From 2b188cc1bb857a9d4701ae59aa7768b5124e262e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 7 Jan 2019 10:46:33 -0700 Subject: Add io_uring IO interface The submission queue (SQ) and completion queue (CQ) rings are shared between the application and the kernel. This eliminates the need to copy data back and forth to submit and complete IO. IO submissions use the io_uring_sqe data structure, and completions are generated in the form of io_uring_cqe data structures. The SQ ring is an index into the io_uring_sqe array, which makes it possible to submit a batch of IOs without them being contiguous in the ring. The CQ ring is always contiguous, as completion events are inherently unordered, and hence any io_uring_cqe entry can point back to an arbitrary submission. Two new system calls are added for this: io_uring_setup(entries, params) Sets up an io_uring instance for doing async IO. On success, returns a file descriptor that the application can mmap to gain access to the SQ ring, CQ ring, and io_uring_sqes. io_uring_enter(fd, to_submit, min_complete, flags, sigset, sigsetsize) Initiates IO against the rings mapped to this fd, or waits for them to complete, or both. The behavior is controlled by the parameters passed in. If 'to_submit' is non-zero, then we'll try and submit new IO. If IORING_ENTER_GETEVENTS is set, the kernel will wait for 'min_complete' events, if they aren't already available. It's valid to set IORING_ENTER_GETEVENTS and 'min_complete' == 0 at the same time, this allows the kernel to return already completed events without waiting for them. This is useful only for polling, as for IRQ driven IO, the application can just check the CQ ring without entering the kernel. With this setup, it's possible to do async IO with a single system call. Future developments will enable polled IO with this interface, and polled submission as well. The latter will enable an application to do IO without doing ANY system calls at all. For IRQ driven IO, an application only needs to enter the kernel for completions if it wants to wait for them to occur. Each io_uring is backed by a workqueue, to support buffered async IO as well. We will only punt to an async context if the command would need to wait for IO on the device side. Any data that can be accessed directly in the page cache is done inline. This avoids the slowness issue of usual threadpools, since cached data is accessed as quickly as a sync interface. Sample application: http://git.kernel.dk/cgit/fio/plain/t/io_uring.c Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/fs.h | 9 +++++++++ include/linux/sched/user.h | 2 +- include/linux/syscalls.h | 6 ++++++ 3 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index dedcc2e9265c..61aa210f0c2b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -3517,4 +3517,13 @@ extern void inode_nohighmem(struct inode *inode); extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice); +#if defined(CONFIG_IO_URING) +extern struct sock *io_uring_get_socket(struct file *file); +#else +static inline struct sock *io_uring_get_socket(struct file *file) +{ + return NULL; +} +#endif + #endif /* _LINUX_FS_H */ diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h index 39ad98c09c58..c7b5f86b91a1 100644 --- a/include/linux/sched/user.h +++ b/include/linux/sched/user.h @@ -40,7 +40,7 @@ struct user_struct { kuid_t uid; #if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \ - defined(CONFIG_NET) + defined(CONFIG_NET) || defined(CONFIG_IO_URING) atomic_long_t locked_vm; #endif diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 257cccba3062..3072dbaa7869 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -69,6 +69,7 @@ struct file_handle; struct sigaltstack; struct rseq; union bpf_attr; +struct io_uring_params; #include #include @@ -309,6 +310,11 @@ asmlinkage long sys_io_pgetevents_time32(aio_context_t ctx_id, struct io_event __user *events, struct old_timespec32 __user *timeout, const struct __aio_sigset *sig); +asmlinkage long sys_io_uring_setup(u32 entries, + struct io_uring_params __user *p); +asmlinkage long sys_io_uring_enter(unsigned int fd, u32 to_submit, + u32 min_complete, u32 flags, + const sigset_t __user *sig, size_t sigsz); /* fs/xattr.c */ asmlinkage long sys_setxattr(const char __user *path, const char __user *name, -- cgit v1.2.3 From 091141a42e15fe47ada737f3996b317072afcefb Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 21 Nov 2018 10:32:39 -0700 Subject: fs: add fget_many() and fput_many() Some uses cases repeatedly get and put references to the same file, but the only exposed interface is doing these one at the time. As each of these entail an atomic inc or dec on a shared structure, that cost can add up. Add fget_many(), which works just like fget(), except it takes an argument for how many references to get on the file. Ditto fput_many(), which can drop an arbitrary number of references to a file. Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/file.h | 2 ++ include/linux/fs.h | 4 +++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/file.h b/include/linux/file.h index 6b2fb032416c..3fcddff56bc4 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -13,6 +13,7 @@ struct file; extern void fput(struct file *); +extern void fput_many(struct file *, unsigned int); struct file_operations; struct vfsmount; @@ -44,6 +45,7 @@ static inline void fdput(struct fd fd) } extern struct file *fget(unsigned int fd); +extern struct file *fget_many(unsigned int fd, unsigned int refs); extern struct file *fget_raw(unsigned int fd); extern unsigned long __fdget(unsigned int fd); extern unsigned long __fdget_raw(unsigned int fd); diff --git a/include/linux/fs.h b/include/linux/fs.h index 61aa210f0c2b..80e1b199a4b1 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -952,7 +952,9 @@ static inline struct file *get_file(struct file *f) atomic_long_inc(&f->f_count); return f; } -#define get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count) +#define get_file_rcu_many(x, cnt) \ + atomic_long_add_unless(&(x)->f_count, (cnt), 0) +#define get_file_rcu(x) get_file_rcu_many((x), 1) #define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1) #define file_count(x) atomic_long_read(&(x)->f_count) -- cgit v1.2.3 From edafccee56ff31678a091ddb7219aba9b28bc3cb Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 9 Jan 2019 09:16:05 -0700 Subject: io_uring: add support for pre-mapped user IO buffers If we have fixed user buffers, we can map them into the kernel when we setup the io_uring. That avoids the need to do get_user_pages() for each and every IO. To utilize this feature, the application must call io_uring_register() after having setup an io_uring instance, passing in IORING_REGISTER_BUFFERS as the opcode. The argument must be a pointer to an iovec array, and the nr_args should contain how many iovecs the application wishes to map. If successful, these buffers are now mapped into the kernel, eligible for IO. To use these fixed buffers, the application must use the IORING_OP_READ_FIXED and IORING_OP_WRITE_FIXED opcodes, and then set sqe->index to the desired buffer index. sqe->addr..sqe->addr+seq->len must point to somewhere inside the indexed buffer. The application may register buffers throughout the lifetime of the io_uring instance. It can call io_uring_register() with IORING_UNREGISTER_BUFFERS as the opcode to unregister the current set of buffers, and then register a new set. The application need not unregister buffers explicitly before shutting down the io_uring instance. It's perfectly valid to setup a larger buffer, and then sometimes only use parts of it for an IO. As long as the range is within the originally mapped region, it will work just fine. For now, buffers must not be file backed. If file backed buffers are passed in, the registration will fail with -1/EOPNOTSUPP. This restriction may be relaxed in the future. RLIMIT_MEMLOCK is used to check how much memory we can pin. A somewhat arbitrary 1G per buffer size is also imposed. Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- include/linux/syscalls.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 3072dbaa7869..3681c05ac538 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -315,6 +315,8 @@ asmlinkage long sys_io_uring_setup(u32 entries, asmlinkage long sys_io_uring_enter(unsigned int fd, u32 to_submit, u32 min_complete, u32 flags, const sigset_t __user *sig, size_t sigsz); +asmlinkage long sys_io_uring_register(unsigned int fd, unsigned int op, + void __user *arg, unsigned int nr_args); /* fs/xattr.c */ asmlinkage long sys_setxattr(const char __user *path, const char __user *name, -- cgit v1.2.3