* [PATCH 13/19] net: split out functions related to registering inflight socket files
From: Jens Axboe @ 2019-02-11 19:00 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api
Cc: hch, jmoyer, avi, jannh, viro, Jens Axboe
In-Reply-To: <20190211190049.7888-1-axboe@kernel.dk>
We need this functionality for the io_uring file registration, but
we cannot rely on it since CONFIG_UNIX can be modular. Move the helpers
to a separate file, that's always builtin to the kernel if CONFIG_UNIX is
m/y.
No functional changes in this patch, just moving code around.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
include/net/af_unix.h | 1 +
net/Makefile | 2 +-
net/unix/Kconfig | 5 ++
net/unix/Makefile | 2 +
net/unix/af_unix.c | 63 +-----------------
net/unix/garbage.c | 71 +-------------------
net/unix/scm.c | 151 ++++++++++++++++++++++++++++++++++++++++++
net/unix/scm.h | 10 +++
8 files changed, 174 insertions(+), 131 deletions(-)
create mode 100644 net/unix/scm.c
create mode 100644 net/unix/scm.h
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index ddbba838d048..3426d6dacc45 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -10,6 +10,7 @@
void unix_inflight(struct user_struct *user, struct file *fp);
void unix_notinflight(struct user_struct *user, struct file *fp);
+void unix_destruct_scm(struct sk_buff *skb);
void unix_gc(void);
void wait_for_unix_gc(void);
struct sock *unix_get_socket(struct file *filp);
diff --git a/net/Makefile b/net/Makefile
index bdaf53925acd..449fc0b221f8 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -18,7 +18,7 @@ obj-$(CONFIG_NETFILTER) += netfilter/
obj-$(CONFIG_INET) += ipv4/
obj-$(CONFIG_TLS) += tls/
obj-$(CONFIG_XFRM) += xfrm/
-obj-$(CONFIG_UNIX) += unix/
+obj-$(CONFIG_UNIX_SCM) += unix/
obj-$(CONFIG_NET) += ipv6/
obj-$(CONFIG_BPFILTER) += bpfilter/
obj-$(CONFIG_PACKET) += packet/
diff --git a/net/unix/Kconfig b/net/unix/Kconfig
index 8b31ab85d050..3b9e450656a4 100644
--- a/net/unix/Kconfig
+++ b/net/unix/Kconfig
@@ -19,6 +19,11 @@ config UNIX
Say Y unless you know what you are doing.
+config UNIX_SCM
+ bool
+ depends on UNIX
+ default y
+
config UNIX_DIAG
tristate "UNIX: socket monitoring interface"
depends on UNIX
diff --git a/net/unix/Makefile b/net/unix/Makefile
index ffd0a275c3a7..54e58cc4f945 100644
--- a/net/unix/Makefile
+++ b/net/unix/Makefile
@@ -10,3 +10,5 @@ unix-$(CONFIG_SYSCTL) += sysctl_net_unix.o
obj-$(CONFIG_UNIX_DIAG) += unix_diag.o
unix_diag-y := diag.o
+
+obj-$(CONFIG_UNIX_SCM) += scm.o
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 74d1eed7cbd4..2ce32dbb2feb 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -119,6 +119,8 @@
#include <linux/freezer.h>
#include <linux/file.h>
+#include "scm.h"
+
struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE];
EXPORT_SYMBOL_GPL(unix_socket_table);
DEFINE_SPINLOCK(unix_table_lock);
@@ -1486,67 +1488,6 @@ static int unix_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
return err;
}
-static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
-{
- int i;
-
- scm->fp = UNIXCB(skb).fp;
- UNIXCB(skb).fp = NULL;
-
- for (i = scm->fp->count-1; i >= 0; i--)
- unix_notinflight(scm->fp->user, scm->fp->fp[i]);
-}
-
-static void unix_destruct_scm(struct sk_buff *skb)
-{
- struct scm_cookie scm;
- memset(&scm, 0, sizeof(scm));
- scm.pid = UNIXCB(skb).pid;
- if (UNIXCB(skb).fp)
- unix_detach_fds(&scm, skb);
-
- /* Alas, it calls VFS */
- /* So fscking what? fput() had been SMP-safe since the last Summer */
- scm_destroy(&scm);
- sock_wfree(skb);
-}
-
-/*
- * The "user->unix_inflight" variable is protected by the garbage
- * collection lock, and we just read it locklessly here. If you go
- * over the limit, there might be a tiny race in actually noticing
- * it across threads. Tough.
- */
-static inline bool too_many_unix_fds(struct task_struct *p)
-{
- struct user_struct *user = current_user();
-
- if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE)))
- return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
- return false;
-}
-
-static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
-{
- int i;
-
- if (too_many_unix_fds(current))
- return -ETOOMANYREFS;
-
- /*
- * Need to duplicate file references for the sake of garbage
- * collection. Otherwise a socket in the fps might become a
- * candidate for GC while the skb is not yet queued.
- */
- UNIXCB(skb).fp = scm_fp_dup(scm->fp);
- if (!UNIXCB(skb).fp)
- return -ENOMEM;
-
- for (i = scm->fp->count - 1; i >= 0; i--)
- unix_inflight(scm->fp->user, scm->fp->fp[i]);
- return 0;
-}
-
static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds)
{
int err = 0;
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index f81854d74c7d..8bbe1b8e4ff7 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -86,80 +86,13 @@
#include <net/scm.h>
#include <net/tcp_states.h>
+#include "scm.h"
+
/* Internal data structures and random procedures: */
-static LIST_HEAD(gc_inflight_list);
static LIST_HEAD(gc_candidates);
-static DEFINE_SPINLOCK(unix_gc_lock);
static DECLARE_WAIT_QUEUE_HEAD(unix_gc_wait);
-unsigned int unix_tot_inflight;
-
-struct sock *unix_get_socket(struct file *filp)
-{
- struct sock *u_sock = NULL;
- struct inode *inode = file_inode(filp);
-
- /* Socket ? */
- if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) {
- struct socket *sock = SOCKET_I(inode);
- struct sock *s = sock->sk;
-
- /* PF_UNIX ? */
- if (s && sock->ops && sock->ops->family == PF_UNIX)
- u_sock = s;
- } else {
- /* Could be an io_uring instance */
- u_sock = io_uring_get_socket(filp);
- }
- return u_sock;
-}
-
-/* Keep the number of times in flight count for the file
- * descriptor if it is for an AF_UNIX socket.
- */
-
-void unix_inflight(struct user_struct *user, struct file *fp)
-{
- struct sock *s = unix_get_socket(fp);
-
- spin_lock(&unix_gc_lock);
-
- if (s) {
- struct unix_sock *u = unix_sk(s);
-
- if (atomic_long_inc_return(&u->inflight) == 1) {
- BUG_ON(!list_empty(&u->link));
- list_add_tail(&u->link, &gc_inflight_list);
- } else {
- BUG_ON(list_empty(&u->link));
- }
- unix_tot_inflight++;
- }
- user->unix_inflight++;
- spin_unlock(&unix_gc_lock);
-}
-
-void unix_notinflight(struct user_struct *user, struct file *fp)
-{
- struct sock *s = unix_get_socket(fp);
-
- spin_lock(&unix_gc_lock);
-
- if (s) {
- struct unix_sock *u = unix_sk(s);
-
- BUG_ON(!atomic_long_read(&u->inflight));
- BUG_ON(list_empty(&u->link));
-
- if (atomic_long_dec_and_test(&u->inflight))
- list_del_init(&u->link);
- unix_tot_inflight--;
- }
- user->unix_inflight--;
- spin_unlock(&unix_gc_lock);
-}
-
static void scan_inflight(struct sock *x, void (*func)(struct unix_sock *),
struct sk_buff_head *hitlist)
{
diff --git a/net/unix/scm.c b/net/unix/scm.c
new file mode 100644
index 000000000000..8c40f2b32392
--- /dev/null
+++ b/net/unix/scm.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/socket.h>
+#include <linux/net.h>
+#include <linux/fs.h>
+#include <net/af_unix.h>
+#include <net/scm.h>
+#include <linux/init.h>
+
+#include "scm.h"
+
+unsigned int unix_tot_inflight;
+EXPORT_SYMBOL(unix_tot_inflight);
+
+LIST_HEAD(gc_inflight_list);
+EXPORT_SYMBOL(gc_inflight_list);
+
+DEFINE_SPINLOCK(unix_gc_lock);
+EXPORT_SYMBOL(unix_gc_lock);
+
+struct sock *unix_get_socket(struct file *filp)
+{
+ struct sock *u_sock = NULL;
+ struct inode *inode = file_inode(filp);
+
+ /* Socket ? */
+ if (S_ISSOCK(inode->i_mode) && !(filp->f_mode & FMODE_PATH)) {
+ struct socket *sock = SOCKET_I(inode);
+ struct sock *s = sock->sk;
+
+ /* PF_UNIX ? */
+ if (s && sock->ops && sock->ops->family == PF_UNIX)
+ u_sock = s;
+ } else {
+ /* Could be an io_uring instance */
+ u_sock = io_uring_get_socket(filp);
+ }
+ return u_sock;
+}
+EXPORT_SYMBOL(unix_get_socket);
+
+/* Keep the number of times in flight count for the file
+ * descriptor if it is for an AF_UNIX socket.
+ */
+void unix_inflight(struct user_struct *user, struct file *fp)
+{
+ struct sock *s = unix_get_socket(fp);
+
+ spin_lock(&unix_gc_lock);
+
+ if (s) {
+ struct unix_sock *u = unix_sk(s);
+
+ if (atomic_long_inc_return(&u->inflight) == 1) {
+ BUG_ON(!list_empty(&u->link));
+ list_add_tail(&u->link, &gc_inflight_list);
+ } else {
+ BUG_ON(list_empty(&u->link));
+ }
+ unix_tot_inflight++;
+ }
+ user->unix_inflight++;
+ spin_unlock(&unix_gc_lock);
+}
+
+void unix_notinflight(struct user_struct *user, struct file *fp)
+{
+ struct sock *s = unix_get_socket(fp);
+
+ spin_lock(&unix_gc_lock);
+
+ if (s) {
+ struct unix_sock *u = unix_sk(s);
+
+ BUG_ON(!atomic_long_read(&u->inflight));
+ BUG_ON(list_empty(&u->link));
+
+ if (atomic_long_dec_and_test(&u->inflight))
+ list_del_init(&u->link);
+ unix_tot_inflight--;
+ }
+ user->unix_inflight--;
+ spin_unlock(&unix_gc_lock);
+}
+
+/*
+ * The "user->unix_inflight" variable is protected by the garbage
+ * collection lock, and we just read it locklessly here. If you go
+ * over the limit, there might be a tiny race in actually noticing
+ * it across threads. Tough.
+ */
+static inline bool too_many_unix_fds(struct task_struct *p)
+{
+ struct user_struct *user = current_user();
+
+ if (unlikely(user->unix_inflight > task_rlimit(p, RLIMIT_NOFILE)))
+ return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
+ return false;
+}
+
+int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
+{
+ int i;
+
+ if (too_many_unix_fds(current))
+ return -ETOOMANYREFS;
+
+ /*
+ * Need to duplicate file references for the sake of garbage
+ * collection. Otherwise a socket in the fps might become a
+ * candidate for GC while the skb is not yet queued.
+ */
+ UNIXCB(skb).fp = scm_fp_dup(scm->fp);
+ if (!UNIXCB(skb).fp)
+ return -ENOMEM;
+
+ for (i = scm->fp->count - 1; i >= 0; i--)
+ unix_inflight(scm->fp->user, scm->fp->fp[i]);
+ return 0;
+}
+EXPORT_SYMBOL(unix_attach_fds);
+
+void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
+{
+ int i;
+
+ scm->fp = UNIXCB(skb).fp;
+ UNIXCB(skb).fp = NULL;
+
+ for (i = scm->fp->count-1; i >= 0; i--)
+ unix_notinflight(scm->fp->user, scm->fp->fp[i]);
+}
+EXPORT_SYMBOL(unix_detach_fds);
+
+void unix_destruct_scm(struct sk_buff *skb)
+{
+ struct scm_cookie scm;
+
+ memset(&scm, 0, sizeof(scm));
+ scm.pid = UNIXCB(skb).pid;
+ if (UNIXCB(skb).fp)
+ unix_detach_fds(&scm, skb);
+
+ /* Alas, it calls VFS */
+ /* So fscking what? fput() had been SMP-safe since the last Summer */
+ scm_destroy(&scm);
+ sock_wfree(skb);
+}
+EXPORT_SYMBOL(unix_destruct_scm);
diff --git a/net/unix/scm.h b/net/unix/scm.h
new file mode 100644
index 000000000000..5a255a477f16
--- /dev/null
+++ b/net/unix/scm.h
@@ -0,0 +1,10 @@
+#ifndef NET_UNIX_SCM_H
+#define NET_UNIX_SCM_H
+
+extern struct list_head gc_inflight_list;
+extern spinlock_t unix_gc_lock;
+
+int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb);
+void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb);
+
+#endif
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 12/19] io_uring: add support for pre-mapped user IO buffers
From: Jens Axboe @ 2019-02-11 19:00 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api
Cc: hch, jmoyer, avi, jannh, viro, Jens Axboe
In-Reply-To: <20190211190049.7888-1-axboe@kernel.dk>
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 <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
arch/x86/entry/syscalls/syscall_32.tbl | 1 +
arch/x86/entry/syscalls/syscall_64.tbl | 1 +
fs/io_uring.c | 373 ++++++++++++++++++++++++-
include/linux/syscalls.h | 2 +
include/uapi/asm-generic/unistd.h | 4 +-
include/uapi/linux/io_uring.h | 13 +-
kernel/sys_ni.c | 1 +
7 files changed, 380 insertions(+), 15 deletions(-)
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 481c126259e9..2eefd2a7c1ce 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -400,3 +400,4 @@
386 i386 rseq sys_rseq __ia32_sys_rseq
425 i386 io_uring_setup sys_io_uring_setup __ia32_sys_io_uring_setup
426 i386 io_uring_enter sys_io_uring_enter __ia32_sys_io_uring_enter
+427 i386 io_uring_register sys_io_uring_register __ia32_sys_io_uring_register
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 6a32a430c8e0..65c026185e61 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -345,6 +345,7 @@
334 common rseq __x64_sys_rseq
425 common io_uring_setup __x64_sys_io_uring_setup
426 common io_uring_enter __x64_sys_io_uring_enter
+427 common io_uring_register __x64_sys_io_uring_register
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/fs/io_uring.c b/fs/io_uring.c
index e330252dc5de..0eba20d18f53 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -45,6 +45,7 @@
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/blkdev.h>
+#include <linux/bvec.h>
#include <linux/net.h>
#include <net/sock.h>
#include <net/af_unix.h>
@@ -52,6 +53,8 @@
#include <linux/sched/mm.h>
#include <linux/uaccess.h>
#include <linux/nospec.h>
+#include <linux/sizes.h>
+#include <linux/hugetlb.h>
#include <uapi/linux/io_uring.h>
@@ -81,6 +84,13 @@ struct io_cq_ring {
struct io_uring_cqe cqes[];
};
+struct io_mapped_ubuf {
+ u64 ubuf;
+ size_t len;
+ struct bio_vec *bvec;
+ unsigned int nr_bvecs;
+};
+
struct io_ring_ctx {
struct {
struct percpu_ref refs;
@@ -113,6 +123,10 @@ struct io_ring_ctx {
struct fasync_struct *cq_fasync;
} ____cacheline_aligned_in_smp;
+ /* if used, fixed mapped user buffers */
+ unsigned nr_user_bufs;
+ struct io_mapped_ubuf *user_bufs;
+
struct user_struct *user;
struct completion ctx_done;
@@ -732,6 +746,46 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
}
}
+static int io_import_fixed(struct io_ring_ctx *ctx, int rw,
+ const struct io_uring_sqe *sqe,
+ struct iov_iter *iter)
+{
+ size_t len = READ_ONCE(sqe->len);
+ struct io_mapped_ubuf *imu;
+ unsigned index, buf_index;
+ size_t offset;
+ u64 buf_addr;
+
+ /* attempt to use fixed buffers without having provided iovecs */
+ if (unlikely(!ctx->user_bufs))
+ return -EFAULT;
+
+ buf_index = READ_ONCE(sqe->buf_index);
+ if (unlikely(buf_index >= ctx->nr_user_bufs))
+ return -EFAULT;
+
+ index = array_index_nospec(buf_index, ctx->nr_user_bufs);
+ imu = &ctx->user_bufs[index];
+ buf_addr = READ_ONCE(sqe->addr);
+
+ /* overflow */
+ if (buf_addr + len < buf_addr)
+ return -EFAULT;
+ /* not inside the mapped region */
+ if (buf_addr < imu->ubuf || buf_addr + len > imu->ubuf + imu->len)
+ return -EFAULT;
+
+ /*
+ * May not be a start of buffer, set size appropriately
+ * and advance us to the beginning.
+ */
+ offset = buf_addr - imu->ubuf;
+ iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len);
+ if (offset)
+ iov_iter_advance(iter, offset);
+ return 0;
+}
+
static int io_import_iovec(struct io_ring_ctx *ctx, int rw,
const struct sqe_submit *s, struct iovec **iovec,
struct iov_iter *iter)
@@ -739,6 +793,23 @@ static int io_import_iovec(struct io_ring_ctx *ctx, int rw,
const struct io_uring_sqe *sqe = s->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);
+ if (opcode == IORING_OP_READ_FIXED ||
+ opcode == IORING_OP_WRITE_FIXED) {
+ ssize_t ret = io_import_fixed(ctx, rw, sqe, iter);
+ *iovec = NULL;
+ return ret;
+ }
if (!s->has_user)
return EFAULT;
@@ -886,7 +957,7 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
return -EINVAL;
- if (unlikely(sqe->addr || sqe->ioprio))
+ if (unlikely(sqe->addr || sqe->ioprio || sqe->buf_index))
return -EINVAL;
fd = READ_ONCE(sqe->fd);
@@ -945,9 +1016,19 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
ret = io_nop(req, req->user_data);
break;
case IORING_OP_READV:
+ if (unlikely(s->sqe->buf_index))
+ return -EINVAL;
ret = io_read(req, s, force_nonblock, state);
break;
case IORING_OP_WRITEV:
+ if (unlikely(s->sqe->buf_index))
+ return -EINVAL;
+ ret = io_write(req, s, force_nonblock, state);
+ break;
+ case IORING_OP_READ_FIXED:
+ ret = io_read(req, s, force_nonblock, state);
+ break;
+ case IORING_OP_WRITE_FIXED:
ret = io_write(req, s, force_nonblock, state);
break;
case IORING_OP_FSYNC:
@@ -976,28 +1057,46 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
return 0;
}
+static inline bool io_sqe_needs_user(const struct io_uring_sqe *sqe)
+{
+ u8 opcode = READ_ONCE(sqe->opcode);
+
+ return !(opcode == IORING_OP_READ_FIXED ||
+ opcode == IORING_OP_WRITE_FIXED);
+}
+
static void io_sq_wq_submit_work(struct work_struct *work)
{
struct io_kiocb *req = container_of(work, struct io_kiocb, work);
struct sqe_submit *s = &req->submit;
const struct io_uring_sqe *sqe = s->sqe;
struct io_ring_ctx *ctx = req->ctx;
- mm_segment_t old_fs = get_fs();
+ mm_segment_t old_fs;
+ bool needs_user;
int ret;
/* Ensure we clear previously set forced non-block flag */
req->flags &= ~REQ_F_FORCE_NONBLOCK;
req->rw.ki_flags &= ~IOCB_NOWAIT;
- if (!mmget_not_zero(ctx->sqo_mm)) {
- ret = -EFAULT;
- goto err;
- }
-
- use_mm(ctx->sqo_mm);
- set_fs(USER_DS);
- s->has_user = true;
s->needs_lock = true;
+ s->has_user = false;
+
+ /*
+ * If we're doing IO to fixed buffers, we don't need to get/set
+ * user context
+ */
+ needs_user = io_sqe_needs_user(s->sqe);
+ if (needs_user) {
+ if (!mmget_not_zero(ctx->sqo_mm)) {
+ ret = -EFAULT;
+ goto err;
+ }
+ use_mm(ctx->sqo_mm);
+ old_fs = get_fs();
+ set_fs(USER_DS);
+ s->has_user = true;
+ }
do {
ret = __io_submit_sqe(ctx, req, s, false, NULL);
@@ -1011,9 +1110,11 @@ static void io_sq_wq_submit_work(struct work_struct *work)
cond_resched();
} while (1);
- set_fs(old_fs);
- unuse_mm(ctx->sqo_mm);
- mmput(ctx->sqo_mm);
+ if (needs_user) {
+ set_fs(old_fs);
+ unuse_mm(ctx->sqo_mm);
+ mmput(ctx->sqo_mm);
+ }
err:
if (ret) {
io_cqring_add_event(ctx, sqe->user_data, ret, 0);
@@ -1308,6 +1409,197 @@ static unsigned long ring_pages(unsigned sq_entries, unsigned cq_entries)
return (bytes + PAGE_SIZE - 1) / PAGE_SIZE;
}
+static int io_sqe_buffer_unregister(struct io_ring_ctx *ctx)
+{
+ int i, j;
+
+ if (!ctx->user_bufs)
+ return -ENXIO;
+
+ for (i = 0; i < ctx->nr_user_bufs; i++) {
+ struct io_mapped_ubuf *imu = &ctx->user_bufs[i];
+
+ for (j = 0; j < imu->nr_bvecs; j++)
+ put_page(imu->bvec[j].bv_page);
+
+ if (ctx->account_mem)
+ io_unaccount_mem(ctx->user, imu->nr_bvecs);
+ kfree(imu->bvec);
+ imu->nr_bvecs = 0;
+ }
+
+ kfree(ctx->user_bufs);
+ ctx->user_bufs = NULL;
+ ctx->nr_user_bufs = 0;
+ return 0;
+}
+
+static int io_copy_iov(struct io_ring_ctx *ctx, struct iovec *dst,
+ void __user *arg, unsigned index)
+{
+ struct iovec __user *src;
+
+#ifdef CONFIG_COMPAT
+ if (ctx->compat) {
+ struct compat_iovec __user *ciovs;
+ struct compat_iovec ciov;
+
+ ciovs = (struct compat_iovec __user *) arg;
+ if (copy_from_user(&ciov, &ciovs[index], sizeof(ciov)))
+ return -EFAULT;
+
+ dst->iov_base = (void __user *) (unsigned long) ciov.iov_base;
+ dst->iov_len = ciov.iov_len;
+ return 0;
+ }
+#endif
+ src = (struct iovec __user *) arg;
+ if (copy_from_user(dst, &src[index], sizeof(*dst)))
+ return -EFAULT;
+ return 0;
+}
+
+static int io_sqe_buffer_register(struct io_ring_ctx *ctx, void __user *arg,
+ unsigned nr_args)
+{
+ struct vm_area_struct **vmas = NULL;
+ struct page **pages = NULL;
+ int i, j, got_pages = 0;
+ int ret = -EINVAL;
+
+ if (ctx->user_bufs)
+ return -EBUSY;
+ if (!nr_args || nr_args > UIO_MAXIOV)
+ return -EINVAL;
+
+ ctx->user_bufs = kcalloc(nr_args, sizeof(struct io_mapped_ubuf),
+ GFP_KERNEL);
+ if (!ctx->user_bufs)
+ return -ENOMEM;
+
+ for (i = 0; i < nr_args; i++) {
+ struct io_mapped_ubuf *imu = &ctx->user_bufs[i];
+ unsigned long off, start, end, ubuf;
+ int pret, nr_pages;
+ struct iovec iov;
+ size_t size;
+
+ ret = io_copy_iov(ctx, &iov, arg, i);
+ if (ret)
+ break;
+
+ /*
+ * Don't impose further limits on the size and buffer
+ * constraints here, we'll -EINVAL later when IO is
+ * submitted if they are wrong.
+ */
+ ret = -EFAULT;
+ if (!iov.iov_base || !iov.iov_len)
+ goto err;
+
+ /* arbitrary limit, but we need something */
+ if (iov.iov_len > SZ_1G)
+ goto err;
+
+ ubuf = (unsigned long) iov.iov_base;
+ end = (ubuf + iov.iov_len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ start = ubuf >> PAGE_SHIFT;
+ nr_pages = end - start;
+
+ if (ctx->account_mem) {
+ ret = io_account_mem(ctx->user, nr_pages);
+ if (ret)
+ goto err;
+ }
+
+ ret = 0;
+ if (!pages || nr_pages > got_pages) {
+ kfree(vmas);
+ kfree(pages);
+ pages = kmalloc_array(nr_pages, sizeof(struct page *),
+ GFP_KERNEL);
+ vmas = kmalloc_array(nr_pages,
+ sizeof(struct vma_area_struct *),
+ GFP_KERNEL);
+ if (!pages || !vmas) {
+ ret = -ENOMEM;
+ if (ctx->account_mem)
+ io_unaccount_mem(ctx->user, nr_pages);
+ goto err;
+ }
+ got_pages = nr_pages;
+ }
+
+ imu->bvec = kmalloc_array(nr_pages, sizeof(struct bio_vec),
+ GFP_KERNEL);
+ ret = -ENOMEM;
+ if (!imu->bvec) {
+ if (ctx->account_mem)
+ io_unaccount_mem(ctx->user, nr_pages);
+ goto err;
+ }
+
+ ret = 0;
+ down_read(¤t->mm->mmap_sem);
+ pret = get_user_pages_longterm(ubuf, nr_pages, FOLL_WRITE,
+ pages, vmas);
+ if (pret == nr_pages) {
+ /* don't support file backed memory */
+ for (j = 0; j < nr_pages; j++) {
+ struct vm_area_struct *vma = vmas[j];
+
+ if (vma->vm_file &&
+ !is_file_hugepages(vma->vm_file)) {
+ ret = -EOPNOTSUPP;
+ break;
+ }
+ }
+ } else {
+ ret = pret < 0 ? pret : -EFAULT;
+ }
+ up_read(¤t->mm->mmap_sem);
+ if (ret) {
+ /*
+ * if we did partial map, or found file backed vmas,
+ * release any pages we did get
+ */
+ if (pret > 0) {
+ for (j = 0; j < pret; j++)
+ put_page(pages[j]);
+ }
+ if (ctx->account_mem)
+ io_unaccount_mem(ctx->user, nr_pages);
+ goto err;
+ }
+
+ off = ubuf & ~PAGE_MASK;
+ size = iov.iov_len;
+ for (j = 0; j < nr_pages; j++) {
+ size_t vec_len;
+
+ vec_len = min_t(size_t, size, PAGE_SIZE - off);
+ imu->bvec[j].bv_page = pages[j];
+ imu->bvec[j].bv_len = vec_len;
+ imu->bvec[j].bv_offset = off;
+ off = 0;
+ size -= vec_len;
+ }
+ /* store original address for later verification */
+ imu->ubuf = ubuf;
+ imu->len = iov.iov_len;
+ imu->nr_bvecs = nr_pages;
+ }
+ kfree(pages);
+ kfree(vmas);
+ ctx->nr_user_bufs = nr_args;
+ return 0;
+err:
+ kfree(pages);
+ kfree(vmas);
+ io_sqe_buffer_unregister(ctx);
+ return ret;
+}
+
static void io_ring_ctx_free(struct io_ring_ctx *ctx)
{
if (ctx->sqo_wq)
@@ -1316,6 +1608,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
mmdrop(ctx->sqo_mm);
io_iopoll_reap_events(ctx);
+ io_sqe_buffer_unregister(ctx);
#if defined(CONFIG_UNIX)
if (ctx->ring_sock)
@@ -1677,6 +1970,60 @@ SYSCALL_DEFINE2(io_uring_setup, u32, entries,
return io_uring_setup(entries, params);
}
+static int __io_uring_register(struct io_ring_ctx *ctx, unsigned opcode,
+ void __user *arg, unsigned nr_args)
+{
+ int ret;
+
+ percpu_ref_kill(&ctx->refs);
+ wait_for_completion(&ctx->ctx_done);
+
+ switch (opcode) {
+ case IORING_REGISTER_BUFFERS:
+ ret = io_sqe_buffer_register(ctx, arg, nr_args);
+ break;
+ case IORING_UNREGISTER_BUFFERS:
+ ret = -EINVAL;
+ if (arg || nr_args)
+ break;
+ ret = io_sqe_buffer_unregister(ctx);
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ /* bring the ctx back to life */
+ reinit_completion(&ctx->ctx_done);
+ percpu_ref_reinit(&ctx->refs);
+ return ret;
+}
+
+SYSCALL_DEFINE4(io_uring_register, unsigned int, fd, unsigned int, opcode,
+ void __user *, arg, unsigned int, nr_args)
+{
+ struct io_ring_ctx *ctx;
+ long ret = -EBADF;
+ struct fd f;
+
+ f = fdget(fd);
+ if (!f.file)
+ return -EBADF;
+
+ ret = -EOPNOTSUPP;
+ if (f.file->f_op != &io_uring_fops)
+ goto out_fput;
+
+ ctx = f.file->private_data;
+
+ mutex_lock(&ctx->uring_lock);
+ ret = __io_uring_register(ctx, opcode, arg, nr_args);
+ mutex_unlock(&ctx->uring_lock);
+out_fput:
+ fdput(f);
+ return ret;
+}
+
static int __init io_uring_init(void)
{
req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC);
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,
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 87871e7b7ea7..d346229a1eb0 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -744,9 +744,11 @@ __SYSCALL(__NR_kexec_file_load, sys_kexec_file_load)
__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
#define __NR_io_uring_enter 426
__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
+#define __NR_io_uring_register 427
+__SYSCALL(__NR_io_uring_register, sys_io_uring_register)
#undef __NR_syscalls
-#define __NR_syscalls 427
+#define __NR_syscalls 428
/*
* 32 bit systems traditionally used different
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 5c457ea396e6..cf28f7a11f12 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -27,7 +27,10 @@ struct io_uring_sqe {
__u32 fsync_flags;
};
__u64 user_data; /* data to be passed back at completion time */
- __u64 __pad2[3];
+ union {
+ __u16 buf_index; /* index into fixed buffers, if used */
+ __u64 __pad2[3];
+ };
};
/*
@@ -39,6 +42,8 @@ struct io_uring_sqe {
#define IORING_OP_READV 1
#define IORING_OP_WRITEV 2
#define IORING_OP_FSYNC 3
+#define IORING_OP_READ_FIXED 4
+#define IORING_OP_WRITE_FIXED 5
/*
* sqe->fsync_flags
@@ -103,4 +108,10 @@ struct io_uring_params {
struct io_cqring_offsets cq_off;
};
+/*
+ * io_uring_register(2) opcodes and arguments
+ */
+#define IORING_REGISTER_BUFFERS 0
+#define IORING_UNREGISTER_BUFFERS 1
+
#endif
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index ee5e523564bb..1bb6604dc19f 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -48,6 +48,7 @@ COND_SYSCALL_COMPAT(io_getevents);
COND_SYSCALL_COMPAT(io_pgetevents);
COND_SYSCALL(io_uring_setup);
COND_SYSCALL(io_uring_enter);
+COND_SYSCALL(io_uring_register);
/* fs/xattr.c */
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 11/19] block: implement bio helper to add iter bvec pages to bio
From: Jens Axboe @ 2019-02-11 19:00 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api
Cc: hch, jmoyer, avi, jannh, viro, Jens Axboe
In-Reply-To: <20190211190049.7888-1-axboe@kernel.dk>
For an ITER_BVEC, we can just iterate the iov and add the pages
to the bio directly. This requires that the caller doesn't releases
the pages on IO completion, we add a BIO_NO_PAGE_REF flag for that.
The current two callers of bio_iov_iter_get_pages() are updated to
check if they need to release pages on completion. This makes them
work with bvecs that contain kernel mapped pages already.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
block/bio.c | 59 ++++++++++++++++++++++++++++++++-------
fs/block_dev.c | 5 ++--
fs/iomap.c | 5 ++--
include/linux/blk_types.h | 1 +
4 files changed, 56 insertions(+), 14 deletions(-)
diff --git a/block/bio.c b/block/bio.c
index 4db1008309ed..330df572cfb8 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -828,6 +828,23 @@ int bio_add_page(struct bio *bio, struct page *page,
}
EXPORT_SYMBOL(bio_add_page);
+static int __bio_iov_bvec_add_pages(struct bio *bio, struct iov_iter *iter)
+{
+ const struct bio_vec *bv = iter->bvec;
+ unsigned int len;
+ size_t size;
+
+ len = min_t(size_t, bv->bv_len, iter->count);
+ size = bio_add_page(bio, bv->bv_page, len,
+ bv->bv_offset + iter->iov_offset);
+ if (size == len) {
+ iov_iter_advance(iter, size);
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
#define PAGE_PTRS_PER_BVEC (sizeof(struct bio_vec) / sizeof(struct page *))
/**
@@ -876,23 +893,43 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
}
/**
- * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio
+ * bio_iov_iter_get_pages - add user or kernel pages to a bio
* @bio: bio to add pages to
- * @iter: iov iterator describing the region to be mapped
+ * @iter: iov iterator describing the region to be added
+ *
+ * This takes either an iterator pointing to user memory, or one pointing to
+ * kernel pages (BVEC iterator). If we're adding user pages, we pin them and
+ * map them into the kernel. On IO completion, the caller should put those
+ * pages. If we're adding kernel pages, we just have to add the pages to the
+ * bio directly. We don't grab an extra reference to those pages (the user
+ * should already have that), and we don't put the page on IO completion.
+ * The caller needs to check if the bio is flagged BIO_NO_PAGE_REF on IO
+ * completion. If it isn't, then pages should be released.
*
- * Pins pages from *iter and appends them to @bio's bvec array. The
- * pages will have to be released using put_page() when done.
* The function tries, but does not guarantee, to pin as many pages as
- * fit into the bio, or are requested in *iter, whatever is smaller.
- * If MM encounters an error pinning the requested pages, it stops.
- * Error is returned only if 0 pages could be pinned.
+ * fit into the bio, or are requested in *iter, whatever is smaller. If
+ * MM encounters an error pinning the requested pages, it stops. Error
+ * is returned only if 0 pages could be pinned.
*/
int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
{
+ const bool is_bvec = iov_iter_is_bvec(iter);
unsigned short orig_vcnt = bio->bi_vcnt;
+ /*
+ * If this is a BVEC iter, then the pages are kernel pages. Don't
+ * release them on IO completion.
+ */
+ if (is_bvec)
+ bio_set_flag(bio, BIO_NO_PAGE_REF);
+
do {
- int ret = __bio_iov_iter_get_pages(bio, iter);
+ int ret;
+
+ if (is_bvec)
+ ret = __bio_iov_bvec_add_pages(bio, iter);
+ else
+ ret = __bio_iov_iter_get_pages(bio, iter);
if (unlikely(ret))
return bio->bi_vcnt > orig_vcnt ? 0 : ret;
@@ -1634,7 +1671,8 @@ static void bio_dirty_fn(struct work_struct *work)
next = bio->bi_private;
bio_set_pages_dirty(bio);
- bio_release_pages(bio);
+ if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+ bio_release_pages(bio);
bio_put(bio);
}
}
@@ -1650,7 +1688,8 @@ void bio_check_pages_dirty(struct bio *bio)
goto defer;
}
- bio_release_pages(bio);
+ if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+ bio_release_pages(bio);
bio_put(bio);
return;
defer:
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 392e2bfb636f..051ab41d1c61 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -338,8 +338,9 @@ static void blkdev_bio_end_io(struct bio *bio)
struct bio_vec *bvec;
int i;
- bio_for_each_segment_all(bvec, bio, i)
- put_page(bvec->bv_page);
+ if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+ bio_for_each_segment_all(bvec, bio, i)
+ put_page(bvec->bv_page);
bio_put(bio);
}
}
diff --git a/fs/iomap.c b/fs/iomap.c
index 2ac9eb746d44..9389cf0a1c6f 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1591,8 +1591,9 @@ static void iomap_dio_bio_end_io(struct bio *bio)
struct bio_vec *bvec;
int i;
- bio_for_each_segment_all(bvec, bio, i)
- put_page(bvec->bv_page);
+ if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+ bio_for_each_segment_all(bvec, bio, i)
+ put_page(bvec->bv_page);
bio_put(bio);
}
}
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d66bf5f32610..791fee35df88 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -215,6 +215,7 @@ struct bio {
/*
* bio flags
*/
+#define BIO_NO_PAGE_REF 0 /* don't put release vec pages */
#define BIO_SEG_VALID 1 /* bi_phys_segments valid */
#define BIO_CLONED 2 /* doesn't own data */
#define BIO_BOUNCED 3 /* bio is a bounce bio */
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 10/19] io_uring: batch io_kiocb allocation
From: Jens Axboe @ 2019-02-11 19:00 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api
Cc: hch, jmoyer, avi, jannh, viro, Jens Axboe
In-Reply-To: <20190211190049.7888-1-axboe@kernel.dk>
Similarly to how we use the state->ios_left to know how many references
to get to a file, we can use it to allocate the io_kiocb's we need in
bulk.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/io_uring.c | 45 ++++++++++++++++++++++++++++++++++++++-------
1 file changed, 38 insertions(+), 7 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 7358dd1dbf3f..e330252dc5de 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -168,6 +168,13 @@ struct io_kiocb {
struct io_submit_state {
struct blk_plug plug;
+ /*
+ * io_kiocb alloc cache
+ */
+ void *reqs[IO_IOPOLL_BATCH];
+ unsigned int free_reqs;
+ unsigned int cur_req;
+
/*
* File reference cache
*/
@@ -305,20 +312,40 @@ static void io_ring_drop_ctx_refs(struct io_ring_ctx *ctx, unsigned refs)
wake_up(&ctx->wait);
}
-static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx)
+static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
+ struct io_submit_state *state)
{
struct io_kiocb *req;
if (!percpu_ref_tryget(&ctx->refs))
return NULL;
- req = kmem_cache_alloc(req_cachep, __GFP_NOWARN);
- if (req) {
- req->ctx = ctx;
- req->flags = 0;
- return req;
+ if (!state) {
+ req = kmem_cache_alloc(req_cachep, __GFP_NOWARN);
+ if (unlikely(!req))
+ goto out;
+ } else if (!state->free_reqs) {
+ size_t sz;
+ int ret;
+
+ sz = min_t(size_t, state->ios_left, ARRAY_SIZE(state->reqs));
+ ret = kmem_cache_alloc_bulk(req_cachep, __GFP_NOWARN, sz,
+ state->reqs);
+ if (unlikely(ret <= 0))
+ goto out;
+ state->free_reqs = ret - 1;
+ state->cur_req = 1;
+ req = state->reqs[0];
+ } else {
+ req = state->reqs[state->cur_req];
+ state->free_reqs--;
+ state->cur_req++;
}
+ req->ctx = ctx;
+ req->flags = 0;
+ return req;
+out:
io_ring_drop_ctx_refs(ctx, 1);
return NULL;
}
@@ -1007,7 +1034,7 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
if (unlikely(s->sqe->flags))
return -EINVAL;
- req = io_get_req(ctx);
+ req = io_get_req(ctx, state);
if (unlikely(!req))
return -EAGAIN;
@@ -1041,6 +1068,9 @@ static void io_submit_state_end(struct io_submit_state *state)
{
blk_finish_plug(&state->plug);
io_file_put(state, NULL);
+ if (state->free_reqs)
+ kmem_cache_free_bulk(req_cachep, state->free_reqs,
+ &state->reqs[state->cur_req]);
}
/*
@@ -1050,6 +1080,7 @@ static void io_submit_state_start(struct io_submit_state *state,
struct io_ring_ctx *ctx, unsigned max_ios)
{
blk_start_plug(&state->plug);
+ state->free_reqs = 0;
state->file = NULL;
state->ios_left = max_ios;
}
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 09/19] io_uring: use fget/fput_many() for file references
From: Jens Axboe @ 2019-02-11 19:00 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api
Cc: hch, jmoyer, avi, jannh, viro, Jens Axboe
In-Reply-To: <20190211190049.7888-1-axboe@kernel.dk>
Add a separate io_submit_state structure, to cache some of the things
we need for IO submission.
One such example is file reference batching. io_submit_state. We get as
many references as the number of sqes we are submitting, and drop
unused ones if we end up switching files. The assumption here is that
we're usually only dealing with one fd, and if there are multiple,
hopefuly they are at least somewhat ordered. Could trivially be extended
to cover multiple fds, if needed.
On the completion side we do the same thing, except this is trivially
done just locally in io_iopoll_reap().
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/io_uring.c | 142 ++++++++++++++++++++++++++++++++++++++++++--------
1 file changed, 121 insertions(+), 21 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 30efe5edf6aa..7358dd1dbf3f 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -165,6 +165,19 @@ struct io_kiocb {
#define IO_PLUG_THRESHOLD 2
#define IO_IOPOLL_BATCH 8
+struct io_submit_state {
+ struct blk_plug plug;
+
+ /*
+ * File reference cache
+ */
+ struct file *file;
+ unsigned int fd;
+ unsigned int has_refs;
+ unsigned int used_refs;
+ unsigned int ios_left;
+};
+
static struct kmem_cache *req_cachep;
static const struct file_operations io_uring_fops;
@@ -332,9 +345,11 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
struct list_head *done)
{
void *reqs[IO_IOPOLL_BATCH];
+ int file_count, to_free;
+ struct file *file = NULL;
struct io_kiocb *req;
- int to_free = 0;
+ file_count = to_free = 0;
while (!list_empty(done)) {
req = list_first_entry(done, struct io_kiocb, list);
list_del(&req->list);
@@ -344,12 +359,28 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
reqs[to_free++] = req;
(*nr_events)++;
- fput(req->rw.ki_filp);
+ /*
+ * Batched puts of the same file, to avoid dirtying the
+ * file usage count multiple times, if avoidable.
+ */
+ if (!file) {
+ file = req->rw.ki_filp;
+ file_count = 1;
+ } else if (file == req->rw.ki_filp) {
+ file_count++;
+ } else {
+ fput_many(file, file_count);
+ file = req->rw.ki_filp;
+ file_count = 1;
+ }
+
if (to_free == ARRAY_SIZE(reqs))
io_free_req_many(ctx, reqs, &to_free);
}
io_commit_cqring(ctx);
+ if (file)
+ fput_many(file, file_count);
io_free_req_many(ctx, reqs, &to_free);
}
@@ -530,6 +561,48 @@ static void io_iopoll_req_issued(struct io_kiocb *req)
list_add_tail(&req->list, &ctx->poll_list);
}
+static void io_file_put(struct io_submit_state *state, struct file *file)
+{
+ if (!state) {
+ fput(file);
+ } else if (state->file) {
+ int diff = state->has_refs - state->used_refs;
+
+ if (diff)
+ fput_many(state->file, diff);
+ state->file = NULL;
+ }
+}
+
+/*
+ * Get as many references to a file as we have IOs left in this submission,
+ * assuming most submissions are for one file, or at least that each file
+ * has more than one submission.
+ */
+static struct file *io_file_get(struct io_submit_state *state, int fd)
+{
+ if (!state)
+ return fget(fd);
+
+ if (state->file) {
+ if (state->fd == fd) {
+ state->used_refs++;
+ state->ios_left--;
+ return state->file;
+ }
+ io_file_put(state, NULL);
+ }
+ state->file = fget_many(fd, state->ios_left);
+ if (!state->file)
+ return NULL;
+
+ state->fd = fd;
+ state->has_refs = state->ios_left;
+ state->used_refs = 1;
+ state->ios_left--;
+ return state->file;
+}
+
/*
* If we tracked the file through the SCM inflight mechanism, we could support
* any file. For now, just ensure that anything potentially problematic is done
@@ -548,7 +621,7 @@ static bool io_file_supports_async(struct file *file)
}
static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
- bool force_nonblock)
+ bool force_nonblock, struct io_submit_state *state)
{
struct io_ring_ctx *ctx = req->ctx;
struct kiocb *kiocb = &req->rw;
@@ -560,7 +633,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
return 0;
fd = READ_ONCE(sqe->fd);
- kiocb->ki_filp = fget(fd);
+ kiocb->ki_filp = io_file_get(state, fd);
if (unlikely(!kiocb->ki_filp))
return -EBADF;
if (force_nonblock && !io_file_supports_async(kiocb->ki_filp))
@@ -604,7 +677,10 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
}
return 0;
out_fput:
- fput(kiocb->ki_filp);
+ /* in case of error, we didn't use this file reference. drop it. */
+ if (state)
+ state->used_refs--;
+ io_file_put(state, kiocb->ki_filp);
return ret;
}
@@ -650,7 +726,7 @@ static int io_import_iovec(struct io_ring_ctx *ctx, int rw,
}
static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s,
- bool force_nonblock)
+ bool force_nonblock, struct io_submit_state *state)
{
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct kiocb *kiocb = &req->rw;
@@ -658,7 +734,7 @@ static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s,
struct file *file;
ssize_t ret;
- ret = io_prep_rw(req, s->sqe, force_nonblock);
+ ret = io_prep_rw(req, s->sqe, force_nonblock, state);
if (ret)
return ret;
file = kiocb->ki_filp;
@@ -694,7 +770,7 @@ static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s,
}
static ssize_t io_write(struct io_kiocb *req, const struct sqe_submit *s,
- bool force_nonblock)
+ bool force_nonblock, struct io_submit_state *state)
{
struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
struct kiocb *kiocb = &req->rw;
@@ -702,7 +778,7 @@ static ssize_t io_write(struct io_kiocb *req, const struct sqe_submit *s,
struct file *file;
ssize_t ret;
- ret = io_prep_rw(req, s->sqe, force_nonblock);
+ ret = io_prep_rw(req, s->sqe, force_nonblock, state);
if (ret)
return ret;
/* Hold on to the file for -EAGAIN */
@@ -826,7 +902,8 @@ static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe,
}
static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
- const struct sqe_submit *s, bool force_nonblock)
+ const struct sqe_submit *s, bool force_nonblock,
+ struct io_submit_state *state)
{
ssize_t ret;
int opcode;
@@ -841,10 +918,10 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
ret = io_nop(req, req->user_data);
break;
case IORING_OP_READV:
- ret = io_read(req, s, force_nonblock);
+ ret = io_read(req, s, force_nonblock, state);
break;
case IORING_OP_WRITEV:
- ret = io_write(req, s, force_nonblock);
+ ret = io_write(req, s, force_nonblock, state);
break;
case IORING_OP_FSYNC:
ret = io_fsync(req, s->sqe, force_nonblock);
@@ -896,7 +973,7 @@ static void io_sq_wq_submit_work(struct work_struct *work)
s->needs_lock = true;
do {
- ret = __io_submit_sqe(ctx, req, s, false);
+ ret = __io_submit_sqe(ctx, req, s, false, NULL);
/*
* We can get EAGAIN for polled IO even though we're forcing
* a sync submission from here, since we can't wait for
@@ -920,7 +997,8 @@ static void io_sq_wq_submit_work(struct work_struct *work)
kfree(sqe);
}
-static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s)
+static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
+ struct io_submit_state *state)
{
struct io_kiocb *req;
ssize_t ret;
@@ -935,7 +1013,7 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s)
req->rw.ki_filp = NULL;
- ret = __io_submit_sqe(ctx, req, s, true);
+ ret = __io_submit_sqe(ctx, req, s, true, state);
if (ret == -EAGAIN) {
struct io_uring_sqe *sqe_copy;
@@ -956,6 +1034,26 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s)
return ret;
}
+/*
+ * Batched submission is done, ensure local IO is flushed out.
+ */
+static void io_submit_state_end(struct io_submit_state *state)
+{
+ blk_finish_plug(&state->plug);
+ io_file_put(state, NULL);
+}
+
+/*
+ * Start submission side cache.
+ */
+static void io_submit_state_start(struct io_submit_state *state,
+ struct io_ring_ctx *ctx, unsigned max_ios)
+{
+ blk_start_plug(&state->plug);
+ state->file = NULL;
+ state->ios_left = max_ios;
+}
+
static void io_commit_sqring(struct io_ring_ctx *ctx)
{
struct io_sq_ring *ring = ctx->sq_ring;
@@ -1023,11 +1121,13 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
{
+ struct io_submit_state state, *statep = NULL;
int i, ret = 0, submit = 0;
- struct blk_plug plug;
- if (to_submit > IO_PLUG_THRESHOLD)
- blk_start_plug(&plug);
+ if (to_submit > IO_PLUG_THRESHOLD) {
+ io_submit_state_start(&state, ctx, to_submit);
+ statep = &state;
+ }
for (i = 0; i < to_submit; i++) {
struct sqe_submit s;
@@ -1038,7 +1138,7 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
s.has_user = true;
s.needs_lock = false;
- ret = io_submit_sqe(ctx, &s);
+ ret = io_submit_sqe(ctx, &s, statep);
if (ret) {
io_drop_sqring(ctx);
break;
@@ -1048,8 +1148,8 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
}
io_commit_sqring(ctx);
- if (to_submit > IO_PLUG_THRESHOLD)
- blk_finish_plug(&plug);
+ if (statep)
+ io_submit_state_end(statep);
return submit ? submit : ret;
}
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 08/19] fs: add fget_many() and fput_many()
From: Jens Axboe @ 2019-02-11 19:00 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api
Cc: hch, jmoyer, avi, jannh, viro, Jens Axboe
In-Reply-To: <20190211190049.7888-1-axboe@kernel.dk>
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 <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/file.c | 15 ++++++++++-----
fs/file_table.c | 9 +++++++--
include/linux/file.h | 2 ++
include/linux/fs.h | 4 +++-
4 files changed, 22 insertions(+), 8 deletions(-)
diff --git a/fs/file.c b/fs/file.c
index 3209ee271c41..97df385d6ab0 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -705,7 +705,7 @@ void do_close_on_exec(struct files_struct *files)
spin_unlock(&files->file_lock);
}
-static struct file *__fget(unsigned int fd, fmode_t mask)
+static struct file *__fget(unsigned int fd, fmode_t mask, unsigned int refs)
{
struct files_struct *files = current->files;
struct file *file;
@@ -720,7 +720,7 @@ static struct file *__fget(unsigned int fd, fmode_t mask)
*/
if (file->f_mode & mask)
file = NULL;
- else if (!get_file_rcu(file))
+ else if (!get_file_rcu_many(file, refs))
goto loop;
}
rcu_read_unlock();
@@ -728,15 +728,20 @@ static struct file *__fget(unsigned int fd, fmode_t mask)
return file;
}
+struct file *fget_many(unsigned int fd, unsigned int refs)
+{
+ return __fget(fd, FMODE_PATH, refs);
+}
+
struct file *fget(unsigned int fd)
{
- return __fget(fd, FMODE_PATH);
+ return __fget(fd, FMODE_PATH, 1);
}
EXPORT_SYMBOL(fget);
struct file *fget_raw(unsigned int fd)
{
- return __fget(fd, 0);
+ return __fget(fd, 0, 1);
}
EXPORT_SYMBOL(fget_raw);
@@ -767,7 +772,7 @@ static unsigned long __fget_light(unsigned int fd, fmode_t mask)
return 0;
return (unsigned long)file;
} else {
- file = __fget(fd, mask);
+ file = __fget(fd, mask, 1);
if (!file)
return 0;
return FDPUT_FPUT | (unsigned long)file;
diff --git a/fs/file_table.c b/fs/file_table.c
index 5679e7fcb6b0..155d7514a094 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -326,9 +326,9 @@ void flush_delayed_fput(void)
static DECLARE_DELAYED_WORK(delayed_fput_work, delayed_fput);
-void fput(struct file *file)
+void fput_many(struct file *file, unsigned int refs)
{
- if (atomic_long_dec_and_test(&file->f_count)) {
+ if (atomic_long_sub_and_test(refs, &file->f_count)) {
struct task_struct *task = current;
if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
@@ -347,6 +347,11 @@ void fput(struct file *file)
}
}
+void fput(struct file *file)
+{
+ fput_many(file, 1);
+}
+
/*
* synchronous analog of fput(); for kernel threads that might be needed
* in some umount() (and thus can't use flush_delayed_fput() without
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)
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 07/19] io_uring: support for IO polling
From: Jens Axboe @ 2019-02-11 19:00 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api
Cc: hch, jmoyer, avi, jannh, viro, Jens Axboe
In-Reply-To: <20190211190049.7888-1-axboe@kernel.dk>
Add support for a polled io_uring instance. When a read or write is
submitted to a polled io_uring, the application must poll for
completions on the CQ ring through io_uring_enter(2). Polled IO may not
generate IRQ completions, hence they need to be actively found by the
application itself.
To use polling, io_uring_setup() must be used with the
IORING_SETUP_IOPOLL flag being set. It is illegal to mix and match
polled and non-polled IO on an io_uring.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/io_uring.c | 275 ++++++++++++++++++++++++++++++++--
include/uapi/linux/io_uring.h | 5 +
2 files changed, 271 insertions(+), 9 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index dc9155b7294e..30efe5edf6aa 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -124,6 +124,14 @@ struct io_ring_ctx {
struct {
spinlock_t completion_lock;
+ bool poll_multi_file;
+ /*
+ * ->poll_list is protected by the ctx->uring_lock for
+ * io_uring instances that don't use IORING_SETUP_SQPOLL.
+ * For SQPOLL, only the single threaded io_sq_thread() will
+ * manipulate the list, hence no extra locking is needed there.
+ */
+ struct list_head poll_list;
} ____cacheline_aligned_in_smp;
#if defined(CONFIG_UNIX)
@@ -135,6 +143,7 @@ struct sqe_submit {
const struct io_uring_sqe *sqe;
unsigned short index;
bool has_user;
+ bool needs_lock;
};
struct io_kiocb {
@@ -146,12 +155,15 @@ struct io_kiocb {
struct list_head list;
unsigned int flags;
#define REQ_F_FORCE_NONBLOCK 1 /* inline submission attempt */
+#define REQ_F_IOPOLL_COMPLETED 2 /* polled IO has completed */
u64 user_data;
+ u64 error;
struct work_struct work;
};
#define IO_PLUG_THRESHOLD 2
+#define IO_IOPOLL_BATCH 8
static struct kmem_cache *req_cachep;
@@ -196,6 +208,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
mutex_init(&ctx->uring_lock);
init_waitqueue_head(&ctx->wait);
spin_lock_init(&ctx->completion_lock);
+ INIT_LIST_HEAD(&ctx->poll_list);
return ctx;
}
@@ -297,12 +310,153 @@ static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx)
return NULL;
}
+static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr)
+{
+ if (*nr) {
+ kmem_cache_free_bulk(req_cachep, *nr, reqs);
+ io_ring_drop_ctx_refs(ctx, *nr);
+ *nr = 0;
+ }
+}
+
static void io_free_req(struct io_kiocb *req)
{
io_ring_drop_ctx_refs(req->ctx, 1);
kmem_cache_free(req_cachep, req);
}
+/*
+ * Find and free completed poll iocbs
+ */
+static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
+ struct list_head *done)
+{
+ void *reqs[IO_IOPOLL_BATCH];
+ struct io_kiocb *req;
+ int to_free = 0;
+
+ while (!list_empty(done)) {
+ req = list_first_entry(done, struct io_kiocb, list);
+ list_del(&req->list);
+
+ io_cqring_fill_event(ctx, req->user_data, req->error, 0);
+
+ reqs[to_free++] = req;
+ (*nr_events)++;
+
+ fput(req->rw.ki_filp);
+ if (to_free == ARRAY_SIZE(reqs))
+ io_free_req_many(ctx, reqs, &to_free);
+ }
+ io_commit_cqring(ctx);
+
+ io_free_req_many(ctx, reqs, &to_free);
+}
+
+static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events,
+ long min)
+{
+ struct io_kiocb *req, *tmp;
+ LIST_HEAD(done);
+ bool spin;
+ int ret;
+
+ /*
+ * Only spin for completions if we don't have multiple devices hanging
+ * off our complete list, and we're under the requested amount.
+ */
+ spin = !ctx->poll_multi_file && *nr_events < min;
+
+ ret = 0;
+ list_for_each_entry_safe(req, tmp, &ctx->poll_list, list) {
+ struct kiocb *kiocb = &req->rw;
+
+ /*
+ * Move completed entries to our local list. If we find a
+ * request that requires polling, break out and complete
+ * the done list first, if we have entries there.
+ */
+ if (req->flags & REQ_F_IOPOLL_COMPLETED) {
+ list_move_tail(&req->list, &done);
+ continue;
+ }
+ if (!list_empty(&done))
+ break;
+
+ ret = kiocb->ki_filp->f_op->iopoll(kiocb, spin);
+ if (ret < 0)
+ break;
+
+ if (ret && spin)
+ spin = false;
+ ret = 0;
+ }
+
+ if (!list_empty(&done))
+ io_iopoll_complete(ctx, nr_events, &done);
+
+ return ret;
+}
+
+/*
+ * Poll for a mininum of 'min' events. Note that if min == 0 we consider that a
+ * non-spinning poll check - we'll still enter the driver poll loop, but only
+ * as a non-spinning completion check.
+ */
+static int io_iopoll_getevents(struct io_ring_ctx *ctx, unsigned int *nr_events,
+ long min)
+{
+ while (!list_empty(&ctx->poll_list)) {
+ int ret;
+
+ ret = io_do_iopoll(ctx, nr_events, min);
+ if (ret < 0)
+ return ret;
+ if (!min || *nr_events >= min)
+ return 0;
+ }
+
+ return 1;
+}
+
+/*
+ * We can't just wait for polled events to come to us, we have to actively
+ * find and complete them.
+ */
+static void io_iopoll_reap_events(struct io_ring_ctx *ctx)
+{
+ if (!(ctx->flags & IORING_SETUP_IOPOLL))
+ return;
+
+ mutex_lock(&ctx->uring_lock);
+ while (!list_empty(&ctx->poll_list)) {
+ unsigned int nr_events = 0;
+
+ io_iopoll_getevents(ctx, &nr_events, 1);
+ }
+ mutex_unlock(&ctx->uring_lock);
+}
+
+static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
+ long min)
+{
+ int ret = 0;
+
+ do {
+ int tmin = 0;
+
+ if (*nr_events < min)
+ tmin = min - *nr_events;
+
+ ret = io_iopoll_getevents(ctx, nr_events, tmin);
+ if (ret <= 0)
+ break;
+ ret = 0;
+ } while (min && !*nr_events && !need_resched());
+
+ return ret;
+}
+
static void kiocb_end_write(struct kiocb *kiocb)
{
if (kiocb->ki_flags & IOCB_WRITE) {
@@ -329,6 +483,53 @@ static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
io_free_req(req);
}
+static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2)
+{
+ struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
+
+ kiocb_end_write(kiocb);
+
+ req->error = res;
+ if (res != -EAGAIN)
+ req->flags |= REQ_F_IOPOLL_COMPLETED;
+}
+
+/*
+ * After the iocb has been issued, it's safe to be found on the poll list.
+ * Adding the kiocb to the list AFTER submission ensures that we don't
+ * find it from a io_iopoll_getevents() thread before the issuer is done
+ * accessing the kiocb cookie.
+ */
+static void io_iopoll_req_issued(struct io_kiocb *req)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+
+ /*
+ * Track whether we have multiple files in our lists. This will impact
+ * how we do polling eventually, not spinning if we're on potentially
+ * different devices.
+ */
+ if (list_empty(&ctx->poll_list)) {
+ ctx->poll_multi_file = false;
+ } else if (!ctx->poll_multi_file) {
+ struct io_kiocb *list_req;
+
+ list_req = list_first_entry(&ctx->poll_list, struct io_kiocb,
+ list);
+ if (list_req->rw.ki_filp != req->rw.ki_filp)
+ ctx->poll_multi_file = true;
+ }
+
+ /*
+ * For fast devices, IO may have already completed. If it has, add
+ * it to the front so we find it first.
+ */
+ if (req->flags & REQ_F_IOPOLL_COMPLETED)
+ list_add(&req->list, &ctx->poll_list);
+ else
+ list_add_tail(&req->list, &ctx->poll_list);
+}
+
/*
* If we tracked the file through the SCM inflight mechanism, we could support
* any file. For now, just ensure that anything potentially problematic is done
@@ -349,6 +550,7 @@ static bool io_file_supports_async(struct file *file)
static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
bool force_nonblock)
{
+ struct io_ring_ctx *ctx = req->ctx;
struct kiocb *kiocb = &req->rw;
unsigned ioprio;
int fd, ret;
@@ -384,12 +586,22 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
kiocb->ki_flags |= IOCB_NOWAIT;
req->flags |= REQ_F_FORCE_NONBLOCK;
}
- if (kiocb->ki_flags & IOCB_HIPRI) {
- ret = -EINVAL;
- goto out_fput;
- }
+ if (ctx->flags & IORING_SETUP_IOPOLL) {
+ ret = -EOPNOTSUPP;
+ if (!(kiocb->ki_flags & IOCB_DIRECT) ||
+ !kiocb->ki_filp->f_op->iopoll)
+ goto out_fput;
- kiocb->ki_complete = io_complete_rw;
+ req->error = 0;
+ kiocb->ki_flags |= IOCB_HIPRI;
+ kiocb->ki_complete = io_complete_rw_iopoll;
+ } else {
+ if (kiocb->ki_flags & IOCB_HIPRI) {
+ ret = -EINVAL;
+ goto out_fput;
+ }
+ kiocb->ki_complete = io_complete_rw;
+ }
return 0;
out_fput:
fput(kiocb->ki_filp);
@@ -543,6 +755,9 @@ static int io_nop(struct io_kiocb *req, u64 user_data)
struct io_ring_ctx *ctx = req->ctx;
long err = 0;
+ if (unlikely(ctx->flags & IORING_SETUP_IOPOLL))
+ return -EINVAL;
+
/*
* Twilight zone - it's possible that someone issued an opcode that
* has a file attached, then got -EAGAIN on submission, and changed
@@ -566,6 +781,8 @@ static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe)
if (req->rw.ki_filp)
return 0;
+ if (unlikely(req->ctx->flags & IORING_SETUP_IOPOLL))
+ return -EINVAL;
if (unlikely(sqe->addr || sqe->ioprio))
return -EINVAL;
@@ -637,7 +854,22 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
break;
}
- return ret;
+ if (ret)
+ return ret;
+
+ if (ctx->flags & IORING_SETUP_IOPOLL) {
+ if (req->error == -EAGAIN)
+ return -EAGAIN;
+
+ /* workqueue context doesn't hold uring_lock, grab it now */
+ if (s->needs_lock)
+ mutex_lock(&ctx->uring_lock);
+ io_iopoll_req_issued(req);
+ if (s->needs_lock)
+ mutex_unlock(&ctx->uring_lock);
+ }
+
+ return 0;
}
static void io_sq_wq_submit_work(struct work_struct *work)
@@ -661,8 +893,19 @@ static void io_sq_wq_submit_work(struct work_struct *work)
use_mm(ctx->sqo_mm);
set_fs(USER_DS);
s->has_user = true;
+ s->needs_lock = true;
- ret = __io_submit_sqe(ctx, req, s, false);
+ do {
+ ret = __io_submit_sqe(ctx, req, s, false);
+ /*
+ * We can get EAGAIN for polled IO even though we're forcing
+ * a sync submission from here, since we can't wait for
+ * request slots on the block side.
+ */
+ if (ret != -EAGAIN)
+ break;
+ cond_resched();
+ } while (1);
set_fs(old_fs);
unuse_mm(ctx->sqo_mm);
@@ -793,6 +1036,8 @@ static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
break;
s.has_user = true;
+ s.needs_lock = false;
+
ret = io_submit_sqe(ctx, &s);
if (ret) {
io_drop_sqring(ctx);
@@ -938,6 +1183,9 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx)
destroy_workqueue(ctx->sqo_wq);
if (ctx->sqo_mm)
mmdrop(ctx->sqo_mm);
+
+ io_iopoll_reap_events(ctx);
+
#if defined(CONFIG_UNIX)
if (ctx->ring_sock)
sock_release(ctx->ring_sock);
@@ -984,6 +1232,7 @@ static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
percpu_ref_kill(&ctx->refs);
mutex_unlock(&ctx->uring_lock);
+ io_iopoll_reap_events(ctx);
wait_for_completion(&ctx->ctx_done);
io_ring_ctx_free(ctx);
}
@@ -1064,6 +1313,8 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
goto out_ctx;
}
if (flags & IORING_ENTER_GETEVENTS) {
+ unsigned nr_events = 0;
+
/*
* The application could have included the 'to_submit' count
* in how many events it wanted to wait for. If we failed to
@@ -1073,7 +1324,13 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
if (submitted < to_submit)
min_complete = min_t(unsigned, submitted, min_complete);
- ret = io_cqring_wait(ctx, min_complete, sig, sigsz);
+ if (ctx->flags & IORING_SETUP_IOPOLL) {
+ mutex_lock(&ctx->uring_lock);
+ ret = io_iopoll_check(ctx, &nr_events, min_complete);
+ mutex_unlock(&ctx->uring_lock);
+ } else {
+ ret = io_cqring_wait(ctx, min_complete, sig, sigsz);
+ }
}
out_ctx:
@@ -1270,7 +1527,7 @@ static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
return -EINVAL;
}
- if (p.flags)
+ if (p.flags & ~IORING_SETUP_IOPOLL)
return -EINVAL;
ret = io_uring_create(entries, &p);
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 4589d56d0b68..5c457ea396e6 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -30,6 +30,11 @@ struct io_uring_sqe {
__u64 __pad2[3];
};
+/*
+ * io_uring_setup() flags
+ */
+#define IORING_SETUP_IOPOLL (1U << 0) /* io_context is polled */
+
#define IORING_OP_NOP 0
#define IORING_OP_READV 1
#define IORING_OP_WRITEV 2
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 06/19] io_uring: add fsync support
From: Jens Axboe @ 2019-02-11 19:00 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api
Cc: hch, jmoyer, avi, jannh, viro, Jens Axboe
In-Reply-To: <20190211190049.7888-1-axboe@kernel.dk>
From: Christoph Hellwig <hch@lst.de>
Add a new fsync opcode, which either syncs a range if one is passed,
or the whole file if the offset and length fields are both cleared
to zero. A flag is provided to use fdatasync semantics, that is only
force out metadata which is required to retrieve the file data, but
not others like metadata.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/io_uring.c | 54 +++++++++++++++++++++++++++++++++++
include/uapi/linux/io_uring.h | 8 +++++-
2 files changed, 61 insertions(+), 1 deletion(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 1b28d38a9b76..dc9155b7294e 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -24,6 +24,7 @@
* data that the application could potentially modify, it remains stable.
*
* Copyright (C) 2018-2019 Jens Axboe
+ * Copyright (c) 2018-2019 Christoph Hellwig
*/
#include <linux/kernel.h>
#include <linux/init.h>
@@ -557,6 +558,56 @@ static int io_nop(struct io_kiocb *req, u64 user_data)
return 0;
}
+static int io_prep_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+ int fd;
+
+ /* Prep already done */
+ if (req->rw.ki_filp)
+ return 0;
+
+ if (unlikely(sqe->addr || sqe->ioprio))
+ return -EINVAL;
+
+ fd = READ_ONCE(sqe->fd);
+ req->rw.ki_filp = fget(fd);
+ if (unlikely(!req->rw.ki_filp))
+ return -EBADF;
+
+ return 0;
+}
+
+static int io_fsync(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+ bool force_nonblock)
+{
+ loff_t sqe_off = READ_ONCE(sqe->off);
+ loff_t sqe_len = READ_ONCE(sqe->len);
+ loff_t end = sqe_off + sqe_len;
+ unsigned fsync_flags;
+ int ret;
+
+ fsync_flags = READ_ONCE(sqe->fsync_flags);
+ if (unlikely(fsync_flags & ~IORING_FSYNC_DATASYNC))
+ return -EINVAL;
+
+ ret = io_prep_fsync(req, sqe);
+ if (ret)
+ return ret;
+
+ /* fsync always requires a blocking context */
+ if (force_nonblock)
+ return -EAGAIN;
+
+ ret = vfs_fsync_range(req->rw.ki_filp, sqe_off,
+ end > 0 ? end : LLONG_MAX,
+ fsync_flags & IORING_FSYNC_DATASYNC);
+
+ fput(req->rw.ki_filp);
+ io_cqring_add_event(req->ctx, sqe->user_data, ret, 0);
+ io_free_req(req);
+ return 0;
+}
+
static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
const struct sqe_submit *s, bool force_nonblock)
{
@@ -578,6 +629,9 @@ static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
case IORING_OP_WRITEV:
ret = io_write(req, s, force_nonblock);
break;
+ case IORING_OP_FSYNC:
+ ret = io_fsync(req, s->sqe, force_nonblock);
+ break;
default:
ret = -EINVAL;
break;
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index ac692823d6f4..4589d56d0b68 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -24,7 +24,7 @@ struct io_uring_sqe {
__u32 len; /* buffer size or number of iovecs */
union {
__kernel_rwf_t rw_flags;
- __u32 __resv;
+ __u32 fsync_flags;
};
__u64 user_data; /* data to be passed back at completion time */
__u64 __pad2[3];
@@ -33,6 +33,12 @@ struct io_uring_sqe {
#define IORING_OP_NOP 0
#define IORING_OP_READV 1
#define IORING_OP_WRITEV 2
+#define IORING_OP_FSYNC 3
+
+/*
+ * sqe->fsync_flags
+ */
+#define IORING_FSYNC_DATASYNC (1U << 0)
/*
* IO completion data structure (Completion Queue Entry)
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 05/19] Add io_uring IO interface
From: Jens Axboe @ 2019-02-11 19:00 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api
Cc: hch, jmoyer, avi, jannh, viro, Jens Axboe
In-Reply-To: <20190211190049.7888-1-axboe@kernel.dk>
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 <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
arch/x86/entry/syscalls/syscall_32.tbl | 2 +
arch/x86/entry/syscalls/syscall_64.tbl | 2 +
fs/Makefile | 1 +
fs/io_uring.c | 1243 ++++++++++++++++++++++++
include/linux/fs.h | 9 +
include/linux/sched/user.h | 2 +-
include/linux/syscalls.h | 6 +
include/uapi/asm-generic/unistd.h | 6 +-
include/uapi/linux/io_uring.h | 95 ++
init/Kconfig | 9 +
kernel/sys_ni.c | 2 +
net/unix/garbage.c | 3 +
12 files changed, 1378 insertions(+), 2 deletions(-)
create mode 100644 fs/io_uring.c
create mode 100644 include/uapi/linux/io_uring.h
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index 3cf7b533b3d1..481c126259e9 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -398,3 +398,5 @@
384 i386 arch_prctl sys_arch_prctl __ia32_compat_sys_arch_prctl
385 i386 io_pgetevents sys_io_pgetevents __ia32_compat_sys_io_pgetevents
386 i386 rseq sys_rseq __ia32_sys_rseq
+425 i386 io_uring_setup sys_io_uring_setup __ia32_sys_io_uring_setup
+426 i386 io_uring_enter sys_io_uring_enter __ia32_sys_io_uring_enter
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index f0b1709a5ffb..6a32a430c8e0 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -343,6 +343,8 @@
332 common statx __x64_sys_statx
333 common io_pgetevents __x64_sys_io_pgetevents
334 common rseq __x64_sys_rseq
+425 common io_uring_setup __x64_sys_io_uring_setup
+426 common io_uring_enter __x64_sys_io_uring_enter
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/fs/Makefile b/fs/Makefile
index 293733f61594..8e15d6fc4340 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -30,6 +30,7 @@ obj-$(CONFIG_TIMERFD) += timerfd.o
obj-$(CONFIG_EVENTFD) += eventfd.o
obj-$(CONFIG_USERFAULTFD) += userfaultfd.o
obj-$(CONFIG_AIO) += aio.o
+obj-$(CONFIG_IO_URING) += io_uring.o
obj-$(CONFIG_FS_DAX) += dax.o
obj-$(CONFIG_FS_ENCRYPTION) += crypto/
obj-$(CONFIG_FILE_LOCKING) += locks.o
diff --git a/fs/io_uring.c b/fs/io_uring.c
new file mode 100644
index 000000000000..1b28d38a9b76
--- /dev/null
+++ b/fs/io_uring.c
@@ -0,0 +1,1243 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Shared application/kernel submission and completion ring pairs, for
+ * supporting fast/efficient IO.
+ *
+ * A note on the read/write ordering memory barriers that are matched between
+ * the application and kernel side. When the application reads the CQ ring
+ * tail, it must use an appropriate smp_rmb() to order with the smp_wmb()
+ * the kernel uses after writing the tail. Failure to do so could cause a
+ * delay in when the application notices that completion events available.
+ * This isn't a fatal condition. Likewise, the application must use an
+ * appropriate smp_wmb() both before writing the SQ tail, and after writing
+ * the SQ tail. The first one orders the sqe writes with the tail write, and
+ * the latter is paired with the smp_rmb() the kernel will issue before
+ * reading the SQ tail on submission.
+ *
+ * Also see the examples in the liburing library:
+ *
+ * git://git.kernel.dk/liburing
+ *
+ * io_uring also uses READ/WRITE_ONCE() for _any_ store or load that happens
+ * from data shared between the kernel and application. This is done both
+ * for ordering purposes, but also to ensure that once a value is loaded from
+ * data that the application could potentially modify, it remains stable.
+ *
+ * Copyright (C) 2018-2019 Jens Axboe
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/syscalls.h>
+#include <linux/compat.h>
+#include <linux/refcount.h>
+#include <linux/uio.h>
+
+#include <linux/sched/signal.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/fdtable.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/mmu_context.h>
+#include <linux/percpu.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+#include <linux/blkdev.h>
+#include <linux/net.h>
+#include <net/sock.h>
+#include <net/af_unix.h>
+#include <linux/anon_inodes.h>
+#include <linux/sched/mm.h>
+#include <linux/uaccess.h>
+#include <linux/nospec.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "internal.h"
+
+#define IORING_MAX_ENTRIES 4096
+
+struct io_uring {
+ u32 head ____cacheline_aligned_in_smp;
+ u32 tail ____cacheline_aligned_in_smp;
+};
+
+struct io_sq_ring {
+ struct io_uring r;
+ u32 ring_mask;
+ u32 ring_entries;
+ u32 dropped;
+ u32 flags;
+ u32 array[];
+};
+
+struct io_cq_ring {
+ struct io_uring r;
+ u32 ring_mask;
+ u32 ring_entries;
+ u32 overflow;
+ struct io_uring_cqe cqes[];
+};
+
+struct io_ring_ctx {
+ struct {
+ struct percpu_ref refs;
+ } ____cacheline_aligned_in_smp;
+
+ struct {
+ unsigned int flags;
+ bool compat;
+ bool account_mem;
+
+ /* SQ ring */
+ struct io_sq_ring *sq_ring;
+ unsigned cached_sq_head;
+ unsigned sq_entries;
+ unsigned sq_mask;
+ struct io_uring_sqe *sq_sqes;
+ } ____cacheline_aligned_in_smp;
+
+ /* IO offload */
+ struct workqueue_struct *sqo_wq;
+ struct mm_struct *sqo_mm;
+
+ struct {
+ /* CQ ring */
+ struct io_cq_ring *cq_ring;
+ unsigned cached_cq_tail;
+ unsigned cq_entries;
+ unsigned cq_mask;
+ struct wait_queue_head cq_wait;
+ struct fasync_struct *cq_fasync;
+ } ____cacheline_aligned_in_smp;
+
+ struct user_struct *user;
+
+ struct completion ctx_done;
+
+ struct {
+ struct mutex uring_lock;
+ wait_queue_head_t wait;
+ } ____cacheline_aligned_in_smp;
+
+ struct {
+ spinlock_t completion_lock;
+ } ____cacheline_aligned_in_smp;
+
+#if defined(CONFIG_UNIX)
+ struct socket *ring_sock;
+#endif
+};
+
+struct sqe_submit {
+ const struct io_uring_sqe *sqe;
+ unsigned short index;
+ bool has_user;
+};
+
+struct io_kiocb {
+ struct kiocb rw;
+
+ struct sqe_submit submit;
+
+ struct io_ring_ctx *ctx;
+ struct list_head list;
+ unsigned int flags;
+#define REQ_F_FORCE_NONBLOCK 1 /* inline submission attempt */
+ u64 user_data;
+
+ struct work_struct work;
+};
+
+#define IO_PLUG_THRESHOLD 2
+
+static struct kmem_cache *req_cachep;
+
+static const struct file_operations io_uring_fops;
+
+struct sock *io_uring_get_socket(struct file *file)
+{
+#if defined(CONFIG_UNIX)
+ if (file->f_op == &io_uring_fops) {
+ struct io_ring_ctx *ctx = file->private_data;
+
+ return ctx->ring_sock->sk;
+ }
+#endif
+ return NULL;
+}
+EXPORT_SYMBOL(io_uring_get_socket);
+
+static void io_ring_ctx_ref_free(struct percpu_ref *ref)
+{
+ struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs);
+
+ complete(&ctx->ctx_done);
+}
+
+static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p)
+{
+ struct io_ring_ctx *ctx;
+
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return NULL;
+
+ if (percpu_ref_init(&ctx->refs, io_ring_ctx_ref_free, 0, GFP_KERNEL)) {
+ kfree(ctx);
+ return NULL;
+ }
+
+ ctx->flags = p->flags;
+ init_waitqueue_head(&ctx->cq_wait);
+ init_completion(&ctx->ctx_done);
+ mutex_init(&ctx->uring_lock);
+ init_waitqueue_head(&ctx->wait);
+ spin_lock_init(&ctx->completion_lock);
+ return ctx;
+}
+
+static void io_commit_cqring(struct io_ring_ctx *ctx)
+{
+ struct io_cq_ring *ring = ctx->cq_ring;
+
+ if (ctx->cached_cq_tail != READ_ONCE(ring->r.tail)) {
+ /* order cqe stores with ring update */
+ smp_wmb();
+ WRITE_ONCE(ring->r.tail, ctx->cached_cq_tail);
+ /*
+ * Write sider barrier of tail update, app has read side. See
+ * comment at the top of this file.
+ */
+ smp_wmb();
+
+ if (wq_has_sleeper(&ctx->cq_wait)) {
+ wake_up_interruptible(&ctx->cq_wait);
+ kill_fasync(&ctx->cq_fasync, SIGIO, POLL_IN);
+ }
+ }
+}
+
+static struct io_uring_cqe *io_get_cqring(struct io_ring_ctx *ctx)
+{
+ struct io_cq_ring *ring = ctx->cq_ring;
+ unsigned tail;
+
+ tail = ctx->cached_cq_tail;
+ /* See comment at the top of the file */
+ smp_rmb();
+ if (tail + 1 == READ_ONCE(ring->r.head))
+ return NULL;
+
+ ctx->cached_cq_tail++;
+ return &ring->cqes[tail & ctx->cq_mask];
+}
+
+static void io_cqring_fill_event(struct io_ring_ctx *ctx, u64 ki_user_data,
+ long res, unsigned ev_flags)
+{
+ struct io_uring_cqe *cqe;
+
+ /*
+ * If we can't get a cq entry, userspace overflowed the
+ * submission (by quite a lot). Increment the overflow count in
+ * the ring.
+ */
+ cqe = io_get_cqring(ctx);
+ if (cqe) {
+ WRITE_ONCE(cqe->user_data, ki_user_data);
+ WRITE_ONCE(cqe->res, res);
+ WRITE_ONCE(cqe->flags, ev_flags);
+ } else {
+ unsigned overflow = READ_ONCE(ctx->cq_ring->overflow);
+
+ WRITE_ONCE(ctx->cq_ring->overflow, overflow + 1);
+ }
+}
+
+static void io_cqring_add_event(struct io_ring_ctx *ctx, u64 ki_user_data,
+ long res, unsigned ev_flags)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&ctx->completion_lock, flags);
+ io_cqring_fill_event(ctx, ki_user_data, res, ev_flags);
+ io_commit_cqring(ctx);
+ spin_unlock_irqrestore(&ctx->completion_lock, flags);
+
+ if (waitqueue_active(&ctx->wait))
+ wake_up(&ctx->wait);
+}
+
+static void io_ring_drop_ctx_refs(struct io_ring_ctx *ctx, unsigned refs)
+{
+ percpu_ref_put_many(&ctx->refs, refs);
+
+ if (waitqueue_active(&ctx->wait))
+ wake_up(&ctx->wait);
+}
+
+static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx)
+{
+ struct io_kiocb *req;
+
+ if (!percpu_ref_tryget(&ctx->refs))
+ return NULL;
+
+ req = kmem_cache_alloc(req_cachep, __GFP_NOWARN);
+ if (req) {
+ req->ctx = ctx;
+ req->flags = 0;
+ return req;
+ }
+
+ io_ring_drop_ctx_refs(ctx, 1);
+ return NULL;
+}
+
+static void io_free_req(struct io_kiocb *req)
+{
+ io_ring_drop_ctx_refs(req->ctx, 1);
+ kmem_cache_free(req_cachep, req);
+}
+
+static void kiocb_end_write(struct kiocb *kiocb)
+{
+ if (kiocb->ki_flags & IOCB_WRITE) {
+ struct inode *inode = file_inode(kiocb->ki_filp);
+
+ /*
+ * Tell lockdep we inherited freeze protection from submission
+ * thread.
+ */
+ if (S_ISREG(inode->i_mode))
+ __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
+ file_end_write(kiocb->ki_filp);
+ }
+}
+
+static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
+{
+ struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
+
+ kiocb_end_write(kiocb);
+
+ fput(kiocb->ki_filp);
+ io_cqring_add_event(req->ctx, req->user_data, res, 0);
+ io_free_req(req);
+}
+
+/*
+ * If we tracked the file through the SCM inflight mechanism, we could support
+ * any file. For now, just ensure that anything potentially problematic is done
+ * inline.
+ */
+static bool io_file_supports_async(struct file *file)
+{
+ umode_t mode = file_inode(file)->i_mode;
+
+ if (S_ISBLK(mode) || S_ISCHR(mode))
+ return true;
+ if (S_ISREG(mode) && file->f_op != &io_uring_fops)
+ return true;
+
+ return false;
+}
+
+static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
+ bool force_nonblock)
+{
+ struct kiocb *kiocb = &req->rw;
+ unsigned ioprio;
+ int fd, ret;
+
+ /* For -EAGAIN retry, everything is already prepped */
+ if (kiocb->ki_filp)
+ return 0;
+
+ fd = READ_ONCE(sqe->fd);
+ kiocb->ki_filp = fget(fd);
+ if (unlikely(!kiocb->ki_filp))
+ return -EBADF;
+ if (force_nonblock && !io_file_supports_async(kiocb->ki_filp))
+ force_nonblock = false;
+ kiocb->ki_pos = READ_ONCE(sqe->off);
+ kiocb->ki_flags = iocb_flags(kiocb->ki_filp);
+ kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp));
+
+ ioprio = READ_ONCE(sqe->ioprio);
+ if (ioprio) {
+ ret = ioprio_check_cap(ioprio);
+ if (ret)
+ goto out_fput;
+
+ kiocb->ki_ioprio = ioprio;
+ } else
+ kiocb->ki_ioprio = get_current_ioprio();
+
+ ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags));
+ if (unlikely(ret))
+ goto out_fput;
+ if (force_nonblock) {
+ kiocb->ki_flags |= IOCB_NOWAIT;
+ req->flags |= REQ_F_FORCE_NONBLOCK;
+ }
+ if (kiocb->ki_flags & IOCB_HIPRI) {
+ ret = -EINVAL;
+ goto out_fput;
+ }
+
+ kiocb->ki_complete = io_complete_rw;
+ return 0;
+out_fput:
+ fput(kiocb->ki_filp);
+ return ret;
+}
+
+static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
+{
+ switch (ret) {
+ case -EIOCBQUEUED:
+ break;
+ case -ERESTARTSYS:
+ case -ERESTARTNOINTR:
+ case -ERESTARTNOHAND:
+ case -ERESTART_RESTARTBLOCK:
+ /*
+ * We can't just restart the syscall, since previously
+ * submitted sqes may already be in progress. Just fail this
+ * IO with EINTR.
+ */
+ ret = -EINTR;
+ /* fall through */
+ default:
+ kiocb->ki_complete(kiocb, ret, 0);
+ }
+}
+
+static int io_import_iovec(struct io_ring_ctx *ctx, int rw,
+ const struct sqe_submit *s, struct iovec **iovec,
+ struct iov_iter *iter)
+{
+ const struct io_uring_sqe *sqe = s->sqe;
+ void __user *buf = u64_to_user_ptr(READ_ONCE(sqe->addr));
+ size_t sqe_len = READ_ONCE(sqe->len);
+
+ if (!s->has_user)
+ return EFAULT;
+
+#ifdef CONFIG_COMPAT
+ if (ctx->compat)
+ return compat_import_iovec(rw, buf, sqe_len, UIO_FASTIOV,
+ iovec, iter);
+#endif
+
+ return import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter);
+}
+
+static ssize_t io_read(struct io_kiocb *req, const struct sqe_submit *s,
+ bool force_nonblock)
+{
+ struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
+ struct kiocb *kiocb = &req->rw;
+ struct iov_iter iter;
+ struct file *file;
+ ssize_t ret;
+
+ ret = io_prep_rw(req, s->sqe, force_nonblock);
+ if (ret)
+ return ret;
+ file = kiocb->ki_filp;
+
+ ret = -EBADF;
+ if (unlikely(!(file->f_mode & FMODE_READ)))
+ goto out_fput;
+ ret = -EINVAL;
+ if (unlikely(!file->f_op->read_iter))
+ goto out_fput;
+
+ ret = io_import_iovec(req->ctx, READ, s, &iovec, &iter);
+ if (ret)
+ goto out_fput;
+
+ ret = rw_verify_area(READ, file, &kiocb->ki_pos, iov_iter_count(&iter));
+ if (!ret) {
+ ssize_t ret2;
+
+ /* Catch -EAGAIN return for forced non-blocking submission */
+ ret2 = call_read_iter(file, kiocb, &iter);
+ if (!force_nonblock || ret2 != -EAGAIN)
+ io_rw_done(kiocb, ret2);
+ else
+ ret = -EAGAIN;
+ }
+ kfree(iovec);
+out_fput:
+ /* Hold on to the file for -EAGAIN */
+ if (unlikely(ret && ret != -EAGAIN))
+ fput(file);
+ return ret;
+}
+
+static ssize_t io_write(struct io_kiocb *req, const struct sqe_submit *s,
+ bool force_nonblock)
+{
+ struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs;
+ struct kiocb *kiocb = &req->rw;
+ struct iov_iter iter;
+ struct file *file;
+ ssize_t ret;
+
+ ret = io_prep_rw(req, s->sqe, force_nonblock);
+ if (ret)
+ return ret;
+ /* Hold on to the file for -EAGAIN */
+ if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT))
+ return -EAGAIN;
+
+ ret = -EBADF;
+ file = kiocb->ki_filp;
+ if (unlikely(!(file->f_mode & FMODE_WRITE)))
+ goto out_fput;
+ ret = -EINVAL;
+ if (unlikely(!file->f_op->write_iter))
+ goto out_fput;
+
+ ret = io_import_iovec(req->ctx, WRITE, s, &iovec, &iter);
+ if (ret)
+ goto out_fput;
+
+ ret = rw_verify_area(WRITE, file, &kiocb->ki_pos,
+ iov_iter_count(&iter));
+ if (!ret) {
+ /*
+ * Open-code file_start_write here to grab freeze protection,
+ * which will be released by another thread in
+ * io_complete_rw(). Fool lockdep by telling it the lock got
+ * released so that it doesn't complain about the held lock when
+ * we return to userspace.
+ */
+ if (S_ISREG(file_inode(file)->i_mode)) {
+ __sb_start_write(file_inode(file)->i_sb,
+ SB_FREEZE_WRITE, true);
+ __sb_writers_release(file_inode(file)->i_sb,
+ SB_FREEZE_WRITE);
+ }
+ kiocb->ki_flags |= IOCB_WRITE;
+ io_rw_done(kiocb, call_write_iter(file, kiocb, &iter));
+ }
+ kfree(iovec);
+out_fput:
+ if (unlikely(ret))
+ fput(file);
+ return ret;
+}
+
+/*
+ * IORING_OP_NOP just posts a completion event, nothing else.
+ */
+static int io_nop(struct io_kiocb *req, u64 user_data)
+{
+ struct io_ring_ctx *ctx = req->ctx;
+ long err = 0;
+
+ /*
+ * Twilight zone - it's possible that someone issued an opcode that
+ * has a file attached, then got -EAGAIN on submission, and changed
+ * the sqe before we retried it from async context. Avoid dropping
+ * a file reference for this malicious case, and flag the error.
+ */
+ if (req->rw.ki_filp) {
+ err = -EBADF;
+ fput(req->rw.ki_filp);
+ }
+ io_cqring_add_event(ctx, user_data, err, 0);
+ io_free_req(req);
+ return 0;
+}
+
+static int __io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
+ const struct sqe_submit *s, bool force_nonblock)
+{
+ ssize_t ret;
+ int opcode;
+
+ if (unlikely(s->index >= ctx->sq_entries))
+ return -EINVAL;
+ req->user_data = READ_ONCE(s->sqe->user_data);
+
+ opcode = READ_ONCE(s->sqe->opcode);
+ switch (opcode) {
+ case IORING_OP_NOP:
+ ret = io_nop(req, req->user_data);
+ break;
+ case IORING_OP_READV:
+ ret = io_read(req, s, force_nonblock);
+ break;
+ case IORING_OP_WRITEV:
+ ret = io_write(req, s, force_nonblock);
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
+static void io_sq_wq_submit_work(struct work_struct *work)
+{
+ struct io_kiocb *req = container_of(work, struct io_kiocb, work);
+ struct sqe_submit *s = &req->submit;
+ const struct io_uring_sqe *sqe = s->sqe;
+ struct io_ring_ctx *ctx = req->ctx;
+ mm_segment_t old_fs = get_fs();
+ int ret;
+
+ /* Ensure we clear previously set forced non-block flag */
+ req->flags &= ~REQ_F_FORCE_NONBLOCK;
+ req->rw.ki_flags &= ~IOCB_NOWAIT;
+
+ if (!mmget_not_zero(ctx->sqo_mm)) {
+ ret = -EFAULT;
+ goto err;
+ }
+
+ use_mm(ctx->sqo_mm);
+ set_fs(USER_DS);
+ s->has_user = true;
+
+ ret = __io_submit_sqe(ctx, req, s, false);
+
+ set_fs(old_fs);
+ unuse_mm(ctx->sqo_mm);
+ mmput(ctx->sqo_mm);
+err:
+ if (ret) {
+ io_cqring_add_event(ctx, sqe->user_data, ret, 0);
+ io_free_req(req);
+ }
+
+ /* async context always use a copy of the sqe */
+ kfree(sqe);
+}
+
+static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s)
+{
+ struct io_kiocb *req;
+ ssize_t ret;
+
+ /* enforce forwards compatibility on users */
+ if (unlikely(s->sqe->flags))
+ return -EINVAL;
+
+ req = io_get_req(ctx);
+ if (unlikely(!req))
+ return -EAGAIN;
+
+ req->rw.ki_filp = NULL;
+
+ ret = __io_submit_sqe(ctx, req, s, true);
+ if (ret == -EAGAIN) {
+ struct io_uring_sqe *sqe_copy;
+
+ sqe_copy = kmalloc(sizeof(*sqe_copy), GFP_KERNEL);
+ if (sqe_copy) {
+ memcpy(sqe_copy, s->sqe, sizeof(*sqe_copy));
+ s->sqe = sqe_copy;
+
+ memcpy(&req->submit, s, sizeof(*s));
+ INIT_WORK(&req->work, io_sq_wq_submit_work);
+ queue_work(ctx->sqo_wq, &req->work);
+ ret = 0;
+ }
+ }
+ if (ret)
+ io_free_req(req);
+
+ return ret;
+}
+
+static void io_commit_sqring(struct io_ring_ctx *ctx)
+{
+ struct io_sq_ring *ring = ctx->sq_ring;
+
+ if (ctx->cached_sq_head != READ_ONCE(ring->r.head)) {
+ WRITE_ONCE(ring->r.head, ctx->cached_sq_head);
+ /*
+ * write side barrier of head update, app has read side. See
+ * comment at the top of this file
+ */
+ smp_wmb();
+ }
+}
+
+/*
+ * Undo last io_get_sqring()
+ */
+static void io_drop_sqring(struct io_ring_ctx *ctx)
+{
+ ctx->cached_sq_head--;
+}
+
+/*
+ * Fetch an sqe, if one is available. Note that s->sqe will point to memory
+ * that is mapped by userspace. This means that care needs to be taken to
+ * ensure that reads are stable, as we cannot rely on userspace always
+ * being a good citizen. If members of the sqe are validated and then later
+ * used, it's important that those reads are done through READ_ONCE() to
+ * prevent a re-load down the line.
+ */
+static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
+{
+ struct io_sq_ring *ring = ctx->sq_ring;
+ unsigned head;
+
+ /*
+ * The cached sq head (or cq tail) serves two purposes:
+ *
+ * 1) allows us to batch the cost of updating the user visible
+ * head updates.
+ * 2) allows the kernel side to track the head on its own, even
+ * though the application is the one updating it.
+ */
+ head = ctx->cached_sq_head;
+ /* See comment at the top of this file */
+ smp_rmb();
+ if (head == READ_ONCE(ring->r.tail))
+ return false;
+
+ head = READ_ONCE(ring->array[head & ctx->sq_mask]);
+ if (head < ctx->sq_entries) {
+ s->index = head;
+ s->sqe = &ctx->sq_sqes[head];
+ ctx->cached_sq_head++;
+ return true;
+ }
+
+ /* drop invalid entries */
+ ctx->cached_sq_head++;
+ ring->dropped++;
+ /* See comment at the top of this file */
+ smp_wmb();
+ return false;
+}
+
+static int io_ring_submit(struct io_ring_ctx *ctx, unsigned int to_submit)
+{
+ int i, ret = 0, submit = 0;
+ struct blk_plug plug;
+
+ if (to_submit > IO_PLUG_THRESHOLD)
+ blk_start_plug(&plug);
+
+ for (i = 0; i < to_submit; i++) {
+ struct sqe_submit s;
+
+ if (!io_get_sqring(ctx, &s))
+ break;
+
+ s.has_user = true;
+ ret = io_submit_sqe(ctx, &s);
+ if (ret) {
+ io_drop_sqring(ctx);
+ break;
+ }
+
+ submit++;
+ }
+ io_commit_sqring(ctx);
+
+ if (to_submit > IO_PLUG_THRESHOLD)
+ blk_finish_plug(&plug);
+
+ return submit ? submit : ret;
+}
+
+/*
+ * Wait until events become available, if we don't already have some. The
+ * application must reap them itself, as they reside on the shared cq ring.
+ */
+static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
+ const sigset_t __user *sig, size_t sigsz)
+{
+ struct io_cq_ring *ring = ctx->cq_ring;
+ sigset_t ksigmask, sigsaved;
+ DEFINE_WAIT(wait);
+ int ret = 0;
+
+ /* See comment at the top of this file */
+ smp_rmb();
+ if (READ_ONCE(ring->r.head) != READ_ONCE(ring->r.tail))
+ return 0;
+ if (!min_events)
+ return 0;
+
+ if (sig) {
+ ret = set_user_sigmask(sig, &ksigmask, &sigsaved, sigsz);
+ if (ret)
+ return ret;
+ }
+
+ do {
+ prepare_to_wait(&ctx->wait, &wait, TASK_INTERRUPTIBLE);
+
+ ret = 0;
+ /* See comment at the top of this file */
+ smp_rmb();
+ if (READ_ONCE(ring->r.head) != READ_ONCE(ring->r.tail))
+ break;
+
+ schedule();
+
+ ret = -EINTR;
+ if (signal_pending(current))
+ break;
+ } while (1);
+
+ finish_wait(&ctx->wait, &wait);
+
+ if (sig)
+ restore_user_sigmask(sig, &sigsaved);
+
+ return READ_ONCE(ring->r.head) == READ_ONCE(ring->r.tail) ? ret : 0;
+}
+
+static int io_sq_offload_start(struct io_ring_ctx *ctx)
+{
+ int ret;
+
+ mmgrab(current->mm);
+ ctx->sqo_mm = current->mm;
+
+ /* Do QD, or 2 * CPUS, whatever is smallest */
+ ctx->sqo_wq = alloc_workqueue("io_ring-wq", WQ_UNBOUND | WQ_FREEZABLE,
+ min(ctx->sq_entries - 1, 2 * num_online_cpus()));
+ if (!ctx->sqo_wq) {
+ ret = -ENOMEM;
+ goto err;
+ }
+
+ return 0;
+err:
+ mmdrop(ctx->sqo_mm);
+ ctx->sqo_mm = NULL;
+ return ret;
+}
+
+static void io_unaccount_mem(struct user_struct *user, unsigned long nr_pages)
+{
+ atomic_long_sub(nr_pages, &user->locked_vm);
+}
+
+static int io_account_mem(struct user_struct *user, unsigned long nr_pages)
+{
+ unsigned long page_limit, cur_pages, new_pages;
+
+ /* Don't allow more pages than we can safely lock */
+ page_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+
+ do {
+ cur_pages = atomic_long_read(&user->locked_vm);
+ new_pages = cur_pages + nr_pages;
+ if (new_pages > page_limit)
+ return -ENOMEM;
+ } while (atomic_long_cmpxchg(&user->locked_vm, cur_pages,
+ new_pages) != cur_pages);
+
+ return 0;
+}
+
+static void io_mem_free(void *ptr)
+{
+ struct page *page = virt_to_head_page(ptr);
+
+ if (put_page_testzero(page))
+ free_compound_page(page);
+}
+
+static void *io_mem_alloc(size_t size)
+{
+ gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | __GFP_COMP |
+ __GFP_NORETRY;
+
+ return (void *) __get_free_pages(gfp_flags, get_order(size));
+}
+
+static unsigned long ring_pages(unsigned sq_entries, unsigned cq_entries)
+{
+ struct io_sq_ring *sq_ring;
+ struct io_cq_ring *cq_ring;
+ size_t bytes;
+
+ bytes = struct_size(sq_ring, array, sq_entries);
+ bytes += array_size(sizeof(struct io_uring_sqe), sq_entries);
+ bytes += struct_size(cq_ring, cqes, cq_entries);
+
+ return (bytes + PAGE_SIZE - 1) / PAGE_SIZE;
+}
+
+static void io_ring_ctx_free(struct io_ring_ctx *ctx)
+{
+ if (ctx->sqo_wq)
+ destroy_workqueue(ctx->sqo_wq);
+ if (ctx->sqo_mm)
+ mmdrop(ctx->sqo_mm);
+#if defined(CONFIG_UNIX)
+ if (ctx->ring_sock)
+ sock_release(ctx->ring_sock);
+#endif
+
+ io_mem_free(ctx->sq_ring);
+ io_mem_free(ctx->sq_sqes);
+ io_mem_free(ctx->cq_ring);
+
+ percpu_ref_exit(&ctx->refs);
+ if (ctx->account_mem)
+ io_unaccount_mem(ctx->user,
+ ring_pages(ctx->sq_entries, ctx->cq_entries));
+ free_uid(ctx->user);
+ kfree(ctx);
+}
+
+static __poll_t io_uring_poll(struct file *file, poll_table *wait)
+{
+ struct io_ring_ctx *ctx = file->private_data;
+ __poll_t mask = 0;
+
+ poll_wait(file, &ctx->cq_wait, wait);
+ /* See comment at the top of this file */
+ smp_rmb();
+ if (READ_ONCE(ctx->sq_ring->r.tail) + 1 != ctx->cached_sq_head)
+ mask |= EPOLLOUT | EPOLLWRNORM;
+ if (READ_ONCE(ctx->cq_ring->r.head) != ctx->cached_cq_tail)
+ mask |= EPOLLIN | EPOLLRDNORM;
+
+ return mask;
+}
+
+static int io_uring_fasync(int fd, struct file *file, int on)
+{
+ struct io_ring_ctx *ctx = file->private_data;
+
+ return fasync_helper(fd, file, on, &ctx->cq_fasync);
+}
+
+static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx)
+{
+ mutex_lock(&ctx->uring_lock);
+ percpu_ref_kill(&ctx->refs);
+ mutex_unlock(&ctx->uring_lock);
+
+ wait_for_completion(&ctx->ctx_done);
+ io_ring_ctx_free(ctx);
+}
+
+static int io_uring_release(struct inode *inode, struct file *file)
+{
+ struct io_ring_ctx *ctx = file->private_data;
+
+ file->private_data = NULL;
+ io_ring_ctx_wait_and_kill(ctx);
+ return 0;
+}
+
+static int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ loff_t offset = (loff_t) vma->vm_pgoff << PAGE_SHIFT;
+ unsigned long sz = vma->vm_end - vma->vm_start;
+ struct io_ring_ctx *ctx = file->private_data;
+ unsigned long pfn;
+ struct page *page;
+ void *ptr;
+
+ switch (offset) {
+ case IORING_OFF_SQ_RING:
+ ptr = ctx->sq_ring;
+ break;
+ case IORING_OFF_SQES:
+ ptr = ctx->sq_sqes;
+ break;
+ case IORING_OFF_CQ_RING:
+ ptr = ctx->cq_ring;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ page = virt_to_head_page(ptr);
+ if (sz > (PAGE_SIZE << compound_order(page)))
+ return -EINVAL;
+
+ pfn = virt_to_phys(ptr) >> PAGE_SHIFT;
+ return remap_pfn_range(vma, vma->vm_start, pfn, sz, vma->vm_page_prot);
+}
+
+SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
+ u32, min_complete, u32, flags, const sigset_t __user *, sig,
+ size_t, sigsz)
+{
+ struct io_ring_ctx *ctx;
+ long ret = -EBADF;
+ int submitted = 0;
+ struct fd f;
+
+ if (flags & ~IORING_ENTER_GETEVENTS)
+ return -EINVAL;
+
+ f = fdget(fd);
+ if (!f.file)
+ return -EBADF;
+
+ ret = -EOPNOTSUPP;
+ if (f.file->f_op != &io_uring_fops)
+ goto out_fput;
+
+ ret = -ENXIO;
+ ctx = f.file->private_data;
+ if (!percpu_ref_tryget(&ctx->refs))
+ goto out_fput;
+
+ if (to_submit) {
+ to_submit = min(to_submit, ctx->sq_entries);
+
+ mutex_lock(&ctx->uring_lock);
+ submitted = io_ring_submit(ctx, to_submit);
+ mutex_unlock(&ctx->uring_lock);
+
+ if (submitted < 0)
+ goto out_ctx;
+ }
+ if (flags & IORING_ENTER_GETEVENTS) {
+ /*
+ * The application could have included the 'to_submit' count
+ * in how many events it wanted to wait for. If we failed to
+ * submit the desired count, we may need to adjust the number
+ * of events to poll/wait for.
+ */
+ if (submitted < to_submit)
+ min_complete = min_t(unsigned, submitted, min_complete);
+
+ ret = io_cqring_wait(ctx, min_complete, sig, sigsz);
+ }
+
+out_ctx:
+ io_ring_drop_ctx_refs(ctx, 1);
+out_fput:
+ fdput(f);
+ return submitted ? submitted : ret;
+}
+
+static const struct file_operations io_uring_fops = {
+ .release = io_uring_release,
+ .mmap = io_uring_mmap,
+ .poll = io_uring_poll,
+ .fasync = io_uring_fasync,
+};
+
+static int io_allocate_scq_urings(struct io_ring_ctx *ctx,
+ struct io_uring_params *p)
+{
+ struct io_sq_ring *sq_ring;
+ struct io_cq_ring *cq_ring;
+ size_t size;
+
+ sq_ring = io_mem_alloc(struct_size(sq_ring, array, p->sq_entries));
+ if (!sq_ring)
+ return -ENOMEM;
+
+ ctx->sq_ring = sq_ring;
+ sq_ring->ring_mask = p->sq_entries - 1;
+ sq_ring->ring_entries = p->sq_entries;
+ ctx->sq_mask = sq_ring->ring_mask;
+ ctx->sq_entries = sq_ring->ring_entries;
+
+ size = array_size(sizeof(struct io_uring_sqe), p->sq_entries);
+ if (size == SIZE_MAX)
+ return -EOVERFLOW;
+
+ ctx->sq_sqes = io_mem_alloc(size);
+ if (!ctx->sq_sqes) {
+ io_mem_free(ctx->sq_ring);
+ return -ENOMEM;
+ }
+
+ cq_ring = io_mem_alloc(struct_size(cq_ring, cqes, p->cq_entries));
+ if (!cq_ring) {
+ io_mem_free(ctx->sq_ring);
+ io_mem_free(ctx->sq_sqes);
+ return -ENOMEM;
+ }
+
+ ctx->cq_ring = cq_ring;
+ cq_ring->ring_mask = p->cq_entries - 1;
+ cq_ring->ring_entries = p->cq_entries;
+ ctx->cq_mask = cq_ring->ring_mask;
+ ctx->cq_entries = cq_ring->ring_entries;
+ return 0;
+}
+
+/*
+ * Allocate an anonymous fd, this is what constitutes the application
+ * visible backing of an io_uring instance. The application mmaps this
+ * fd to gain access to the SQ/CQ ring details. If UNIX sockets are enabled,
+ * we have to tie this fd to a socket for file garbage collection purposes.
+ */
+static int io_uring_get_fd(struct io_ring_ctx *ctx)
+{
+ struct file *file;
+ int ret;
+
+#if defined(CONFIG_UNIX)
+ ret = sock_create_kern(&init_net, PF_UNIX, SOCK_RAW, IPPROTO_IP,
+ &ctx->ring_sock);
+ if (ret)
+ return ret;
+#endif
+
+ ret = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
+ if (ret < 0)
+ goto err;
+
+ file = anon_inode_getfile("[io_uring]", &io_uring_fops, ctx,
+ O_RDWR | O_CLOEXEC);
+ if (IS_ERR(file)) {
+ put_unused_fd(ret);
+ ret = PTR_ERR(file);
+ goto err;
+ }
+
+#if defined(CONFIG_UNIX)
+ ctx->ring_sock->file = file;
+#endif
+ fd_install(ret, file);
+ return ret;
+err:
+#if defined(CONFIG_UNIX)
+ sock_release(ctx->ring_sock);
+ ctx->ring_sock = NULL;
+#endif
+ return ret;
+}
+
+static int io_uring_create(unsigned entries, struct io_uring_params *p)
+{
+ struct user_struct *user = NULL;
+ struct io_ring_ctx *ctx;
+ bool account_mem;
+ int ret;
+
+ if (!entries || entries > IORING_MAX_ENTRIES)
+ return -EINVAL;
+
+ /*
+ * Use twice as many entries for the CQ ring. It's possible for the
+ * application to drive a higher depth than the size of the SQ ring,
+ * since the sqes are only used at submission time. This allows for
+ * some flexibility in overcommitting a bit.
+ */
+ p->sq_entries = roundup_pow_of_two(entries);
+ p->cq_entries = 2 * p->sq_entries;
+
+ user = get_uid(current_user());
+ account_mem = !capable(CAP_IPC_LOCK);
+
+ if (account_mem) {
+ ret = io_account_mem(user,
+ ring_pages(p->sq_entries, p->cq_entries));
+ if (ret) {
+ free_uid(user);
+ return ret;
+ }
+ }
+
+ ctx = io_ring_ctx_alloc(p);
+ if (!ctx) {
+ if (account_mem)
+ io_unaccount_mem(user, ring_pages(p->sq_entries,
+ p->cq_entries));
+ free_uid(user);
+ return -ENOMEM;
+ }
+ ctx->compat = in_compat_syscall();
+ ctx->account_mem = account_mem;
+ ctx->user = user;
+
+ ret = io_allocate_scq_urings(ctx, p);
+ if (ret)
+ goto err;
+
+ ret = io_sq_offload_start(ctx);
+ if (ret)
+ goto err;
+
+ ret = io_uring_get_fd(ctx);
+ if (ret < 0)
+ goto err;
+
+ memset(&p->sq_off, 0, sizeof(p->sq_off));
+ p->sq_off.head = offsetof(struct io_sq_ring, r.head);
+ p->sq_off.tail = offsetof(struct io_sq_ring, r.tail);
+ p->sq_off.ring_mask = offsetof(struct io_sq_ring, ring_mask);
+ p->sq_off.ring_entries = offsetof(struct io_sq_ring, ring_entries);
+ p->sq_off.flags = offsetof(struct io_sq_ring, flags);
+ p->sq_off.dropped = offsetof(struct io_sq_ring, dropped);
+ p->sq_off.array = offsetof(struct io_sq_ring, array);
+
+ memset(&p->cq_off, 0, sizeof(p->cq_off));
+ p->cq_off.head = offsetof(struct io_cq_ring, r.head);
+ p->cq_off.tail = offsetof(struct io_cq_ring, r.tail);
+ p->cq_off.ring_mask = offsetof(struct io_cq_ring, ring_mask);
+ p->cq_off.ring_entries = offsetof(struct io_cq_ring, ring_entries);
+ p->cq_off.overflow = offsetof(struct io_cq_ring, overflow);
+ p->cq_off.cqes = offsetof(struct io_cq_ring, cqes);
+ return ret;
+err:
+ io_ring_ctx_wait_and_kill(ctx);
+ return ret;
+}
+
+/*
+ * Sets up an aio uring context, and returns the fd. Applications asks for a
+ * ring size, we return the actual sq/cq ring sizes (among other things) in the
+ * params structure passed in.
+ */
+static long io_uring_setup(u32 entries, struct io_uring_params __user *params)
+{
+ struct io_uring_params p;
+ long ret;
+ int i;
+
+ if (copy_from_user(&p, params, sizeof(p)))
+ return -EFAULT;
+ for (i = 0; i < ARRAY_SIZE(p.resv); i++) {
+ if (p.resv[i])
+ return -EINVAL;
+ }
+
+ if (p.flags)
+ return -EINVAL;
+
+ ret = io_uring_create(entries, &p);
+ if (ret < 0)
+ return ret;
+
+ if (copy_to_user(params, &p, sizeof(p)))
+ return -EFAULT;
+
+ return ret;
+}
+
+SYSCALL_DEFINE2(io_uring_setup, u32, entries,
+ struct io_uring_params __user *, params)
+{
+ return io_uring_setup(entries, params);
+}
+
+static int __init io_uring_init(void)
+{
+ req_cachep = KMEM_CACHE(io_kiocb, SLAB_HWCACHE_ALIGN | SLAB_PANIC);
+ return 0;
+};
+__initcall(io_uring_init);
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 <linux/types.h>
#include <linux/aio_abi.h>
@@ -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,
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index d90127298f12..87871e7b7ea7 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -740,9 +740,13 @@ __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
__SYSCALL(__NR_rseq, sys_rseq)
#define __NR_kexec_file_load 294
__SYSCALL(__NR_kexec_file_load, sys_kexec_file_load)
+#define __NR_io_uring_setup 425
+__SYSCALL(__NR_io_uring_setup, sys_io_uring_setup)
+#define __NR_io_uring_enter 426
+__SYSCALL(__NR_io_uring_enter, sys_io_uring_enter)
#undef __NR_syscalls
-#define __NR_syscalls 295
+#define __NR_syscalls 427
/*
* 32 bit systems traditionally used different
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
new file mode 100644
index 000000000000..ac692823d6f4
--- /dev/null
+++ b/include/uapi/linux/io_uring.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Header file for the io_uring interface.
+ *
+ * Copyright (C) 2019 Jens Axboe
+ * Copyright (C) 2019 Christoph Hellwig
+ */
+#ifndef LINUX_IO_URING_H
+#define LINUX_IO_URING_H
+
+#include <linux/fs.h>
+#include <linux/types.h>
+
+/*
+ * IO submission data structure (Submission Queue Entry)
+ */
+struct io_uring_sqe {
+ __u8 opcode; /* type of operation for this sqe */
+ __u8 flags; /* as of now unused */
+ __u16 ioprio; /* ioprio for the request */
+ __s32 fd; /* file descriptor to do IO on */
+ __u64 off; /* offset into file */
+ __u64 addr; /* pointer to buffer or iovecs */
+ __u32 len; /* buffer size or number of iovecs */
+ union {
+ __kernel_rwf_t rw_flags;
+ __u32 __resv;
+ };
+ __u64 user_data; /* data to be passed back at completion time */
+ __u64 __pad2[3];
+};
+
+#define IORING_OP_NOP 0
+#define IORING_OP_READV 1
+#define IORING_OP_WRITEV 2
+
+/*
+ * IO completion data structure (Completion Queue Entry)
+ */
+struct io_uring_cqe {
+ __u64 user_data; /* sqe->data submission passed back */
+ __s32 res; /* result code for this event */
+ __u32 flags;
+};
+
+/*
+ * Magic offsets for the application to mmap the data it needs
+ */
+#define IORING_OFF_SQ_RING 0ULL
+#define IORING_OFF_CQ_RING 0x8000000ULL
+#define IORING_OFF_SQES 0x10000000ULL
+
+/*
+ * Filled with the offset for mmap(2)
+ */
+struct io_sqring_offsets {
+ __u32 head;
+ __u32 tail;
+ __u32 ring_mask;
+ __u32 ring_entries;
+ __u32 flags;
+ __u32 dropped;
+ __u32 array;
+ __u32 resv1;
+ __u64 resv2;
+};
+
+struct io_cqring_offsets {
+ __u32 head;
+ __u32 tail;
+ __u32 ring_mask;
+ __u32 ring_entries;
+ __u32 overflow;
+ __u32 cqes;
+ __u64 resv[2];
+};
+
+/*
+ * io_uring_enter(2) flags
+ */
+#define IORING_ENTER_GETEVENTS (1U << 0)
+
+/*
+ * Passed in for io_uring_setup(2). Copied back with updated info on success
+ */
+struct io_uring_params {
+ __u32 sq_entries;
+ __u32 cq_entries;
+ __u32 flags;
+ __u32 resv[7];
+ struct io_sqring_offsets sq_off;
+ struct io_cqring_offsets cq_off;
+};
+
+#endif
diff --git a/init/Kconfig b/init/Kconfig
index c9386a365eea..53b54214a36e 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1414,6 +1414,15 @@ config AIO
by some high performance threaded applications. Disabling
this option saves about 7k.
+config IO_URING
+ bool "Enable IO uring support" if EXPERT
+ select ANON_INODES
+ default y
+ help
+ This option enables support for the io_uring interface, enabling
+ applications to submit and complete IO through submission and
+ completion rings that are shared between the kernel and application.
+
config ADVISE_SYSCALLS
bool "Enable madvise/fadvise syscalls" if EXPERT
default y
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index ab9d0e3c6d50..ee5e523564bb 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -46,6 +46,8 @@ COND_SYSCALL(io_getevents);
COND_SYSCALL(io_pgetevents);
COND_SYSCALL_COMPAT(io_getevents);
COND_SYSCALL_COMPAT(io_pgetevents);
+COND_SYSCALL(io_uring_setup);
+COND_SYSCALL(io_uring_enter);
/* fs/xattr.c */
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index c36757e72844..f81854d74c7d 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -108,6 +108,9 @@ struct sock *unix_get_socket(struct file *filp)
/* PF_UNIX ? */
if (s && sock->ops && sock->ops->family == PF_UNIX)
u_sock = s;
+ } else {
+ /* Could be an io_uring instance */
+ u_sock = io_uring_get_socket(filp);
}
return u_sock;
}
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 04/19] iomap: wire up the iopoll method
From: Jens Axboe @ 2019-02-11 19:00 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api
Cc: hch, jmoyer, avi, jannh, viro, Jens Axboe
In-Reply-To: <20190211190049.7888-1-axboe@kernel.dk>
From: Christoph Hellwig <hch@lst.de>
Store the request queue the last bio was submitted to in the iocb
private data in addition to the cookie so that we find the right block
device. Also refactor the common direct I/O bio submission code into a
nice little helper.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Modified to use bio_set_polled().
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/gfs2/file.c | 2 ++
fs/iomap.c | 43 ++++++++++++++++++++++++++++---------------
fs/xfs/xfs_file.c | 1 +
include/linux/iomap.h | 1 +
4 files changed, 32 insertions(+), 15 deletions(-)
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index a2dea5bc0427..58a768e59712 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1280,6 +1280,7 @@ const struct file_operations gfs2_file_fops = {
.llseek = gfs2_llseek,
.read_iter = gfs2_file_read_iter,
.write_iter = gfs2_file_write_iter,
+ .iopoll = iomap_dio_iopoll,
.unlocked_ioctl = gfs2_ioctl,
.mmap = gfs2_mmap,
.open = gfs2_open,
@@ -1310,6 +1311,7 @@ const struct file_operations gfs2_file_fops_nolock = {
.llseek = gfs2_llseek,
.read_iter = gfs2_file_read_iter,
.write_iter = gfs2_file_write_iter,
+ .iopoll = iomap_dio_iopoll,
.unlocked_ioctl = gfs2_ioctl,
.mmap = gfs2_mmap,
.open = gfs2_open,
diff --git a/fs/iomap.c b/fs/iomap.c
index 897c60215dd1..2ac9eb746d44 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1463,6 +1463,28 @@ struct iomap_dio {
};
};
+int iomap_dio_iopoll(struct kiocb *kiocb, bool spin)
+{
+ struct request_queue *q = READ_ONCE(kiocb->private);
+
+ if (!q)
+ return 0;
+ return blk_poll(q, READ_ONCE(kiocb->ki_cookie), spin);
+}
+EXPORT_SYMBOL_GPL(iomap_dio_iopoll);
+
+static void iomap_dio_submit_bio(struct iomap_dio *dio, struct iomap *iomap,
+ struct bio *bio)
+{
+ atomic_inc(&dio->ref);
+
+ if (dio->iocb->ki_flags & IOCB_HIPRI)
+ bio_set_polled(bio, dio->iocb);
+
+ dio->submit.last_queue = bdev_get_queue(iomap->bdev);
+ dio->submit.cookie = submit_bio(bio);
+}
+
static ssize_t iomap_dio_complete(struct iomap_dio *dio)
{
struct kiocb *iocb = dio->iocb;
@@ -1575,7 +1597,7 @@ static void iomap_dio_bio_end_io(struct bio *bio)
}
}
-static blk_qc_t
+static void
iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
unsigned len)
{
@@ -1589,15 +1611,10 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
bio->bi_private = dio;
bio->bi_end_io = iomap_dio_bio_end_io;
- if (dio->iocb->ki_flags & IOCB_HIPRI)
- flags |= REQ_HIPRI;
-
get_page(page);
__bio_add_page(bio, page, len, 0);
bio_set_op_attrs(bio, REQ_OP_WRITE, flags);
-
- atomic_inc(&dio->ref);
- return submit_bio(bio);
+ iomap_dio_submit_bio(dio, iomap, bio);
}
static loff_t
@@ -1700,9 +1717,6 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
bio_set_pages_dirty(bio);
}
- if (dio->iocb->ki_flags & IOCB_HIPRI)
- bio->bi_opf |= REQ_HIPRI;
-
iov_iter_advance(dio->submit.iter, n);
dio->size += n;
@@ -1710,11 +1724,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
copied += n;
nr_pages = iov_iter_npages(&iter, BIO_MAX_PAGES);
-
- atomic_inc(&dio->ref);
-
- dio->submit.last_queue = bdev_get_queue(iomap->bdev);
- dio->submit.cookie = submit_bio(bio);
+ iomap_dio_submit_bio(dio, iomap, bio);
} while (nr_pages);
/*
@@ -1925,6 +1935,9 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
if (dio->flags & IOMAP_DIO_WRITE_FUA)
dio->flags &= ~IOMAP_DIO_NEED_SYNC;
+ WRITE_ONCE(iocb->ki_cookie, dio->submit.cookie);
+ WRITE_ONCE(iocb->private, dio->submit.last_queue);
+
/*
* We are about to drop our additional submission reference, which
* might be the last reference to the dio. There are three three
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index e47425071e65..60c2da41f0fc 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1203,6 +1203,7 @@ const struct file_operations xfs_file_operations = {
.write_iter = xfs_file_write_iter,
.splice_read = generic_file_splice_read,
.splice_write = iter_file_splice_write,
+ .iopoll = iomap_dio_iopoll,
.unlocked_ioctl = xfs_file_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = xfs_file_compat_ioctl,
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 9a4258154b25..0fefb5455bda 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -162,6 +162,7 @@ typedef int (iomap_dio_end_io_t)(struct kiocb *iocb, ssize_t ret,
unsigned flags);
ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
const struct iomap_ops *ops, iomap_dio_end_io_t end_io);
+int iomap_dio_iopoll(struct kiocb *kiocb, bool spin);
#ifdef CONFIG_SWAP
struct file;
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 03/19] block: add bio_set_polled() helper
From: Jens Axboe @ 2019-02-11 19:00 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api
Cc: hch, jmoyer, avi, jannh, viro, Jens Axboe
In-Reply-To: <20190211190049.7888-1-axboe@kernel.dk>
For the upcoming async polled IO, we can't sleep allocating requests.
If we do, then we introduce a deadlock where the submitter already
has async polled IO in-flight, but can't wait for them to complete
since polled requests must be active found and reaped.
Utilize the helper in the blockdev DIRECT_IO code.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/block_dev.c | 4 ++--
include/linux/bio.h | 14 ++++++++++++++
2 files changed, 16 insertions(+), 2 deletions(-)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index f18d076a2596..392e2bfb636f 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -247,7 +247,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
task_io_account_write(ret);
}
if (iocb->ki_flags & IOCB_HIPRI)
- bio.bi_opf |= REQ_HIPRI;
+ bio_set_polled(&bio, iocb);
qc = submit_bio(&bio);
for (;;) {
@@ -415,7 +415,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES);
if (!nr_pages) {
if (iocb->ki_flags & IOCB_HIPRI)
- bio->bi_opf |= REQ_HIPRI;
+ bio_set_polled(bio, iocb);
qc = submit_bio(bio);
WRITE_ONCE(iocb->ki_cookie, qc);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 7380b094dcca..f6f0a2b3cbc8 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -823,5 +823,19 @@ static inline int bio_integrity_add_page(struct bio *bio, struct page *page,
#endif /* CONFIG_BLK_DEV_INTEGRITY */
+/*
+ * Mark a bio as polled. Note that for async polled IO, the caller must
+ * expect -EWOULDBLOCK if we cannot allocate a request (or other resources).
+ * We cannot block waiting for requests on polled IO, as those completions
+ * must be found by the caller. This is different than IRQ driven IO, where
+ * it's safe to wait for IO to complete.
+ */
+static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb)
+{
+ bio->bi_opf |= REQ_HIPRI;
+ if (!is_sync_kiocb(kiocb))
+ bio->bi_opf |= REQ_NOWAIT;
+}
+
#endif /* CONFIG_BLOCK */
#endif /* __LINUX_BIO_H */
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 02/19] block: wire up block device iopoll method
From: Jens Axboe @ 2019-02-11 19:00 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api
Cc: hch, jmoyer, avi, jannh, viro, Jens Axboe
In-Reply-To: <20190211190049.7888-1-axboe@kernel.dk>
From: Christoph Hellwig <hch@lst.de>
Just call blk_poll on the iocb cookie, we can derive the block device
from the inode trivially.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/block_dev.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 58a4c1217fa8..f18d076a2596 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -293,6 +293,14 @@ struct blkdev_dio {
static struct bio_set blkdev_dio_pool;
+static int blkdev_iopoll(struct kiocb *kiocb, bool wait)
+{
+ struct block_device *bdev = I_BDEV(kiocb->ki_filp->f_mapping->host);
+ struct request_queue *q = bdev_get_queue(bdev);
+
+ return blk_poll(q, READ_ONCE(kiocb->ki_cookie), wait);
+}
+
static void blkdev_bio_end_io(struct bio *bio)
{
struct blkdev_dio *dio = bio->bi_private;
@@ -410,6 +418,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
bio->bi_opf |= REQ_HIPRI;
qc = submit_bio(bio);
+ WRITE_ONCE(iocb->ki_cookie, qc);
break;
}
@@ -2076,6 +2085,7 @@ const struct file_operations def_blk_fops = {
.llseek = block_llseek,
.read_iter = blkdev_read_iter,
.write_iter = blkdev_write_iter,
+ .iopoll = blkdev_iopoll,
.mmap = generic_file_mmap,
.fsync = blkdev_fsync,
.unlocked_ioctl = block_ioctl,
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH] io_uring: add io_uring_event cache hit information
From: Jens Axboe @ 2019-02-11 19:00 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api
Cc: hch, jmoyer, avi, jannh, viro, Jens Axboe
In-Reply-To: <20190211190049.7888-1-axboe@kernel.dk>
Add hint on whether a read was served out of the page cache, or if it
hit media. This is useful for buffered async IO, O_DIRECT reads would
never have this set (for obvious reasons).
If the read hit page cache, cqe->flags will have IOCQE_FLAG_CACHEHIT
set.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/io_uring.c | 7 ++++++-
include/uapi/linux/io_uring.h | 5 +++++
2 files changed, 11 insertions(+), 1 deletion(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 00c7c11ca699..8114723517d6 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -611,11 +611,16 @@ static void io_fput(struct io_kiocb *req)
static void io_complete_rw(struct kiocb *kiocb, long res, long res2)
{
struct io_kiocb *req = container_of(kiocb, struct io_kiocb, rw);
+ unsigned ev_flags = 0;
kiocb_end_write(kiocb);
io_fput(req);
- io_cqring_add_event(req->ctx, req->user_data, res, 0);
+
+ if (res > 0 && (req->flags & REQ_F_FORCE_NONBLOCK))
+ ev_flags = IOCQE_FLAG_CACHEHIT;
+
+ io_cqring_add_event(req->ctx, req->user_data, res, ev_flags);
io_free_req(req);
}
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index e23408692118..24906e99fdc7 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -69,6 +69,11 @@ struct io_uring_cqe {
__u32 flags;
};
+/*
+ * io_uring_event->flags
+ */
+#define IOCQE_FLAG_CACHEHIT (1U << 0) /* IO did not hit media */
+
/*
* Magic offsets for the application to mmap the data it needs
*/
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCH 01/19] fs: add an iopoll method to struct file_operations
From: Jens Axboe @ 2019-02-11 19:00 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api
Cc: hch, jmoyer, avi, jannh, viro, Jens Axboe
In-Reply-To: <20190211190049.7888-1-axboe@kernel.dk>
From: Christoph Hellwig <hch@lst.de>
This new methods is used to explicitly poll for I/O completion for an
iocb. It must be called for any iocb submitted asynchronously (that
is with a non-null ki_complete) which has the IOCB_HIPRI flag set.
The method is assisted by a new ki_cookie field in struct iocb to store
the polling cookie.
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
Documentation/filesystems/vfs.txt | 3 +++
include/linux/fs.h | 2 ++
2 files changed, 5 insertions(+)
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 8dc8e9c2913f..761c6fd24a53 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -857,6 +857,7 @@ struct file_operations {
ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
+ int (*iopoll)(struct kiocb *kiocb, bool spin);
int (*iterate) (struct file *, struct dir_context *);
int (*iterate_shared) (struct file *, struct dir_context *);
__poll_t (*poll) (struct file *, struct poll_table_struct *);
@@ -902,6 +903,8 @@ otherwise noted.
write_iter: possibly asynchronous write with iov_iter as source
+ iopoll: called when aio wants to poll for completions on HIPRI iocbs
+
iterate: called when the VFS needs to read the directory contents
iterate_shared: called when the VFS needs to read the directory contents
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 29d8e2cfed0e..dedcc2e9265c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -310,6 +310,7 @@ struct kiocb {
int ki_flags;
u16 ki_hint;
u16 ki_ioprio; /* See linux/ioprio.h */
+ unsigned int ki_cookie; /* for ->iopoll */
} __randomize_layout;
static inline bool is_sync_kiocb(struct kiocb *kiocb)
@@ -1787,6 +1788,7 @@ struct file_operations {
ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
+ int (*iopoll)(struct kiocb *kiocb, bool spin);
int (*iterate) (struct file *, struct dir_context *);
int (*iterate_shared) (struct file *, struct dir_context *);
__poll_t (*poll) (struct file *, struct poll_table_struct *);
--
2.17.1
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply related
* [PATCHSET v15] io_uring IO interface
From: Jens Axboe @ 2019-02-11 19:00 UTC (permalink / raw)
To: linux-aio, linux-block, linux-api; +Cc: hch, jmoyer, avi, jannh, viro
Some final tweaks, mostly cosmetic, but also two important fixes:
1) Ensure that we account the skb appropriately against the socket.
Some network config options apparently return is an skb with
->truesize != 0 when allocated with a size of 0, ensure we add
those as references against sock->sk_wmem_alloc. Reported by
Matt Mullins.
2) Ensure that ANY async punt of an sqe operates on a copy. We've
already committed the SQ ring change at this point, we don't want
the application inadvertently reusing the SQE causing issues for
an SQE that got punted with -EAGAIN. This change ensures that
whatever io_uring_enter(2) returned that got submitted, it's
totally safe to reuse those SQE entries in the ring.
Outside of that, just cosmetic changes and additions of comments. I've
run this version in various torture overnight, using the various modes
(polled, buffered, sq thread, any combination thereof) and it's help up
perfectly. As far as I'm concerned, this is ready to get staged for 5.1.
The liburing git repo has a full set of man pages for this, though they
could probably still use a bit of polish. I'd also like to see a
io_uring(7) man page to describe the overall design of the project,
expect that in the not-so-distant future. You can clone that here:
git://git.kernel.dk/liburing
Patches are against 5.0-rc6, and can also be found in my io_uring branch
here:
git://git.kernel.dk/linux-block io_uring
Changes since v14:
- Fix skb/sock referencing if skb->truesize != 0
- Add comments on memory ordering
- Add comments on READ/WRITE_ONCE()
- Various function comments
- Align struct members of io_poll_iocb and io_submit_state
- Use io_fput() in two places where it was open-coded
- Make async context always use a copy of the sqe
- Don't reset s->needs_fixed_file for async context
- Rebase on v5.0-rc6
Documentation/filesystems/vfs.txt | 3 +
arch/x86/entry/syscalls/syscall_32.tbl | 3 +
arch/x86/entry/syscalls/syscall_64.tbl | 3 +
block/bio.c | 59 +-
fs/Makefile | 1 +
fs/block_dev.c | 19 +-
fs/file.c | 15 +-
fs/file_table.c | 9 +-
fs/gfs2/file.c | 2 +
fs/io_uring.c | 2920 ++++++++++++++++++++++++
fs/iomap.c | 48 +-
fs/xfs/xfs_file.c | 1 +
include/linux/bio.h | 14 +
include/linux/blk_types.h | 1 +
include/linux/file.h | 2 +
include/linux/fs.h | 15 +-
include/linux/iomap.h | 1 +
include/linux/sched/user.h | 2 +-
include/linux/syscalls.h | 8 +
include/net/af_unix.h | 1 +
include/uapi/asm-generic/unistd.h | 8 +-
include/uapi/linux/io_uring.h | 142 ++
init/Kconfig | 9 +
kernel/sys_ni.c | 3 +
net/Makefile | 2 +-
net/unix/Kconfig | 5 +
net/unix/Makefile | 2 +
net/unix/af_unix.c | 63 +-
net/unix/garbage.c | 68 +-
net/unix/scm.c | 151 ++
net/unix/scm.h | 10 +
31 files changed, 3421 insertions(+), 169 deletions(-)
--
Jens Axboe
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply
* Re: [PATCH 13/18] io_uring: add file set registration
From: Al Viro @ 2019-02-11 17:35 UTC (permalink / raw)
To: Jonathan Corbet
Cc: Jens Axboe, Jann Horn, linux-aio, linux-block, Linux API, hch,
jmoyer, avi, linux-fsdevel
In-Reply-To: <20190211085533.35190404@lwn.net>
On Mon, Feb 11, 2019 at 08:55:33AM -0700, Jonathan Corbet wrote:
> On Thu, 7 Feb 2019 11:45:40 -0700
> Jens Axboe <axboe@kernel.dk> wrote:
>
> > > OK, braindump time:
> >
> > [snip]
> >
> > This is great info, and I think it belongs in Documentation/ somewhere.
> > Not sure I've ever seen such a good and detailed dump of this before.
>
> I suspect I might be able to make something like that happen :) Stay
> tuned.
There are several typos I see in there (e.g. in
* struct file instances A and B being AF_UNIX sockets.
* A is a listener
* B is an established connection, with the other end
yet to be accepted on A
* the only references to A and B are in an SCM_RIGHTS
datagram sent over by A.
the last line should be "datagram sent over by B", of course - you can't
send anything over a listener socket, to start with).
Another thing is this:
* references cannot be extracted from SCM_RIGHTS datagrams
while the garbage collector is running (achieved by having
unix_notinflight() done before references out of SCM_RIGHTS)
* removal of SCM_RIGHTS associated with a socket can't
be done without a reference to that socket _outside_ of any
SCM_RIGHTS (automatically true).
That's worse than a typo - that's an actual bug (see the subthread
with Miklos). Correct version would be
* any references extracted from SCM_RIGHTS during the
garbage collector run will not be actually used until the end
of garbage collection. For normal recvmsg() it is guaranteed
by having unix_notinflight() called between the extraction of
scm_fp_list from the packet and doing anything else with the
references extracted. For MSG_PEEK recvmsg() it's actually
broken and lacks synchronization; Miklos has proposed to grab
and release unix_gc_lock in those, between scm_fp_dup() and
doing anything else with the references copied.
If you turn that thing into a coherent text, I'd appreciate a chance
to take a look at the result and see if anything else needs to be
corrected...
--
To unsubscribe, send a message with 'unsubscribe linux-aio' in
the body to majordomo@kvack.org. For more info on Linux AIO,
see: http://www.kvack.org/aio/
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>
^ permalink raw reply
* [RFC PATCH v2 20/20] fscrypt: document the new ioctls and policy version
From: Eric Biggers @ 2019-02-11 17:27 UTC (permalink / raw)
To: linux-fscrypt
Cc: Satya Tangirala, linux-api, linux-f2fs-devel, keyrings, linux-mtd,
linux-crypto, linux-fsdevel, linux-ext4, Paul Crowley
In-Reply-To: <20190211172738.4633-1-ebiggers@kernel.org>
From: Eric Biggers <ebiggers@google.com>
Update the fscrypt documentation file to catch up to all the latest
changes, including the new ioctls to manage master encryption keys in
the filesystem-level keyring and the support for v2 encryption policies.
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
Documentation/filesystems/fscrypt.rst | 646 +++++++++++++++++++++-----
1 file changed, 530 insertions(+), 116 deletions(-)
diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst
index 4f9df6ba669e..c5d6c34ddf79 100644
--- a/Documentation/filesystems/fscrypt.rst
+++ b/Documentation/filesystems/fscrypt.rst
@@ -72,6 +72,9 @@ Online attacks
fscrypt (and storage encryption in general) can only provide limited
protection, if any at all, against online attacks. In detail:
+Side-channel attacks
+~~~~~~~~~~~~~~~~~~~~
+
fscrypt is only resistant to side-channel attacks, such as timing or
electromagnetic attacks, to the extent that the underlying Linux
Cryptographic API algorithms are. If a vulnerable algorithm is used,
@@ -80,29 +83,84 @@ attacker to mount a side channel attack against the online system.
Side channel attacks may also be mounted against applications
consuming decrypted data.
-After an encryption key has been provided, fscrypt is not designed to
-hide the plaintext file contents or filenames from other users on the
-same system, regardless of the visibility of the keyring key.
-Instead, existing access control mechanisms such as file mode bits,
-POSIX ACLs, LSMs, or mount namespaces should be used for this purpose.
-Also note that as long as the encryption keys are *anywhere* in
-memory, an online attacker can necessarily compromise them by mounting
-a physical attack or by exploiting any kernel security vulnerability
-which provides an arbitrary memory read primitive.
-
-While it is ostensibly possible to "evict" keys from the system,
-recently accessed encrypted files will remain accessible at least
-until the filesystem is unmounted or the VFS caches are dropped, e.g.
-using ``echo 2 > /proc/sys/vm/drop_caches``. Even after that, if the
-RAM is compromised before being powered off, it will likely still be
-possible to recover portions of the plaintext file contents, if not
-some of the encryption keys as well. (Since Linux v4.12, all
-in-kernel keys related to fscrypt are sanitized before being freed.
-However, userspace would need to do its part as well.)
-
-Currently, fscrypt does not prevent a user from maliciously providing
-an incorrect key for another user's existing encrypted files. A
-protection against this is planned.
+Unauthorized file access
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+After an encryption key has been added, fscrypt does not hide the
+plaintext file contents or filenames from other users on the same
+system. Instead, existing access control mechanisms such as file mode
+bits, POSIX ACLs, LSMs, or namespaces should be used for this purpose.
+
+(For the reasoning behind this, understand that while the key is
+added, the confidentiality of the data, from the perspective of the
+system itself, is *not* protected by the mathematical properties of
+encryption but rather only by the correctness of the kernel.
+Therefore, any encryption-specific access control checks would merely
+be enforced by kernel *code* and therefore would be largely redundant
+with the wide variety of access control mechanisms already available.)
+
+Kernel memory compromise
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+An attacker who compromises the system enough to read from arbitrary
+memory, e.g. by mounting a physical attack or by exploiting a kernel
+security vulnerability, can compromise all encryption keys that are
+currently in use.
+
+However, fscrypt allows encryption keys to be removed from the kernel,
+which may protect them from later compromise.
+
+In more detail, the FS_IOC_REMOVE_ENCRYPTION_KEY ioctl will wipe a
+master encryption key from kernel memory. Moreover, it will try to
+evict all cached inodes which had been "unlocked" using the key,
+thereby wiping their per-file keys and making them once again appear
+"locked", i.e. in ciphertext or encrypted form.
+
+However, FS_IOC_REMOVE_ENCRYPTION_KEY has some limitations:
+
+- Per-file keys for in-use files will *not* be removed or wiped.
+ Therefore, for maximum effect, userspace should close the relevant
+ encrypted files and directories before removing a master key, as
+ well as kill any processes whose working directory is in an affected
+ encrypted directory.
+
+- The kernel cannot magically wipe copies of the master key(s) that
+ userspace might have as well. Therefore, userspace must wipe all
+ copies of the master key(s) it makes as well. Naturally, the same
+ also applies to all higher levels in the key hierarchy. Userspace
+ should also follow other security precautions such as mlock()ing
+ memory containing keys to prevent it from being swapped out.
+
+- In general, decrypted contents and filenames in the kernel VFS
+ caches are freed but not wiped. Therefore, portions thereof may be
+ recoverable from freed memory, even after the corresponding key(s)
+ were wiped. To partially solve this, you can set
+ CONFIG_PAGE_POISONING=y in your kernel config and add page_poison=1
+ to your kernel command line. However, this has a performance cost.
+
+- Secret keys might still exist in CPU registers, in crypto
+ accelerator hardware (if used by the crypto API to implement any of
+ the algorithms), or in other places not explicitly considered here.
+
+Limitations of v1 policies
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+v1 encryption policies have some weaknesses with respect to online
+attacks:
+
+- There is no verification that the provided master key is correct.
+ Consequently, malicious users can associate the wrong key with
+ encrypted files, even files to which they have only read-only
+ access.
+
+- A compromise of a per-file key also compromises the master key from
+ which it was derived.
+
+- Non-root users cannot securely remove encryption keys.
+
+All the above problems are fixed with v2 encryption policies. For
+this reason among others, it is recommended to use v2 encryption
+policies on all new encrypted directories.
Key hierarchy
=============
@@ -123,11 +181,46 @@ appropriate master key. There can be any number of master keys, each
of which protects any number of directory trees on any number of
filesystems.
-Userspace should generate master keys either using a cryptographically
-secure random number generator, or by using a KDF (Key Derivation
-Function). Note that whenever a KDF is used to "stretch" a
-lower-entropy secret such as a passphrase, it is critical that a KDF
-designed for this purpose be used, such as scrypt, PBKDF2, or Argon2.
+Master keys should be pseudorandom, i.e. indistinguishable from random
+bytestrings of the same length. This implies that users **must not**
+directly use a password as a master key, zero-pad a shorter key, or
+repeat a shorter key. Instead, users should generate master keys
+either using a cryptographically secure random number generator, or by
+using a KDF (Key Derivation Function). Note that whenever a KDF is
+used to "stretch" a lower-entropy secret such as a passphrase, it is
+critical that a KDF designed for this purpose be used, such as scrypt,
+PBKDF2, or Argon2.
+
+Key derivation function
+-----------------------
+
+With one exception, fscrypt never uses the master key(s) for
+encryption directly. Instead, they are only used as input to a KDF
+(Key Derivation Function) to derive the actual keys.
+
+The KDF used for a particular master key differs depending on whether
+the key is used for v1 encryption policies or for v2 encryption
+policies. Users **must not** use the same key for both v1 and v2
+encryption policies.
+
+For v1 encryption policies, the KDF only supports deriving per-file
+encryption keys. It works by encrypting the master key with
+AES-128-ECB, using the file's 16-byte nonce as the AES key. The
+resulting ciphertext is used as the derived key. If the ciphertext is
+longer than needed, then it is truncated to the needed length.
+
+For v2 encryption policies, the KDF is HKDF-SHA512. The master key is
+passed as the "input keying material", a fixed value is passed as the
+"salt", and a distinct "application-specific information string" is
+used for each distinct key to be derived. For example, when a
+per-file encryption key is derived, the application-specific
+information string is the file's nonce prefixed with a context byte.
+Different context bytes are used for other types of derived keys.
+
+HKDF-SHA512 is preferred to the original AES-128-ECB based KDF because
+HKDF is more flexible, is nonreversible, and evenly distributes
+entropy from the master key. HKDF is also standardized and widely
+used by other software, whereas the AES-128-ECB based KDF is ad-hoc.
Per-file keys
-------------
@@ -138,29 +231,9 @@ files doesn't map to the same ciphertext, or vice versa. In most
cases, fscrypt does this by deriving per-file keys. When a new
encrypted inode (regular file, directory, or symlink) is created,
fscrypt randomly generates a 16-byte nonce and stores it in the
-inode's encryption xattr. Then, it uses a KDF (Key Derivation
-Function) to derive the file's key from the master key and nonce.
-
-The Adiantum encryption mode (see `Encryption modes and usage`_) is
-special, since it accepts longer IVs and is suitable for both contents
-and filenames encryption. For it, a "direct key" option is offered
-where the file's nonce is included in the IVs and the master key is
-used for encryption directly. This improves performance; however,
-users must not use the same master key for any other encryption mode.
-
-Below, the KDF and design considerations are described in more detail.
-
-The current KDF works by encrypting the master key with AES-128-ECB,
-using the file's nonce as the AES key. The output is used as the
-derived key. If the output is longer than needed, then it is
-truncated to the needed length.
-
-Note: this KDF meets the primary security requirement, which is to
-produce unique derived keys that preserve the entropy of the master
-key, assuming that the master key is already a good pseudorandom key.
-However, it is nonstandard and has some problems such as being
-reversible, so it is generally considered to be a mistake! It may be
-replaced with HKDF or another more standard KDF in the future.
+inode's encryption xattr. Then, it uses a KDF (as described in `Key
+derivation function`_) to derive the file's key from the master key
+and nonce.
Key derivation was chosen over key wrapping because wrapped keys would
require larger xattrs which would be less likely to fit in-line in the
@@ -176,6 +249,37 @@ rejected as it would have prevented ext4 filesystems from being
resized, and by itself still wouldn't have been sufficient to prevent
the same key from being directly reused for both XTS and CTS-CBC.
+DIRECT_KEY and per-mode keys
+----------------------------
+
+The Adiantum encryption mode (see `Encryption modes and usage`_) is
+suitable for both contents and filenames encryption, and it accepts
+long IVs --- long enough to hold both an 8-byte logical block number
+and a 16-byte per-file nonce. Also, the overhead of each Adiantum key
+is greater than that of an AES-256-XTS key.
+
+Therefore, to improve performance and save memory, for Adiantum a
+"direct key" configuration is supported. When the user has enabled
+this by setting FSCRYPT_POLICY_FLAG_DIRECT_KEY in the fscrypt policy,
+per-file keys are not used. Instead, whenever any data (contents or
+filenames) is encrypted, the file's 16-byte nonce is included in the
+IV. Moreover:
+
+- For v1 encryption policies, the encryption is done directly with the
+ master key. Because of this, users **must not** use the same master
+ key for any other purpose, even for other v1 policies.
+
+- For v2 encryption policies, the encryption is done with a per-mode
+ key derived using the KDF. Users may use the same master key for
+ other v2 encryption policies.
+
+Key identifiers
+---------------
+
+For master keys used for v2 encryption policies, a unique 16-byte "key
+identifier" is also derived using the KDF. This value is stored in
+the clear, since it is needed to reliably identify the key itself.
+
Encryption modes and usage
==========================
@@ -271,21 +375,38 @@ Setting an encryption policy
The FS_IOC_SET_ENCRYPTION_POLICY ioctl sets an encryption policy on an
empty directory or verifies that a directory or regular file already
has the specified encryption policy. It takes in a pointer to a
-:c:type:`struct fscrypt_policy`, defined as follows::
+:c:type:`struct fscrypt_policy_v1` or a :c:type:`struct
+fscrypt_policy_v2`, defined as follows::
- #define FSCRYPT_KEY_DESCRIPTOR_SIZE 8
-
- struct fscrypt_policy {
+ #define FSCRYPT_POLICY_V1 0
+ #define FSCRYPT_KEY_DESCRIPTOR_SIZE 8
+ struct fscrypt_policy_v1 {
__u8 version;
__u8 contents_encryption_mode;
__u8 filenames_encryption_mode;
__u8 flags;
__u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
};
+ #define fscrypt_policy fscrypt_policy_v1
+
+ #define FSCRYPT_POLICY_V2 2
+ #define FSCRYPT_KEY_IDENTIFIER_SIZE 16
+ struct fscrypt_policy_v2 {
+ __u8 version;
+ __u8 contents_encryption_mode;
+ __u8 filenames_encryption_mode;
+ __u8 flags;
+ __u8 __reserved[4];
+ __u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
+ };
This structure must be initialized as follows:
-- ``version`` must be 0.
+- ``version`` must be FSCRYPT_POLICY_V1 (0) if the struct is
+ :c:type:`fscrypt_policy_v1` or FSCRYPT_POLICY_V2 (2) if the struct
+ is :c:type:`fscrypt_policy_v2`. (Note: we refer to the original
+ policy version as "v1", though its version code is really 0.) For
+ new encrypted directories, use v2 policies.
- ``contents_encryption_mode`` and ``filenames_encryption_mode`` must
be set to constants from ``<linux/fs.h>`` which identify the
@@ -295,21 +416,30 @@ This structure must be initialized as follows:
- ``flags`` must contain a value from ``<linux/fs.h>`` which
identifies the amount of NUL-padding to use when encrypting
- filenames. If unsure, use FSCRYPT_POLICY_FLAGS_PAD_32 (0x3). In
- addition, if the chosen encryption modes are both
+ filenames. If unsure, use FSCRYPT_POLICY_FLAGS_PAD_32 (0x3).
+ Additionally, if the encryption modes are both
FSCRYPT_MODE_ADIANTUM, this can contain
- FSCRYPT_POLICY_FLAG_DIRECT_KEY to specify that the master key should
- be used directly, without key derivation.
+ FSCRYPT_POLICY_FLAG_DIRECT_KEY; see `DIRECT_KEY and per-mode keys`_.
-- ``master_key_descriptor`` specifies how to find the master key in
- the keyring; see `Adding keys`_. It is up to userspace to choose a
- unique ``master_key_descriptor`` for each master key. The e4crypt
- and fscrypt tools use the first 8 bytes of
+- For v2 encryption policies, ``__reserved`` must be zeroed.
+
+- For v1 encryption policies, ``master_key_descriptor`` specifies how
+ to find the master key in a keyring; see `Adding keys`_. It is up
+ to userspace to choose a unique ``master_key_descriptor`` for each
+ master key. The e4crypt and fscrypt tools use the first 8 bytes of
``SHA-512(SHA-512(master_key))``, but this particular scheme is not
required. Also, the master key need not be in the keyring yet when
FS_IOC_SET_ENCRYPTION_POLICY is executed. However, it must be added
before any files can be created in the encrypted directory.
+ For v2 encryption policies, ``master_key_descriptor`` has been
+ replaced with ``master_key_identifier``, which is longer and cannot
+ be arbitrarily chosen. Instead, the key must first be added using
+ FS_IOC_ADD_ENCRYPTION_KEY, as described in `Adding keys`_. Then,
+ the ``key_spec.u.identifier`` the kernel returned in the
+ :c:type:`struct fscrypt_add_key_arg` must be used as the
+ ``master_key_identifier`` in the :c:type:`struct fscrypt_policy_v2`.
+
If the file is not yet encrypted, then FS_IOC_SET_ENCRYPTION_POLICY
verifies that the file is an empty directory. If so, the specified
encryption policy is assigned to the directory, turning it into an
@@ -325,6 +455,15 @@ policy exactly matches the actual one. If they match, then the ioctl
returns 0. Otherwise, it fails with EEXIST. This works on both
regular files and directories, including nonempty directories.
+When a v2 encryption policy is assigned to a directory, it is also
+required that either the specified key has been added by the current
+user or that the caller has CAP_FOWNER in the initial user namespace.
+(This is needed to prevent a user from encrypting their data with
+another user's key.) The key must remain added while
+FS_IOC_SET_ENCRYPTION_POLICY is executing. However, if the new
+encrypted directory does not need to be accessed immediately, then the
+key can be removed right away afterwards.
+
Note that the ext4 filesystem does not allow the root directory to be
encrypted, even if it is empty. Users who want to encrypt an entire
filesystem with one key should consider using dm-crypt instead.
@@ -337,7 +476,11 @@ FS_IOC_SET_ENCRYPTION_POLICY can fail with the following errors:
- ``EEXIST``: the file is already encrypted with an encryption policy
different from the one specified
- ``EINVAL``: an invalid encryption policy was specified (invalid
- version, mode(s), or flags)
+ version, mode(s), or flags; or reserved bits were set)
+- ``ENOKEY``: a v2 encryption policy was specified, but the key with
+ the specified ``master_key_identifier`` has not been added, nor does
+ the process have the CAP_FOWNER capability in the initial user
+ namespace
- ``ENOTDIR``: the file is unencrypted and is a regular file, not a
directory
- ``ENOTEMPTY``: the file is unencrypted and is a nonempty directory
@@ -356,25 +499,78 @@ FS_IOC_SET_ENCRYPTION_POLICY can fail with the following errors:
Getting an encryption policy
----------------------------
-The FS_IOC_GET_ENCRYPTION_POLICY ioctl retrieves the :c:type:`struct
-fscrypt_policy`, if any, for a directory or regular file. See above
-for the struct definition. No additional permissions are required
-beyond the ability to open the file.
+Two ioctls are available to get a file's encryption policy:
+
+- FS_IOC_GET_ENCRYPTION_POLICY_EX
+- FS_IOC_GET_ENCRYPTION_POLICY
+
+The extended (_EX) version of the ioctl is more general and is
+recommended to use when possible. However, on older kernels only the
+original ioctl is available. Applications should try the extended
+version, and if it fails with ENOTTY fall back to the original
+version.
+
+Preferred method
+~~~~~~~~~~~~~~~~
+
+The FS_IOC_GET_ENCRYPTION_POLICY_EX ioctl retrieves the encryption
+policy, if any, for a directory or regular file. No additional
+permissions are required beyond the ability to open the file. It
+takes in a pointer to a :c:type:`struct fscrypt_get_policy_ex_arg`,
+defined as follows::
+
+ struct fscrypt_get_policy_ex_arg {
+ __u64 policy_size; /* input/output */
+ union {
+ __u8 version;
+ struct fscrypt_policy_v1 v1;
+ struct fscrypt_policy_v2 v2;
+ } policy; /* output */
+ };
+
+The caller must initialize ``policy_size`` to the size available for
+the policy struct, i.e. ``sizeof(arg.policy)``.
+
+On success, the policy struct is returned in ``policy``, and its
+actual size is returned in ``policy_size``. ``policy.version`` should
+be checked to determine the version of policy returned. Note that the
+version code for the "v1" policy is actually 0 (FSCRYPT_POLICY_V1).
-FS_IOC_GET_ENCRYPTION_POLICY can fail with the following errors:
+FS_IOC_GET_ENCRYPTION_POLICY_EX can fail with the following errors:
- ``EINVAL``: the file is encrypted, but it uses an unrecognized
- encryption context format
+ encryption policy version
- ``ENODATA``: the file is not encrypted
-- ``ENOTTY``: this type of filesystem does not implement encryption
+- ``ENOTTY``: this type of filesystem does not implement encryption,
+ or this kernel is too old to support FS_IOC_GET_ENCRYPTION_POLICY_EX
+ (try FS_IOC_GET_ENCRYPTION_POLICY instead)
- ``EOPNOTSUPP``: the kernel was not configured with encryption
support for this filesystem
+- ``EOVERFLOW``: the file is encrypted and uses a recognized
+ encryption policy version, but the policy struct does not fit into
+ the provided buffer
Note: if you only need to know whether a file is encrypted or not, on
most filesystems it is also possible to use the FS_IOC_GETFLAGS ioctl
and check for FS_ENCRYPT_FL, or to use the statx() system call and
check for STATX_ATTR_ENCRYPTED in stx_attributes.
+Legacy method
+~~~~~~~~~~~~~
+
+The FS_IOC_GET_ENCRYPTION_POLICY ioctl can also retrieve the
+encryption policy, if any, for a directory or regular file. However,
+unlike the extended version (FS_IOC_GET_ENCRYPTION_POLICY_EX),
+FS_IOC_GET_ENCRYPTION_POLICY only supports the original policy
+version. It takes in a pointer directly to a :c:type:`struct
+fscrypt_policy_v1` rather than a :c:type:`struct
+fscrypt_get_policy_ex_arg`.
+
+The error codes for FS_IOC_GET_ENCRYPTION_POLICY are the same as those
+for FS_IOC_GET_ENCRYPTION_POLICY_EX, except that
+FS_IOC_GET_ENCRYPTION_POLICY also returns ``EINVAL`` if the file is
+encrypted using a newer encryption policy version.
+
Getting the per-filesystem salt
-------------------------------
@@ -390,8 +586,98 @@ generate and manage any needed salt(s) in userspace.
Adding keys
-----------
-To provide a master key, userspace must add it to an appropriate
-keyring using the add_key() system call (see:
+Preferred method
+~~~~~~~~~~~~~~~~
+
+The FS_IOC_ADD_ENCRYPTION_KEY ioctl adds a master encryption key to
+the filesystem, making all files on the filesystem which were
+encrypted using that key appear "unlocked", i.e. in plaintext form.
+It can be executed on any file or directory on the target filesystem,
+but using the filesystem's root directory is recommended. It takes in
+a pointer to a :c:type:`struct fscrypt_add_key_arg`, defined as
+follows::
+
+ struct fscrypt_add_key_arg {
+ struct fscrypt_key_specifier key_spec;
+ __u32 raw_size;
+ __u32 __reserved[9];
+ __u8 raw[];
+ };
+
+ struct fscrypt_key_specifier {
+ #define FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR 1
+ #define FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER 2
+ __u32 type;
+ __u32 __reserved;
+ union {
+ __u8 __reserved[32]; /* reserve some extra space */
+ __u8 descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
+ __u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
+ } u;
+ };
+
+:c:type:`struct fscrypt_add_key_arg` must be zeroed, then initialized
+as follows:
+
+- If the key is being added for use by v1 encryption policies, then
+ ``key_spec.type`` must contain FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR, and
+ ``key_spec.u.descriptor`` must contain the descriptor of the key
+ being added, corresponding to the value in the
+ ``master_key_descriptor`` field of :c:type:`struct
+ fscrypt_policy_v1`. To add this type of key, the calling process
+ must have the CAP_SYS_ADMIN capability in the initial user
+ namespace.
+
+ Alternatively, if the key is being added for use by v2 encryption
+ policies, then ``key_spec.type`` must contain
+ FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER, and ``key_spec.u.identifier`` is
+ an *output* field which the kernel fills in with a cryptographic
+ hash of the key. To add this type of key, the calling process does
+ not need any privileges. However, the number of keys that can be
+ added is limited by the user's quota for the keyrings service (see
+ ``Documentation/security/keys/core.rst``).
+
+- ``raw_size`` must be the size of the ``raw`` key provided, in bytes.
+
+- ``raw`` is a variable-length field which must contain the actual
+ key, ``raw_size`` bytes long.
+
+FS_IOC_ADD_ENCRYPTION_KEY can fail with the following errors:
+
+- ``EACCES``: FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR was specified, but the
+ caller does not have the CAP_SYS_ADMIN capability in the initial
+ user namespace
+- ``EDQUOT``: the key quota for this user would be exceeded by adding
+ the key
+- ``EINVAL``: invalid key size or key specifier type, or reserved bits
+ were set
+- ``ENOTTY``: this type of filesystem does not implement encryption
+- ``EOPNOTSUPP``: the kernel was not configured with encryption
+ support for this filesystem, or the filesystem superblock has not
+ had encryption enabled on it
+
+Legacy method
+~~~~~~~~~~~~~
+
+For v1 encryption policies, a master encryption key can also be
+provided by adding it to a process-subscribed keyring, e.g. to a
+session keyring, or to a user keyring if the user keyring is linked
+into the session keyring.
+
+This method is deprecated (and not supported for v2 encryption
+policies) for several reasons. First, it cannot be used in
+combination with FS_IOC_REMOVE_ENCRYPTION_KEY (see `Removing keys`_),
+so for removing a key a workaround such as keyctl_unlink() in
+combination with ``sync; echo 2 > /proc/sys/vm/drop_caches`` would
+have to be used. Second, it doesn't match the fact that the
+locked/unlocked status of encrypted files (i.e. whether they appear to
+be in plaintext form or in ciphertext form) is global. This mismatch
+has caused much confusion as well as real problems when processes
+running under different UIDs, such as a ``sudo`` command, need to
+access encrypted files.
+
+Nevertheless, to add a key to one of the process-subscribed keyrings,
+the add_key() system call can be used (see:
``Documentation/security/keys/core.rst``). The key type must be
"logon"; keys of this type are kept in kernel memory and cannot be
read back by userspace. The key description must be "fscrypt:"
@@ -399,12 +685,12 @@ followed by the 16-character lower case hex representation of the
``master_key_descriptor`` that was set in the encryption policy. The
key payload must conform to the following structure::
- #define FSCRYPT_MAX_KEY_SIZE 64
+ #define FSCRYPT_MAX_KEY_SIZE 64
struct fscrypt_key {
- u32 mode;
- u8 raw[FSCRYPT_MAX_KEY_SIZE];
- u32 size;
+ __u32 mode;
+ __u8 raw[FSCRYPT_MAX_KEY_SIZE];
+ __u32 size;
};
``mode`` is ignored; just set it to 0. The actual key is provided in
@@ -416,26 +702,143 @@ with a filesystem-specific prefix such as "ext4:". However, the
filesystem-specific prefixes are deprecated and should not be used in
new programs.
-There are several different types of keyrings in which encryption keys
-may be placed, such as a session keyring, a user session keyring, or a
-user keyring. Each key must be placed in a keyring that is "attached"
-to all processes that might need to access files encrypted with it, in
-the sense that request_key() will find the key. Generally, if only
-processes belonging to a specific user need to access a given
-encrypted directory and no session keyring has been installed, then
-that directory's key should be placed in that user's user session
-keyring or user keyring. Otherwise, a session keyring should be
-installed if needed, and the key should be linked into that session
-keyring, or in a keyring linked into that session keyring.
-
-Note: introducing the complex visibility semantics of keyrings here
-was arguably a mistake --- especially given that by design, after any
-process successfully opens an encrypted file (thereby setting up the
-per-file key), possessing the keyring key is not actually required for
-any process to read/write the file until its in-memory inode is
-evicted. In the future there probably should be a way to provide keys
-directly to the filesystem instead, which would make the intended
-semantics clearer.
+Removing keys
+-------------
+
+The FS_IOC_REMOVE_ENCRYPTION_KEY ioctl can be used to remove a master
+encryption key from the kernel, wiping the corresponding secrets from
+memory and causing any files which were "unlocked" with the key to
+appear "locked" again. It can be executed on any file or directory on
+the target filesystem, but using the filesystem's root directory is
+recommended. It takes in a pointer to a :c:type:`struct
+fscrypt_remove_key_arg`, defined as follows::
+
+ struct fscrypt_remove_key_arg {
+ struct fscrypt_key_specifier key_spec;
+ #define FSCRYPT_REMOVE_KEY_FLAG_ALL_USERS 0x00000001
+ __u32 flags;
+ __u32 __reserved[5];
+ };
+
+This structure must be zeroed, then initialized as follows:
+
+- The key to remove is specified by ``key_spec``:
+
+ - To remove a key used by v1 encryption policies, set
+ ``key_spec.type`` to FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR and fill
+ in ``key_spec.u.descriptor``. To remove this type of key, the
+ calling process must have the CAP_SYS_ADMIN capability in the
+ initial user namespace.
+
+ - To remove a key used by v2 encryption policies, set
+ ``key_spec.type`` to FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER and fill
+ in ``key_spec.u.identifier``. To remove this type of key, no
+ privileges are needed. However, users can only remove keys that
+ they added themselves, subject to privileged override with
+ FSCRYPT_REMOVE_KEY_FLAG_ALL_USERS.
+
+- ``flags`` can contain the following flags:
+
+ - ``FSCRYPT_REMOVE_KEY_FLAG_ALL_USERS`` specifies that the key
+ should be removed even if it has also been added by other users.
+ Specifying this flag requires the CAP_SYS_ADMIN capability in
+ the initial user namespace.
+
+FS_IOC_REMOVE_ENCRYPTION_KEY can fail with the following errors:
+
+- ``EACCES``: The FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR key specifier type
+ and/or the FSCRYPT_REMOVE_KEY_FLAG_ALL_USERS flag was specified, but
+ the caller does not have the CAP_SYS_ADMIN capability in the initial
+ user namespace
+- ``EBUSY``: the master key secret was wiped from memory, but some
+ files which were unlocked with it are still in use. Such files
+ could not be locked, nor could their per-file keys be wiped from
+ memory. The ioctl may be retried later to re-attempt locking the
+ remaining files.
+- ``EINVAL``: invalid flags or key specifier type, or reserved bits
+ were set
+- ``ENOKEY``: the key is not present or has already been removed
+- ``ENOTTY``: this type of filesystem does not implement encryption
+- ``EOPNOTSUPP``: the kernel was not configured with encryption
+ support for this filesystem, or the filesystem superblock has not
+ had encryption enabled on it
+- ``EUSERS``: the key cannot be removed because other users have added
+ it too
+
+Before using this ioctl, read the `Kernel memory compromise`_ section
+for a discussion of the security goals and limitations of this ioctl.
+
+Getting key status
+------------------
+
+The FS_IOC_GET_ENCRYPTION_KEY_STATUS ioctl retrieves the status of a
+master encryption key. It can be executed on any file or directory on
+the target filesystem, but using the filesystem's root directory is
+recommended. It takes in a pointer to a :c:type:`struct
+fscrypt_get_key_status_arg`, defined as follows::
+
+ struct fscrypt_get_key_status_arg {
+ /* input */
+ struct fscrypt_key_specifier key_spec;
+ __u32 __reserved[6];
+
+ /* output */
+ #define FSCRYPT_KEY_STATUS_ABSENT 1
+ #define FSCRYPT_KEY_STATUS_PRESENT 2
+ #define FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED 3
+ __u32 status;
+ #define FSCRYPT_KEY_STATUS_FLAG_ADDED_BY_SELF 0x00000001
+ __u32 status_flags;
+ __u32 user_count;
+ __u32 __out_reserved[13];
+ };
+
+The caller must zero all input fields, then fill in ``key_spec``:
+
+ - To get the status of a key for v1 encryption policies, set
+ ``key_spec.type`` to FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR and fill
+ in ``key_spec.u.descriptor``.
+
+ - To get the status of a key for v2 encryption policies, set
+ ``key_spec.type`` to FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER and fill
+ in ``key_spec.u.identifier``.
+
+On success, 0 is returned and the kernel fills in the output fields:
+
+- ``status`` indicates whether the key is absent, present, or
+ incompletely removed. Incompletely removed means that the master
+ secret has been removed, but some files are still in use; i.e.,
+ FS_IOC_REMOVE_ENCRYPTION_KEY returned EBUSY.
+
+- ``status_flags`` can contain the following flags:
+
+ - ``FSCRYPT_KEY_STATUS_FLAG_ADDED_BY_SELF`` indicates that the key
+ has added by the current user. This is only set for keys
+ identified by ``identifier`` rather than by ``descriptor``.
+
+- ``user_count`` specifies the number of users who have added the key.
+ This is only set for keys identified by ``identifier`` rather than
+ by ``descriptor``.
+
+FS_IOC_GET_ENCRYPTION_KEY_STATUS can fail with the following errors:
+
+- ``EINVAL``: invalid key specifier type, or reserved bits were set
+- ``ENOTTY``: this type of filesystem does not implement encryption
+- ``EOPNOTSUPP``: the kernel was not configured with encryption
+ support for this filesystem, or the filesystem superblock has not
+ had encryption enabled on it
+
+Among other use cases, FS_IOC_GET_ENCRYPTION_KEY_STATUS might be
+useful for determining whether the key for a given encrypted directory
+needs to be added before prompting the user for the passphrase needed
+to derive the key.
+
+FS_IOC_GET_ENCRYPTION_KEY_STATUS can only get the status of keys in
+the filesystem-level keyring, i.e. the keyring managed by
+FS_IOC_ADD_ENCRYPTION_KEY and FS_IOC_REMOVE_ENCRYPTION_KEY. It cannot
+get the status of a key that has only been added for use by v1
+encryption policies using the legacy mechanism involving
+process-subscribed keyrings.
Access semantics
================
@@ -498,7 +901,7 @@ Without the key
Some filesystem operations may be performed on encrypted regular
files, directories, and symlinks even before their encryption key has
-been provided:
+been added, or after their encryption key has been removed:
- File metadata may be read, e.g. using stat().
@@ -563,20 +966,20 @@ Encryption context
------------------
An encryption policy is represented on-disk by a :c:type:`struct
-fscrypt_context`. It is up to individual filesystems to decide where
-to store it, but normally it would be stored in a hidden extended
-attribute. It should *not* be exposed by the xattr-related system
-calls such as getxattr() and setxattr() because of the special
-semantics of the encryption xattr. (In particular, there would be
-much confusion if an encryption policy were to be added to or removed
-from anything other than an empty directory.) The struct is defined
-as follows::
+fscrypt_context_v1` or a :c:type:`struct fscrypt_context_v2`. It is
+up to individual filesystems to decide where to store it, but normally
+it would be stored in a hidden extended attribute. It should *not* be
+exposed by the xattr-related system calls such as getxattr() and
+setxattr() because of the special semantics of the encryption xattr.
+(In particular, there would be much confusion if an encryption policy
+were to be added to or removed from anything other than an empty
+directory.) These structs are defined as follows::
- #define FSCRYPT_KEY_DESCRIPTOR_SIZE 8
#define FS_KEY_DERIVATION_NONCE_SIZE 16
- struct fscrypt_context {
- u8 format;
+ #define FSCRYPT_KEY_DESCRIPTOR_SIZE 8
+ struct fscrypt_context_v1 {
+ u8 version;
u8 contents_encryption_mode;
u8 filenames_encryption_mode;
u8 flags;
@@ -584,12 +987,23 @@ as follows::
u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE];
};
-Note that :c:type:`struct fscrypt_context` contains the same
-information as :c:type:`struct fscrypt_policy` (see `Setting an
-encryption policy`_), except that :c:type:`struct fscrypt_context`
-also contains a nonce. The nonce is randomly generated by the kernel
-and is used to derive the inode's encryption key as described in
-`Per-file keys`_.
+ #define FSCRYPT_KEY_IDENTIFIER_SIZE 16
+ struct fscrypt_context_v2 {
+ u8 version;
+ u8 contents_encryption_mode;
+ u8 filenames_encryption_mode;
+ u8 flags;
+ u8 __reserved[4];
+ u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
+ u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE];
+ };
+
+The context structs contain the same information as the corresponding
+policy structs (see `Setting an encryption policy`_), except that the
+context structs also contain a nonce. The nonce is randomly generated
+by the kernel and is used as KDF input or as a tweak to cause
+different files to be encrypted differently; see `Per-file keys`_ and
+`DIRECT_KEY and per-mode keys`_.
Data path changes
-----------------
--
2.20.1
^ permalink raw reply related
* [RFC PATCH v2 19/20] ubifs: wire up new fscrypt ioctls
From: Eric Biggers @ 2019-02-11 17:27 UTC (permalink / raw)
To: linux-fscrypt
Cc: Satya Tangirala, linux-api, linux-f2fs-devel, keyrings, linux-mtd,
linux-crypto, linux-fsdevel, linux-ext4, Paul Crowley
In-Reply-To: <20190211172738.4633-1-ebiggers@kernel.org>
From: Eric Biggers <ebiggers@google.com>
Wire up the new ioctls for adding and removing fscrypt keys to/from the
filesystem, and the new ioctl for retrieving v2 encryption policies.
For more details see Documentation/filesystems/fscrypt.rst, as well as
the fscrypt patches that added the implementation of these ioctls.
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
fs/ubifs/ioctl.c | 24 ++++++++++++++++++------
1 file changed, 18 insertions(+), 6 deletions(-)
diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c
index 0f9c362a3402..5f4c4620f9c4 100644
--- a/fs/ubifs/ioctl.c
+++ b/fs/ubifs/ioctl.c
@@ -197,13 +197,21 @@ long ubifs_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
return -EOPNOTSUPP;
#endif
}
- case FS_IOC_GET_ENCRYPTION_POLICY: {
-#ifdef CONFIG_FS_ENCRYPTION
+
+ case FS_IOC_GET_ENCRYPTION_POLICY:
return fscrypt_ioctl_get_policy(file, (void __user *)arg);
-#else
- return -EOPNOTSUPP;
-#endif
- }
+
+ case FS_IOC_GET_ENCRYPTION_POLICY_EX:
+ return fscrypt_ioctl_get_policy_ex(file, (void __user *)arg);
+
+ case FS_IOC_ADD_ENCRYPTION_KEY:
+ return fscrypt_ioctl_add_key(file, (void __user *)arg);
+
+ case FS_IOC_REMOVE_ENCRYPTION_KEY:
+ return fscrypt_ioctl_remove_key(file, (const void __user *)arg);
+
+ case FS_IOC_GET_ENCRYPTION_KEY_STATUS:
+ return fscrypt_ioctl_get_key_status(file, (void __user *)arg);
default:
return -ENOTTY;
@@ -222,6 +230,10 @@ long ubifs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
break;
case FS_IOC_SET_ENCRYPTION_POLICY:
case FS_IOC_GET_ENCRYPTION_POLICY:
+ case FS_IOC_GET_ENCRYPTION_POLICY_EX:
+ case FS_IOC_ADD_ENCRYPTION_KEY:
+ case FS_IOC_REMOVE_ENCRYPTION_KEY:
+ case FS_IOC_GET_ENCRYPTION_KEY_STATUS:
break;
default:
return -ENOIOCTLCMD;
--
2.20.1
^ permalink raw reply related
* [RFC PATCH v2 18/20] f2fs: wire up new fscrypt ioctls
From: Eric Biggers @ 2019-02-11 17:27 UTC (permalink / raw)
To: linux-fscrypt
Cc: Satya Tangirala, linux-api, linux-f2fs-devel, keyrings, linux-mtd,
linux-crypto, linux-fsdevel, linux-ext4, Paul Crowley
In-Reply-To: <20190211172738.4633-1-ebiggers@kernel.org>
From: Eric Biggers <ebiggers@google.com>
Wire up the new ioctls for adding and removing fscrypt keys to/from the
filesystem, and the new ioctl for retrieving v2 encryption policies.
For more details see Documentation/filesystems/fscrypt.rst, as well as
the fscrypt patches that added the implementation of these ioctls.
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
fs/f2fs/file.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 46 insertions(+)
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index ba5954f41e14..3e6da48e0530 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -2093,6 +2093,40 @@ static int f2fs_ioc_get_encryption_pwsalt(struct file *filp, unsigned long arg)
return err;
}
+static int f2fs_ioc_get_encryption_policy_ex(struct file *filp,
+ unsigned long arg)
+{
+ if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
+ return -EOPNOTSUPP;
+
+ return fscrypt_ioctl_get_policy_ex(filp, (void __user *)arg);
+}
+
+static int f2fs_ioc_add_encryption_key(struct file *filp, unsigned long arg)
+{
+ if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
+ return -EOPNOTSUPP;
+
+ return fscrypt_ioctl_add_key(filp, (void __user *)arg);
+}
+
+static int f2fs_ioc_remove_encryption_key(struct file *filp, unsigned long arg)
+{
+ if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
+ return -EOPNOTSUPP;
+
+ return fscrypt_ioctl_remove_key(filp, (const void __user *)arg);
+}
+
+static int f2fs_ioc_get_encryption_key_status(struct file *filp,
+ unsigned long arg)
+{
+ if (!f2fs_sb_has_encrypt(F2FS_I_SB(file_inode(filp))))
+ return -EOPNOTSUPP;
+
+ return fscrypt_ioctl_get_key_status(filp, (void __user *)arg);
+}
+
static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
{
struct inode *inode = file_inode(filp);
@@ -2998,6 +3032,14 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return f2fs_ioc_get_encryption_policy(filp, arg);
case F2FS_IOC_GET_ENCRYPTION_PWSALT:
return f2fs_ioc_get_encryption_pwsalt(filp, arg);
+ case FS_IOC_GET_ENCRYPTION_POLICY_EX:
+ return f2fs_ioc_get_encryption_policy_ex(filp, arg);
+ case FS_IOC_ADD_ENCRYPTION_KEY:
+ return f2fs_ioc_add_encryption_key(filp, arg);
+ case FS_IOC_REMOVE_ENCRYPTION_KEY:
+ return f2fs_ioc_remove_encryption_key(filp, arg);
+ case FS_IOC_GET_ENCRYPTION_KEY_STATUS:
+ return f2fs_ioc_get_encryption_key_status(filp, arg);
case F2FS_IOC_GARBAGE_COLLECT:
return f2fs_ioc_gc(filp, arg);
case F2FS_IOC_GARBAGE_COLLECT_RANGE:
@@ -3117,6 +3159,10 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case F2FS_IOC_SET_ENCRYPTION_POLICY:
case F2FS_IOC_GET_ENCRYPTION_PWSALT:
case F2FS_IOC_GET_ENCRYPTION_POLICY:
+ case FS_IOC_GET_ENCRYPTION_POLICY_EX:
+ case FS_IOC_ADD_ENCRYPTION_KEY:
+ case FS_IOC_REMOVE_ENCRYPTION_KEY:
+ case FS_IOC_GET_ENCRYPTION_KEY_STATUS:
case F2FS_IOC_GARBAGE_COLLECT:
case F2FS_IOC_GARBAGE_COLLECT_RANGE:
case F2FS_IOC_WRITE_CHECKPOINT:
--
2.20.1
^ permalink raw reply related
* [RFC PATCH v2 17/20] ext4: wire up new fscrypt ioctls
From: Eric Biggers @ 2019-02-11 17:27 UTC (permalink / raw)
To: linux-fscrypt
Cc: Satya Tangirala, linux-api, linux-f2fs-devel, keyrings, linux-mtd,
linux-crypto, linux-fsdevel, linux-ext4, Paul Crowley
In-Reply-To: <20190211172738.4633-1-ebiggers@kernel.org>
From: Eric Biggers <ebiggers@google.com>
Wire up the new ioctls for adding and removing fscrypt keys to/from the
filesystem, and the new ioctl for retrieving v2 encryption policies.
For more details see Documentation/filesystems/fscrypt.rst, as well as
the fscrypt patches that added the implementation of these ioctls.
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
fs/ext4/ioctl.c | 24 ++++++++++++++++++++++++
1 file changed, 24 insertions(+)
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index d26bcac291bb..c939dbd2f2ac 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -1020,6 +1020,26 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
case EXT4_IOC_GET_ENCRYPTION_POLICY:
return fscrypt_ioctl_get_policy(filp, (void __user *)arg);
+ case FS_IOC_GET_ENCRYPTION_POLICY_EX:
+ if (!ext4_has_feature_encrypt(sb))
+ return -EOPNOTSUPP;
+ return fscrypt_ioctl_get_policy_ex(filp, (void __user *)arg);
+
+ case FS_IOC_ADD_ENCRYPTION_KEY:
+ if (!ext4_has_feature_encrypt(sb))
+ return -EOPNOTSUPP;
+ return fscrypt_ioctl_add_key(filp, (void __user *)arg);
+
+ case FS_IOC_REMOVE_ENCRYPTION_KEY:
+ if (!ext4_has_feature_encrypt(sb))
+ return -EOPNOTSUPP;
+ return fscrypt_ioctl_remove_key(filp, (const void __user *)arg);
+
+ case FS_IOC_GET_ENCRYPTION_KEY_STATUS:
+ if (!ext4_has_feature_encrypt(sb))
+ return -EOPNOTSUPP;
+ return fscrypt_ioctl_get_key_status(filp, (void __user *)arg);
+
case EXT4_IOC_FSGETXATTR:
{
struct fsxattr fa;
@@ -1138,6 +1158,10 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case EXT4_IOC_SET_ENCRYPTION_POLICY:
case EXT4_IOC_GET_ENCRYPTION_PWSALT:
case EXT4_IOC_GET_ENCRYPTION_POLICY:
+ case FS_IOC_GET_ENCRYPTION_POLICY_EX:
+ case FS_IOC_ADD_ENCRYPTION_KEY:
+ case FS_IOC_REMOVE_ENCRYPTION_KEY:
+ case FS_IOC_GET_ENCRYPTION_KEY_STATUS:
case EXT4_IOC_SHUTDOWN:
case FS_IOC_GETFSMAP:
break;
--
2.20.1
^ permalink raw reply related
* [RFC PATCH v2 16/20] fscrypt: require that key be added when setting a v2 encryption policy
From: Eric Biggers @ 2019-02-11 17:27 UTC (permalink / raw)
To: linux-fscrypt
Cc: Satya Tangirala, linux-api, linux-f2fs-devel, keyrings, linux-mtd,
linux-crypto, linux-fsdevel, linux-ext4, Paul Crowley
In-Reply-To: <20190211172738.4633-1-ebiggers@kernel.org>
From: Eric Biggers <ebiggers@google.com>
By looking up the master keys in a filesystem-level keyring rather than
in the calling processes' key hierarchy, it becomes possible for a user
to set an encryption policy which refers to some key they don't actually
know, then encrypt their files using that key. Cryptographically this
isn't much of a problem, but the semantics of this would be a bit weird.
Thus, enforce that a v2 encryption policy can only be set if the user
has previously added the key, or has capable(CAP_FOWNER).
We tolerate that this problem will continue to exist for v1 encryption
policies, however; there is no way around that.
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
fs/crypto/fscrypt_private.h | 3 +++
fs/crypto/keyring.c | 47 +++++++++++++++++++++++++++++++++++++
fs/crypto/policy.c | 6 +++++
3 files changed, 56 insertions(+)
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index b16cf3bd6cf1..2b58520ab0e2 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -402,6 +402,9 @@ extern struct key *
fscrypt_find_master_key(struct super_block *sb,
const struct fscrypt_key_specifier *mk_spec);
+extern int fscrypt_verify_key_added(struct super_block *sb,
+ const u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE]);
+
extern int __init fscrypt_init_keyring(void);
extern void fscrypt_exit_keyring(void);
diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c
index 15ca0f1d04e7..42462452e34e 100644
--- a/fs/crypto/keyring.c
+++ b/fs/crypto/keyring.c
@@ -556,6 +556,53 @@ int fscrypt_ioctl_add_key(struct file *filp, void __user *_uarg)
}
EXPORT_SYMBOL_GPL(fscrypt_ioctl_add_key);
+/*
+ * Verify that the current user has added a master key with the given identifier
+ * (returns -ENOKEY if not). This is needed to prevent a user from encrypting
+ * their files using some other user's key which they don't actually know.
+ * Cryptographically this isn't much of a problem, but the semantics of this
+ * would be a bit weird, so it's best to just forbid it.
+ *
+ * The system administrator (CAP_FOWNER) can override this, which should be
+ * enough for any use cases where encryption policies are being set using keys
+ * that were chosen ahead of time but aren't available at the moment.
+ *
+ * Note that the key may have already removed by the time this returns, but
+ * that's okay; we just care whether the key was there at some point.
+ *
+ * Return: 0 if the key is added, -ENOKEY if it isn't, or another -errno code
+ */
+int fscrypt_verify_key_added(struct super_block *sb,
+ const u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE])
+{
+ struct fscrypt_key_specifier mk_spec;
+ struct key *key, *mk_user;
+ struct fscrypt_master_key *mk;
+ int err;
+
+ mk_spec.type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER;
+ memcpy(mk_spec.u.identifier, identifier, FSCRYPT_KEY_IDENTIFIER_SIZE);
+
+ key = fscrypt_find_master_key(sb, &mk_spec);
+ if (IS_ERR(key)) {
+ err = PTR_ERR(key);
+ goto out;
+ }
+ mk = key->payload.data[0];
+ mk_user = find_master_key_user(mk);
+ if (IS_ERR(mk_user)) {
+ err = PTR_ERR(mk_user);
+ } else {
+ key_put(mk_user);
+ err = 0;
+ }
+ key_put(key);
+out:
+ if (err == -ENOKEY && capable(CAP_FOWNER))
+ err = 0;
+ return err;
+}
+
static void evict_dentries_for_decrypted_inodes(struct fscrypt_master_key *mk)
{
struct fscrypt_info *ci;
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 07fec2f7fc72..456c25796844 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -209,6 +209,7 @@ static int set_encryption_policy(struct inode *inode,
{
union fscrypt_context ctx;
int ctxsize;
+ int err;
if (!fscrypt_supported_policy(policy))
return -EINVAL;
@@ -227,6 +228,11 @@ static int set_encryption_policy(struct inode *inode,
*/
pr_warn_once("%s (pid %d) is setting deprecated v1 encryption policy; recommend upgrading to v2.\n",
current->comm, current->pid);
+ } else {
+ err = fscrypt_verify_key_added(inode->i_sb,
+ policy->v2.master_key_identifier);
+ if (err)
+ return err;
}
ctxsize = fscrypt_new_context_from_policy(&ctx, policy);
--
2.20.1
^ permalink raw reply related
* [RFC PATCH v2 15/20] fscrypt: allow unprivileged users to add/remove keys for v2 policies
From: Eric Biggers @ 2019-02-11 17:27 UTC (permalink / raw)
To: linux-fscrypt
Cc: Satya Tangirala, linux-api, linux-f2fs-devel, keyrings, linux-mtd,
linux-crypto, linux-fsdevel, linux-ext4, Paul Crowley
In-Reply-To: <20190211172738.4633-1-ebiggers@kernel.org>
From: Eric Biggers <ebiggers@google.com>
Allow the FS_IOC_ADD_ENCRYPTION_KEY and FS_IOC_REMOVE_ENCRYPTION_KEY
ioctls to be used by non-root users to add and remove encryption keys
from the filesystem-level crypto keyrings, subject to limitations.
Motivation: while privileged fscrypt key management is sufficient for
some users (e.g. Android and Chromium OS, where a privileged process
manages all keys), the old API by design also allows non-root users to
set up and use encrypted directories, and we don't want to regress on
that. Especially, we don't want to force users to continue using the
old API, running into the visibility mismatch between files and keyrings
and being unable to "lock" encrypted directories.
Intuitively, the ioctls have to be privileged since they manipulate
filesystem-level state. However, it's actually safe to make them
unprivileged if we very carefully enforce some specific limitations.
First, each key must be identified by a cryptographic hash so that a
user can't add the wrong key for another user's files. For v2
encryption policies, we use the key_identifier for this. v1 policies
don't have this, so managing keys for them remains privileged.
Second, each key a user adds is charged to their quota for the keyrings
service. Thus, a user can't exhaust memory by adding a huge number of
keys. By default each non-root user is allowed up to 200 keys; this can
be changed using the existing sysctl 'kernel.keys.maxkeys'.
Third, if multiple users add the same key, we keep track of those users
of the key (of which there remains a single copy), and won't really
remove the key, i.e. "lock" the encrypted files, until all those users
have removed it. This prevents denial of service attacks that would be
possible under simpler schemes, such allowing the first user who added a
key to remove it -- since that could be a malicious user who has
compromised the key. Of course, encryption keys should be kept secret,
but the idea is that using encryption should never be *less* secure than
not using encryption, even if your key was compromised.
We tolerate that a user will be unable to really remove a key, i.e.
unable to "lock" their encrypted files, if another user has added the
same key. But in a sense, this is actually a good thing because it will
avoid providing a false notion of security where a key appears to have
been removed when actually it's still in memory, available to any
attacker who compromises the operating system kernel.
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
fs/crypto/fscrypt_private.h | 25 ++-
fs/crypto/keyring.c | 310 +++++++++++++++++++++++++++++++++--
fs/crypto/keysetup.c | 16 +-
include/uapi/linux/fscrypt.h | 9 +-
4 files changed, 336 insertions(+), 24 deletions(-)
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index 1a40f7359655..b16cf3bd6cf1 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -336,9 +336,16 @@ struct fscrypt_master_key {
* FS_IOC_REMOVE_ENCRYPTION_KEY can be retried, or
* FS_IOC_ADD_ENCRYPTION_KEY can add the secret again.
*
- * Locking: protected by key->sem.
+ * Locking: protected by key->sem (outer) and mk_secret_sem (inner).
+ * The reason for two locks is that key->sem also protects modifying
+ * mk_users, which ranks it above the semaphore for the keyring key
+ * type, which is in turn above page faults (via keyring_read). But
+ * sometimes filesystems call fscrypt_get_encryption_info() from within
+ * a transaction, which ranks it below page faults. So we need a
+ * separate lock which protects mk_secret but not also mk_users.
*/
struct fscrypt_master_key_secret mk_secret;
+ struct rw_semaphore mk_secret_sem;
/*
* For v1 policy keys: an arbitrary key descriptor which was assigned by
@@ -348,6 +355,22 @@ struct fscrypt_master_key {
*/
struct fscrypt_key_specifier mk_spec;
+ /*
+ * Keyring which contains a key of type 'key_type_fscrypt_user' for each
+ * user who has added this key. Normally each key will be added by just
+ * one user, but it's possible that multiple users share a key, and in
+ * that case we need to keep track of those users so that one user can't
+ * remove the key before the others want it removed too.
+ *
+ * This is NULL for v1 policy keys; those can only be added by root.
+ *
+ * Locking: in addition to this keyrings own semaphore, this is
+ * protected by the master key's key->sem, so we can do atomic
+ * search+insert. It can also be searched without taking any locks, but
+ * in that case the returned key may have already been removed.
+ */
+ struct key *mk_users;
+
/*
* Length of ->mk_decrypted_inodes, plus one if mk_secret is present.
* Once this goes to 0, the master key is removed from ->s_master_keys.
diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c
index 6bf1e0672a09..15ca0f1d04e7 100644
--- a/fs/crypto/keyring.c
+++ b/fs/crypto/keyring.c
@@ -42,6 +42,7 @@ static void free_master_key(struct fscrypt_master_key *mk)
for (i = 0; i < ARRAY_SIZE(mk->mk_mode_keys); i++)
crypto_free_skcipher(mk->mk_mode_keys[i]);
+ key_put(mk->mk_users);
kzfree(mk);
}
@@ -101,7 +102,39 @@ static struct key_type key_type_fscrypt = {
.describe = fscrypt_key_describe,
};
-/* Search ->s_master_keys */
+static int fscrypt_user_key_instantiate(struct key *key,
+ struct key_preparsed_payload *prep)
+{
+ /*
+ * We just charge FSCRYPT_MAX_KEY_SIZE bytes to the user's key quota for
+ * each key, regardless of the exact key size. The amount of memory
+ * actually used is greater than the size of the raw key anyway.
+ */
+ return key_payload_reserve(key, FSCRYPT_MAX_KEY_SIZE);
+}
+
+static void fscrypt_user_key_describe(const struct key *key, struct seq_file *m)
+{
+ seq_puts(m, key->description);
+}
+
+/*
+ * Type of key in ->mk_users. Each key of this type represents a particular
+ * user who has added a particular master key.
+ *
+ * Note that the name of this key type really should be something like
+ * ".fscrypt-user" instead of simply ".fscrypt". But the shorter name is chosen
+ * mainly for simplicity of presentation in /proc/keys when read by a non-root
+ * user. And it is expected to be rare that a key is actually added by multiple
+ * users, since users should keep their encryption keys confidential.
+ */
+static struct key_type key_type_fscrypt_user = {
+ .name = ".fscrypt",
+ .instantiate = fscrypt_user_key_instantiate,
+ .describe = fscrypt_user_key_describe,
+};
+
+/* Search ->s_master_keys or ->mk_users */
static struct key *search_fscrypt_keyring(struct key *keyring,
struct key_type *type,
const char *description)
@@ -127,6 +160,13 @@ static struct key *search_fscrypt_keyring(struct key *keyring,
#define FSCRYPT_MK_DESCRIPTION_SIZE (2 * FSCRYPT_KEY_IDENTIFIER_SIZE + 1)
+#define FSCRYPT_MK_USERS_DESCRIPTION_SIZE \
+ (CONST_STRLEN("fscrypt-") + 2 * FSCRYPT_KEY_IDENTIFIER_SIZE + \
+ CONST_STRLEN("-users") + 1)
+
+#define FSCRYPT_MK_USER_DESCRIPTION_SIZE \
+ (2 * FSCRYPT_KEY_IDENTIFIER_SIZE + CONST_STRLEN(".uid.") + 10 + 1)
+
static void format_fs_keyring_description(
char description[FSCRYPT_FS_KEYRING_DESCRIPTION_SIZE],
const struct super_block *sb)
@@ -142,6 +182,23 @@ static void format_mk_description(
master_key_spec_len(mk_spec), (u8 *)&mk_spec->u);
}
+static void format_mk_users_keyring_description(
+ char description[FSCRYPT_MK_USERS_DESCRIPTION_SIZE],
+ const u8 mk_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE])
+{
+ sprintf(description, "fscrypt-%*phN-users",
+ FSCRYPT_KEY_IDENTIFIER_SIZE, mk_identifier);
+}
+
+static void format_mk_user_description(
+ char description[FSCRYPT_MK_USER_DESCRIPTION_SIZE],
+ const u8 mk_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE])
+{
+
+ sprintf(description, "%*phN.uid.%u", FSCRYPT_KEY_IDENTIFIER_SIZE,
+ mk_identifier, __kuid_val(current_fsuid()));
+}
+
/* Create ->s_master_keys if needed. Synchronized by fscrypt_add_key_mutex. */
static int allocate_filesystem_keyring(struct super_block *sb)
{
@@ -183,6 +240,81 @@ struct key *fscrypt_find_master_key(struct super_block *sb,
return search_fscrypt_keyring(keyring, &key_type_fscrypt, description);
}
+static int allocate_master_key_users_keyring(struct fscrypt_master_key *mk)
+{
+ char description[FSCRYPT_MK_USERS_DESCRIPTION_SIZE];
+ struct key *keyring;
+
+ format_mk_users_keyring_description(description,
+ mk->mk_spec.u.identifier);
+ keyring = keyring_alloc(description, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
+ current_cred(), KEY_POS_SEARCH |
+ KEY_USR_SEARCH | KEY_USR_READ | KEY_USR_VIEW,
+ KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL);
+ if (IS_ERR(keyring))
+ return PTR_ERR(keyring);
+
+ mk->mk_users = keyring;
+ return 0;
+}
+
+/*
+ * Find the current user's key in the master key's ->mk_users.
+ * Returns ERR_PTR(-ENOKEY) if not found.
+ */
+static struct key *find_master_key_user(struct fscrypt_master_key *mk)
+{
+ char description[FSCRYPT_MK_USER_DESCRIPTION_SIZE];
+
+ format_mk_user_description(description, mk->mk_spec.u.identifier);
+ return search_fscrypt_keyring(mk->mk_users, &key_type_fscrypt_user,
+ description);
+}
+
+/*
+ * Give the current user a key in ->mk_users. This charges the user's quota and
+ * marks the master key as added by the current user, so that it cannot be
+ * removed by another user with the key. Either the master key's key->sem must
+ * be held for write, or the master key must be still undergoing initialization.
+ */
+static int add_master_key_user(struct fscrypt_master_key *mk)
+{
+ char description[FSCRYPT_MK_USER_DESCRIPTION_SIZE];
+ struct key *mk_user;
+ int err;
+
+ format_mk_user_description(description, mk->mk_spec.u.identifier);
+ mk_user = key_alloc(&key_type_fscrypt_user, description,
+ current_fsuid(), current_gid(), current_cred(),
+ KEY_POS_SEARCH | KEY_USR_VIEW, 0, NULL);
+ if (IS_ERR(mk_user))
+ return PTR_ERR(mk_user);
+
+ err = key_instantiate_and_link(mk_user, NULL, 0, mk->mk_users, NULL);
+ key_put(mk_user);
+ return err;
+}
+
+/*
+ * Remove the current user's key from ->mk_users, if present.
+ * The master key's key->sem must be held for write.
+ */
+static int remove_master_key_user(struct fscrypt_master_key *mk)
+{
+ struct key *mk_user;
+ int err;
+
+ mk_user = find_master_key_user(mk);
+ if (IS_ERR(mk_user)) {
+ if (mk_user != ERR_PTR(-ENOKEY))
+ return PTR_ERR(mk_user);
+ return 0;
+ }
+ err = key_unlink(mk->mk_users, mk_user);
+ key_put(mk_user);
+ return err;
+}
+
/*
* Allocate a new fscrypt_master_key which contains the given secret, set it as
* the payload of a new 'struct key' of type fscrypt, and link the 'struct key'
@@ -204,11 +336,26 @@ static int add_new_master_key(struct fscrypt_master_key_secret *secret,
mk->mk_spec = *mk_spec;
move_master_key_secret(&mk->mk_secret, secret);
+ init_rwsem(&mk->mk_secret_sem);
refcount_set(&mk->mk_refcount, 1); /* secret is present */
INIT_LIST_HEAD(&mk->mk_decrypted_inodes);
spin_lock_init(&mk->mk_decrypted_inodes_lock);
+ if (mk_spec->type != FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR) {
+ err = allocate_master_key_users_keyring(mk);
+ if (err)
+ goto out_free_mk;
+ err = add_master_key_user(mk);
+ if (err)
+ goto out_free_mk;
+ }
+
+ /*
+ * Note that we don't charge this key to anyone's quota, since when
+ * ->mk_users is in use those keys are charged instead, and otherwise
+ * (when ->mk_users isn't in use) only root can add these keys.
+ */
format_mk_description(description, mk_spec);
key = key_alloc(&key_type_fscrypt, description,
GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, current_cred(),
@@ -236,13 +383,45 @@ static int add_existing_master_key(struct fscrypt_master_key *mk,
struct fscrypt_master_key_secret *secret,
const struct fscrypt_key_specifier *mk_spec)
{
- if (is_master_key_secret_present(&mk->mk_secret))
- return 0;
+ struct key *mk_user;
+ bool rekey;
+ int err;
+
+ /*
+ * If the current user is already in ->mk_users, then there's nothing to
+ * do. (Not applicable for v1 policy keys, which have NULL ->mk_users.)
+ */
+ if (mk->mk_users) {
+ mk_user = find_master_key_user(mk);
+ if (mk_user != ERR_PTR(-ENOKEY)) {
+ if (IS_ERR(mk_user))
+ return PTR_ERR(mk_user);
+ key_put(mk_user);
+ return 0;
+ }
+ }
- if (!refcount_inc_not_zero(&mk->mk_refcount))
+ /* If we'll be re-adding ->mk_secret, try to take the reference. */
+ rekey = !is_master_key_secret_present(&mk->mk_secret);
+ if (rekey && !refcount_inc_not_zero(&mk->mk_refcount))
return KEY_DEAD;
- move_master_key_secret(&mk->mk_secret, secret);
+ /* Add the current user to ->mk_users, if applicable. */
+ if (mk->mk_users) {
+ err = add_master_key_user(mk);
+ if (err) {
+ if (rekey && refcount_dec_and_test(&mk->mk_refcount))
+ return KEY_DEAD;
+ return err;
+ }
+ }
+
+ /* Re-add the secret if needed. */
+ if (rekey) {
+ down_write(&mk->mk_secret_sem);
+ move_master_key_secret(&mk->mk_secret, secret);
+ up_write(&mk->mk_secret_sem);
+ }
return 0;
}
@@ -269,7 +448,7 @@ static int add_master_key(struct super_block *sb,
} else {
/*
* Found the key in ->s_master_keys. Re-add the secret if
- * needed.
+ * needed, and add the user to ->mk_users if needed.
*/
down_write(&key->sem);
err = add_existing_master_key(key->payload.data[0], secret,
@@ -291,6 +470,23 @@ static int add_master_key(struct super_block *sb,
/*
* Add a master encryption key to the filesystem, causing all files which were
* encrypted with it to appear "unlocked" (decrypted) when accessed.
+ *
+ * When adding a key for use by v1 encryption policies, this ioctl is
+ * privileged, and userspace must provide the 'key_descriptor'.
+ *
+ * When adding a key for use by v2+ encryption policies, this ioctl is
+ * unprivileged. This is needed, in general, to allow non-root users to use
+ * encryption without encountering the visibility problems of process-subscribed
+ * keyrings and the inability to properly remove keys. This works by having
+ * each key identified by its cryptographically secure hash --- the
+ * 'key_identifier'. The cryptographic hash ensures that a malicious user
+ * cannot add the wrong key for a given identifier. Furthermore, each added key
+ * is charged to the appropriate user's quota for the keyrings service, which
+ * prevents a malicious user from adding too many keys. Finally, we forbid a
+ * user from removing a key while other users have added it too, which prevents
+ * a user who knows another user's key from causing a denial-of-service by
+ * removing it at an inopportune time. (We tolerate that a user who knows a key
+ * can prevent other users from removing it.)
*/
int fscrypt_ioctl_add_key(struct file *filp, void __user *_uarg)
{
@@ -319,11 +515,16 @@ int fscrypt_ioctl_add_key(struct file *filp, void __user *_uarg)
if (copy_from_user(secret.raw, uarg->raw, secret.size))
goto out_wipe_secret;
- err = -EACCES;
- if (!capable(CAP_SYS_ADMIN))
- goto out_wipe_secret;
-
- if (arg.key_spec.type != FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR) {
+ if (arg.key_spec.type == FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR) {
+ /*
+ * Only root can add keys that are identified by an arbitrary
+ * descriptor rather than by a cryptographic hash --- since
+ * otherwise a malicious user could add the wrong key.
+ */
+ err = -EACCES;
+ if (!capable(CAP_SYS_ADMIN))
+ goto out_wipe_secret;
+ } else {
err = fscrypt_init_hkdf(&secret.hkdf, secret.raw, secret.size);
if (err)
goto out_wipe_secret;
@@ -511,13 +712,29 @@ int fscrypt_ioctl_remove_key(struct file *filp, const void __user *uarg)
if (copy_from_user(&arg, uarg, sizeof(arg)))
return -EFAULT;
+ if (arg.flags & ~FSCRYPT_REMOVE_KEY_FLAG_ALL_USERS)
+ return -EINVAL;
+
if (memchr_inv(arg.__reserved, 0, sizeof(arg.__reserved)))
return -EINVAL;
if (!valid_key_spec(&arg.key_spec))
return -EINVAL;
- if (!capable(CAP_SYS_ADMIN))
+ /*
+ * Only root can request that the key be removed no matter how many
+ * users have added it.
+ */
+ if ((arg.flags & FSCRYPT_REMOVE_KEY_FLAG_ALL_USERS) &&
+ !capable(CAP_SYS_ADMIN))
+ return -EACCES;
+
+ /*
+ * Only root can add and remove keys that are identified by an arbitrary
+ * descriptor rather than by a cryptographic hash.
+ */
+ if (arg.key_spec.type == FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR &&
+ !capable(CAP_SYS_ADMIN))
return -EACCES;
/* Find the key being removed. */
@@ -528,11 +745,35 @@ int fscrypt_ioctl_remove_key(struct file *filp, const void __user *uarg)
down_write(&key->sem);
- /* Wipe the secret. */
+ /* If relevant, remove current user's (or all users) usage of the key */
+ if (mk->mk_users && mk->mk_users->keys.nr_leaves_on_tree != 0) {
+ if (arg.flags & FSCRYPT_REMOVE_KEY_FLAG_ALL_USERS)
+ err = keyring_clear(mk->mk_users);
+ else
+ err = remove_master_key_user(mk);
+ if (err) {
+ up_write(&key->sem);
+ goto out_put_key;
+ }
+ if (mk->mk_users->keys.nr_leaves_on_tree != 0) {
+ /*
+ * Other users have still added the key too. We removed
+ * the current user's usage of the key if there was one,
+ * but we still can't remove the key itself.
+ */
+ err = -EUSERS;
+ up_write(&key->sem);
+ goto out_put_key;
+ }
+ }
+
+ /* No usages remaining. Go ahead and wipe the secret. */
dead = false;
if (is_master_key_secret_present(&mk->mk_secret)) {
+ down_write(&mk->mk_secret_sem);
wipe_master_key_secret(&mk->mk_secret);
dead = refcount_dec_and_test(&mk->mk_refcount);
+ up_write(&mk->mk_secret_sem);
}
up_write(&key->sem);
if (dead) {
@@ -546,6 +787,7 @@ int fscrypt_ioctl_remove_key(struct file *filp, const void __user *uarg)
/* Some inodes still reference this key; try to evict them. */
err = try_to_lock_encrypted_files(sb, mk);
}
+out_put_key:
key_put(key);
return err;
}
@@ -561,6 +803,15 @@ EXPORT_SYMBOL_GPL(fscrypt_ioctl_remove_key);
* of an encrypted directory without using a hack such as trying to open a
* regular file in it (which can confuse the "incompletely removed" state with
* absent or present).
+ *
+ * In addition, for v2 policy keys we allow applications to determine, via
+ * ->status_flags and ->user_count, whether the key has been added by the
+ * current user, by other users, or by both. Most applications should not need
+ * this, since ordinarily only one user should know a given key. However, if a
+ * secret key is shared by multiple users, applications may wish to add an
+ * already-present key to prevent other users from removing it. This ioctl can
+ * be used to check whether that really is the case before the work is done to
+ * add the key --- which might e.g. require prompting the user for a passphrase.
*/
int fscrypt_ioctl_get_key_status(struct file *filp, void __user *uarg)
{
@@ -579,6 +830,8 @@ int fscrypt_ioctl_get_key_status(struct file *filp, void __user *uarg)
if (!valid_key_spec(&arg.key_spec))
return -EINVAL;
+ arg.status_flags = 0;
+ arg.user_count = 0;
memset(arg.__out_reserved, 0, sizeof(arg.__out_reserved));
key = fscrypt_find_master_key(sb, &arg.key_spec);
@@ -599,6 +852,20 @@ int fscrypt_ioctl_get_key_status(struct file *filp, void __user *uarg)
}
arg.status = FSCRYPT_KEY_STATUS_PRESENT;
+ if (mk->mk_users) {
+ struct key *mk_user;
+
+ arg.user_count = mk->mk_users->keys.nr_leaves_on_tree;
+ mk_user = find_master_key_user(mk);
+ if (!IS_ERR(mk_user)) {
+ arg.status_flags |=
+ FSCRYPT_KEY_STATUS_FLAG_ADDED_BY_SELF;
+ key_put(mk_user);
+ } else if (mk_user != ERR_PTR(-ENOKEY)) {
+ err = PTR_ERR(mk_user);
+ goto out_release_key;
+ }
+ }
err = 0;
out_release_key:
up_read(&key->sem);
@@ -612,10 +879,25 @@ EXPORT_SYMBOL_GPL(fscrypt_ioctl_get_key_status);
int __init fscrypt_init_keyring(void)
{
- return register_key_type(&key_type_fscrypt);
+ int err;
+
+ err = register_key_type(&key_type_fscrypt);
+ if (err)
+ return err;
+
+ err = register_key_type(&key_type_fscrypt_user);
+ if (err)
+ goto err_unregister_fscrypt;
+
+ return 0;
+
+err_unregister_fscrypt:
+ unregister_key_type(&key_type_fscrypt);
+ return err;
}
void fscrypt_exit_keyring(void)
{
unregister_key_type(&key_type_fscrypt);
+ unregister_key_type(&key_type_fscrypt_user);
}
diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c
index a15a4bbafa3c..a783b6195618 100644
--- a/fs/crypto/keysetup.c
+++ b/fs/crypto/keysetup.c
@@ -283,10 +283,10 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci,
*
* If the master key is found in the filesystem-level keyring, then the
* corresponding 'struct key' is returned in *master_key_ret with
- * ->sem read-locked. This is needed to ensure that only one task links the
- * fscrypt_info into ->mk_decrypted_inodes (as multiple tasks may race to create
- * an fscrypt_info for the same inode), and to synchronize the key being removed
- * with a new inode starting to use it.
+ * ->mk_secret_sem read-locked. This is needed to ensure that only one task
+ * links the fscrypt_info into ->mk_decrypted_inodes (as multiple tasks may race
+ * to create an fscrypt_info for the same inode), and to synchronize the key
+ * being removed with a new inode starting to use it.
*/
static int setup_file_encryption_key(struct fscrypt_info *ci,
struct key **master_key_ret)
@@ -324,7 +324,7 @@ static int setup_file_encryption_key(struct fscrypt_info *ci,
}
mk = key->payload.data[0];
- down_read(&key->sem);
+ down_read(&mk->mk_secret_sem);
/* Has the secret been removed (via FS_IOC_REMOVE_ENCRYPTION_KEY)? */
if (!is_master_key_secret_present(&mk->mk_secret)) {
@@ -358,7 +358,7 @@ static int setup_file_encryption_key(struct fscrypt_info *ci,
return 0;
out_release_key:
- up_read(&key->sem);
+ up_read(&mk->mk_secret_sem);
key_put(key);
return err;
}
@@ -484,7 +484,9 @@ int fscrypt_get_encryption_info(struct inode *inode)
res = 0;
out:
if (master_key) {
- up_read(&master_key->sem);
+ struct fscrypt_master_key *mk = master_key->payload.data[0];
+
+ up_read(&mk->mk_secret_sem);
key_put(master_key);
}
if (res == -ENOKEY)
diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h
index 26879e669dfa..fd1c3e2b0b7c 100644
--- a/include/uapi/linux/fscrypt.h
+++ b/include/uapi/linux/fscrypt.h
@@ -103,7 +103,9 @@ struct fscrypt_add_key_arg {
/* Struct passed to FS_IOC_REMOVE_ENCRYPTION_KEY */
struct fscrypt_remove_key_arg {
struct fscrypt_key_specifier key_spec;
- __u32 __reserved[6];
+#define FSCRYPT_REMOVE_KEY_FLAG_ALL_USERS 0x00000001
+ __u32 flags;
+ __u32 __reserved[5];
};
/* Struct passed to FS_IOC_GET_ENCRYPTION_KEY_STATUS */
@@ -117,7 +119,10 @@ struct fscrypt_get_key_status_arg {
#define FSCRYPT_KEY_STATUS_PRESENT 2
#define FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED 3
__u32 status;
- __u32 __out_reserved[15];
+#define FSCRYPT_KEY_STATUS_FLAG_ADDED_BY_SELF 0x00000001
+ __u32 status_flags;
+ __u32 user_count;
+ __u32 __out_reserved[13];
};
#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy)
--
2.20.1
^ permalink raw reply related
* [RFC PATCH v2 14/20] fscrypt: v2 encryption policy support
From: Eric Biggers @ 2019-02-11 17:27 UTC (permalink / raw)
To: linux-fscrypt
Cc: Satya Tangirala, linux-api, linux-f2fs-devel, keyrings, linux-mtd,
linux-crypto, linux-fsdevel, linux-ext4, Paul Crowley
In-Reply-To: <20190211172738.4633-1-ebiggers@kernel.org>
From: Eric Biggers <ebiggers@google.com>
Add a new fscrypt policy version, "v2". It has the following changes
from the original policy version, which we call "v1" (*):
- The encryption key is identified by a 16-byte master_key_identifier,
which is derived from the key itself using HKDF-SHA512. This prevents
users from associating the wrong key with an encrypted file or
directory. This was easily possible with v1 policies, which
identified the key by an arbitrary 8-byte master_key_descriptor.
- Per-file keys are derived using HKDF-SHA512 rather than the
AES-128-ECB based KDF. This has various advantages, e.g. it's
nonreversible and it evenly distributes entropy from the master key.
- The semantics of the DIRECT_KEY flag are implemented by deriving a
per-mode key, again with HKDF-SHA512, rather than using the master key
directly. Thus the master key is only ever used as HKDF input, and
it's much more difficult for userspace to screw things up.
- The key must be provided in the filesystem-level keyring, not in a
process-subscribed keyring.
The following UAPI additions are made:
- The existing ioctl FS_IOC_SET_ENCRYPTION_POLICY can now be passed a
fscrypt_policy_v2 to set a v2 encryption policy. It's disambiguated
from fscrypt_policy/fscrypt_policy_v1 by the version code prefix.
- A new ioctl FS_IOC_GET_ENCRYPTION_POLICY_EX is added. It allows
getting the v1 or v2 encryption policy of an encrypted file or
directory. The existing FS_IOC_GET_ENCRYPTION_POLICY ioctl could not
be used because it did not have a way for userspace to indicate which
policy structure is expected. The new ioctl includes a size field, so
it is extensible to future fscrypt policy versions.
- The ioctls FS_IOC_ADD_ENCRYPTION_KEY, FS_IOC_REMOVE_ENCRYPTION_KEY,
and FS_IOC_GET_ENCRYPTION_KEY_STATUS now support managing keys for v2
encryption policies. Such keys are kept logically separate from keys
for v1 encryption policies, and are identified by 'identifier' rather
than by 'descriptor'. The 'identifier' need not be provided when
adding a key, since the kernel will calculate it anyway.
This patch temporarily keeps adding/removing v2 policy keys behind the
same permission check done for adding/removing v1 policy keys:
capable(CAP_SYS_ADMIN). However, the next patch will carefully take
advantage of the cryptographically secure master_key_identifier to allow
non-root users to add/remove v2 policy keys, thus providing a full
replacement for v1 policies.
(*) Actually, in the API fscrypt_policy::version is 0 while on-disk
fscrypt_context::format is 1. But I believe it makes the most sense
to advance both to '2' to have them be in sync, and to consider the
numbering to start at 1 except for the API quirk.
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
fs/crypto/crypto.c | 3 +-
fs/crypto/fname.c | 3 +-
fs/crypto/fscrypt_private.h | 180 ++++++++++++++---
fs/crypto/keyring.c | 37 +++-
fs/crypto/keysetup.c | 174 ++++++++++++----
fs/crypto/keysetup_legacy.c | 18 +-
fs/crypto/policy.c | 382 +++++++++++++++++++++++++----------
include/linux/fscrypt.h | 9 +-
include/uapi/linux/fscrypt.h | 42 +++-
9 files changed, 665 insertions(+), 183 deletions(-)
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index 8726c4e94077..7abc6695fa4d 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -26,7 +26,6 @@
#include <linux/ratelimit.h>
#include <linux/dcache.h>
#include <linux/namei.h>
-#include <crypto/aes.h>
#include <crypto/skcipher.h>
#include "fscrypt_private.h"
@@ -139,7 +138,7 @@ void fscrypt_generate_iv(union fscrypt_iv *iv, u64 lblk_num,
memset(iv, 0, ci->ci_mode->ivsize);
iv->lblk_num = cpu_to_le64(lblk_num);
- if (ci->ci_flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY)
+ if (fscrypt_is_direct_key_policy(&ci->ci_policy))
memcpy(iv->nonce, ci->ci_nonce, FS_KEY_DERIVATION_NONCE_SIZE);
if (ci->ci_essiv_tfm != NULL)
diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 37c26ad36d0e..57e0caba9d12 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -186,7 +186,8 @@ static int digest_decode(const char *src, int len, char *dst)
bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len,
u32 max_len, u32 *encrypted_len_ret)
{
- int padding = 4 << (inode->i_crypt_info->ci_flags &
+ const struct fscrypt_info *ci = inode->i_crypt_info;
+ int padding = 4 << (fscrypt_policy_flags(&ci->ci_policy) &
FSCRYPT_POLICY_FLAGS_PAD_MASK);
u32 encrypted_len;
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index f8b8358e9527..1a40f7359655 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -20,27 +20,125 @@
#define FSCRYPT_MIN_KEY_SIZE 16
-/**
- * Encryption context for inode
- *
- * Protector format:
- * 1 byte: Protector format (1 = this version)
- * 1 byte: File contents encryption mode
- * 1 byte: File names encryption mode
- * 1 byte: Flags
- * 8 bytes: Master Key descriptor
- * 16 bytes: Encryption Key derivation nonce
- */
-struct fscrypt_context {
- u8 format;
+#define FSCRYPT_CONTEXT_V1 1
+#define FSCRYPT_CONTEXT_V2 2
+
+struct fscrypt_context_v1 {
+ u8 version; /* FSCRYPT_CONTEXT_V1 */
u8 contents_encryption_mode;
u8 filenames_encryption_mode;
u8 flags;
u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE];
-} __packed;
+};
+
+struct fscrypt_context_v2 {
+ u8 version; /* FSCRYPT_CONTEXT_V2 */
+ u8 contents_encryption_mode;
+ u8 filenames_encryption_mode;
+ u8 flags;
+ u8 __reserved[4];
+ u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
+ u8 nonce[FS_KEY_DERIVATION_NONCE_SIZE];
+};
+
+/**
+ * fscrypt_context - the encryption context of an inode
+ *
+ * This is the on-disk equivalent of an fscrypt_policy, stored alongside each
+ * encrypted file usually in a hidden extended attribute. It contains the
+ * fields from the fscrypt_policy, in order to identify the encryption algorithm
+ * and key with which the file is encrypted. It also contains a nonce that was
+ * randomly generated by fscrypt itself; this is used as KDF input or as a tweak
+ * to cause different files to be encrypted differently.
+ */
+union fscrypt_context {
+ struct fscrypt_context_v1 v1;
+ struct fscrypt_context_v2 v2;
+};
+
+/*
+ * Return the size expected for the given fscrypt_context based on its version
+ * number, or 0 if the context version is unrecognized.
+ */
+static inline int fscrypt_context_size(const union fscrypt_context *ctx)
+{
+ switch (ctx->v1.version) {
+ case FSCRYPT_CONTEXT_V1:
+ BUILD_BUG_ON(sizeof(ctx->v1) != 28);
+ return sizeof(ctx->v1);
+ case FSCRYPT_CONTEXT_V2:
+ BUILD_BUG_ON(sizeof(ctx->v2) != 40);
+ return sizeof(ctx->v2);
+ }
+ return 0;
+}
+
+#undef fscrypt_policy
+union fscrypt_policy {
+ struct fscrypt_policy_v1 v1;
+ struct fscrypt_policy_v2 v2;
+};
+
+/*
+ * Return the size expected for the given fscrypt_policy based on its version
+ * number, or 0 if the policy version is unrecognized.
+ */
+static inline int fscrypt_policy_size(const union fscrypt_policy *policy)
+{
+ switch (policy->v1.version) {
+ case FSCRYPT_POLICY_V1:
+ return sizeof(policy->v1);
+ case FSCRYPT_POLICY_V2:
+ return sizeof(policy->v2);
+ }
+ return 0;
+}
-#define FS_ENCRYPTION_CONTEXT_FORMAT_V1 1
+/* Return the contents encryption mode of a valid encryption policy */
+static inline u8
+fscrypt_policy_contents_mode(const union fscrypt_policy *policy)
+{
+ switch (policy->v1.version) {
+ case FSCRYPT_POLICY_V1:
+ return policy->v1.contents_encryption_mode;
+ case FSCRYPT_POLICY_V2:
+ return policy->v2.contents_encryption_mode;
+ }
+ BUG();
+}
+
+/* Return the filenames encryption mode of a valid encryption policy */
+static inline u8
+fscrypt_policy_fnames_mode(const union fscrypt_policy *policy)
+{
+ switch (policy->v1.version) {
+ case FSCRYPT_POLICY_V1:
+ return policy->v1.filenames_encryption_mode;
+ case FSCRYPT_POLICY_V2:
+ return policy->v2.filenames_encryption_mode;
+ }
+ BUG();
+}
+
+/* Return the flags (FSCRYPT_POLICY_FLAG*) of a valid encryption policy */
+static inline u8
+fscrypt_policy_flags(const union fscrypt_policy *policy)
+{
+ switch (policy->v1.version) {
+ case FSCRYPT_POLICY_V1:
+ return policy->v1.flags;
+ case FSCRYPT_POLICY_V2:
+ return policy->v2.flags;
+ }
+ BUG();
+}
+
+static inline bool
+fscrypt_is_direct_key_policy(const union fscrypt_policy *policy)
+{
+ return fscrypt_policy_flags(policy) & FSCRYPT_POLICY_FLAG_DIRECT_KEY;
+}
/**
* For encrypted symlinks, the ciphertext length is stored at the beginning
@@ -70,8 +168,8 @@ struct fscrypt_info {
struct crypto_cipher *ci_essiv_tfm;
/*
- * Encryption mode used for this inode. It corresponds to either
- * ci_data_mode or ci_filename_mode, depending on the inode type.
+ * Encryption mode used for this inode. It corresponds to either the
+ * contents or filenames encryption mode, depending on the inode type.
*/
struct fscrypt_mode *ci_mode;
@@ -97,11 +195,10 @@ struct fscrypt_info {
*/
struct fscrypt_direct_key *ci_direct_key;
- /* fields from the fscrypt_context */
- u8 ci_data_mode;
- u8 ci_filename_mode;
- u8 ci_flags;
- u8 ci_master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
+ /* The encryption policy used by this inode */
+ union fscrypt_policy ci_policy;
+
+ /* This inode's nonce, copied from the fscrypt_context */
u8 ci_nonce[FS_KEY_DERIVATION_NONCE_SIZE];
};
@@ -184,6 +281,17 @@ struct fscrypt_hkdf {
extern int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key,
unsigned int master_key_size);
+/*
+ * The list of contexts in which fscrypt uses HKDF. These values are used as
+ * the first byte of the HKDF application-specific info string to guarantee that
+ * info strings are never repeated between contexts. This ensures that all HKDF
+ * outputs are unique and cryptographically isolated, i.e. knowledge of one
+ * output doesn't reveal another.
+ */
+#define HKDF_CONTEXT_KEY_IDENTIFIER 1
+#define HKDF_CONTEXT_PER_FILE_KEY 2
+#define HKDF_CONTEXT_PER_MODE_KEY 3
+
extern int fscrypt_hkdf_expand(struct fscrypt_hkdf *hkdf, u8 context,
const u8 *info, unsigned int infolen,
u8 *okm, unsigned int okmlen);
@@ -197,10 +305,16 @@ extern void fscrypt_destroy_hkdf(struct fscrypt_hkdf *hkdf);
*/
struct fscrypt_master_key_secret {
- /* Size of the raw key in bytes */
+ /*
+ * For v2 policy keys: HKDF context keyed by this master key.
+ * For v1 policy keys: not set (hkdf.hmac_tfm == NULL).
+ */
+ struct fscrypt_hkdf hkdf;
+
+ /* Size of the raw key in bytes. Set even if ->raw isn't set. */
u32 size;
- /* The raw key */
+ /* For v1 policy keys: the raw key. Wiped for v2 policy keys. */
u8 raw[FSCRYPT_MAX_KEY_SIZE];
} __randomize_layout;
@@ -226,7 +340,12 @@ struct fscrypt_master_key {
*/
struct fscrypt_master_key_secret mk_secret;
- /* Arbitrary key descriptor which was assigned by userspace */
+ /*
+ * For v1 policy keys: an arbitrary key descriptor which was assigned by
+ * userspace (->descriptor).
+ *
+ * For v2 policy keys: a cryptographic hash of this key (->identifier).
+ */
struct fscrypt_key_specifier mk_spec;
/*
@@ -245,6 +364,9 @@ struct fscrypt_master_key {
struct list_head mk_decrypted_inodes;
spinlock_t mk_decrypted_inodes_lock;
+ /* Per-mode tfms for DIRECT_KEY policies, allocated on-demand */
+ struct crypto_skcipher *mk_mode_keys[__FSCRYPT_MODE_MAX + 1];
+
} __randomize_layout;
static inline bool
@@ -295,5 +417,13 @@ extern int fscrypt_setup_v1_file_key(struct fscrypt_info *ci,
extern int fscrypt_setup_v1_file_key_via_subscribed_keyrings(
struct fscrypt_info *ci);
+/* policy.c */
+
+extern bool fscrypt_policies_equal(const union fscrypt_policy *policy1,
+ const union fscrypt_policy *policy2);
+extern bool fscrypt_supported_policy(const union fscrypt_policy *policy_u);
+extern int fscrypt_policy_from_context(union fscrypt_policy *policy_u,
+ const union fscrypt_context *ctx_u,
+ int ctx_size);
#endif /* _FSCRYPT_PRIVATE_H */
diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c
index 73be8bda49bd..6bf1e0672a09 100644
--- a/fs/crypto/keyring.c
+++ b/fs/crypto/keyring.c
@@ -14,6 +14,7 @@
* - FS_IOC_GET_ENCRYPTION_KEY_STATUS: get key status
*/
+#include <crypto/skcipher.h>
#include <linux/key-type.h>
#include <linux/seq_file.h>
@@ -21,6 +22,7 @@
static void wipe_master_key_secret(struct fscrypt_master_key_secret *secret)
{
+ fscrypt_destroy_hkdf(&secret->hkdf);
memzero_explicit(secret, sizeof(*secret));
}
@@ -33,7 +35,13 @@ static void move_master_key_secret(struct fscrypt_master_key_secret *dst,
static void free_master_key(struct fscrypt_master_key *mk)
{
+ size_t i;
+
wipe_master_key_secret(&mk->mk_secret);
+
+ for (i = 0; i < ARRAY_SIZE(mk->mk_mode_keys); i++)
+ crypto_free_skcipher(mk->mk_mode_keys[i]);
+
kzfree(mk);
}
@@ -42,6 +50,8 @@ static inline int master_key_spec_len(const struct fscrypt_key_specifier *spec)
switch (spec->type) {
case FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR:
return FSCRYPT_KEY_DESCRIPTOR_SIZE;
+ case FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER:
+ return FSCRYPT_KEY_IDENTIFIER_SIZE;
}
return 0;
}
@@ -115,7 +125,7 @@ static struct key *search_fscrypt_keyring(struct key *keyring,
#define FSCRYPT_FS_KEYRING_DESCRIPTION_SIZE \
(CONST_STRLEN("fscrypt-") + FIELD_SIZEOF(struct super_block, s_id))
-#define FSCRYPT_MK_DESCRIPTION_SIZE (2 * FSCRYPT_KEY_DESCRIPTOR_SIZE + 1)
+#define FSCRYPT_MK_DESCRIPTION_SIZE (2 * FSCRYPT_KEY_IDENTIFIER_SIZE + 1)
static void format_fs_keyring_description(
char description[FSCRYPT_FS_KEYRING_DESCRIPTION_SIZE],
@@ -313,6 +323,31 @@ int fscrypt_ioctl_add_key(struct file *filp, void __user *_uarg)
if (!capable(CAP_SYS_ADMIN))
goto out_wipe_secret;
+ if (arg.key_spec.type != FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR) {
+ err = fscrypt_init_hkdf(&secret.hkdf, secret.raw, secret.size);
+ if (err)
+ goto out_wipe_secret;
+
+ /*
+ * Now that the HKDF context is initialized, the raw key is no
+ * longer needed.
+ */
+ memzero_explicit(secret.raw, sizeof(secret.raw));
+
+ /* Calculate the key identifier and return it to userspace. */
+ err = fscrypt_hkdf_expand(&secret.hkdf,
+ HKDF_CONTEXT_KEY_IDENTIFIER,
+ NULL, 0, arg.key_spec.u.identifier,
+ FSCRYPT_KEY_IDENTIFIER_SIZE);
+ if (err)
+ goto out_wipe_secret;
+ err = -EFAULT;
+ if (copy_to_user(uarg->key_spec.u.identifier,
+ arg.key_spec.u.identifier,
+ FSCRYPT_KEY_IDENTIFIER_SIZE))
+ goto out_wipe_secret;
+ }
+
err = add_master_key(sb, &secret, &arg.key_spec);
out_wipe_secret:
wipe_master_key_secret(&secret);
diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c
index 8ffcfee73702..a15a4bbafa3c 100644
--- a/fs/crypto/keysetup.c
+++ b/fs/crypto/keysetup.c
@@ -52,21 +52,14 @@ static struct fscrypt_mode available_modes[] = {
};
static struct fscrypt_mode *
-select_encryption_mode(const struct fscrypt_info *ci, const struct inode *inode)
+select_encryption_mode(const union fscrypt_policy *policy,
+ const struct inode *inode)
{
- if (!fscrypt_valid_enc_modes(ci->ci_data_mode, ci->ci_filename_mode)) {
- fscrypt_warn(inode->i_sb,
- "inode %lu uses unsupported encryption modes (contents mode %d, filenames mode %d)",
- inode->i_ino, ci->ci_data_mode,
- ci->ci_filename_mode);
- return ERR_PTR(-EINVAL);
- }
-
if (S_ISREG(inode->i_mode))
- return &available_modes[ci->ci_data_mode];
+ return &available_modes[fscrypt_policy_contents_mode(policy)];
if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
- return &available_modes[ci->ci_filename_mode];
+ return &available_modes[fscrypt_policy_fnames_mode(policy)];
WARN_ONCE(1, "fscrypt: filesystem tried to load encryption info for inode %lu, which is not encryptable (file type %d)\n",
inode->i_ino, (inode->i_mode & S_IFMT));
@@ -208,6 +201,83 @@ int fscrypt_set_derived_key(struct fscrypt_info *ci, const u8 *derived_key)
return 0;
}
+static int setup_per_mode_key(struct fscrypt_info *ci,
+ struct fscrypt_master_key *mk)
+{
+ u8 mode_num = ci->ci_mode - available_modes;
+ struct crypto_skcipher **tfm_p;
+ struct crypto_skcipher *tfm;
+ u8 mode_key[FSCRYPT_MAX_KEY_SIZE];
+ int err;
+
+ if (WARN_ON(mode_num >= ARRAY_SIZE(mk->mk_mode_keys)))
+ return -EINVAL;
+ tfm_p = &mk->mk_mode_keys[mode_num];
+retry:
+ /* pairs with cmpxchg_release() below */
+ tfm = smp_load_acquire(tfm_p);
+ if (likely(tfm != NULL))
+ goto done;
+
+ BUILD_BUG_ON(sizeof(mode_num) != 1);
+ err = fscrypt_hkdf_expand(&mk->mk_secret.hkdf,
+ HKDF_CONTEXT_PER_MODE_KEY,
+ &mode_num, sizeof(mode_num),
+ mode_key, ci->ci_mode->keysize);
+ if (err)
+ return err;
+ tfm = fscrypt_allocate_skcipher(ci->ci_mode, mode_key, ci->ci_inode);
+ memzero_explicit(mode_key, ci->ci_mode->keysize);
+ if (IS_ERR(tfm))
+ return PTR_ERR(tfm);
+
+ /* pairs with smp_load_acquire() above */
+ if (cmpxchg_release(tfm_p, NULL, tfm) != NULL) {
+ crypto_free_skcipher(tfm);
+ goto retry;
+ }
+done:
+ ci->ci_ctfm = tfm;
+ return 0;
+}
+
+static int fscrypt_setup_v2_file_key(struct fscrypt_info *ci,
+ struct fscrypt_master_key *mk)
+{
+ u8 derived_key[FSCRYPT_MAX_KEY_SIZE];
+ int err;
+
+ if (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY) {
+ /*
+ * DIRECT_KEY: instead of deriving per-file keys, the per-file
+ * nonce will be included in all the IVs. But unlike v1
+ * policies, for v2 policies in this case we don't encrypt with
+ * the master key directly but rather derive a per-mode key.
+ * This ensures that the master key is consistently used only
+ * for HKDF, avoiding key reuse issues.
+ */
+ if (!fscrypt_mode_supports_direct_key(ci->ci_mode)) {
+ fscrypt_warn(ci->ci_inode->i_sb,
+ "direct key flag not allowed with %s",
+ ci->ci_mode->friendly_name);
+ return -EINVAL;
+ }
+ return setup_per_mode_key(ci, mk);
+ }
+
+ err = fscrypt_hkdf_expand(&mk->mk_secret.hkdf,
+ HKDF_CONTEXT_PER_FILE_KEY,
+ ci->ci_nonce,
+ FS_KEY_DERIVATION_NONCE_SIZE,
+ derived_key, ci->ci_mode->keysize);
+ if (err)
+ return err;
+
+ err = fscrypt_set_derived_key(ci, derived_key);
+ memzero_explicit(derived_key, ci->ci_mode->keysize);
+ return err;
+}
+
/*
* Find the master key, then set up the inode's actual encryption key.
*
@@ -226,15 +296,30 @@ static int setup_file_encryption_key(struct fscrypt_info *ci,
struct fscrypt_key_specifier mk_spec;
int err;
- mk_spec.type = FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR;
- memcpy(mk_spec.u.descriptor, ci->ci_master_key_descriptor,
- FSCRYPT_KEY_DESCRIPTOR_SIZE);
+ if (ci->ci_policy.v1.version == FSCRYPT_POLICY_V1) {
+ mk_spec.type = FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR;
+ memcpy(mk_spec.u.descriptor,
+ ci->ci_policy.v1.master_key_descriptor,
+ FSCRYPT_KEY_DESCRIPTOR_SIZE);
+ } else {
+ mk_spec.type = FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER;
+ memcpy(mk_spec.u.identifier,
+ ci->ci_policy.v2.master_key_identifier,
+ FSCRYPT_KEY_IDENTIFIER_SIZE);
+ }
key = fscrypt_find_master_key(ci->ci_inode->i_sb, &mk_spec);
if (IS_ERR(key)) {
- if (key != ERR_PTR(-ENOKEY))
+ if (key != ERR_PTR(-ENOKEY) ||
+ ci->ci_policy.v1.version != FSCRYPT_POLICY_V1)
return PTR_ERR(key);
+ /*
+ * As a legacy fallback for v1 policies, search for the key in
+ * the current task's subscribed keyrings too. Don't move this
+ * to before the search of ->s_master_keys, since users
+ * shouldn't be able to override filesystem-level keys.
+ */
return fscrypt_setup_v1_file_key_via_subscribed_keyrings(ci);
}
@@ -247,6 +332,12 @@ static int setup_file_encryption_key(struct fscrypt_info *ci,
goto out_release_key;
}
+ /*
+ * Require that the master key be at least as long as the derived key.
+ * Otherwise, the derived key cannot possibly contain as much entropy as
+ * that required by the encryption mode it will be used for. For v1
+ * policies it's also required for the KDF to work at all.
+ */
if (mk->mk_secret.size < ci->ci_mode->keysize) {
fscrypt_warn(NULL,
"key with description '%s' is too short (got %u bytes, need %u+ bytes)",
@@ -256,7 +347,10 @@ static int setup_file_encryption_key(struct fscrypt_info *ci,
goto out_release_key;
}
- err = fscrypt_setup_v1_file_key(ci, mk->mk_secret.raw);
+ if (ci->ci_policy.v1.version == FSCRYPT_POLICY_V1)
+ err = fscrypt_setup_v1_file_key(ci, mk->mk_secret.raw);
+ else
+ err = fscrypt_setup_v2_file_key(ci, mk);
if (err)
goto out_release_key;
@@ -278,7 +372,8 @@ static void put_crypt_info(struct fscrypt_info *ci)
if (ci->ci_direct_key) {
fscrypt_put_direct_key(ci->ci_direct_key);
- } else {
+ } else if ((ci->ci_ctfm != NULL || ci->ci_essiv_tfm != NULL) &&
+ !fscrypt_is_direct_key_policy(&ci->ci_policy)) {
crypto_free_skcipher(ci->ci_ctfm);
crypto_free_cipher(ci->ci_essiv_tfm);
}
@@ -308,7 +403,7 @@ static void put_crypt_info(struct fscrypt_info *ci)
int fscrypt_get_encryption_info(struct inode *inode)
{
struct fscrypt_info *crypt_info;
- struct fscrypt_context ctx;
+ union fscrypt_context ctx;
struct fscrypt_mode *mode;
struct key *master_key = NULL;
int res;
@@ -327,35 +422,40 @@ int fscrypt_get_encryption_info(struct inode *inode)
return res;
/* Fake up a context for an unencrypted directory */
memset(&ctx, 0, sizeof(ctx));
- ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
- ctx.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS;
- ctx.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS;
- memset(ctx.master_key_descriptor, 0x42,
+ ctx.v1.version = FSCRYPT_CONTEXT_V1;
+ ctx.v1.contents_encryption_mode = FSCRYPT_MODE_AES_256_XTS;
+ ctx.v1.filenames_encryption_mode = FSCRYPT_MODE_AES_256_CTS;
+ memset(ctx.v1.master_key_descriptor, 0x42,
FSCRYPT_KEY_DESCRIPTOR_SIZE);
- } else if (res != sizeof(ctx)) {
- return -EINVAL;
+ res = sizeof(ctx.v1);
}
- if (ctx.format != FS_ENCRYPTION_CONTEXT_FORMAT_V1)
- return -EINVAL;
-
- if (ctx.flags & ~FSCRYPT_POLICY_FLAGS_VALID)
- return -EINVAL;
-
crypt_info = kmem_cache_zalloc(fscrypt_info_cachep, GFP_NOFS);
if (!crypt_info)
return -ENOMEM;
crypt_info->ci_inode = inode;
- crypt_info->ci_flags = ctx.flags;
- crypt_info->ci_data_mode = ctx.contents_encryption_mode;
- crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
- memcpy(crypt_info->ci_master_key_descriptor, ctx.master_key_descriptor,
- FSCRYPT_KEY_DESCRIPTOR_SIZE);
- memcpy(crypt_info->ci_nonce, ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE);
+ res = fscrypt_policy_from_context(&crypt_info->ci_policy, &ctx, res);
+ if (res)
+ goto out;
+
+ if (ctx.v1.version == FSCRYPT_CONTEXT_V1)
+ memcpy(crypt_info->ci_nonce, ctx.v1.nonce,
+ FS_KEY_DERIVATION_NONCE_SIZE);
+ else
+ memcpy(crypt_info->ci_nonce, ctx.v2.nonce,
+ FS_KEY_DERIVATION_NONCE_SIZE);
+
+ if (!fscrypt_supported_policy(&crypt_info->ci_policy)) {
+ fscrypt_warn(inode->i_sb,
+ "inode %lu uses unsupported encryption policy",
+ inode->i_ino);
+ res = -EINVAL;
+ goto out;
+ }
- mode = select_encryption_mode(crypt_info, inode);
+ mode = select_encryption_mode(&crypt_info->ci_policy, inode);
if (IS_ERR(mode)) {
res = PTR_ERR(mode);
goto out;
diff --git a/fs/crypto/keysetup_legacy.c b/fs/crypto/keysetup_legacy.c
index a48588458f07..a35a7a9c204c 100644
--- a/fs/crypto/keysetup_legacy.c
+++ b/fs/crypto/keysetup_legacy.c
@@ -189,12 +189,13 @@ find_or_insert_direct_key(struct fscrypt_direct_key *to_insert,
*/
BUILD_BUG_ON(sizeof(hash_key) > FSCRYPT_KEY_DESCRIPTOR_SIZE);
- memcpy(&hash_key, ci->ci_master_key_descriptor, sizeof(hash_key));
+ memcpy(&hash_key, ci->ci_policy.v1.master_key_descriptor,
+ sizeof(hash_key));
spin_lock(&fscrypt_direct_keys_lock);
hash_for_each_possible(fscrypt_direct_keys, dk, dk_node, hash_key) {
- if (memcmp(ci->ci_master_key_descriptor, dk->dk_descriptor,
- FSCRYPT_KEY_DESCRIPTOR_SIZE) != 0)
+ if (memcmp(ci->ci_policy.v1.master_key_descriptor,
+ dk->dk_descriptor, FSCRYPT_KEY_DESCRIPTOR_SIZE) != 0)
continue;
if (ci->ci_mode != dk->dk_mode)
continue;
@@ -237,7 +238,7 @@ fscrypt_get_direct_key(const struct fscrypt_info *ci, const u8 *raw_key)
dk->dk_ctfm = NULL;
goto err_free_dk;
}
- memcpy(dk->dk_descriptor, ci->ci_master_key_descriptor,
+ memcpy(dk->dk_descriptor, ci->ci_policy.v1.master_key_descriptor,
FSCRYPT_KEY_DESCRIPTOR_SIZE);
memcpy(dk->dk_raw, raw_key, ci->ci_mode->keysize);
@@ -262,7 +263,8 @@ static int setup_v1_file_key_direct(struct fscrypt_info *ci,
return -EINVAL;
}
- if (ci->ci_data_mode != ci->ci_filename_mode) {
+ if (ci->ci_policy.v1.contents_encryption_mode !=
+ ci->ci_policy.v1.filenames_encryption_mode) {
fscrypt_warn(ci->ci_inode->i_sb,
"direct key flag not allowed with different contents and filenames modes");
return -EINVAL;
@@ -309,7 +311,7 @@ static int setup_v1_file_key_derived(struct fscrypt_info *ci,
int fscrypt_setup_v1_file_key(struct fscrypt_info *ci, const u8 *raw_master_key)
{
- if (ci->ci_flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY)
+ if (ci->ci_policy.v1.flags & FSCRYPT_POLICY_FLAG_DIRECT_KEY)
return setup_v1_file_key_direct(ci, raw_master_key);
else
return setup_v1_file_key_derived(ci, raw_master_key);
@@ -322,11 +324,11 @@ int fscrypt_setup_v1_file_key_via_subscribed_keyrings(struct fscrypt_info *ci)
int err;
key = find_and_lock_process_key(FSCRYPT_KEY_DESC_PREFIX,
- ci->ci_master_key_descriptor,
+ ci->ci_policy.v1.master_key_descriptor,
ci->ci_mode->keysize, &payload);
if (key == ERR_PTR(-ENOKEY) && ci->ci_inode->i_sb->s_cop->key_prefix) {
key = find_and_lock_process_key(ci->ci_inode->i_sb->s_cop->key_prefix,
- ci->ci_master_key_descriptor,
+ ci->ci_policy.v1.master_key_descriptor,
ci->ci_mode->keysize, &payload);
}
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index 1e0563cea1a5..07fec2f7fc72 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -5,8 +5,9 @@
* Copyright (C) 2015, Google, Inc.
* Copyright (C) 2015, Motorola Mobility.
*
- * Written by Michael Halcrow, 2015.
+ * Originally written by Michael Halcrow, 2015.
* Modified by Jaegeuk Kim, 2015.
+ * Modified by Eric Biggers, 2019 for v2 policy support.
*/
#include <linux/random.h>
@@ -14,84 +15,263 @@
#include <linux/mount.h>
#include "fscrypt_private.h"
-/*
- * check whether an encryption policy is consistent with an encryption context
+/**
+ * fscrypt_policies_equal - check whether two encryption policies are the same
+ *
+ * Return: %true if equal, else %false
+ */
+bool fscrypt_policies_equal(const union fscrypt_policy *policy1,
+ const union fscrypt_policy *policy2)
+{
+ if (policy1->v1.version != policy2->v1.version)
+ return false;
+
+ return !memcmp(policy1, policy2, fscrypt_policy_size(policy1));
+}
+
+/**
+ * fscrypt_supported_policy - check whether an encryption policy is supported
+ *
+ * Given an encryption policy, check whether all its encryption modes and other
+ * settings are supported by this kernel. (But we don't currently don't check
+ * for crypto API support here, so attempting to use an algorithm not configured
+ * into the crypto API will still fail later.)
+ *
+ * Return: %true if supported, else %false
*/
-static bool is_encryption_context_consistent_with_policy(
- const struct fscrypt_context *ctx,
- const struct fscrypt_policy *policy)
+bool fscrypt_supported_policy(const union fscrypt_policy *policy_u)
{
- return memcmp(ctx->master_key_descriptor, policy->master_key_descriptor,
- FSCRYPT_KEY_DESCRIPTOR_SIZE) == 0 &&
- (ctx->flags == policy->flags) &&
- (ctx->contents_encryption_mode ==
- policy->contents_encryption_mode) &&
- (ctx->filenames_encryption_mode ==
- policy->filenames_encryption_mode);
+ switch (policy_u->v1.version) {
+ case FSCRYPT_POLICY_V1: {
+ const struct fscrypt_policy_v1 *policy = &policy_u->v1;
+
+ if (!fscrypt_valid_enc_modes(policy->contents_encryption_mode,
+ policy->filenames_encryption_mode))
+ return false;
+
+ if (policy->flags & ~FSCRYPT_POLICY_FLAGS_VALID)
+ return false;
+
+ return true;
+ }
+ case FSCRYPT_POLICY_V2: {
+ const struct fscrypt_policy_v2 *policy = &policy_u->v2;
+
+ if (!fscrypt_valid_enc_modes(policy->contents_encryption_mode,
+ policy->filenames_encryption_mode))
+ return false;
+
+ if (policy->flags & ~FSCRYPT_POLICY_FLAGS_VALID)
+ return false;
+
+ if (memchr_inv(policy->__reserved, 0,
+ sizeof(policy->__reserved)))
+ return false;
+
+ return true;
+ }
+ }
+ return false;
}
-static int create_encryption_context_from_policy(struct inode *inode,
- const struct fscrypt_policy *policy)
+/**
+ * fscrypt_new_context_from_policy - create a new fscrypt_context from a policy
+ *
+ * Create an fscrypt_context for an inode that is being assigned the given
+ * encryption policy. A new nonce is randomly generated.
+ *
+ * Return: the size of the new context in bytes.
+ */
+static int fscrypt_new_context_from_policy(union fscrypt_context *ctx_u,
+ const union fscrypt_policy *policy_u)
{
- struct fscrypt_context ctx;
+ memset(ctx_u, 0, sizeof(*ctx_u));
+
+ switch (policy_u->v1.version) {
+ case FSCRYPT_POLICY_V1: {
+ const struct fscrypt_policy_v1 *policy = &policy_u->v1;
+ struct fscrypt_context_v1 *ctx = &ctx_u->v1;
+
+ ctx->version = FSCRYPT_CONTEXT_V1;
+ ctx->contents_encryption_mode =
+ policy->contents_encryption_mode;
+ ctx->filenames_encryption_mode =
+ policy->filenames_encryption_mode;
+ ctx->flags = policy->flags;
+ memcpy(ctx->master_key_descriptor,
+ policy->master_key_descriptor,
+ sizeof(ctx->master_key_descriptor));
+ get_random_bytes(ctx->nonce, sizeof(ctx->nonce));
+ return sizeof(*ctx);
+ }
+ case FSCRYPT_POLICY_V2: {
+ const struct fscrypt_policy_v2 *policy = &policy_u->v2;
+ struct fscrypt_context_v2 *ctx = &ctx_u->v2;
+
+ ctx->version = FSCRYPT_CONTEXT_V2;
+ ctx->contents_encryption_mode =
+ policy->contents_encryption_mode;
+ ctx->filenames_encryption_mode =
+ policy->filenames_encryption_mode;
+ ctx->flags = policy->flags;
+ memcpy(ctx->master_key_identifier,
+ policy->master_key_identifier,
+ sizeof(ctx->master_key_identifier));
+ get_random_bytes(ctx->nonce, sizeof(ctx->nonce));
+ return sizeof(*ctx);
+ }
+ }
+ BUG();
+}
- ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
- memcpy(ctx.master_key_descriptor, policy->master_key_descriptor,
- FSCRYPT_KEY_DESCRIPTOR_SIZE);
+/**
+ * fscrypt_policy_from_context - convert an fscrypt_context to an fscrypt_policy
+ *
+ * Given an fscrypt_context, build the corresponding fscrypt_policy.
+ *
+ * Return: 0 on success, or -EINVAL if the fscrypt_context has an unrecognized
+ * version number or size.
+ *
+ * This does *not* validate the settings within the policy itself, e.g. the
+ * modes, flags, and reserved bits. Use fscrypt_supported_policy() for that.
+ */
+int fscrypt_policy_from_context(union fscrypt_policy *policy_u,
+ const union fscrypt_context *ctx_u,
+ int ctx_size)
+{
+ memset(policy_u, 0, sizeof(*policy_u));
- if (!fscrypt_valid_enc_modes(policy->contents_encryption_mode,
- policy->filenames_encryption_mode))
+ if (ctx_size <= 0 || ctx_size != fscrypt_context_size(ctx_u))
return -EINVAL;
- if (policy->flags & ~FSCRYPT_POLICY_FLAGS_VALID)
+ switch (ctx_u->v1.version) {
+ case FSCRYPT_CONTEXT_V1: {
+ const struct fscrypt_context_v1 *ctx = &ctx_u->v1;
+ struct fscrypt_policy_v1 *policy = &policy_u->v1;
+
+ policy->version = FSCRYPT_POLICY_V1;
+ policy->contents_encryption_mode =
+ ctx->contents_encryption_mode;
+ policy->filenames_encryption_mode =
+ ctx->filenames_encryption_mode;
+ policy->flags = ctx->flags;
+ memcpy(policy->master_key_descriptor,
+ ctx->master_key_descriptor,
+ sizeof(policy->master_key_descriptor));
+ return 0;
+ }
+ case FSCRYPT_CONTEXT_V2: {
+ const struct fscrypt_context_v2 *ctx = &ctx_u->v2;
+ struct fscrypt_policy_v2 *policy = &policy_u->v2;
+
+ policy->version = FSCRYPT_POLICY_V2;
+ policy->contents_encryption_mode =
+ ctx->contents_encryption_mode;
+ policy->filenames_encryption_mode =
+ ctx->filenames_encryption_mode;
+ policy->flags = ctx->flags;
+ memcpy(policy->__reserved, ctx->__reserved,
+ sizeof(policy->__reserved));
+ memcpy(policy->master_key_identifier,
+ ctx->master_key_identifier,
+ sizeof(policy->master_key_identifier));
+ return 0;
+ }
+ }
+ /* unreachable */
+ return -EINVAL;
+}
+
+/* Retrieve an inode's encryption policy */
+static int fscrypt_get_policy(struct inode *inode, union fscrypt_policy *policy)
+{
+ union fscrypt_context ctx;
+ int ret;
+
+ if (inode->i_crypt_info) {
+ /* key available, use the cached policy */
+ *policy = inode->i_crypt_info->ci_policy;
+ return 0;
+ }
+
+ if (!IS_ENCRYPTED(inode))
+ return -ENODATA;
+
+ ret = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+ if (ret < 0)
+ return (ret == -ERANGE) ? -EINVAL : ret;
+
+ return fscrypt_policy_from_context(policy, &ctx, ret);
+}
+
+static int set_encryption_policy(struct inode *inode,
+ const union fscrypt_policy *policy)
+{
+ union fscrypt_context ctx;
+ int ctxsize;
+
+ if (!fscrypt_supported_policy(policy))
return -EINVAL;
- ctx.contents_encryption_mode = policy->contents_encryption_mode;
- ctx.filenames_encryption_mode = policy->filenames_encryption_mode;
- ctx.flags = policy->flags;
- BUILD_BUG_ON(sizeof(ctx.nonce) != FS_KEY_DERIVATION_NONCE_SIZE);
- get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE);
+ if (policy->v1.version == FSCRYPT_POLICY_V1) {
+ /*
+ * The original encryption policy version provided no way of
+ * verifying that the correct master key was supplied, which was
+ * insecure in scenarios where multiple users have access to the
+ * same encrypted files (even just read-only access). The new
+ * encryption policy version fixes this and also implies use of
+ * an improved key derivation function and allows non-root users
+ * to securely remove keys. So as long as compatibility with
+ * old kernels isn't required, it is recommended to use the new
+ * policy version for all new encrypted directories.
+ */
+ pr_warn_once("%s (pid %d) is setting deprecated v1 encryption policy; recommend upgrading to v2.\n",
+ current->comm, current->pid);
+ }
+
+ ctxsize = fscrypt_new_context_from_policy(&ctx, policy);
- return inode->i_sb->s_cop->set_context(inode, &ctx, sizeof(ctx), NULL);
+ return inode->i_sb->s_cop->set_context(inode, &ctx, ctxsize, NULL);
}
int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg)
{
- struct fscrypt_policy policy;
+ union fscrypt_policy policy;
+ union fscrypt_policy existing_policy;
struct inode *inode = file_inode(filp);
+ int size;
int ret;
- struct fscrypt_context ctx;
- if (copy_from_user(&policy, arg, sizeof(policy)))
+ if (copy_from_user(&policy, arg, sizeof(u8)))
+ return -EFAULT;
+
+ size = fscrypt_policy_size(&policy);
+ if (size <= 0)
+ return -EINVAL;
+
+ if (copy_from_user((u8 *)&policy + 1, arg + 1, size - 1))
return -EFAULT;
if (!inode_owner_or_capable(inode))
return -EACCES;
- if (policy.version != 0)
- return -EINVAL;
-
ret = mnt_want_write_file(filp);
if (ret)
return ret;
inode_lock(inode);
- ret = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+ ret = fscrypt_get_policy(inode, &existing_policy);
if (ret == -ENODATA) {
if (!S_ISDIR(inode->i_mode))
ret = -ENOTDIR;
else if (!inode->i_sb->s_cop->empty_dir(inode))
ret = -ENOTEMPTY;
else
- ret = create_encryption_context_from_policy(inode,
- &policy);
- } else if (ret == sizeof(ctx) &&
- is_encryption_context_consistent_with_policy(&ctx,
- &policy)) {
- /* The file already uses the same encryption policy. */
- ret = 0;
- } else if (ret >= 0 || ret == -ERANGE) {
+ ret = set_encryption_policy(inode, &policy);
+ } else if (ret == -EINVAL ||
+ (ret == 0 && !fscrypt_policies_equal(&policy,
+ &existing_policy))) {
/* The file already uses a different encryption policy. */
ret = -EEXIST;
}
@@ -103,37 +283,55 @@ int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg)
}
EXPORT_SYMBOL(fscrypt_ioctl_set_policy);
+/* Original ioctl version; can only get the original policy version */
int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg)
{
- struct inode *inode = file_inode(filp);
- struct fscrypt_context ctx;
- struct fscrypt_policy policy;
- int res;
+ union fscrypt_policy policy;
+ int err;
- if (!IS_ENCRYPTED(inode))
- return -ENODATA;
+ err = fscrypt_get_policy(file_inode(filp), &policy);
+ if (err)
+ return err;
- res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
- if (res < 0 && res != -ERANGE)
- return res;
- if (res != sizeof(ctx))
- return -EINVAL;
- if (ctx.format != FS_ENCRYPTION_CONTEXT_FORMAT_V1)
+ if (policy.v1.version != FSCRYPT_POLICY_V1)
return -EINVAL;
- policy.version = 0;
- policy.contents_encryption_mode = ctx.contents_encryption_mode;
- policy.filenames_encryption_mode = ctx.filenames_encryption_mode;
- policy.flags = ctx.flags;
- memcpy(policy.master_key_descriptor, ctx.master_key_descriptor,
- FSCRYPT_KEY_DESCRIPTOR_SIZE);
-
- if (copy_to_user(arg, &policy, sizeof(policy)))
+ if (copy_to_user(arg, &policy, sizeof(policy.v1)))
return -EFAULT;
return 0;
}
EXPORT_SYMBOL(fscrypt_ioctl_get_policy);
+/* Extended ioctl version; can get policies of any version */
+int fscrypt_ioctl_get_policy_ex(struct file *filp, void __user *_uarg)
+{
+ struct fscrypt_get_policy_ex_arg __user *uarg = _uarg;
+ struct fscrypt_get_policy_ex_arg arg;
+ union fscrypt_policy *policy = (union fscrypt_policy *)&arg.policy;
+ u64 avail_size;
+ int err;
+
+ BUILD_BUG_ON(sizeof(arg.policy) != sizeof(union fscrypt_policy));
+ BUILD_BUG_ON(sizeof(arg.policy_size) !=
+ offsetof(struct fscrypt_get_policy_ex_arg, policy));
+
+ err = fscrypt_get_policy(file_inode(filp), policy);
+ if (err)
+ return err;
+ arg.policy_size = fscrypt_policy_size(policy);
+
+ if (get_user(avail_size, &uarg->policy_size))
+ return -EFAULT;
+
+ if (avail_size < arg.policy_size)
+ return -EOVERFLOW;
+
+ if (copy_to_user(uarg, &arg, sizeof(arg.policy_size) + arg.policy_size))
+ return -EFAULT;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(fscrypt_ioctl_get_policy_ex);
+
/**
* fscrypt_has_permitted_context() - is a file's encryption policy permitted
* within its directory?
@@ -155,10 +353,8 @@ EXPORT_SYMBOL(fscrypt_ioctl_get_policy);
*/
int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
{
- const struct fscrypt_operations *cops = parent->i_sb->s_cop;
- const struct fscrypt_info *parent_ci, *child_ci;
- struct fscrypt_context parent_ctx, child_ctx;
- int res;
+ union fscrypt_policy parent_policy, child_policy;
+ int err;
/* No restrictions on file types which are never encrypted */
if (!S_ISREG(child->i_mode) && !S_ISDIR(child->i_mode) &&
@@ -188,41 +384,22 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
* In any case, if an unexpected error occurs, fall back to "forbidden".
*/
- res = fscrypt_get_encryption_info(parent);
- if (res)
+ err = fscrypt_get_encryption_info(parent);
+ if (err)
return 0;
- res = fscrypt_get_encryption_info(child);
- if (res)
+ err = fscrypt_get_encryption_info(child);
+ if (err)
return 0;
- parent_ci = parent->i_crypt_info;
- child_ci = child->i_crypt_info;
-
- if (parent_ci && child_ci) {
- return memcmp(parent_ci->ci_master_key_descriptor,
- child_ci->ci_master_key_descriptor,
- FSCRYPT_KEY_DESCRIPTOR_SIZE) == 0 &&
- (parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
- (parent_ci->ci_filename_mode ==
- child_ci->ci_filename_mode) &&
- (parent_ci->ci_flags == child_ci->ci_flags);
- }
- res = cops->get_context(parent, &parent_ctx, sizeof(parent_ctx));
- if (res != sizeof(parent_ctx))
+ err = fscrypt_get_policy(parent, &parent_policy);
+ if (err)
return 0;
- res = cops->get_context(child, &child_ctx, sizeof(child_ctx));
- if (res != sizeof(child_ctx))
+ err = fscrypt_get_policy(child, &child_policy);
+ if (err)
return 0;
- return memcmp(parent_ctx.master_key_descriptor,
- child_ctx.master_key_descriptor,
- FSCRYPT_KEY_DESCRIPTOR_SIZE) == 0 &&
- (parent_ctx.contents_encryption_mode ==
- child_ctx.contents_encryption_mode) &&
- (parent_ctx.filenames_encryption_mode ==
- child_ctx.filenames_encryption_mode) &&
- (parent_ctx.flags == child_ctx.flags);
+ return fscrypt_policies_equal(&parent_policy, &child_policy);
}
EXPORT_SYMBOL(fscrypt_has_permitted_context);
@@ -238,7 +415,8 @@ EXPORT_SYMBOL(fscrypt_has_permitted_context);
int fscrypt_inherit_context(struct inode *parent, struct inode *child,
void *fs_data, bool preload)
{
- struct fscrypt_context ctx;
+ union fscrypt_context ctx;
+ int ctxsize;
struct fscrypt_info *ci;
int res;
@@ -250,16 +428,10 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child,
if (ci == NULL)
return -ENOKEY;
- ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
- ctx.contents_encryption_mode = ci->ci_data_mode;
- ctx.filenames_encryption_mode = ci->ci_filename_mode;
- ctx.flags = ci->ci_flags;
- memcpy(ctx.master_key_descriptor, ci->ci_master_key_descriptor,
- FSCRYPT_KEY_DESCRIPTOR_SIZE);
- get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE);
+ ctxsize = fscrypt_new_context_from_policy(&ctx, &ci->ci_policy);
+
BUILD_BUG_ON(sizeof(ctx) != FSCRYPT_SET_CONTEXT_MAX_SIZE);
- res = parent->i_sb->s_cop->set_context(child, &ctx,
- sizeof(ctx), fs_data);
+ res = parent->i_sb->s_cop->set_context(child, &ctx, ctxsize, fs_data);
if (res)
return res;
return preload ? fscrypt_get_encryption_info(child): 0;
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index dace3fd1bf19..ec84b48fcc11 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -42,7 +42,7 @@ struct fscrypt_name {
#define fname_len(p) ((p)->disk_name.len)
/* Maximum value for the third parameter of fscrypt_operations.set_context(). */
-#define FSCRYPT_SET_CONTEXT_MAX_SIZE 28
+#define FSCRYPT_SET_CONTEXT_MAX_SIZE 40
#ifdef CONFIG_FS_ENCRYPTION
/*
@@ -109,6 +109,7 @@ extern void fscrypt_restore_control_page(struct page *);
/* policy.c */
extern int fscrypt_ioctl_set_policy(struct file *, const void __user *);
extern int fscrypt_ioctl_get_policy(struct file *, void __user *);
+extern int fscrypt_ioctl_get_policy_ex(struct file *, void __user *);
extern int fscrypt_has_permitted_context(struct inode *, struct inode *);
extern int fscrypt_inherit_context(struct inode *, struct inode *,
void *, bool);
@@ -304,6 +305,12 @@ static inline int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg)
return -EOPNOTSUPP;
}
+static inline int fscrypt_ioctl_get_policy_ex(struct file *filp,
+ void __user *arg)
+{
+ return -EOPNOTSUPP;
+}
+
static inline int fscrypt_has_permitted_context(struct inode *parent,
struct inode *child)
{
diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h
index 042e70a4ff7e..26879e669dfa 100644
--- a/include/uapi/linux/fscrypt.h
+++ b/include/uapi/linux/fscrypt.h
@@ -8,7 +8,6 @@
* File system encryption support
*/
/* Policy provided via an ioctl on the topmost directory */
-#define FSCRYPT_KEY_DESCRIPTOR_SIZE 8
/* Encryption policy flags */
#define FSCRYPT_POLICY_FLAGS_PAD_4 0x00
@@ -16,7 +15,7 @@
#define FSCRYPT_POLICY_FLAGS_PAD_16 0x02
#define FSCRYPT_POLICY_FLAGS_PAD_32 0x03
#define FSCRYPT_POLICY_FLAGS_PAD_MASK 0x03
-#define FSCRYPT_POLICY_FLAG_DIRECT_KEY 0x04 /* use master key directly */
+#define FSCRYPT_POLICY_FLAG_DIRECT_KEY 0x04
#define FSCRYPT_POLICY_FLAGS_VALID 0x07
/* Encryption algorithms */
@@ -25,14 +24,24 @@
#define FSCRYPT_MODE_AES_128_CBC 5
#define FSCRYPT_MODE_AES_128_CTS 6
#define FSCRYPT_MODE_ADIANTUM 9
+#define __FSCRYPT_MODE_MAX 9
-struct fscrypt_policy {
+/*
+ * Legacy policy version; ad-hoc KDF and no key verification.
+ * For new encrypted directories, use fscrypt_policy_v2 instead.
+ *
+ * Careful: the .version field for this is actually 0, not 1.
+ */
+#define FSCRYPT_POLICY_V1 0
+#define FSCRYPT_KEY_DESCRIPTOR_SIZE 8
+struct fscrypt_policy_v1 {
__u8 version;
__u8 contents_encryption_mode;
__u8 filenames_encryption_mode;
__u8 flags;
__u8 master_key_descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
};
+#define fscrypt_policy fscrypt_policy_v1
/*
* Process-subscribed "logon" key description prefix and payload format.
@@ -47,13 +56,39 @@ struct fscrypt_key {
__u32 size;
};
+/*
+ * New policy version with HKDF and key verification (recommended).
+ */
+#define FSCRYPT_POLICY_V2 2
+#define FSCRYPT_KEY_IDENTIFIER_SIZE 16
+struct fscrypt_policy_v2 {
+ __u8 version;
+ __u8 contents_encryption_mode;
+ __u8 filenames_encryption_mode;
+ __u8 flags;
+ __u8 __reserved[4];
+ __u8 master_key_identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
+};
+
+/* Struct passed to FS_IOC_GET_ENCRYPTION_POLICY_EX */
+struct fscrypt_get_policy_ex_arg {
+ __u64 policy_size; /* input/output */
+ union {
+ __u8 version;
+ struct fscrypt_policy_v1 v1;
+ struct fscrypt_policy_v2 v2;
+ } policy; /* output */
+};
+
struct fscrypt_key_specifier {
#define FSCRYPT_KEY_SPEC_TYPE_DESCRIPTOR 1
+#define FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER 2
__u32 type;
__u32 __reserved;
union {
__u8 __reserved[32]; /* reserve some extra space */
__u8 descriptor[FSCRYPT_KEY_DESCRIPTOR_SIZE];
+ __u8 identifier[FSCRYPT_KEY_IDENTIFIER_SIZE];
} u;
};
@@ -88,6 +123,7 @@ struct fscrypt_get_key_status_arg {
#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy)
#define FS_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16])
#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy)
+#define FS_IOC_GET_ENCRYPTION_POLICY_EX _IOWR('f', 22, __u8[9]) /* size + version */
#define FS_IOC_ADD_ENCRYPTION_KEY _IOWR('f', 23, struct fscrypt_add_key_arg)
#define FS_IOC_REMOVE_ENCRYPTION_KEY _IOW('f', 24, struct fscrypt_remove_key_arg)
#define FS_IOC_GET_ENCRYPTION_KEY_STATUS _IOWR('f', 25, struct fscrypt_get_key_status_arg)
--
2.20.1
^ permalink raw reply related
* [RFC PATCH v2 13/20] fscrypt: add an HKDF-SHA512 implementation
From: Eric Biggers @ 2019-02-11 17:27 UTC (permalink / raw)
To: linux-fscrypt
Cc: Satya Tangirala, linux-api, linux-f2fs-devel, keyrings, linux-mtd,
linux-crypto, linux-fsdevel, linux-ext4, Paul Crowley
In-Reply-To: <20190211172738.4633-1-ebiggers@kernel.org>
From: Eric Biggers <ebiggers@google.com>
Add an implementation of HKDF (RFC 5869) to fscrypt, for the purpose of
deriving additional key material from the fscrypt master keys for v2
encryption policies. HKDF is a key derivation function built on top of
HMAC. We choose SHA-512 for the underlying unkeyed hash, and use an
"hmac(sha512)" transform allocated from the crypto API.
We'll be using this to replace the AES-ECB based KDF currently used to
derive the per-file encryption keys. While the AES-ECB based KDF is
believed to meet the original security requirements, it is nonstandard
and has problems that don't exist in modern KDFs such as HKDF:
1. It's reversible. Given a derived key and nonce, an attacker can
easily compute the master key. This is okay if the master key and
derived keys are equally hard to compromise, but now we'd like to be
more robust against threats such as a derived key being compromised
through a timing attack, or a derived key for an in-use file being
compromised after the master key has already been removed.
2. It doesn't evenly distribute the entropy from the master key; each 16
input bytes only affects the corresponding 16 output bytes.
3. It isn't easily extensible to deriving other values or keys that are
or will be needed, such as per-mode keys (which is what DIRECT_KEY
policies really should use, rather than the master key directly as
they do now) or a public hash for securely identifying the key (to
ensure that an encrypted file cannot be set up with the wrong key).
HKDF solves all the above problems.
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
fs/crypto/Kconfig | 2 +
fs/crypto/Makefile | 1 +
fs/crypto/fscrypt_private.h | 15 +++
fs/crypto/hkdf.c | 188 ++++++++++++++++++++++++++++++++++++
4 files changed, 206 insertions(+)
create mode 100644 fs/crypto/hkdf.c
diff --git a/fs/crypto/Kconfig b/fs/crypto/Kconfig
index f0de238000c0..c160598a9fe2 100644
--- a/fs/crypto/Kconfig
+++ b/fs/crypto/Kconfig
@@ -7,6 +7,8 @@ config FS_ENCRYPTION
select CRYPTO_XTS
select CRYPTO_CTS
select CRYPTO_SHA256
+ select CRYPTO_SHA512
+ select CRYPTO_HMAC
select KEYS
help
Enable encryption of files and directories. This
diff --git a/fs/crypto/Makefile b/fs/crypto/Makefile
index accdd622c908..4977b4347928 100644
--- a/fs/crypto/Makefile
+++ b/fs/crypto/Makefile
@@ -2,6 +2,7 @@ obj-$(CONFIG_FS_ENCRYPTION) += fscrypto.o
fscrypto-y := crypto.o \
fname.o \
+ hkdf.o \
hooks.o \
keyring.o \
keysetup.o \
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index b09fc2939a89..f8b8358e9527 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -175,6 +175,21 @@ extern bool fscrypt_fname_encrypted_size(const struct inode *inode,
u32 orig_len, u32 max_len,
u32 *encrypted_len_ret);
+/* hkdf.c */
+
+struct fscrypt_hkdf {
+ struct crypto_shash *hmac_tfm;
+};
+
+extern int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key,
+ unsigned int master_key_size);
+
+extern int fscrypt_hkdf_expand(struct fscrypt_hkdf *hkdf, u8 context,
+ const u8 *info, unsigned int infolen,
+ u8 *okm, unsigned int okmlen);
+
+extern void fscrypt_destroy_hkdf(struct fscrypt_hkdf *hkdf);
+
/* keyring.c */
/*
diff --git a/fs/crypto/hkdf.c b/fs/crypto/hkdf.c
new file mode 100644
index 000000000000..9c6346e3f227
--- /dev/null
+++ b/fs/crypto/hkdf.c
@@ -0,0 +1,188 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Implementation of HKDF ("HMAC-based Extract-and-Expand Key Derivation
+ * Function"), aka RFC 5869. See also the original paper (Krawczyk 2010):
+ * "Cryptographic Extraction and Key Derivation: The HKDF Scheme".
+ *
+ * This is used to derive keys from the fscrypt master keys.
+ *
+ * Copyright 2019 Google LLC
+ */
+
+#include <crypto/hash.h>
+#include <crypto/sha.h>
+
+#include "fscrypt_private.h"
+
+/*
+ * HKDF supports any unkeyed cryptographic hash algorithm, but fscrypt uses
+ * SHA-512 because it is reasonably secure and efficient; and since it produces
+ * a 64-byte digest, deriving an AES-256-XTS key preserves all 64 bytes of
+ * entropy from the master key and requires only one iteration of HKDF-Expand.
+ */
+#define HKDF_HMAC_ALG "hmac(sha512)"
+#define HKDF_HASHLEN SHA512_DIGEST_SIZE
+
+/*
+ * HKDF consists of two steps:
+ *
+ * 1. HKDF-Extract: extract a pseudorandom key of length HKDF_HASHLEN bytes from
+ * the input keying material and optional salt.
+ * 2. HKDF-Expand: expand the pseudorandom key into output keying material of
+ * any length, parameterized by an application-specific info string.
+ *
+ * HKDF-Extract can be skipped if the input is already a pseudorandom key of
+ * length HKDF_HASHLEN bytes. However, cipher modes other than AES-256-XTS take
+ * shorter keys, and we don't want to force users of those modes to generate
+ * unnecessarily long keys. Thus fscrypt still does HKDF-Extract.
+ *
+ * HKDF-Extract also supports a salt. Choosing a random salt per input key
+ * would permit the input key to come from *any* source with sufficient entropy,
+ * even if it's not distributed uniformly. However, fscrypt doesn't take
+ * advantage of this because userspace should already provide good pseudorandom
+ * keys, which makes this unnecessary; also, having to persist a random salt per
+ * key from kernel mode would pose significant implementation complexity. Thus
+ * fscrypt uses a fixed salt. But to be slightly more robust against userspace
+ * (unwisely) reusing the fscrypt keys for another purpose, and to force
+ * brute-force attacks to target the fscrypt KDF specifically, fscrypt uses
+ * "fscrypt_hkdf_salt" rather than the default of all 0's defined by RFC 5869.
+ */
+
+#define HKDF_SALT "fscrypt_hkdf_salt"
+#define HKDF_SALT_LEN CONST_STRLEN(HKDF_SALT)
+
+/* HKDF-Extract (RFC 5869 section 2.2), see explanation above */
+static int hkdf_extract(struct crypto_shash *hmac_tfm, const u8 *ikm,
+ unsigned int ikmlen, u8 prk[HKDF_HASHLEN])
+{
+ SHASH_DESC_ON_STACK(desc, hmac_tfm);
+ int err;
+
+ desc->tfm = hmac_tfm;
+ desc->flags = 0;
+
+ err = crypto_shash_setkey(hmac_tfm, HKDF_SALT, HKDF_SALT_LEN);
+ if (err)
+ goto out;
+
+ err = crypto_shash_digest(desc, ikm, ikmlen, prk);
+out:
+ shash_desc_zero(desc);
+ return err;
+}
+
+/*
+ * Compute HKDF-Extract using the given master key as the input keying material,
+ * and prepare an HMAC transform object keyed by the resulting pseudorandom key.
+ *
+ * Afterwards, the keyed HMAC transform object can be used for HKDF-Expand many
+ * times without having to recompute HKDF-Extract each time.
+ */
+int fscrypt_init_hkdf(struct fscrypt_hkdf *hkdf, const u8 *master_key,
+ unsigned int master_key_size)
+{
+ struct crypto_shash *hmac_tfm;
+ u8 prk[HKDF_HASHLEN];
+ int err;
+
+ hmac_tfm = crypto_alloc_shash(HKDF_HMAC_ALG, 0, 0);
+ if (IS_ERR(hmac_tfm)) {
+ fscrypt_warn(NULL, "error allocating " HKDF_HMAC_ALG ": %ld",
+ PTR_ERR(hmac_tfm));
+ return PTR_ERR(hmac_tfm);
+ }
+
+ BUG_ON(crypto_shash_digestsize(hmac_tfm) != sizeof(prk));
+
+ err = hkdf_extract(hmac_tfm, master_key, master_key_size, prk);
+ if (err)
+ goto err_free_tfm;
+
+ err = crypto_shash_setkey(hmac_tfm, prk, sizeof(prk));
+ if (err)
+ goto err_free_tfm;
+
+ hkdf->hmac_tfm = hmac_tfm;
+ goto out;
+
+err_free_tfm:
+ crypto_free_shash(hmac_tfm);
+out:
+ memzero_explicit(prk, sizeof(prk));
+ return err;
+}
+
+/*
+ * HKDF-Expand (RFC 5869 section 2.3). This expands the pseudorandom key, which
+ * was already keyed into 'hkdf->hmac_tfm' by fscrypt_init_hkdf(), into 'okmlen'
+ * bytes of output keying material parameterized by the application-specific
+ * 'info' of length 'infolen' bytes, prefixed with the 'context' byte. This is
+ * thread-safe and may be called by multiple threads in parallel.
+ *
+ * ('context' isn't part of the HKDF specification; it's just a prefix fscrypt
+ * adds to its application-specific info strings to guarantee that it doesn't
+ * accidentally repeat an info string when using HKDF for different purposes.)
+ */
+int fscrypt_hkdf_expand(struct fscrypt_hkdf *hkdf, u8 context,
+ const u8 *info, unsigned int infolen,
+ u8 *okm, unsigned int okmlen)
+{
+ SHASH_DESC_ON_STACK(desc, hkdf->hmac_tfm);
+ int err;
+ const u8 *prev = NULL;
+ unsigned int i;
+ u8 counter = 1;
+ u8 tmp[HKDF_HASHLEN];
+
+ desc->tfm = hkdf->hmac_tfm;
+ desc->flags = 0;
+
+ if (WARN_ON(okmlen > 255 * HKDF_HASHLEN))
+ return -EINVAL;
+
+ for (i = 0; i < okmlen; i += HKDF_HASHLEN) {
+
+ err = crypto_shash_init(desc);
+ if (err)
+ goto out;
+
+ if (prev) {
+ err = crypto_shash_update(desc, prev, HKDF_HASHLEN);
+ if (err)
+ goto out;
+ }
+
+ err = crypto_shash_update(desc, &context, 1);
+ if (err)
+ goto out;
+
+ err = crypto_shash_update(desc, info, infolen);
+ if (err)
+ goto out;
+
+ if (okmlen - i < HKDF_HASHLEN) {
+ err = crypto_shash_finup(desc, &counter, 1, tmp);
+ if (err)
+ goto out;
+ memcpy(&okm[i], tmp, okmlen - i);
+ memzero_explicit(tmp, sizeof(tmp));
+ } else {
+ err = crypto_shash_finup(desc, &counter, 1, &okm[i]);
+ if (err)
+ goto out;
+ }
+ counter++;
+ prev = &okm[i];
+ }
+ err = 0;
+out:
+ if (unlikely(err))
+ memzero_explicit(okm, okmlen); /* so caller doesn't need to */
+ shash_desc_zero(desc);
+ return err;
+}
+
+void fscrypt_destroy_hkdf(struct fscrypt_hkdf *hkdf)
+{
+ crypto_free_shash(hkdf->hmac_tfm);
+}
--
2.20.1
^ permalink raw reply related
* [RFC PATCH v2 12/20] fscrypt: add FS_IOC_GET_ENCRYPTION_KEY_STATUS ioctl
From: Eric Biggers @ 2019-02-11 17:27 UTC (permalink / raw)
To: linux-fscrypt
Cc: Satya Tangirala, linux-api, linux-f2fs-devel, keyrings, linux-mtd,
linux-crypto, linux-fsdevel, linux-ext4, Paul Crowley
In-Reply-To: <20190211172738.4633-1-ebiggers@kernel.org>
From: Eric Biggers <ebiggers@google.com>
Add a new fscrypt ioctl, FS_IOC_GET_ENCRYPTION_KEY_STATUS. Given a key
specified by 'struct fscrypt_key_specifier' (the same way a key is
specified for the other fscrypt key management ioctls), it returns
status information in a 'struct fscrypt_get_key_status_arg'.
The main motivation for this is that applications need to be able to
check whether an encrypted directory is "unlocked" or not, so that they
can add the key if it is not, and avoid adding the key (which may
involve prompting the user for a passphrase) if it already is.
It's possible to use some workarounds such as checking whether opening a
regular file fails with ENOKEY, or checking whether the filenames "look
like gibberish" or not. However, no workaround is usable in all cases.
Like the other key management ioctls, the keyrings syscalls may seem at
first to be a good fit for this. Unfortunately, they are not. Even if
we exposed the keyring ID of the ->s_master_keys keyring and gave
everyone Search permission on it (note: currently the keyrings
permission system would also allow everyone to "invalidate" the keyring
too), the fscrypt keys have an additional state that doesn't map cleanly
to the keyrings API: the secret can be removed, but we can be still
tracking the files that were using the key, and the removal can be
re-attempted or the secret added again.
After later patches, some applications will also need a way to determine
whether a key was added by the current user vs. by some other user.
Reserved fields are included in fscrypt_get_key_status_arg for this and
other future extensions.
Signed-off-by: Eric Biggers <ebiggers@google.com>
---
fs/crypto/keyring.c | 60 ++++++++++++++++++++++++++++++++++++
include/linux/fscrypt.h | 7 +++++
include/uapi/linux/fscrypt.h | 15 +++++++++
3 files changed, 82 insertions(+)
diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c
index 82d272c20969..73be8bda49bd 100644
--- a/fs/crypto/keyring.c
+++ b/fs/crypto/keyring.c
@@ -11,6 +11,7 @@
*
* - FS_IOC_ADD_ENCRYPTION_KEY: add a key
* - FS_IOC_REMOVE_ENCRYPTION_KEY: remove a key
+ * - FS_IOC_GET_ENCRYPTION_KEY_STATUS: get key status
*/
#include <linux/key-type.h>
@@ -515,6 +516,65 @@ int fscrypt_ioctl_remove_key(struct file *filp, const void __user *uarg)
}
EXPORT_SYMBOL_GPL(fscrypt_ioctl_remove_key);
+/*
+ * Retrieve the status of an fscrypt master encryption key.
+ *
+ * We set ->status to indicate whether the key is absent, present, or
+ * incompletely removed. "Incompletely removed" means that the master key
+ * secret has been removed, but some files which had been unlocked with it are
+ * still in use. This field allows applications to easily determine the state
+ * of an encrypted directory without using a hack such as trying to open a
+ * regular file in it (which can confuse the "incompletely removed" state with
+ * absent or present).
+ */
+int fscrypt_ioctl_get_key_status(struct file *filp, void __user *uarg)
+{
+ struct super_block *sb = file_inode(filp)->i_sb;
+ struct fscrypt_get_key_status_arg arg;
+ struct key *key;
+ struct fscrypt_master_key *mk;
+ int err;
+
+ if (copy_from_user(&arg, uarg, sizeof(arg)))
+ return -EFAULT;
+
+ if (memchr_inv(arg.__reserved, 0, sizeof(arg.__reserved)))
+ return -EINVAL;
+
+ if (!valid_key_spec(&arg.key_spec))
+ return -EINVAL;
+
+ memset(arg.__out_reserved, 0, sizeof(arg.__out_reserved));
+
+ key = fscrypt_find_master_key(sb, &arg.key_spec);
+ if (IS_ERR(key)) {
+ if (key != ERR_PTR(-ENOKEY))
+ return PTR_ERR(key);
+ arg.status = FSCRYPT_KEY_STATUS_ABSENT;
+ err = 0;
+ goto out;
+ }
+ mk = key->payload.data[0];
+ down_read(&key->sem);
+
+ if (!is_master_key_secret_present(&mk->mk_secret)) {
+ arg.status = FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED;
+ err = 0;
+ goto out_release_key;
+ }
+
+ arg.status = FSCRYPT_KEY_STATUS_PRESENT;
+ err = 0;
+out_release_key:
+ up_read(&key->sem);
+ key_put(key);
+out:
+ if (!err && copy_to_user(uarg, &arg, sizeof(arg)))
+ err = -EFAULT;
+ return err;
+}
+EXPORT_SYMBOL_GPL(fscrypt_ioctl_get_key_status);
+
int __init fscrypt_init_keyring(void)
{
return register_key_type(&key_type_fscrypt);
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index a8fabae9a5fe..dace3fd1bf19 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -115,6 +115,7 @@ extern int fscrypt_inherit_context(struct inode *, struct inode *,
/* keyring.c */
extern int fscrypt_ioctl_add_key(struct file *filp, void __user *arg);
extern int fscrypt_ioctl_remove_key(struct file *filp, const void __user *arg);
+extern int fscrypt_ioctl_get_key_status(struct file *filp, void __user *arg);
/* keysetup.c */
extern int fscrypt_get_encryption_info(struct inode *);
@@ -339,6 +340,12 @@ static inline void fscrypt_put_encryption_info(struct inode *inode)
return;
}
+static inline int fscrypt_ioctl_get_key_status(struct file *filp,
+ void __user *arg)
+{
+ return -EOPNOTSUPP;
+}
+
/* fname.c */
static inline int fscrypt_setup_filename(struct inode *dir,
const struct qstr *iname,
diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h
index 3302a407131e..042e70a4ff7e 100644
--- a/include/uapi/linux/fscrypt.h
+++ b/include/uapi/linux/fscrypt.h
@@ -71,11 +71,26 @@ struct fscrypt_remove_key_arg {
__u32 __reserved[6];
};
+/* Struct passed to FS_IOC_GET_ENCRYPTION_KEY_STATUS */
+struct fscrypt_get_key_status_arg {
+ /* input */
+ struct fscrypt_key_specifier key_spec;
+ __u32 __reserved[6];
+
+ /* output */
+#define FSCRYPT_KEY_STATUS_ABSENT 1
+#define FSCRYPT_KEY_STATUS_PRESENT 2
+#define FSCRYPT_KEY_STATUS_INCOMPLETELY_REMOVED 3
+ __u32 status;
+ __u32 __out_reserved[15];
+};
+
#define FS_IOC_SET_ENCRYPTION_POLICY _IOR('f', 19, struct fscrypt_policy)
#define FS_IOC_GET_ENCRYPTION_PWSALT _IOW('f', 20, __u8[16])
#define FS_IOC_GET_ENCRYPTION_POLICY _IOW('f', 21, struct fscrypt_policy)
#define FS_IOC_ADD_ENCRYPTION_KEY _IOWR('f', 23, struct fscrypt_add_key_arg)
#define FS_IOC_REMOVE_ENCRYPTION_KEY _IOW('f', 24, struct fscrypt_remove_key_arg)
+#define FS_IOC_GET_ENCRYPTION_KEY_STATUS _IOWR('f', 25, struct fscrypt_get_key_status_arg)
/**********************************************************************/
--
2.20.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox