred = 0;
+	struct file **fp;
+	int m;
 
-	if (*fp)
-		return 0;
-	nfserr = nlmsvc_ops->fopen(rqstp, &file->f_handle, fp, mode);
-	if (nfserr)
-		dprintk("lockd: open failed (error %d)\n", nfserr);
+	for (m = O_RDONLY ; m <= O_WRONLY ; m++) {
+		if (mode != O_RDWR && mode != m)
+			continue;
+
+		fp = &file->f_file[m];
+		if (*fp)
+			return 0;
+		nfserr = nlmsvc_ops->fopen(rqstp, &file->f_handle, fp, m);
+		if (!nfserr)
+			return 0;
+		if (nfserr == nlm_drop_reply)
+			deferred = nfserr;
+	}
+	if (deferred)
+		return deferred;
+	dprintk("lockd: open failed (error %d)\n", ntohl(nfserr));
 	return nfserr;
 }
 

@@ -103,17 +120,15 @@ static __be32 nlm_do_fopen(struct svc_rqst *rqstp,
  */
 __be32
 nlm_lookup_file(struct svc_rqst *rqstp, struct nlm_file **result,
-					struct nlm_lock *lock)
+		struct nlm_lock *lock, int mode)
 {
 	struct nlm_file	*file;
 	unsigned int	hash;
 	__be32		nfserr;
-	int		mode;
 
 	nlm_debug_print_fh("nlm_lookup_file", &lock->fh);
 
 	hash = file_hash(&lock->fh);
-	mode = lock_to_openmode(&lock->fl);
 
 	/* Lock file table */
 	mutex_lock(&nlm_file_mutex);

index c8f0f9458f2cc0..d9930fc43ca540 100644
@@ -293,7 +293,7 @@ void		  nlmsvc_locks_init_private(struct file_lock *, struct nlm_host *, pid_t);
  * File handling for the server personality
  */
 __be32		  nlm_lookup_file(struct svc_rqst *, struct nlm_file **,
-					struct nlm_lock *);
+				  struct nlm_lock *, int);
 void		  nlm_release_file(struct nlm_file *);
 void		  nlmsvc_put_lockowner(struct nlm_lockowner *);
 void		  nlmsvc_release_lockowner(struct nlm_lock *);

index b1629e0ac82683..f222c5093b647e 100644
@@ -1325,7 +1325,7 @@ static bool batadv_tp_handle_out_of_order(struct batadv_tp_vars *tp_vars,
 		 * one is attached _after_ it. In this way the list is kept in
 		 * ascending order
 		 */
-		list_add_tail(&new->list, &un->list);
+		list_add(&new->list, &un->list);
 		added = true;
 		break;
 	}

index f222c5093b647e..fe9a447643074a 100644
@@ -1045,6 +1045,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst,
 	tp_vars->icmp_uid = icmp_uid;
 
 	tp_vars->last_sent = BATADV_TP_FIRST_SEQ;
+	atomic_set(&tp_vars->dup_acks, 0);
 	atomic_set(&tp_vars->last_acked, BATADV_TP_FIRST_SEQ);
 	tp_vars->fast_recovery = false;
 	tp_vars->recover = BATADV_TP_FIRST_SEQ;

index fe9a447643074a..473641d32dc683 100644
@@ -1055,6 +1055,8 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst,
 	 * mesh_interface, hence its MTU
 	 */
 	tp_vars->cwnd = BATADV_TP_PLEN * 3;
+	tp_vars->dec_cwnd = 0;
+
 	/* at the beginning initialise the SS threshold to the biggest possible
 	 * window size, hence the AWND size
 	 */

index 473641d32dc683..71a4352cd78c77 100644
@@ -817,10 +817,15 @@ static void batadv_tp_recv_ack(struct batadv_priv *bat_priv,
 static bool batadv_tp_avail(struct batadv_tp_vars *tp_vars,
 			    size_t payload_len)
 {
+	u32 last_sent = READ_ONCE(tp_vars->last_sent);
 	u32 win_left, win_limit;
 
 	win_limit = atomic_read(&tp_vars->last_acked) + tp_vars->cwnd;
-	win_left = win_limit - tp_vars->last_sent;
+
+	if (batadv_seq_before(last_sent, win_limit))
+		win_left = win_limit - last_sent;
+	else
+		win_left = 0;
 
 	return win_left >= payload_len;
 }

index 71a4352cd78c77..00d8bb01611f99 100644
@@ -154,9 +154,12 @@ static void batadv_tp_update_cwnd(struct batadv_tp_vars *tp_vars, u32 mss)
 		return;
 	}
 
+	/* prevent overflow in (mss * mss) << 3 */
+	mss = min_t(u32, mss, (1U << 14) - 1);
+
 	/* increment CWND at least of 1 (section 3.1 of RFC5681) */
 	tp_vars->dec_cwnd += max_t(u32, 1U << 3,
-				   ((mss * mss) << 6) / (tp_vars->cwnd << 3));
+				   ((mss * mss) << 3) / tp_vars->cwnd);
 	if (tp_vars->dec_cwnd < (mss << 3)) {
 		spin_unlock_bh(&tp_vars->cwnd_lock);
 		return;

index 00d8bb01611f99..a85622267ba655 100644
@@ -733,7 +733,7 @@ static void batadv_tp_recv_ack(struct batadv_priv *bat_priv,
 		if (atomic_read(&tp_vars->dup_acks) != 3)
 			goto out;
 
-		if (recv_ack >= tp_vars->recover)
+		if (tp_vars->recover >= recv_ack)
 			goto out;
 
 		/* if this is the third duplicate ACK do Fast Retransmit */

index a85622267ba655..0ebfc4462b8f17 100644
@@ -733,7 +733,7 @@ static void batadv_tp_recv_ack(struct batadv_priv *bat_priv,
 		if (atomic_read(&tp_vars->dup_acks) != 3)
 			goto out;
 
-		if (tp_vars->recover >= recv_ack)
+		if (!batadv_seq_before(tp_vars->recover, recv_ack))
 			goto out;
 
 		/* if this is the third duplicate ACK do Fast Retransmit */

index 0ebfc4462b8f17..0444aa46b95c29 100644
@@ -1096,21 +1096,21 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst,
 	tp_vars->prerandom_offset = 0;
 	spin_lock_init(&tp_vars->prerandom_lock);
 
-	kref_get(&tp_vars->refcount);
-	hlist_add_head_rcu(&tp_vars->list, &bat_priv->tp_list);
-	spin_unlock_bh(&bat_priv->tp_list_lock);
-
 	tp_vars->test_length = test_length;
 	if (!tp_vars->test_length)
 		tp_vars->test_length = BATADV_TP_DEF_TEST_LENGTH;
 
+	/* init work item for finished tp tests */
+	INIT_DELAYED_WORK(&tp_vars->finish_work, batadv_tp_sender_finish);
+
+	kref_get(&tp_vars->refcount);
+	hlist_add_head_rcu(&tp_vars->list, &bat_priv->tp_list);
+	spin_unlock_bh(&bat_priv->tp_list_lock);
+
 	batadv_dbg(BATADV_DBG_TP_METER, bat_priv,
 		   "Meter: starting throughput meter towards %pM (length=%ums)\n",
 		   dst, test_length);
 
-	/* init work item for finished tp tests */
-	INIT_DELAYED_WORK(&tp_vars->finish_work, batadv_tp_sender_finish);
-
 	/* start tp kthread. This way the write() call issued from userspace can
 	 * happily return and avoid to block
 	 */

@@ -1430,10 +1430,10 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv,
 	INIT_LIST_HEAD(&tp_vars->unacked_list);
 
 	kref_get(&tp_vars->refcount);
-	hlist_add_head_rcu(&tp_vars->list, &bat_priv->tp_list);
+	timer_setup(&tp_vars->timer, batadv_tp_receiver_shutdown, 0);
 
 	kref_get(&tp_vars->refcount);
-	timer_setup(&tp_vars->timer, batadv_tp_receiver_shutdown, 0);
+	hlist_add_head_rcu(&tp_vars->list, &bat_priv->tp_list);
 
 	batadv_tp_reset_receiver_timer(tp_vars);
 

index 3072f94275ac60..2c6e2b0d1ded48 100644
@@ -513,7 +513,7 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, const u8 *orig,
 		return NULL;
 
 	entry->vid = vid;
-	entry->lasttime = jiffies;
+	WRITE_ONCE(entry->lasttime, jiffies);
 	entry->crc = BATADV_BLA_CRC_INIT;
 	entry->bat_priv = bat_priv;
 	spin_lock_init(&entry->crc_lock);

@@ -581,7 +581,7 @@ batadv_bla_update_own_backbone_gw(struct batadv_priv *bat_priv,
 	if (unlikely(!backbone_gw))
 		return;
 
-	backbone_gw->lasttime = jiffies;
+	WRITE_ONCE(backbone_gw->lasttime, jiffies);
 	batadv_backbone_gw_put(backbone_gw);
 }
 

@@ -715,7 +715,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv,
 		ether_addr_copy(claim->addr, mac);
 		spin_lock_init(&claim->backbone_lock);
 		claim->vid = vid;
-		claim->lasttime = jiffies;
+		WRITE_ONCE(claim->lasttime, jiffies);
 		kref_get(&backbone_gw->refcount);
 		claim->backbone_gw = backbone_gw;
 		kref_init(&claim->refcount);

@@ -737,7 +737,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv,
 			return;
 		}
 	} else {
-		claim->lasttime = jiffies;
+		WRITE_ONCE(claim->lasttime, jiffies);
 		if (claim->backbone_gw == backbone_gw)
 			/* no need to register a new backbone */
 			goto claim_free_ref;

@@ -770,7 +770,7 @@ static void batadv_bla_add_claim(struct batadv_priv *bat_priv,
 	spin_lock_bh(&backbone_gw->crc_lock);
 	backbone_gw->crc ^= crc16(0, claim->addr, ETH_ALEN);
 	spin_unlock_bh(&backbone_gw->crc_lock);
-	backbone_gw->lasttime = jiffies;
+	WRITE_ONCE(backbone_gw->lasttime, jiffies);
 
 claim_free_ref:
 	batadv_claim_put(claim);

@@ -859,7 +859,7 @@ static bool batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr,
 		return true;
 
 	/* handle as ANNOUNCE frame */
-	backbone_gw->lasttime = jiffies;
+	WRITE_ONCE(backbone_gw->lasttime, jiffies);
 	crc = ntohs(*((__force __be16 *)(&an_addr[4])));
 
 	batadv_dbg(BATADV_DBG_BLA, bat_priv,

@@ -1254,7 +1254,7 @@ static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now)
 						  head, hash_entry) {
 				if (now)
 					goto purge_now;
-				if (!batadv_has_timed_out(backbone_gw->lasttime,
+				if (!batadv_has_timed_out(READ_ONCE(backbone_gw->lasttime),
 							  BATADV_BLA_BACKBONE_TIMEOUT))
 					continue;
 

@@ -1335,7 +1335,7 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv,
 						primary_if->net_dev->dev_addr))
 				goto skip;
 
-			if (!batadv_has_timed_out(claim->lasttime,
+			if (!batadv_has_timed_out(READ_ONCE(claim->lasttime),
 						  BATADV_BLA_CLAIM_TIMEOUT))
 				goto skip;
 

@@ -1495,7 +1495,7 @@ static void batadv_bla_periodic_work(struct work_struct *work)
 		eth_random_addr(bat_priv->bla.loopdetect_addr);
 		bat_priv->bla.loopdetect_addr[0] = 0xba;
 		bat_priv->bla.loopdetect_addr[1] = 0xbe;
-		bat_priv->bla.loopdetect_lasttime = jiffies;
+		WRITE_ONCE(bat_priv->bla.loopdetect_lasttime, jiffies);
 		atomic_set(&bat_priv->bla.loopdetect_next,
 			   BATADV_BLA_LOOPDETECT_PERIODS);
 

@@ -1516,7 +1516,7 @@ static void batadv_bla_periodic_work(struct work_struct *work)
 						primary_if->net_dev->dev_addr))
 				continue;
 
-			backbone_gw->lasttime = jiffies;
+			WRITE_ONCE(backbone_gw->lasttime, jiffies);
 
 			batadv_bla_send_announce(bat_priv, backbone_gw);
 			if (send_loopdetect)

@@ -1934,7 +1934,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb,
 	/* If the packet came too late, don't forward it on the mesh
 	 * but don't consider that as loop. It might be a coincidence.
 	 */
-	if (batadv_has_timed_out(bat_priv->bla.loopdetect_lasttime,
+	if (batadv_has_timed_out(READ_ONCE(bat_priv->bla.loopdetect_lasttime),
 				 BATADV_BLA_LOOPDETECT_TIMEOUT))
 		return true;
 

@@ -2049,7 +2049,7 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
 
 	if (own_claim) {
 		/* ... allow it in any case */
-		claim->lasttime = jiffies;
+		WRITE_ONCE(claim->lasttime, jiffies);
 		goto allow;
 	}
 

@@ -2151,7 +2151,7 @@ bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb,
 		/* if yes, the client has roamed and we have
 		 * to unclaim it.
 		 */
-		if (batadv_has_timed_out(claim->lasttime, 100)) {
+		if (batadv_has_timed_out(READ_ONCE(claim->lasttime), 100)) {
 			/* only unclaim if the last claim entry is
 			 * older than 100 ms to make sure we really
 			 * have a roaming client here.

@@ -2396,7 +2396,7 @@ batadv_bla_backbone_dump_entry(struct sk_buff *msg, u32 portid,
 	backbone_crc = backbone_gw->crc;
 	spin_unlock_bh(&backbone_gw->crc_lock);
 
-	msecs = jiffies_to_msecs(jiffies - backbone_gw->lasttime);
+	msecs = jiffies_to_msecs(jiffies - READ_ONCE(backbone_gw->lasttime));
 
 	if (is_own)
 		if (nla_put_flag(msg, BATADV_ATTR_BLA_OWN)) {

index 78c651f634cd39..1d144d8cc0928e 100644
@@ -917,9 +917,15 @@ static int batadv_netlink_set_hardif(struct sk_buff *skb,
 #ifdef CONFIG_BATMAN_ADV_BATMAN_V
 
 	if (info->attrs[BATADV_ATTR_ELP_INTERVAL]) {
+		u32 elp_interval;
+
 		attr = info->attrs[BATADV_ATTR_ELP_INTERVAL];
+		elp_interval = nla_get_u32(attr);
+
+		elp_interval = min_t(u32, elp_interval, INT_MAX);
+		elp_interval = max_t(u32, elp_interval, BATADV_JITTER);
 
-		atomic_set(&hard_iface->bat_v.elp_interval, nla_get_u32(attr));
+		atomic_set(&hard_iface->bat_v.elp_interval, elp_interval);
 	}
 
 	if (info->attrs[BATADV_ATTR_THROUGHPUT_OVERRIDE]) {

index 0444aa46b95c29..10b8daca3a6154 100644
@@ -1403,8 +1403,10 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv,
 
 	tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig,
 					      icmp->session, BATADV_TP_RECEIVER);
-	if (tp_vars)
+	if (tp_vars) {
+		tp_vars->last_recv_time = jiffies;
 		goto out_unlock;
+	}
 
 	if (!atomic_add_unless(&bat_priv->tp_num, 1, BATADV_TP_MAX_NUM)) {
 		batadv_dbg(BATADV_DBG_TP_METER, bat_priv,

@@ -1432,6 +1434,8 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv,
 	kref_get(&tp_vars->refcount);
 	timer_setup(&tp_vars->timer, batadv_tp_receiver_shutdown, 0);
 
+	tp_vars->last_recv_time = jiffies;
+
 	kref_get(&tp_vars->refcount);
 	hlist_add_head_rcu(&tp_vars->list, &bat_priv->tp_list);
 

@@ -1480,9 +1484,9 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv,
 				   icmp->orig);
 			goto out;
 		}
-	}
 
-	tp_vars->last_recv_time = jiffies;
+		tp_vars->last_recv_time = jiffies;
+	}
 
 	/* if the packet is a duplicate, it may be the case that an ACK has been
 	 * lost. Resend the ACK

index 1c488049d55463..39b1ed813497d2 100644
@@ -786,30 +786,6 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 	return ret;
 }
 
-/**
- * batadv_hardif_cnt() - get number of interfaces enslaved to mesh interface
- * @mesh_iface: mesh interface to check
- *
- * This function is only using RCU for locking - the result can therefore be
- * off when another function is modifying the list at the same time. The
- * caller can use the rtnl_lock to make sure that the count is accurate.
- *
- * Return: number of connected/enslaved hard interfaces
- */
-static size_t batadv_hardif_cnt(struct net_device *mesh_iface)
-{
-	struct batadv_hard_iface *hard_iface;
-	struct list_head *iter;
-	size_t count = 0;
-
-	rcu_read_lock();
-	netdev_for_each_lower_private_rcu(mesh_iface, hard_iface, iter)
-		count++;
-	rcu_read_unlock();
-
-	return count;
-}
-
 /**
  * batadv_hardif_disable_interface() - Remove hard interface from mesh interface
  * @hard_iface: hard interface to be removed

@@ -850,8 +826,8 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface)
 	netdev_upper_dev_unlink(hard_iface->net_dev, hard_iface->mesh_iface);
 	batadv_hardif_recalc_extra_skbroom(hard_iface->mesh_iface);
 
-	/* nobody uses this interface anymore */
-	if (batadv_hardif_cnt(hard_iface->mesh_iface) <= 1)
+	/* nobody uses this mesh interface anymore */
+	if (list_empty(&hard_iface->mesh_iface->adj_list.lower))
 		batadv_gw_check_client_stop(bat_priv);
 
 	hard_iface->mesh_iface = NULL;

index 12c16f81cc51df..0672dc30bed3b1 100644
@@ -1191,6 +1191,12 @@ int batadv_recv_bcast_packet(struct sk_buff *skb,
 	if (batadv_is_my_mac(bat_priv, bcast_packet->orig))
 		goto free_skb;
 
+	/* create a copy of the skb, if needed, to modify it. */
+	if (skb_cow(skb, ETH_HLEN) < 0)
+		goto free_skb;
+
+	bcast_packet = (struct batadv_bcast_packet *)skb->data;
+
 	if (bcast_packet->ttl-- < 2)
 		goto free_skb;
 

index 0672dc30bed3b1..cdcea90db61235 100644
@@ -8,6 +8,7 @@
 #include "main.h"
 
 #include <linux/atomic.h>
+#include <linux/build_bug.h>
 #include <linux/byteorder/generic.h>
 #include <linux/compiler.h>
 #include <linux/errno.h>

@@ -204,6 +205,59 @@ bool batadv_check_management_packet(struct sk_buff *skb,
 	return true;
 }
 
+/**
+ * batadv_skb_decrement_ttl() - decrement ttl in a batman-adv header, csum-safe
+ * @skb: the received packet with @skb->data pointing to the batman-adv header
+ *
+ * Supports the following packet types, all of which carry the TTL at offset 2:
+ *
+ * - batadv_ogm_packet
+ * - batadv_ogm2_packet
+ * - batadv_icmp_header
+ * - batadv_icmp_packet
+ * - batadv_icmp_tp_packet
+ * - batadv_icmp_packet_rr
+ * - batadv_unicast_packet
+ * - batadv_frag_packet
+ * - batadv_bcast_packet
+ * - batadv_mcast_packet
+ * - batadv_coded_packet
+ * - batadv_unicast_tvlv_packet
+ *
+ * Return: true if the packet may be forwarded (ttl decremented),
+ *  false if it must be dropped (ttl would expire)
+ */
+static bool batadv_skb_decrement_ttl(struct sk_buff *skb)
+{
+	static const size_t ttl_offset = 2;
+	u8 *ttl_pos;
+
+	BUILD_BUG_ON(offsetof(struct batadv_ogm_packet, ttl) != ttl_offset);
+	BUILD_BUG_ON(offsetof(struct batadv_ogm2_packet, ttl) != ttl_offset);
+	BUILD_BUG_ON(offsetof(struct batadv_icmp_header, ttl) != ttl_offset);
+	BUILD_BUG_ON(offsetof(struct batadv_icmp_packet, ttl) != ttl_offset);
+	BUILD_BUG_ON(offsetof(struct batadv_icmp_tp_packet, ttl) != ttl_offset);
+	BUILD_BUG_ON(offsetof(struct batadv_icmp_packet_rr, ttl) != ttl_offset);
+	BUILD_BUG_ON(offsetof(struct batadv_unicast_packet, ttl) != ttl_offset);
+	BUILD_BUG_ON(offsetof(struct batadv_frag_packet, ttl) != ttl_offset);
+	BUILD_BUG_ON(offsetof(struct batadv_bcast_packet, ttl) != ttl_offset);
+	BUILD_BUG_ON(offsetof(struct batadv_mcast_packet, ttl) != ttl_offset);
+	BUILD_BUG_ON(offsetof(struct batadv_coded_packet, ttl) != ttl_offset);
+	BUILD_BUG_ON(offsetof(struct batadv_unicast_tvlv_packet, ttl) != ttl_offset);
+
+	ttl_pos = skb->data + ttl_offset;
+
+	/* would expire on this hop -> drop, leave header + csum untouched */
+	if (*ttl_pos < 2)
+		return false;
+
+	skb_postpull_rcsum(skb, ttl_pos, 1);
+	(*ttl_pos)--;
+	skb_postpush_rcsum(skb, ttl_pos, 1);
+
+	return true;
+}
+
 /**
  * batadv_recv_my_icmp_packet() - receive an icmp packet locally
  * @bat_priv: the bat priv with all the mesh interface information

@@ -1197,7 +1251,7 @@ int batadv_recv_bcast_packet(struct sk_buff *skb,
 
 	bcast_packet = (struct batadv_bcast_packet *)skb->data;
 
-	if (bcast_packet->ttl-- < 2)
+	if (!batadv_skb_decrement_ttl(skb))
 		goto free_skb;
 
 	orig_node = batadv_orig_hash_find(bat_priv, bcast_packet->orig);

@@ -1304,7 +1358,7 @@ int batadv_recv_mcast_packet(struct sk_buff *skb,
 		goto free_skb;
 
 	mcast_packet = (struct batadv_mcast_packet *)skb->data;
-	if (mcast_packet->ttl-- < 2)
+	if (!batadv_skb_decrement_ttl(skb))
 		goto free_skb;
 
 	tvlv_buff = (unsigned char *)(skb->data + hdr_size);

index 31395281692cb5..ffa5d4b0740959 100644
@@ -384,6 +384,8 @@ bool batadv_frag_skb_buffer(struct sk_buff **skb,
  * @skb: skb to forward
  * @recv_if: interface that the skb is received on
  * @orig_node_src: originator that the skb is received from
+ * @rx_result: set to NET_RX_SUCCESS when the fragment was forwarded and
+ *  NET_RX_DROP when it was dropped; only valid when true is returned
  *
  * Look up the next-hop of the fragments payload and check if the merged packet
  * will exceed the MTU towards the next-hop. If so, the fragment is forwarded

@@ -393,7 +395,8 @@ bool batadv_frag_skb_buffer(struct sk_buff **skb,
  */
 bool batadv_frag_skb_fwd(struct sk_buff *skb,
 			 struct batadv_hard_iface *recv_if,
-			 struct batadv_orig_node *orig_node_src)
+			 struct batadv_orig_node *orig_node_src,
+			 int *rx_result)
 {
 	struct batadv_priv *bat_priv = netdev_priv(recv_if->mesh_iface);
 	struct batadv_neigh_node *neigh_node = NULL;

@@ -412,12 +415,22 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb,
 	 */
 	total_size = ntohs(packet->total_size);
 	if (total_size > neigh_node->if_incoming->net_dev->mtu) {
+		if (skb_cow(skb, ETH_HLEN) < 0) {
+			kfree_skb(skb);
+			*rx_result = NET_RX_DROP;
+			ret = true;
+			goto out;
+		}
+
+		packet = (struct batadv_frag_packet *)skb->data;
+
 		batadv_inc_counter(bat_priv, BATADV_CNT_FRAG_FWD);
 		batadv_add_counter(bat_priv, BATADV_CNT_FRAG_FWD_BYTES,
 				   skb->len + ETH_HLEN);
 
 		packet->ttl--;
 		batadv_send_unicast_skb(skb, neigh_node);
+		*rx_result = NET_RX_SUCCESS;
 		ret = true;
 	}
 

index dbf0871f870303..51e281027ab630 100644
@@ -19,7 +19,8 @@ void batadv_frag_purge_orig(struct batadv_orig_node *orig,
 			    bool (*check_cb)(struct batadv_frag_table_entry *));
 bool batadv_frag_skb_fwd(struct sk_buff *skb,
 			 struct batadv_hard_iface *recv_if,
-			 struct batadv_orig_node *orig_node_src);
+			 struct batadv_orig_node *orig_node_src,
+			 int *rx_result);
 bool batadv_frag_skb_buffer(struct sk_buff **skb,
 			    struct batadv_orig_node *orig_node);
 int batadv_frag_send_packet(struct sk_buff *skb,

index cdcea90db61235..4483f8d9c75831 100644
@@ -1168,10 +1168,9 @@ int batadv_recv_frag_packet(struct sk_buff *skb,
 
 	/* Route the fragment if it is not for us and too big to be merged. */
 	if (!batadv_is_my_mac(bat_priv, frag_packet->dest) &&
-	    batadv_frag_skb_fwd(skb, recv_if, orig_node_src)) {
+	    batadv_frag_skb_fwd(skb, recv_if, orig_node_src, &ret)) {
 		/* skb was consumed */
 		skb = NULL;
-		ret = NET_RX_SUCCESS;
 		goto put_orig_node;
 	}
 

index ffa5d4b0740959..4779741e7273ea 100644
@@ -415,6 +415,13 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb,
 	 */
 	total_size = ntohs(packet->total_size);
 	if (total_size > neigh_node->if_incoming->net_dev->mtu) {
+		if (packet->ttl < 2) {
+			kfree_skb(skb);
+			*rx_result = NET_RX_DROP;
+			ret = true;
+			goto out;
+		}
+
 		if (skb_cow(skb, ETH_HLEN) < 0) {
 			kfree_skb(skb);
 			*rx_result = NET_RX_DROP;

index de94447142642e..17d2a1ccdce67a 100644
@@ -817,6 +817,7 @@ void batadv_v_hardif_init(struct batadv_hard_iface *hard_iface)
 
 	hard_iface->bat_v.aggr_len = 0;
 	skb_queue_head_init(&hard_iface->bat_v.aggr_list);
+	hard_iface->bat_v.aggr_list_enabled = false;
 	INIT_DELAYED_WORK(&hard_iface->bat_v.aggr_wq,
 			  batadv_v_ogm_aggr_work);
 }

index d66ca77b1aaa3c..6852bf5da8c558 100644
@@ -252,11 +252,18 @@ static void batadv_v_ogm_queue_on_if(struct batadv_priv *bat_priv,
 	}
 
 	spin_lock_bh(&hard_iface->bat_v.aggr_list.lock);
+	if (!hard_iface->bat_v.aggr_list_enabled) {
+		kfree_skb(skb);
+		goto unlock;
+	}
+
 	if (!batadv_v_ogm_queue_left(skb, hard_iface))
 		batadv_v_ogm_aggr_send(bat_priv, hard_iface);
 
 	hard_iface->bat_v.aggr_len += batadv_v_ogm_len(skb);
 	__skb_queue_tail(&hard_iface->bat_v.aggr_list, skb);
+
+unlock:
 	spin_unlock_bh(&hard_iface->bat_v.aggr_list.lock);
 }
 

@@ -417,6 +424,10 @@ int batadv_v_ogm_iface_enable(struct batadv_hard_iface *hard_iface)
 {
 	struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface);
 
+	spin_lock_bh(&hard_iface->bat_v.aggr_list.lock);
+	hard_iface->bat_v.aggr_list_enabled = true;
+	spin_unlock_bh(&hard_iface->bat_v.aggr_list.lock);
+
 	batadv_v_ogm_start_queue_timer(hard_iface);
 	batadv_v_ogm_start_timer(bat_priv);
 

@@ -432,6 +443,7 @@ void batadv_v_ogm_iface_disable(struct batadv_hard_iface *hard_iface)
 	cancel_delayed_work_sync(&hard_iface->bat_v.aggr_wq);
 
 	spin_lock_bh(&hard_iface->bat_v.aggr_list.lock);
+	hard_iface->bat_v.aggr_list_enabled = false;
 	batadv_v_ogm_aggr_list_free(hard_iface);
 	spin_unlock_bh(&hard_iface->bat_v.aggr_list.lock);
 }

index c9bd49d23547ef..417d653021c7af 100644
@@ -130,6 +130,12 @@ struct batadv_hard_iface_bat_v {
 	/** @aggr_list: queue for to be aggregated OGM packets */
 	struct sk_buff_head aggr_list;
 
+	/**
+	 * @aggr_list_enabled: aggr_list is active and new skbs can be
+	 * enqueued. Protected by aggr_list.lock after initialization
+	 */
+	bool aggr_list_enabled:1;
+
 	/** @aggr_len: size of the OGM aggregate (excluding ethernet header) */
 	unsigned int aggr_len;
 

index 10b8daca3a6154..e5387e8f33244a 100644
@@ -87,6 +87,11 @@
 #define BATADV_TP_PLEN (BATADV_TP_PACKET_LEN - ETH_HLEN - \
 			sizeof(struct batadv_unicast_packet))
 
+/**
+ * BATADV_TP_MAX_UNACKED - maximum number of packets a receiver didn't yet ack
+ */
+#define BATADV_TP_MAX_UNACKED 100
+
 static u8 batadv_tp_prerandom[4096] __read_mostly;
 
 /**

@@ -1195,6 +1200,7 @@ static void batadv_tp_receiver_shutdown(struct timer_list *t)
 	list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) {
 		list_del(&un->list);
 		kfree(un);
+		tp_vars->unacked_count--;
 	}
 	spin_unlock_bh(&tp_vars->unacked_lock);
 

@@ -1308,6 +1314,7 @@ static bool batadv_tp_handle_out_of_order(struct batadv_tp_vars *tp_vars,
 	/* if the list is empty immediately attach this new object */
 	if (list_empty(&tp_vars->unacked_list)) {
 		list_add(&new->list, &tp_vars->unacked_list);
+		tp_vars->unacked_count++;
 		goto out;
 	}
 

@@ -1338,12 +1345,24 @@ static bool batadv_tp_handle_out_of_order(struct batadv_tp_vars *tp_vars,
 		 */
 		list_add(&new->list, &un->list);
 		added = true;
+		tp_vars->unacked_count++;
 		break;
 	}
 
 	/* received packet with smallest seqno out of order; add it to front */
-	if (!added)
+	if (!added) {
 		list_add(&new->list, &tp_vars->unacked_list);
+		tp_vars->unacked_count++;
+	}
+
+	/* remove the last (biggest) unacked seqno when list is too large */
+	if (tp_vars->unacked_count > BATADV_TP_MAX_UNACKED) {
+		un = list_last_entry(&tp_vars->unacked_list,
+				     struct batadv_tp_unacked, list);
+		list_del(&un->list);
+		kfree(un);
+		tp_vars->unacked_count--;
+	}
 
 out:
 	spin_unlock_bh(&tp_vars->unacked_lock);

@@ -1380,6 +1399,7 @@ static void batadv_tp_ack_unordered(struct batadv_tp_vars *tp_vars)
 
 		list_del(&un->list);
 		kfree(un);
+		tp_vars->unacked_count--;
 	}
 	spin_unlock_bh(&tp_vars->unacked_lock);
 }

@@ -1430,6 +1450,7 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv,
 
 	spin_lock_init(&tp_vars->unacked_lock);
 	INIT_LIST_HEAD(&tp_vars->unacked_list);
+	tp_vars->unacked_count = 0;
 
 	kref_get(&tp_vars->refcount);
 	timer_setup(&tp_vars->timer, batadv_tp_receiver_shutdown, 0);

index 417d653021c7af..8b180d8245b2a6 100644
@@ -1426,6 +1426,9 @@ struct batadv_tp_vars {
 	/** @unacked_lock: protect unacked_list */
 	spinlock_t unacked_lock;
 
+	/** @unacked_count: number of unacked entries */
+	size_t unacked_count;
+
 	/** @last_recv_time: time (jiffies) a msg was received */
 	unsigned long last_recv_time;
 

index e5387e8f33244a..e69bf10e66ac33 100644
@@ -1183,7 +1183,7 @@ static void batadv_tp_receiver_shutdown(struct timer_list *t)
 	bat_priv = tp_vars->bat_priv;
 
 	/* if there is recent activity rearm the timer */
-	if (!batadv_has_timed_out(tp_vars->last_recv_time,
+	if (!batadv_has_timed_out(READ_ONCE(tp_vars->last_recv_time),
 				  BATADV_TP_RECV_TIMEOUT)) {
 		/* reset the receiver shutdown timer */
 		batadv_tp_reset_receiver_timer(tp_vars);

@@ -1424,7 +1424,7 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv,
 	tp_vars = batadv_tp_list_find_session(bat_priv, icmp->orig,
 					      icmp->session, BATADV_TP_RECEIVER);
 	if (tp_vars) {
-		tp_vars->last_recv_time = jiffies;
+		WRITE_ONCE(tp_vars->last_recv_time, jiffies);
 		goto out_unlock;
 	}
 

@@ -1455,7 +1455,7 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv,
 	kref_get(&tp_vars->refcount);
 	timer_setup(&tp_vars->timer, batadv_tp_receiver_shutdown, 0);
 
-	tp_vars->last_recv_time = jiffies;
+	WRITE_ONCE(tp_vars->last_recv_time, jiffies);
 
 	kref_get(&tp_vars->refcount);
 	hlist_add_head_rcu(&tp_vars->list, &bat_priv->tp_list);

@@ -1506,7 +1506,7 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv,
 			goto out;
 		}
 
-		tp_vars->last_recv_time = jiffies;
+		WRITE_ONCE(tp_vars->last_recv_time, jiffies);
 	}
 
 	/* if the packet is a duplicate, it may be the case that an ACK has been

index e69bf10e66ac33..629831ea9a58e5 100644
@@ -1294,6 +1294,7 @@ static int batadv_tp_send_ack(struct batadv_priv *bat_priv, const u8 *dst,
  */
 static bool batadv_tp_handle_out_of_order(struct batadv_tp_vars *tp_vars,
 					  const struct sk_buff *skb)
+	__must_hold(&tp_vars->unacked_lock)
 {
 	const struct batadv_icmp_tp_packet *icmp;
 	struct batadv_tp_unacked *un, *new;

@@ -1310,12 +1311,11 @@ static bool batadv_tp_handle_out_of_order(struct batadv_tp_vars *tp_vars,
 	payload_len = skb->len - sizeof(struct batadv_unicast_packet);
 	new->len = payload_len;
 
-	spin_lock_bh(&tp_vars->unacked_lock);
 	/* if the list is empty immediately attach this new object */
 	if (list_empty(&tp_vars->unacked_list)) {
 		list_add(&new->list, &tp_vars->unacked_list);
 		tp_vars->unacked_count++;
-		goto out;
+		return true;
 	}
 
 	/* otherwise loop over the list and either drop the packet because this

@@ -1364,9 +1364,6 @@ static bool batadv_tp_handle_out_of_order(struct batadv_tp_vars *tp_vars,
 		tp_vars->unacked_count--;
 	}
 
-out:
-	spin_unlock_bh(&tp_vars->unacked_lock);
-
 	return true;
 }
 

@@ -1376,6 +1373,7 @@ static bool batadv_tp_handle_out_of_order(struct batadv_tp_vars *tp_vars,
  * @tp_vars: the private data of the current TP meter session
  */
 static void batadv_tp_ack_unordered(struct batadv_tp_vars *tp_vars)
+	__must_hold(&tp_vars->unacked_lock)
 {
 	struct batadv_tp_unacked *un, *safe;
 	u32 to_ack;

@@ -1383,7 +1381,6 @@ static void batadv_tp_ack_unordered(struct batadv_tp_vars *tp_vars)
 	/* go through the unacked packet list and possibly ACK them as
 	 * well
 	 */
-	spin_lock_bh(&tp_vars->unacked_lock);
 	list_for_each_entry_safe(un, safe, &tp_vars->unacked_list, list) {
 		/* the list is ordered, therefore it is possible to stop as soon
 		 * there is a gap between the last acked seqno and the seqno of

@@ -1401,7 +1398,6 @@ static void batadv_tp_ack_unordered(struct batadv_tp_vars *tp_vars)
 		kfree(un);
 		tp_vars->unacked_count--;
 	}
-	spin_unlock_bh(&tp_vars->unacked_lock);
 }
 
 /**

@@ -1481,6 +1477,7 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv,
 	const struct batadv_icmp_tp_packet *icmp;
 	struct batadv_tp_vars *tp_vars;
 	size_t packet_size;
+	u32 to_ack;
 	u32 seqno;
 
 	icmp = (struct batadv_icmp_tp_packet *)skb->data;

@@ -1509,6 +1506,8 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv,
 		WRITE_ONCE(tp_vars->last_recv_time, jiffies);
 	}
 
+	spin_lock_bh(&tp_vars->unacked_lock);
+
 	/* if the packet is a duplicate, it may be the case that an ACK has been
 	 * lost. Resend the ACK
 	 */

@@ -1520,8 +1519,10 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv,
 		/* exit immediately (and do not send any ACK) if the packet has
 		 * not been enqueued correctly
 		 */
-		if (!batadv_tp_handle_out_of_order(tp_vars, skb))
+		if (!batadv_tp_handle_out_of_order(tp_vars, skb)) {
+			spin_unlock_bh(&tp_vars->unacked_lock);
 			goto out;
+		}
 
 		/* send a duplicate ACK */
 		goto send_ack;

@@ -1535,11 +1536,14 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv,
 	batadv_tp_ack_unordered(tp_vars);
 
 send_ack:
+	to_ack = tp_vars->last_recv;
+	spin_unlock_bh(&tp_vars->unacked_lock);
+
 	/* send the ACK. If the received packet was out of order, the ACK that
 	 * is going to be sent is a duplicate (the sender will count them and
 	 * possibly enter Fast Retransmit as soon as it has reached 3)
 	 */
-	batadv_tp_send_ack(bat_priv, icmp->orig, tp_vars->last_recv,
+	batadv_tp_send_ack(bat_priv, icmp->orig, to_ack,
 			   icmp->timestamp, icmp->session, icmp->uid);
 out:
 	batadv_tp_vars_put(tp_vars);

index 8b180d8245b2a6..84de2570eac3ed 100644
@@ -1423,7 +1423,7 @@ struct batadv_tp_vars {
 	/** @unacked_list: list of unacked packets (meta-info only) */
 	struct list_head unacked_list;
 
-	/** @unacked_lock: protect unacked_list */
+	/** @unacked_lock: protect unacked_list + &batadv_tp_receiver.last_recv */
 	spinlock_t unacked_lock;
 
 	/** @unacked_count: number of unacked entries */

index 629831ea9a58e5..02af19aaaff291 100644
@@ -1284,7 +1284,8 @@ static int batadv_tp_send_ack(struct batadv_priv *bat_priv, const u8 *dst,
 /**
  * batadv_tp_handle_out_of_order() - store an out of order packet
  * @tp_vars: the private data of the current TP meter session
- * @skb: the buffer containing the received packet
+ * @seqno: sequence number of new received packet
+ * @payload_len: length of the received packet
  *
  * Store the out of order packet in the unacked list for late processing. This
  * packets are kept in this list so that they can be ACKed at once as soon as

@@ -1293,22 +1294,17 @@ static int batadv_tp_send_ack(struct batadv_priv *bat_priv, const u8 *dst,
  * Return: true if the packed has been successfully processed, false otherwise
  */
 static bool batadv_tp_handle_out_of_order(struct batadv_tp_vars *tp_vars,
-					  const struct sk_buff *skb)
+					  u32 seqno, u32 payload_len)
 	__must_hold(&tp_vars->unacked_lock)
 {
-	const struct batadv_icmp_tp_packet *icmp;
 	struct batadv_tp_unacked *un, *new;
-	u32 payload_len;
 	bool added = false;
 
 	new = kmalloc(sizeof(*new), GFP_ATOMIC);
 	if (unlikely(!new))
 		return false;
 
-	icmp = (struct batadv_icmp_tp_packet *)skb->data;
-
-	new->seqno = ntohl(icmp->seqno);
-	payload_len = skb->len - sizeof(struct batadv_unicast_packet);
+	new->seqno = seqno;
 	new->len = payload_len;
 
 	/* if the list is empty immediately attach this new object */

@@ -1476,7 +1472,7 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv,
 {
 	const struct batadv_icmp_tp_packet *icmp;
 	struct batadv_tp_vars *tp_vars;
-	size_t packet_size;
+	u32 payload_len;
 	u32 to_ack;
 	u32 seqno;
 

@@ -1511,15 +1507,17 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv,
 	/* if the packet is a duplicate, it may be the case that an ACK has been
 	 * lost. Resend the ACK
 	 */
-	if (batadv_seq_before(seqno, tp_vars->last_recv))
+	payload_len = skb->len - sizeof(struct batadv_unicast_packet);
+	to_ack = seqno + payload_len;
+	if (batadv_seq_before(to_ack, tp_vars->last_recv))
 		goto send_ack;
 
 	/* if the packet is out of order enqueue it */
-	if (ntohl(icmp->seqno) != tp_vars->last_recv) {
+	if (batadv_seq_before(tp_vars->last_recv, seqno)) {
 		/* exit immediately (and do not send any ACK) if the packet has
 		 * not been enqueued correctly
 		 */
-		if (!batadv_tp_handle_out_of_order(tp_vars, skb)) {
+		if (!batadv_tp_handle_out_of_order(tp_vars, seqno, payload_len)) {
 			spin_unlock_bh(&tp_vars->unacked_lock);
 			goto out;
 		}

@@ -1529,8 +1527,7 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv,
 	}
 
 	/* if everything was fine count the ACKed bytes */
-	packet_size = skb->len - sizeof(struct batadv_unicast_packet);
-	tp_vars->last_recv += packet_size;
+	tp_vars->last_recv = to_ack;
 
 	/* check if this ordered message filled a gap.... */
 	batadv_tp_ack_unordered(tp_vars);

index 9f6e67771ffa80..acd8af4446671f 100644
@@ -446,6 +446,9 @@ static void batadv_tt_local_event(struct batadv_priv *bat_priv,
 		if (!batadv_compare_eth(entry->change.addr, common->addr))
 			continue;
 
+		if (entry->change.vid != tt_change_node->change.vid)
+			continue;
+
 		del_op_entry = entry->change.flags & BATADV_TT_CLIENT_DEL;
 		if (del_op_requested != del_op_entry) {
 			/* DEL+ADD in the same orig interval have no effect and

index acd8af4446671f..83dfd804a143ab 100644
@@ -3442,6 +3442,7 @@ static void batadv_tt_roam_purge(struct batadv_priv *bat_priv)
  * batadv_tt_check_roam_count() - check if a client has roamed too frequently
  * @bat_priv: the bat priv with all the mesh interface information
  * @client: mac address of the roaming client
+ * @vid: VLAN identifier
  *
  * This function checks whether the client already reached the
  * maximum number of possible roaming phases. In this case the ROAMING_ADV

@@ -3449,7 +3450,7 @@ static void batadv_tt_roam_purge(struct batadv_priv *bat_priv)
  *
  * Return: true if the ROAMING_ADV can be sent, false otherwise
  */
-static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, u8 *client)
+static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, u8 *client, u16 vid)
 {
 	struct batadv_tt_roam_node *tt_roam_node;
 	bool ret = false;

@@ -3462,6 +3463,9 @@ static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, u8 *client)
 		if (!batadv_compare_eth(tt_roam_node->addr, client))
 			continue;
 
+		if (tt_roam_node->vid != vid)
+			continue;
+
 		if (batadv_has_timed_out(tt_roam_node->first_time,
 					 BATADV_ROAMING_MAX_TIME))
 			continue;

@@ -3483,6 +3487,7 @@ static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, u8 *client)
 		atomic_set(&tt_roam_node->counter,
 			   BATADV_ROAMING_MAX_COUNT - 1);
 		ether_addr_copy(tt_roam_node->addr, client);
+		tt_roam_node->vid = vid;
 
 		list_add(&tt_roam_node->list, &bat_priv->tt.roam_list);
 		ret = true;

@@ -3519,7 +3524,7 @@ static void batadv_send_roam_adv(struct batadv_priv *bat_priv, u8 *client,
 	/* before going on we have to check whether the client has
 	 * already roamed to us too many times
 	 */
-	if (!batadv_tt_check_roam_count(bat_priv, client))
+	if (!batadv_tt_check_roam_count(bat_priv, client, vid))
 		goto out;
 
 	batadv_dbg(BATADV_DBG_TT, bat_priv,

index 84de2570eac3ed..ef712ba4fff2cb 100644
@@ -1912,6 +1912,9 @@ struct batadv_tt_roam_node {
 	/** @addr: mac address of the client in the roaming phase */
 	u8 addr[ETH_ALEN];
 
+	/** @vid: VLAN identifier */
+	u16 vid;
+
 	/**
 	 * @counter: number of allowed roaming events per client within a single
 	 * OGM interval (changes are committed with each OGM)

index 031c295fff1b1d..860db505e8697f 100644
@@ -214,10 +214,13 @@ static void batadv_dat_purge(struct work_struct *work)
  */
 static bool batadv_compare_dat(const struct hlist_node *node, const void *data2)
 {
-	const void *data1 = container_of(node, struct batadv_dat_entry,
-					 hash_entry);
+	const struct batadv_dat_entry *entry1;
+	const struct batadv_dat_entry *entry2;
 
-	return memcmp(data1, data2, sizeof(__be32)) == 0;
+	entry1 = container_of(node, struct batadv_dat_entry, hash_entry);
+	entry2 = data2;
+
+	return entry1->ip == entry2->ip && entry1->vid == entry2->vid;
 }
 
 /**

@@ -344,6 +347,9 @@ batadv_dat_entry_hash_find(struct batadv_priv *bat_priv, __be32 ip,
 		if (dat_entry->ip != ip)
 			continue;
 
+		if (dat_entry->vid != vid)
+			continue;
+
 		if (!kref_get_unless_zero(&dat_entry->refcount))
 			continue;
 

index b8b1b997960a96..6e79f69c2fedec 100644
@@ -311,14 +311,23 @@ batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len,
 			  const struct batadv_ogm_packet *ogm_packet)
 {
 	int next_buff_pos = 0;
+	u16 tvlv_len;
 
 	/* check if there is enough space for the header */
 	next_buff_pos += buff_pos + sizeof(*ogm_packet);
 	if (next_buff_pos > packet_len)
 		return false;
 
+	tvlv_len = ntohs(ogm_packet->tvlv_len);
+
+	/* the fields of an aggregated OGM are accessed assuming (at least)
+	 * 2-byte alignment, so a following OGM must start at an even offset.
+	 */
+	if (tvlv_len & 1)
+		return false;
+
 	/* check if there is enough space for the optional TVLV */
-	next_buff_pos += ntohs(ogm_packet->tvlv_len);
+	next_buff_pos += tvlv_len;
 
 	return next_buff_pos <= packet_len;
 }

index 6852bf5da8c558..1f9b2d2b4831ce 100644
@@ -849,14 +849,23 @@ batadv_v_ogm_aggr_packet(int buff_pos, int packet_len,
 			 const struct batadv_ogm2_packet *ogm2_packet)
 {
 	int next_buff_pos = 0;
+	u16 tvlv_len;
 
 	/* check if there is enough space for the header */
 	next_buff_pos += buff_pos + sizeof(*ogm2_packet);
 	if (next_buff_pos > packet_len)
 		return false;
 
+	tvlv_len = ntohs(ogm2_packet->tvlv_len);
+
+	/* the fields of an aggregated OGMv2 are accessed assuming (at least)
+	 * 2-byte alignment, so a following OGMv2 must start at an even offset.
+	 */
+	if (tvlv_len & 1)
+		return false;
+
 	/* check if there is enough space for the optional TVLV */
-	next_buff_pos += ntohs(ogm2_packet->tvlv_len);
+	next_buff_pos += tvlv_len;
 
 	return next_buff_pos <= packet_len;
 }

index 4483f8d9c75831..41951c7a1c50b2 100644
@@ -1366,6 +1366,12 @@ int batadv_recv_mcast_packet(struct sk_buff *skb,
 	if (tvlv_buff_len > skb->len - hdr_size)
 		goto free_skb;
 
+	/* the fields of an multicast payload are accessed assuming (at least)
+	 * 2-byte alignment, so a following packet must start at an even offset.
+	 */
+	if (tvlv_buff_len & 1)
+		goto free_skb;
+
 	ret = batadv_tvlv_containers_process(bat_priv, BATADV_MCAST, NULL, skb,
 					     tvlv_buff, tvlv_buff_len);
 	if (ret >= 0) {

index cde798c82dcf13..63fb54024d1543 100644
@@ -464,6 +464,12 @@ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv,
 		if (tvlv_value_cont_len > tvlv_value_len)
 			break;
 
+		/* the next tvlv header is accessed assuming (at least) 2-byte
+		 * alignment, so it must start at an even offset.
+		 */
+		if (tvlv_value_cont_len & 1)
+			break;
+
 		tvlv_handler = batadv_tvlv_handler_get(bat_priv,
 						       tvlv_hdr->type,
 						       tvlv_hdr->version);

index 63fb54024d1543..a91f1891747c0a 100644
@@ -398,7 +398,6 @@ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv,
 		tvlv_handler->ogm_handler(bat_priv, orig_node,
 					  BATADV_NO_FLAGS,
 					  tvlv_value, tvlv_value_len);
-		tvlv_handler->flags |= BATADV_TVLV_HANDLER_OGM_CALLED;
 		break;
 	case BATADV_UNICAST_TVLV:
 		if (!skb)

@@ -430,6 +429,48 @@ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv,
 	return NET_RX_SUCCESS;
 }
 
+/**
+ * batadv_tvlv_containers_contain() - check if a tvlv buffer holds a container
+ * @tvlv_value: tvlv content
+ * @tvlv_value_len: tvlv content length
+ * @type: tvlv container type to look for
+ * @version: tvlv container version to look for
+ *
+ * Return: true if a container of the given type and version is present in the
+ * tvlv buffer, false otherwise.
+ */
+static bool batadv_tvlv_containers_contain(void *tvlv_value,
+					   u16 tvlv_value_len, u8 type,
+					   u8 version)
+{
+	struct batadv_tvlv_hdr *tvlv_hdr;
+	u16 tvlv_value_cont_len;
+
+	while (tvlv_value_len >= sizeof(*tvlv_hdr)) {
+		tvlv_hdr = tvlv_value;
+		tvlv_value_cont_len = ntohs(tvlv_hdr->len);
+		tvlv_value = tvlv_hdr + 1;
+		tvlv_value_len -= sizeof(*tvlv_hdr);
+
+		if (tvlv_value_cont_len > tvlv_value_len)
+			break;
+
+		/* the next tvlv header is accessed assuming (at least) 2-byte
+		 * alignment, so it must start at an even offset.
+		 */
+		if (tvlv_value_cont_len & 1)
+			break;
+
+		if (tvlv_hdr->type == type && tvlv_hdr->version == version)
+			return true;
+
+		tvlv_value = (u8 *)tvlv_value + tvlv_value_cont_len;
+		tvlv_value_len -= tvlv_value_cont_len;
+	}
+
+	return false;
+}
+
 /**
  * batadv_tvlv_containers_process() - parse the given tvlv buffer to call the
  *  appropriate handlers

@@ -449,7 +490,9 @@ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv,
 				   struct sk_buff *skb, void *tvlv_value,
 				   u16 tvlv_value_len)
 {
+	u16 tvlv_value_start_len = tvlv_value_len;
 	struct batadv_tvlv_handler *tvlv_handler;
+	void *tvlv_value_start = tvlv_value;
 	struct batadv_tvlv_hdr *tvlv_hdr;
 	u16 tvlv_value_cont_len;
 	u8 cifnotfound = BATADV_TVLV_HANDLER_OGM_CIFNOTFND;

@@ -493,12 +536,20 @@ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv,
 		if (!tvlv_handler->ogm_handler)
 			continue;
 
-		if ((tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) &&
-		    !(tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CALLED))
-			tvlv_handler->ogm_handler(bat_priv, orig_node,
-						  cifnotfound, NULL, 0);
+		if (!(tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND))
+			continue;
 
-		tvlv_handler->flags &= ~BATADV_TVLV_HANDLER_OGM_CALLED;
+		/* if the corresponding container was present then the handler
+		 * was already called from the loop above
+		 */
+		if (batadv_tvlv_containers_contain(tvlv_value_start,
+						   tvlv_value_start_len,
+						   tvlv_handler->type,
+						   tvlv_handler->version))
+			continue;
+
+		tvlv_handler->ogm_handler(bat_priv, orig_node,
+					  cifnotfound, NULL, 0);
 	}
 	rcu_read_unlock();
 

index ef712ba4fff2cb..ac4494f1b8e2a8 100644
@@ -2245,13 +2245,6 @@ enum batadv_tvlv_handler_flags {
 	 *  will call this handler even if its type was not found (with no data)
 	 */
 	BATADV_TVLV_HANDLER_OGM_CIFNOTFND = BIT(1),
-
-	/**
-	 * @BATADV_TVLV_HANDLER_OGM_CALLED: interval tvlv handling flag - the
-	 *  API marks a handler as being called, so it won't be called if the
-	 *  BATADV_TVLV_HANDLER_OGM_CIFNOTFND flag was set
-	 */
-	BATADV_TVLV_HANDLER_OGM_CALLED = BIT(2),
 };
 
 #endif /* _NET_BATMAN_ADV_TYPES_H_ */

@@ -1648,8 +1648,8 @@ alloc_new_skb:
 				  !(rt->dst.dev->features & NETIF_F_SG)))
 				alloclen = fraglen;
 			else {
-				alloclen = fragheaderlen + transhdrlen;
-				pagedlen = datalen - transhdrlen;
+				alloclen = fragheaderlen + transhdrlen + fraggap;
+				pagedlen = datalen - transhdrlen - fraggap;
 			}
 			alloclen += alloc_extra;
 

@@ -1664,10 +1664,7 @@ alloc_new_skb:
 			fraglen = datalen + fragheaderlen;
 
 			copy = datalen - transhdrlen - fraggap - pagedlen;
-			/* [!] NOTE: copy may be negative if pagedlen>0
-			 * because then the equation may reduces to -fraggap.
-			 */
-			if (copy < 0 && !(flags & MSG_SPLICE_PAGES)) {
+			if (copy < 0) {
 				err = -EINVAL;
 				goto error;
 			}

index 7c005263262ff3..7eaf35a6e24ba6 100644
@@ -1117,8 +1117,8 @@ static int __ip_append_data(struct sock *sk,
 				  !(rt->dst.dev->features & NETIF_F_SG)))
 				alloclen = fraglen;
 			else {
-				alloclen = fragheaderlen + transhdrlen;
-				pagedlen = datalen - transhdrlen;
+				alloclen = fragheaderlen + transhdrlen + fraggap;
+				pagedlen = datalen - transhdrlen - fraggap;
 			}
 
 			alloclen += alloc_extra;

@@ -1165,9 +1165,6 @@ static int __ip_append_data(struct sock *sk,
 			}
 
 			copy = datalen - transhdrlen - fraggap - pagedlen;
-			/* [!] NOTE: copy will be negative if pagedlen>0
-			 * because then the equation reduces to -fraggap.
-			 */
 			if (copy > 0 &&
 			    INDIRECT_CALL_1(getfrag, ip_generic_getfrag,
 					    from, data + transhdrlen, offset,

@@ -845,6 +845,12 @@ out:
 	return err;
 }
 
+static bool ntfs_is_reserved_lxattr(const char *name)
+{
+	return !strcmp(name, "$LXUID") || !strcmp(name, "$LXGID") ||
+	       !strcmp(name, "$LXMOD") || !strcmp(name, "$LXDEV");
+}
+
 /*
  * ntfs_setxattr - inode_operations::setxattr
  */

@@ -949,6 +955,12 @@ set_new_fa:
 		goto out;
 	}
 
+	/* Do not allow non privileged users to change $LXUID/$LXGID... */
+	if (ntfs_is_reserved_lxattr(name) && !capable(CAP_SYS_ADMIN)) {
+		err = -EPERM;
+		goto out;
+	}
+
 	/* Deal with NTFS extended attribute. */
 	err = ntfs_set_ea(inode, name, strlen(name), value, size, flags, 0,
 			  NULL);

@@ -1568,6 +1568,7 @@ mt76_sta_add(struct mt76_phy *phy, struc
 {
 	struct mt76_wcid *wcid = (struct mt76_wcid *)sta->drv_priv;
 	struct mt76_dev *dev = phy->dev;
+	struct mt76_wcid *published;
 	int ret;
 	int i;
 

@@ -1587,11 +1588,19 @@ mt76_sta_add(struct mt76_phy *phy, struc
 		mtxq->wcid = wcid->idx;
 	}
 
-	ewma_signal_init(&wcid->rssi);
-	rcu_assign_pointer(dev->wcid[wcid->idx], wcid);
+	published = rcu_dereference_protected(dev->wcid[wcid->idx],
+					      lockdep_is_held(&dev->mutex));
+	if (published != wcid) {
+		WARN_ON_ONCE(published);
+		ewma_signal_init(&wcid->rssi);
+		rcu_assign_pointer(dev->wcid[wcid->idx], wcid);
+		mt76_wcid_init(wcid, phy->band_idx);
+	} else {
+		wcid->phy_idx = phy->band_idx;
+	}
+
 	phy->num_sta++;
 
-	mt76_wcid_init(wcid, phy->band_idx);
 out:
 	mutex_unlock(&dev->mutex);
 

index 529b21d043d927..39867170902662 100644
@@ -606,6 +606,8 @@ static void __unix_gc(struct work_struct *work)
 	struct sk_buff_head hitlist;
 	struct sk_buff *skb;
 
+	WRITE_ONCE(gc_in_progress, true);
+
 	spin_lock(&unix_gc_lock);
 
 	if (unix_graph_state == UNIX_GRAPH_NOT_CYCLIC) {

@@ -710,6 +710,7 @@ int mac802154_llsec_encrypt(struct mac80
 {
 	struct ieee802154_hdr hdr;
 	int rc, authlen, hlen;
+	struct sk_buff *trailer;
 	struct mac802154_llsec_key *key;
 	u32 frame_ctr;
 

@@ -769,6 +770,12 @@ int mac802154_llsec_encrypt(struct mac80
 	skb->mac_len = ieee802154_hdr_push(skb, &hdr);
 	skb_reset_mac_header(skb);
 
+	rc = skb_cow_data(skb, 0, &trailer);
+	if (rc < 0) {
+		llsec_key_put(key);
+		return rc;
+	}
+
 	rc = llsec_do_encrypt(skb, sec, &hdr, key);
 	llsec_key_put(key);
 

@@ -908,6 +915,13 @@ llsec_do_decrypt(struct sk_buff *skb, co
 		 const struct ieee802154_hdr *hdr,
 		 struct mac802154_llsec_key *key, __le64 dev_addr)
 {
+	struct sk_buff *trailer;
+	int err;
+
+	err = skb_cow_data(skb, 0, &trailer);
+	if (err < 0)
+		return err;
+
 	if (hdr->sec.level == IEEE802154_SCF_SECLEVEL_ENC)
 		return llsec_do_decrypt_unauth(skb, sec, hdr, key, dev_addr);
 	else

@@ -4,6 +4,7 @@
 #ifndef _LINUX_SKMSG_H
 #define _LINUX_SKMSG_H
 
+#include <linux/bitops.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
 #include <linux/scatterlist.h>

@@ -199,11 +200,14 @@ static inline void sk_msg_xfer(struct sk
 			       int which, u32 size)
 {
 	dst->sg.data[which] = src->sg.data[which];
+	__assign_bit(which, dst->sg.copy, test_bit(which, src->sg.copy));
 	dst->sg.data[which].length  = size;
 	dst->sg.size		   += size;
 	src->sg.size		   -= size;
 	src->sg.data[which].length -= size;
 	src->sg.data[which].offset += size;
+	if (!src->sg.data[which].length)
+		__clear_bit(which, src->sg.copy);
 }
 
 static inline void sk_msg_xfer_full(struct sk_msg *dst, struct sk_msg *src)

@@ -273,16 +277,19 @@ static inline void sk_msg_page_add(struc
 static inline void sk_msg_sg_copy(struct sk_msg *msg, u32 i, bool copy_state)
 {
 	do {
-		if (copy_state)
-			__set_bit(i, msg->sg.copy);
-		else
-			__clear_bit(i, msg->sg.copy);
+		__assign_bit(i, msg->sg.copy, copy_state);
 		sk_msg_iter_var_next(i);
 		if (i == msg->sg.end)
 			break;
 	} while (1);
 }
 
+static inline void sk_msg_sg_copy_assign(struct sk_msg *dst, u32 dst_i,
+					 const struct sk_msg *src, u32 src_i)
+{
+	__assign_bit(dst_i, dst->sg.copy, test_bit(src_i, src->sg.copy));
+}
+
 static inline void sk_msg_sg_copy_set(struct sk_msg *msg, u32 start)
 {
 	sk_msg_sg_copy(msg, start, true);

@@ -2732,11 +2732,13 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_
 		poffset += len;
 		sge->length = 0;
 		put_page(sg_page(sge));
+		__clear_bit(i, msg->sg.copy);
 
 		sk_msg_iter_var_next(i);
 	} while (i != last_sge);
 
 	sg_set_page(&msg->sg.data[first_sge], page, copy, 0);
+	__clear_bit(first_sge, msg->sg.copy);
 
 	/* To repair sg ring we need to shift entries. If we only
 	 * had a single entry though we can just replace it and

@@ -2762,9 +2764,11 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_
 			break;
 
 		msg->sg.data[i] = msg->sg.data[move_from];
+		sk_msg_sg_copy_assign(msg, i, msg, move_from);
 		msg->sg.data[move_from].length = 0;
 		msg->sg.data[move_from].page_link = 0;
 		msg->sg.data[move_from].offset = 0;
+		__clear_bit(move_from, msg->sg.copy);
 		sk_msg_iter_var_next(i);
 	} while (1);