diff options
Diffstat (limited to 'fs')
-rw-r--r-- | fs/io_uring.c | 60 | ||||
-rw-r--r-- | fs/nfsd/nfs4xdr.c | 20 | ||||
-rw-r--r-- | fs/xattr.c | 84 |
3 files changed, 113 insertions, 51 deletions
diff --git a/fs/io_uring.c b/fs/io_uring.c index e0200406765c..be3d595a607f 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -279,6 +279,7 @@ struct sqe_submit { bool has_user; bool needs_lock; bool needs_fixed_file; + u8 opcode; }; /* @@ -505,7 +506,7 @@ static inline void io_queue_async_work(struct io_ring_ctx *ctx, int rw = 0; if (req->submit.sqe) { - switch (req->submit.sqe->opcode) { + switch (req->submit.opcode) { case IORING_OP_WRITEV: case IORING_OP_WRITE_FIXED: rw = !(req->rw.ki_flags & IOCB_DIRECT); @@ -1254,23 +1255,15 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw, } static ssize_t io_import_iovec(struct io_ring_ctx *ctx, int rw, - const struct sqe_submit *s, struct iovec **iovec, + struct io_kiocb *req, struct iovec **iovec, struct iov_iter *iter) { - const struct io_uring_sqe *sqe = s->sqe; + const struct io_uring_sqe *sqe = req->submit.sqe; void __user *buf = u64_to_user_ptr(READ_ONCE(sqe->addr)); size_t sqe_len = READ_ONCE(sqe->len); u8 opcode; - /* - * We're reading ->opcode for the second time, but the first read - * doesn't care whether it's _FIXED or not, so it doesn't matter - * whether ->opcode changes concurrently. The first read does care - * about whether it is a READ or a WRITE, so we don't trust this read - * for that purpose and instead let the caller pass in the read/write - * flag. - */ - opcode = READ_ONCE(sqe->opcode); + opcode = req->submit.opcode; if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { ssize_t ret = io_import_fixed(ctx, rw, sqe, iter); @@ -1278,7 +1271,7 @@ static ssize_t io_import_iovec(struct io_ring_ctx *ctx, int rw, return ret; } - if (!s->has_user) + if (!req->submit.has_user) return -EFAULT; #ifdef CONFIG_COMPAT @@ -1425,7 +1418,7 @@ static int io_read(struct io_kiocb *req, const struct sqe_submit *s, if (unlikely(!(file->f_mode & FMODE_READ))) return -EBADF; - ret = io_import_iovec(req->ctx, READ, s, &iovec, &iter); + ret = io_import_iovec(req->ctx, READ, req, &iovec, &iter); if (ret < 0) return ret; @@ -1490,7 +1483,7 @@ static int io_write(struct io_kiocb *req, const struct sqe_submit *s, if (unlikely(!(file->f_mode & FMODE_WRITE))) return -EBADF; - ret = io_import_iovec(req->ctx, WRITE, s, &iovec, &iter); + ret = io_import_iovec(req->ctx, WRITE, req, &iovec, &iter); if (ret < 0) return ret; @@ -2109,15 +2102,14 @@ static int io_req_defer(struct io_ring_ctx *ctx, struct io_kiocb *req, static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, const struct sqe_submit *s, bool force_nonblock) { - int ret, opcode; + int ret; req->user_data = READ_ONCE(s->sqe->user_data); if (unlikely(s->index >= ctx->sq_entries)) return -EINVAL; - opcode = READ_ONCE(s->sqe->opcode); - switch (opcode) { + switch (req->submit.opcode) { case IORING_OP_NOP: ret = io_nop(req, req->user_data); break; @@ -2181,10 +2173,10 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, return 0; } -static struct async_list *io_async_list_from_sqe(struct io_ring_ctx *ctx, - const struct io_uring_sqe *sqe) +static struct async_list *io_async_list_from_req(struct io_ring_ctx *ctx, + struct io_kiocb *req) { - switch (sqe->opcode) { + switch (req->submit.opcode) { case IORING_OP_READV: case IORING_OP_READ_FIXED: return &ctx->pending_async[READ]; @@ -2196,12 +2188,10 @@ static struct async_list *io_async_list_from_sqe(struct io_ring_ctx *ctx, } } -static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe) +static inline bool io_req_needs_user(struct io_kiocb *req) { - u8 opcode = READ_ONCE(sqe->opcode); - - return !(opcode == IORING_OP_READ_FIXED || - opcode == IORING_OP_WRITE_FIXED); + return !(req->submit.opcode == IORING_OP_READ_FIXED || + req->submit.opcode == IORING_OP_WRITE_FIXED); } static void io_sq_wq_submit_work(struct work_struct *work) @@ -2217,7 +2207,7 @@ static void io_sq_wq_submit_work(struct work_struct *work) int ret; old_cred = override_creds(ctx->creds); - async_list = io_async_list_from_sqe(ctx, req->submit.sqe); + async_list = io_async_list_from_req(ctx, req); allow_kernel_signal(SIGINT); restart: @@ -2239,9 +2229,10 @@ restart: } ret = 0; - if (io_sqe_needs_user(sqe) && !cur_mm) { + if (io_req_needs_user(req) && !cur_mm) { if (!mmget_not_zero(ctx->sqo_mm)) { ret = -EFAULT; + goto end_req; } else { cur_mm = ctx->sqo_mm; use_mm(cur_mm); @@ -2387,11 +2378,9 @@ static bool io_add_to_prev_work(struct async_list *list, struct io_kiocb *req) return ret; } -static bool io_op_needs_file(const struct io_uring_sqe *sqe) +static bool io_op_needs_file(struct io_kiocb *req) { - int op = READ_ONCE(sqe->opcode); - - switch (op) { + switch (req->submit.opcode) { case IORING_OP_NOP: case IORING_OP_POLL_REMOVE: case IORING_OP_TIMEOUT: @@ -2419,7 +2408,7 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s, */ req->sequence = s->sequence; - if (!io_op_needs_file(s->sqe)) + if (!io_op_needs_file(req)) return 0; if (flags & IOSQE_FIXED_FILE) { @@ -2460,7 +2449,7 @@ static int __io_queue_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, s->sqe = sqe_copy; memcpy(&req->submit, s, sizeof(*s)); - list = io_async_list_from_sqe(ctx, s->sqe); + list = io_async_list_from_req(ctx, req); if (!io_add_to_prev_work(list, req)) { if (list) atomic_inc(&list->cnt); @@ -2582,7 +2571,7 @@ err: req->user_data = s->sqe->user_data; #if defined(CONFIG_NET) - switch (READ_ONCE(s->sqe->opcode)) { + switch (req->submit.opcode) { case IORING_OP_SENDMSG: case IORING_OP_RECVMSG: spin_lock(¤t->fs->lock); @@ -2697,6 +2686,7 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s) if (head < ctx->sq_entries) { s->index = head; s->sqe = &ctx->sq_sqes[head]; + s->opcode = READ_ONCE(s->sqe->opcode); s->sequence = ctx->cached_sq_head; ctx->cached_sq_head++; return true; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 533d0fc3c96b..d6f244559e75 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3530,17 +3530,17 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, u32 zzz = 0; int pad; + /* + * svcrdma requires every READ payload to start somewhere + * in xdr->pages. + */ + if (xdr->iov == xdr->buf->head) { + xdr->iov = NULL; + xdr->end = xdr->p; + } + len = maxcount; v = 0; - - thislen = min_t(long, len, ((void *)xdr->end - (void *)xdr->p)); - p = xdr_reserve_space(xdr, (thislen+3)&~3); - WARN_ON_ONCE(!p); - resp->rqstp->rq_vec[v].iov_base = p; - resp->rqstp->rq_vec[v].iov_len = thislen; - v++; - len -= thislen; - while (len) { thislen = min_t(long, len, PAGE_SIZE); p = xdr_reserve_space(xdr, (thislen+3)&~3); @@ -3559,6 +3559,8 @@ static __be32 nfsd4_encode_readv(struct nfsd4_compoundres *resp, read->rd_length = maxcount; if (nfserr) return nfserr; + if (svc_encode_read_payload(resp->rqstp, starting_len + 8, maxcount)) + return nfserr_io; xdr_truncate_encode(xdr, starting_len + 8 + ((maxcount+3)&~3)); tmp = htonl(eof); diff --git a/fs/xattr.c b/fs/xattr.c index 90dd78f0eb27..f2854570d411 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -204,10 +204,22 @@ int __vfs_setxattr_noperm(struct dentry *dentry, const char *name, return error; } - +/** + * __vfs_setxattr_locked: set an extended attribute while holding the inode + * lock + * + * @dentry - object to perform setxattr on + * @name - xattr name to set + * @value - value to set @name to + * @size - size of @value + * @flags - flags to pass into filesystem operations + * @delegated_inode - on return, will contain an inode pointer that + * a delegation was broken on, NULL if none. + */ int -vfs_setxattr(struct dentry *dentry, const char *name, const void *value, - size_t size, int flags) +__vfs_setxattr_locked(struct dentry *dentry, const char *name, + const void *value, size_t size, int flags, + struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; @@ -216,15 +228,40 @@ vfs_setxattr(struct dentry *dentry, const char *name, const void *value, if (error) return error; - inode_lock(inode); error = security_inode_setxattr(dentry, name, value, size, flags); if (error) goto out; + error = try_break_deleg(inode, delegated_inode); + if (error) + goto out; + error = __vfs_setxattr_noperm(dentry, name, value, size, flags); out: + return error; +} +EXPORT_SYMBOL_GPL(__vfs_setxattr_locked); + +int +vfs_setxattr(struct dentry *dentry, const char *name, const void *value, + size_t size, int flags) +{ + struct inode *inode = dentry->d_inode; + struct inode *delegated_inode = NULL; + int error; + +retry_deleg: + inode_lock(inode); + error = __vfs_setxattr_locked(dentry, name, value, size, flags, + &delegated_inode); inode_unlock(inode); + + if (delegated_inode) { + error = break_deleg_wait(&delegated_inode); + if (!error) + goto retry_deleg; + } return error; } EXPORT_SYMBOL_GPL(vfs_setxattr); @@ -378,8 +415,18 @@ __vfs_removexattr(struct dentry *dentry, const char *name) } EXPORT_SYMBOL(__vfs_removexattr); +/** + * __vfs_removexattr_locked: set an extended attribute while holding the inode + * lock + * + * @dentry - object to perform setxattr on + * @name - name of xattr to remove + * @delegated_inode - on return, will contain an inode pointer that + * a delegation was broken on, NULL if none. + */ int -vfs_removexattr(struct dentry *dentry, const char *name) +__vfs_removexattr_locked(struct dentry *dentry, const char *name, + struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; int error; @@ -388,11 +435,14 @@ vfs_removexattr(struct dentry *dentry, const char *name) if (error) return error; - inode_lock(inode); error = security_inode_removexattr(dentry, name); if (error) goto out; + error = try_break_deleg(inode, delegated_inode); + if (error) + goto out; + error = __vfs_removexattr(dentry, name); if (!error) { @@ -401,12 +451,32 @@ vfs_removexattr(struct dentry *dentry, const char *name) } out: + return error; +} +EXPORT_SYMBOL_GPL(__vfs_removexattr_locked); + +int +vfs_removexattr(struct dentry *dentry, const char *name) +{ + struct inode *inode = dentry->d_inode; + struct inode *delegated_inode = NULL; + int error; + +retry_deleg: + inode_lock(inode); + error = __vfs_removexattr_locked(dentry, name, &delegated_inode); inode_unlock(inode); + + if (delegated_inode) { + error = break_deleg_wait(&delegated_inode); + if (!error) + goto retry_deleg; + } + return error; } EXPORT_SYMBOL_GPL(vfs_removexattr); - /* * Extended attribute SET operations */ |