diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-11-04 17:41:05 (GMT) |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-11-04 17:41:05 (GMT) |
commit | b0f85fa11aefc4f3e03306b4cd47f113bd57dcba (patch) | |
tree | 1333d36d99fde3f97210795941fc246f0ad08a75 /kernel/bpf/inode.c | |
parent | ccc9d4a6d640cbde05d519edeb727881646cf71b (diff) | |
parent | f32bfb9a8ca083f8d148ea90ae5ba66f4831836e (diff) | |
download | linux-b0f85fa11aefc4f3e03306b4cd47f113bd57dcba.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
Changes of note:
1) Allow to schedule ICMP packets in IPVS, from Alex Gartrell.
2) Provide FIB table ID in ipv4 route dumps just as ipv6 does, from
David Ahern.
3) Allow the user to ask for the statistics to be filtered out of
ipv4/ipv6 address netlink dumps. From Sowmini Varadhan.
4) More work to pass the network namespace context around deep into
various packet path APIs, starting with the netfilter hooks. From
Eric W Biederman.
5) Add layer 2 TX/RX checksum offloading to qeth driver, from Thomas
Richter.
6) Use usec resolution for SYN/ACK RTTs in TCP, from Yuchung Cheng.
7) Support Very High Throughput in wireless MESH code, from Bob
Copeland.
8) Allow setting the ageing_time in switchdev/rocker. From Scott
Feldman.
9) Properly autoload L2TP type modules, from Stephen Hemminger.
10) Fix and enable offload features by default in 8139cp driver, from
David Woodhouse.
11) Support both ipv4 and ipv6 sockets in a single vxlan device, from
Jiri Benc.
12) Fix CWND limiting of thin streams in TCP, from Bendik Rønning
Opstad.
13) Fix IPSEC flowcache overflows on large systems, from Steffen
Klassert.
14) Convert bridging to track VLANs using rhashtable entries rather than
a bitmap. From Nikolay Aleksandrov.
15) Make TCP listener handling completely lockless, this is a major
accomplishment. Incoming request sockets now live in the
established hash table just like any other socket too.
From Eric Dumazet.
15) Provide more bridging attributes to netlink, from Nikolay
Aleksandrov.
16) Use hash based algorithm for ipv4 multipath routing, this was very
long overdue. From Peter Nørlund.
17) Several y2038 cures, mostly avoiding timespec. From Arnd Bergmann.
18) Allow non-root execution of EBPF programs, from Alexei Starovoitov.
19) Support SO_INCOMING_CPU as setsockopt, from Eric Dumazet. This
influences the port binding selection logic used by SO_REUSEPORT.
20) Add ipv6 support to VRF, from David Ahern.
21) Add support for Mellanox Spectrum switch ASIC, from Jiri Pirko.
22) Add rtl8xxxu Realtek wireless driver, from Jes Sorensen.
23) Implement RACK loss recovery in TCP, from Yuchung Cheng.
24) Support multipath routes in MPLS, from Roopa Prabhu.
25) Fix POLLOUT notification for listening sockets in AF_UNIX, from Eric
Dumazet.
26) Add new QED Qlogic river, from Yuval Mintz, Manish Chopra, and
Sudarsana Kalluru.
27) Don't fetch timestamps on AF_UNIX sockets, from Hannes Frederic
Sowa.
28) Support ipv6 geneve tunnels, from John W Linville.
29) Add flood control support to switchdev layer, from Ido Schimmel.
30) Fix CHECKSUM_PARTIAL handling of potentially fragmented frames, from
Hannes Frederic Sowa.
31) Support persistent maps and progs in bpf, from Daniel Borkmann.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1790 commits)
sh_eth: use DMA barriers
switchdev: respect SKIP_EOPNOTSUPP flag in case there is no recursion
net: sched: kill dead code in sch_choke.c
irda: Delete an unnecessary check before the function call "irlmp_unregister_service"
net: dsa: mv88e6xxx: include DSA ports in VLANs
net: dsa: mv88e6xxx: disable SA learning for DSA and CPU ports
net/core: fix for_each_netdev_feature
vlan: Invoke driver vlan hooks only if device is present
arcnet/com20020: add LEDS_CLASS dependency
bpf, verifier: annotate verbose printer with __printf
dp83640: Only wait for timestamps for packets with timestamping enabled.
ptp: Change ptp_class to a proper bitmask
dp83640: Prune rx timestamp list before reading from it
dp83640: Delay scheduled work.
dp83640: Include hash in timestamp/packet matching
ipv6: fix tunnel error handling
net/mlx5e: Fix LSO vlan insertion
net/mlx5e: Re-eanble client vlan TX acceleration
net/mlx5e: Return error in case mlx5e_set_features() fails
net/mlx5e: Don't allow more than max supported channels
...
Diffstat (limited to 'kernel/bpf/inode.c')
-rw-r--r-- | kernel/bpf/inode.c | 387 |
1 files changed, 387 insertions, 0 deletions
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c new file mode 100644 index 0000000..be6d726 --- /dev/null +++ b/kernel/bpf/inode.c @@ -0,0 +1,387 @@ +/* + * Minimal file system backend for holding eBPF maps and programs, + * used by bpf(2) object pinning. + * + * Authors: + * + * Daniel Borkmann <daniel@iogearbox.net> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + */ + +#include <linux/module.h> +#include <linux/magic.h> +#include <linux/major.h> +#include <linux/mount.h> +#include <linux/namei.h> +#include <linux/fs.h> +#include <linux/kdev_t.h> +#include <linux/filter.h> +#include <linux/bpf.h> + +enum bpf_type { + BPF_TYPE_UNSPEC = 0, + BPF_TYPE_PROG, + BPF_TYPE_MAP, +}; + +static void *bpf_any_get(void *raw, enum bpf_type type) +{ + switch (type) { + case BPF_TYPE_PROG: + atomic_inc(&((struct bpf_prog *)raw)->aux->refcnt); + break; + case BPF_TYPE_MAP: + atomic_inc(&((struct bpf_map *)raw)->refcnt); + break; + default: + WARN_ON_ONCE(1); + break; + } + + return raw; +} + +static void bpf_any_put(void *raw, enum bpf_type type) +{ + switch (type) { + case BPF_TYPE_PROG: + bpf_prog_put(raw); + break; + case BPF_TYPE_MAP: + bpf_map_put(raw); + break; + default: + WARN_ON_ONCE(1); + break; + } +} + +static void *bpf_fd_probe_obj(u32 ufd, enum bpf_type *type) +{ + void *raw; + + *type = BPF_TYPE_MAP; + raw = bpf_map_get(ufd); + if (IS_ERR(raw)) { + *type = BPF_TYPE_PROG; + raw = bpf_prog_get(ufd); + } + + return raw; +} + +static const struct inode_operations bpf_dir_iops; + +static const struct inode_operations bpf_prog_iops = { }; +static const struct inode_operations bpf_map_iops = { }; + +static struct inode *bpf_get_inode(struct super_block *sb, + const struct inode *dir, + umode_t mode) +{ + struct inode *inode; + + switch (mode & S_IFMT) { + case S_IFDIR: + case S_IFREG: + break; + default: + return ERR_PTR(-EINVAL); + } + + inode = new_inode(sb); + if (!inode) + return ERR_PTR(-ENOSPC); + + inode->i_ino = get_next_ino(); + inode->i_atime = CURRENT_TIME; + inode->i_mtime = inode->i_atime; + inode->i_ctime = inode->i_atime; + + inode_init_owner(inode, dir, mode); + + return inode; +} + +static int bpf_inode_type(const struct inode *inode, enum bpf_type *type) +{ + *type = BPF_TYPE_UNSPEC; + if (inode->i_op == &bpf_prog_iops) + *type = BPF_TYPE_PROG; + else if (inode->i_op == &bpf_map_iops) + *type = BPF_TYPE_MAP; + else + return -EACCES; + + return 0; +} + +static bool bpf_dname_reserved(const struct dentry *dentry) +{ + return strchr(dentry->d_name.name, '.'); +} + +static int bpf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + struct inode *inode; + + if (bpf_dname_reserved(dentry)) + return -EPERM; + + inode = bpf_get_inode(dir->i_sb, dir, mode | S_IFDIR); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + inode->i_op = &bpf_dir_iops; + inode->i_fop = &simple_dir_operations; + + inc_nlink(inode); + inc_nlink(dir); + + d_instantiate(dentry, inode); + dget(dentry); + + return 0; +} + +static int bpf_mkobj_ops(struct inode *dir, struct dentry *dentry, + umode_t mode, const struct inode_operations *iops) +{ + struct inode *inode; + + if (bpf_dname_reserved(dentry)) + return -EPERM; + + inode = bpf_get_inode(dir->i_sb, dir, mode | S_IFREG); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + inode->i_op = iops; + inode->i_private = dentry->d_fsdata; + + d_instantiate(dentry, inode); + dget(dentry); + + return 0; +} + +static int bpf_mkobj(struct inode *dir, struct dentry *dentry, umode_t mode, + dev_t devt) +{ + enum bpf_type type = MINOR(devt); + + if (MAJOR(devt) != UNNAMED_MAJOR || !S_ISREG(mode) || + dentry->d_fsdata == NULL) + return -EPERM; + + switch (type) { + case BPF_TYPE_PROG: + return bpf_mkobj_ops(dir, dentry, mode, &bpf_prog_iops); + case BPF_TYPE_MAP: + return bpf_mkobj_ops(dir, dentry, mode, &bpf_map_iops); + default: + return -EPERM; + } +} + +static const struct inode_operations bpf_dir_iops = { + .lookup = simple_lookup, + .mknod = bpf_mkobj, + .mkdir = bpf_mkdir, + .rmdir = simple_rmdir, + .unlink = simple_unlink, +}; + +static int bpf_obj_do_pin(const struct filename *pathname, void *raw, + enum bpf_type type) +{ + struct dentry *dentry; + struct inode *dir; + struct path path; + umode_t mode; + dev_t devt; + int ret; + + dentry = kern_path_create(AT_FDCWD, pathname->name, &path, 0); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + + mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); + devt = MKDEV(UNNAMED_MAJOR, type); + + ret = security_path_mknod(&path, dentry, mode, devt); + if (ret) + goto out; + + dir = d_inode(path.dentry); + if (dir->i_op != &bpf_dir_iops) { + ret = -EPERM; + goto out; + } + + dentry->d_fsdata = raw; + ret = vfs_mknod(dir, dentry, mode, devt); + dentry->d_fsdata = NULL; +out: + done_path_create(&path, dentry); + return ret; +} + +int bpf_obj_pin_user(u32 ufd, const char __user *pathname) +{ + struct filename *pname; + enum bpf_type type; + void *raw; + int ret; + + pname = getname(pathname); + if (IS_ERR(pname)) + return PTR_ERR(pname); + + raw = bpf_fd_probe_obj(ufd, &type); + if (IS_ERR(raw)) { + ret = PTR_ERR(raw); + goto out; + } + + ret = bpf_obj_do_pin(pname, raw, type); + if (ret != 0) + bpf_any_put(raw, type); +out: + putname(pname); + return ret; +} + +static void *bpf_obj_do_get(const struct filename *pathname, + enum bpf_type *type) +{ + struct inode *inode; + struct path path; + void *raw; + int ret; + + ret = kern_path(pathname->name, LOOKUP_FOLLOW, &path); + if (ret) + return ERR_PTR(ret); + + inode = d_backing_inode(path.dentry); + ret = inode_permission(inode, MAY_WRITE); + if (ret) + goto out; + + ret = bpf_inode_type(inode, type); + if (ret) + goto out; + + raw = bpf_any_get(inode->i_private, *type); + touch_atime(&path); + + path_put(&path); + return raw; +out: + path_put(&path); + return ERR_PTR(ret); +} + +int bpf_obj_get_user(const char __user *pathname) +{ + enum bpf_type type = BPF_TYPE_UNSPEC; + struct filename *pname; + int ret = -ENOENT; + void *raw; + + pname = getname(pathname); + if (IS_ERR(pname)) + return PTR_ERR(pname); + + raw = bpf_obj_do_get(pname, &type); + if (IS_ERR(raw)) { + ret = PTR_ERR(raw); + goto out; + } + + if (type == BPF_TYPE_PROG) + ret = bpf_prog_new_fd(raw); + else if (type == BPF_TYPE_MAP) + ret = bpf_map_new_fd(raw); + else + goto out; + + if (ret < 0) + bpf_any_put(raw, type); +out: + putname(pname); + return ret; +} + +static void bpf_evict_inode(struct inode *inode) +{ + enum bpf_type type; + + truncate_inode_pages_final(&inode->i_data); + clear_inode(inode); + + if (!bpf_inode_type(inode, &type)) + bpf_any_put(inode->i_private, type); +} + +static const struct super_operations bpf_super_ops = { + .statfs = simple_statfs, + .drop_inode = generic_delete_inode, + .evict_inode = bpf_evict_inode, +}; + +static int bpf_fill_super(struct super_block *sb, void *data, int silent) +{ + static struct tree_descr bpf_rfiles[] = { { "" } }; + struct inode *inode; + int ret; + + ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles); + if (ret) + return ret; + + sb->s_op = &bpf_super_ops; + + inode = sb->s_root->d_inode; + inode->i_op = &bpf_dir_iops; + inode->i_mode &= ~S_IALLUGO; + inode->i_mode |= S_ISVTX | S_IRWXUGO; + + return 0; +} + +static struct dentry *bpf_mount(struct file_system_type *type, int flags, + const char *dev_name, void *data) +{ + return mount_ns(type, flags, current->nsproxy->mnt_ns, bpf_fill_super); +} + +static struct file_system_type bpf_fs_type = { + .owner = THIS_MODULE, + .name = "bpf", + .mount = bpf_mount, + .kill_sb = kill_litter_super, + .fs_flags = FS_USERNS_MOUNT, +}; + +MODULE_ALIAS_FS("bpf"); + +static int __init bpf_init(void) +{ + int ret; + + ret = sysfs_create_mount_point(fs_kobj, "bpf"); + if (ret) + return ret; + + ret = register_filesystem(&bpf_fs_type); + if (ret) + sysfs_remove_mount_point(fs_kobj, "bpf"); + + return ret; +} +fs_initcall(bpf_init); |