Merge tag 'selinux-pr-20211101' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/selinux
Pull selinux updates from Paul Moore:
- Add LSM/SELinux/Smack controls and auditing for io-uring.
As usual, the individual commit descriptions have more detail, but we
were basically missing two things which we're adding here:
+ establishment of a proper audit context so that auditing of
io-uring ops works similarly to how it does for syscalls (with
some io-uring additions because io-uring ops are *not* syscalls)
+ additional LSM hooks to enable access control points for some of
the more unusual io-uring features, e.g. credential overrides.
The additional audit callouts and LSM hooks were done in conjunction
with the io-uring folks, based on conversations and RFC patches
earlier in the year.
- Fixup the binder credential handling so that the proper credentials
are used in the LSM hooks; the commit description and the code
comment which is removed in these patches are helpful to understand
the background and why this is the proper fix.
- Enable SELinux genfscon policy support for securityfs, allowing
improved SELinux filesystem labeling for other subsystems which make
use of securityfs, e.g. IMA.
* tag 'selinux-pr-20211101' of git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/selinux:
security: Return xattr name from security_dentry_init_security()
selinux: fix a sock regression in selinux_ip_postroute_compat()
binder: use cred instead of task for getsecid
binder: use cred instead of task for selinux checks
binder: use euid from cred instead of using task
LSM: Avoid warnings about potentially unused hook variables
selinux: fix all of the W=1 build warnings
selinux: make better use of the nf_hook_state passed to the NF hooks
selinux: fix race condition when computing ocontext SIDs
selinux: remove unneeded ipv6 hook wrappers
selinux: remove the SELinux lockdown implementation
selinux: enable genfscon labeling for securityfs
Smack: Brutalist io_uring support
selinux: add support for the io_uring access controls
lsm,io_uring: add LSM hooks to io_uring
io_uring: convert io_uring to the secure anon inode interface
fs: add anon_inode_getfile_secure() similar to anon_inode_getfd_secure()
audit: add filtering for io_uring records
audit,io_uring,io-wq: add some basic audit support to io_uring
audit: prepare audit_context for use in calling contexts beyond syscalls
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index a280156..e0c3e33 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -148,6 +148,35 @@ struct file *anon_inode_getfile(const char *name,
}
EXPORT_SYMBOL_GPL(anon_inode_getfile);
+/**
+ * anon_inode_getfile_secure - Like anon_inode_getfile(), but creates a new
+ * !S_PRIVATE anon inode rather than reuse the
+ * singleton anon inode and calls the
+ * inode_init_security_anon() LSM hook. This
+ * allows for both the inode to have its own
+ * security context and for the LSM to enforce
+ * policy on the inode's creation.
+ *
+ * @name: [in] name of the "class" of the new file
+ * @fops: [in] file operations for the new file
+ * @priv: [in] private data for the new file (will be file's private_data)
+ * @flags: [in] flags
+ * @context_inode:
+ * [in] the logical relationship with the new inode (optional)
+ *
+ * The LSM may use @context_inode in inode_init_security_anon(), but a
+ * reference to it is not held. Returns the newly created file* or an error
+ * pointer. See the anon_inode_getfile() documentation for more information.
+ */
+struct file *anon_inode_getfile_secure(const char *name,
+ const struct file_operations *fops,
+ void *priv, int flags,
+ const struct inode *context_inode)
+{
+ return __anon_inode_getfile(name, fops, priv, flags,
+ context_inode, true);
+}
+
static int __anon_inode_getfd(const char *name,
const struct file_operations *fops,
void *priv, int flags,
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index 159a1ff..fcf7dfde 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -1311,7 +1311,7 @@ int ceph_security_init_secctx(struct dentry *dentry, umode_t mode,
int err;
err = security_dentry_init_security(dentry, mode, &dentry->d_name,
- &as_ctx->sec_ctx,
+ &name, &as_ctx->sec_ctx,
&as_ctx->sec_ctxlen);
if (err < 0) {
WARN_ON_ONCE(err != -EOPNOTSUPP);
@@ -1335,7 +1335,6 @@ int ceph_security_init_secctx(struct dentry *dentry, umode_t mode,
* It only supports single security module and only selinux has
* dentry_init_security hook.
*/
- name = XATTR_NAME_SELINUX;
name_len = strlen(name);
err = ceph_pagelist_reserve(pagelist,
4 * 2 + name_len + as_ctx->sec_ctxlen);
diff --git a/fs/io-wq.c b/fs/io-wq.c
index 38b33ad..c516912 100644
--- a/fs/io-wq.c
+++ b/fs/io-wq.c
@@ -14,6 +14,7 @@
#include <linux/rculist_nulls.h>
#include <linux/cpu.h>
#include <linux/tracehook.h>
+#include <linux/audit.h>
#include <uapi/linux/io_uring.h>
#include "io-wq.h"
@@ -593,6 +594,8 @@ static int io_wqe_worker(void *data)
snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task->pid);
set_task_comm(current, buf);
+ audit_alloc_kernel(current);
+
while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) {
long ret;
@@ -631,6 +634,7 @@ static int io_wqe_worker(void *data)
io_worker_handle_work(worker);
}
+ audit_free(current);
io_worker_exit(worker);
return 0;
}
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 3a4af97..3ecd4b5 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -79,6 +79,8 @@
#include <linux/pagemap.h>
#include <linux/io_uring.h>
#include <linux/tracehook.h>
+#include <linux/audit.h>
+#include <linux/security.h>
#define CREATE_TRACE_POINTS
#include <trace/events/io_uring.h>
@@ -912,6 +914,8 @@ struct io_op_def {
unsigned needs_async_setup : 1;
/* opcode is not supported by this kernel */
unsigned not_supported : 1;
+ /* skip auditing */
+ unsigned audit_skip : 1;
/* size of async data needed, if any */
unsigned short async_size;
};
@@ -925,6 +929,7 @@ static const struct io_op_def io_op_defs[] = {
.buffer_select = 1,
.needs_async_setup = 1,
.plug = 1,
+ .audit_skip = 1,
.async_size = sizeof(struct io_async_rw),
},
[IORING_OP_WRITEV] = {
@@ -934,16 +939,19 @@ static const struct io_op_def io_op_defs[] = {
.pollout = 1,
.needs_async_setup = 1,
.plug = 1,
+ .audit_skip = 1,
.async_size = sizeof(struct io_async_rw),
},
[IORING_OP_FSYNC] = {
.needs_file = 1,
+ .audit_skip = 1,
},
[IORING_OP_READ_FIXED] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollin = 1,
.plug = 1,
+ .audit_skip = 1,
.async_size = sizeof(struct io_async_rw),
},
[IORING_OP_WRITE_FIXED] = {
@@ -952,15 +960,20 @@ static const struct io_op_def io_op_defs[] = {
.unbound_nonreg_file = 1,
.pollout = 1,
.plug = 1,
+ .audit_skip = 1,
.async_size = sizeof(struct io_async_rw),
},
[IORING_OP_POLL_ADD] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
+ .audit_skip = 1,
},
- [IORING_OP_POLL_REMOVE] = {},
+ [IORING_OP_POLL_REMOVE] = {
+ .audit_skip = 1,
+ },
[IORING_OP_SYNC_FILE_RANGE] = {
.needs_file = 1,
+ .audit_skip = 1,
},
[IORING_OP_SENDMSG] = {
.needs_file = 1,
@@ -978,18 +991,23 @@ static const struct io_op_def io_op_defs[] = {
.async_size = sizeof(struct io_async_msghdr),
},
[IORING_OP_TIMEOUT] = {
+ .audit_skip = 1,
.async_size = sizeof(struct io_timeout_data),
},
[IORING_OP_TIMEOUT_REMOVE] = {
/* used by timeout updates' prep() */
+ .audit_skip = 1,
},
[IORING_OP_ACCEPT] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollin = 1,
},
- [IORING_OP_ASYNC_CANCEL] = {},
+ [IORING_OP_ASYNC_CANCEL] = {
+ .audit_skip = 1,
+ },
[IORING_OP_LINK_TIMEOUT] = {
+ .audit_skip = 1,
.async_size = sizeof(struct io_timeout_data),
},
[IORING_OP_CONNECT] = {
@@ -1004,14 +1022,19 @@ static const struct io_op_def io_op_defs[] = {
},
[IORING_OP_OPENAT] = {},
[IORING_OP_CLOSE] = {},
- [IORING_OP_FILES_UPDATE] = {},
- [IORING_OP_STATX] = {},
+ [IORING_OP_FILES_UPDATE] = {
+ .audit_skip = 1,
+ },
+ [IORING_OP_STATX] = {
+ .audit_skip = 1,
+ },
[IORING_OP_READ] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollin = 1,
.buffer_select = 1,
.plug = 1,
+ .audit_skip = 1,
.async_size = sizeof(struct io_async_rw),
},
[IORING_OP_WRITE] = {
@@ -1020,39 +1043,50 @@ static const struct io_op_def io_op_defs[] = {
.unbound_nonreg_file = 1,
.pollout = 1,
.plug = 1,
+ .audit_skip = 1,
.async_size = sizeof(struct io_async_rw),
},
[IORING_OP_FADVISE] = {
.needs_file = 1,
+ .audit_skip = 1,
},
[IORING_OP_MADVISE] = {},
[IORING_OP_SEND] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollout = 1,
+ .audit_skip = 1,
},
[IORING_OP_RECV] = {
.needs_file = 1,
.unbound_nonreg_file = 1,
.pollin = 1,
.buffer_select = 1,
+ .audit_skip = 1,
},
[IORING_OP_OPENAT2] = {
},
[IORING_OP_EPOLL_CTL] = {
.unbound_nonreg_file = 1,
+ .audit_skip = 1,
},
[IORING_OP_SPLICE] = {
.needs_file = 1,
.hash_reg_file = 1,
.unbound_nonreg_file = 1,
+ .audit_skip = 1,
},
- [IORING_OP_PROVIDE_BUFFERS] = {},
- [IORING_OP_REMOVE_BUFFERS] = {},
+ [IORING_OP_PROVIDE_BUFFERS] = {
+ .audit_skip = 1,
+ },
+ [IORING_OP_REMOVE_BUFFERS] = {
+ .audit_skip = 1,
+ },
[IORING_OP_TEE] = {
.needs_file = 1,
.hash_reg_file = 1,
.unbound_nonreg_file = 1,
+ .audit_skip = 1,
},
[IORING_OP_SHUTDOWN] = {
.needs_file = 1,
@@ -6581,6 +6615,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred()))
creds = override_creds(req->creds);
+ if (!io_op_defs[req->opcode].audit_skip)
+ audit_uring_entry(req->opcode);
+
switch (req->opcode) {
case IORING_OP_NOP:
ret = io_nop(req, issue_flags);
@@ -6696,6 +6733,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags)
break;
}
+ if (!io_op_defs[req->opcode].audit_skip)
+ audit_uring_exit(!ret, ret);
+
if (creds)
revert_creds(creds);
if (ret)
@@ -7090,10 +7130,17 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
personality = READ_ONCE(sqe->personality);
if (personality) {
+ int ret;
+
req->creds = xa_load(&ctx->personalities, personality);
if (!req->creds)
return -EINVAL;
get_cred(req->creds);
+ ret = security_uring_override_creds(req->creds);
+ if (ret) {
+ put_cred(req->creds);
+ return ret;
+ }
req->flags |= REQ_F_CREDS;
}
@@ -7400,6 +7447,8 @@ static int io_sq_thread(void *data)
set_cpus_allowed_ptr(current, cpu_online_mask);
current->flags |= PF_NO_SETAFFINITY;
+ audit_alloc_kernel(current);
+
mutex_lock(&sqd->lock);
while (1) {
bool cap_entries, sqt_spin = false;
@@ -7465,6 +7514,8 @@ static int io_sq_thread(void *data)
io_run_task_work();
mutex_unlock(&sqd->lock);
+ audit_free(current);
+
complete(&sqd->exited);
do_exit(0);
}
@@ -8622,6 +8673,10 @@ static __cold int io_sq_offload_create(struct io_ring_ctx *ctx,
struct io_sq_data *sqd;
bool attached;
+ ret = security_uring_sqpoll();
+ if (ret)
+ return ret;
+
sqd = io_get_sq_data(p, &attached);
if (IS_ERR(sqd)) {
ret = PTR_ERR(sqd);
@@ -10276,8 +10331,8 @@ static struct file *io_uring_get_file(struct io_ring_ctx *ctx)
return ERR_PTR(ret);
#endif
- file = anon_inode_getfile("[io_uring]", &io_uring_fops, ctx,
- O_RDWR | O_CLOEXEC);
+ file = anon_inode_getfile_secure("[io_uring]", &io_uring_fops, ctx,
+ O_RDWR | O_CLOEXEC, NULL);
#if defined(CONFIG_UNIX)
if (IS_ERR(file)) {
sock_release(ctx->ring_sock);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index e1214bb..459860a 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -127,7 +127,8 @@ nfs4_label_init_security(struct inode *dir, struct dentry *dentry,
return NULL;
err = security_dentry_init_security(dentry, sattr->ia_mode,
- &dentry->d_name, (void **)&label->label, &label->len);
+ &dentry->d_name, NULL,
+ (void **)&label->label, &label->len);
if (err == 0)
return label;