summaryrefslogtreecommitdiff
path: root/kernel/bpf/inode.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2020-10-15 18:42:13 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2020-10-15 18:42:13 -0700
commit9ff9b0d392ea08090cd1780fb196f36dbb586529 (patch)
tree276a3a5c4525b84dee64eda30b423fc31bf94850 /kernel/bpf/inode.c
parent840e5bb326bbcb16ce82dd2416d2769de4839aea (diff)
parent105faa8742437c28815b2a3eb8314ebc5fd9288c (diff)
Merge tag 'net-next-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from Jakub Kicinski: - Add redirect_neigh() BPF packet redirect helper, allowing to limit stack traversal in common container configs and improving TCP back-pressure. Daniel reports ~10Gbps => ~15Gbps single stream TCP performance gain. - Expand netlink policy support and improve policy export to user space. (Ge)netlink core performs request validation according to declared policies. Expand the expressiveness of those policies (min/max length and bitmasks). Allow dumping policies for particular commands. This is used for feature discovery by user space (instead of kernel version parsing or trial and error). - Support IGMPv3/MLDv2 multicast listener discovery protocols in bridge. - Allow more than 255 IPv4 multicast interfaces. - Add support for Type of Service (ToS) reflection in SYN/SYN-ACK packets of TCPv6. - In Multi-patch TCP (MPTCP) support concurrent transmission of data on multiple subflows in a load balancing scenario. Enhance advertising addresses via the RM_ADDR/ADD_ADDR options. - Support SMC-Dv2 version of SMC, which enables multi-subnet deployments. - Allow more calls to same peer in RxRPC. - Support two new Controller Area Network (CAN) protocols - CAN-FD and ISO 15765-2:2016. - Add xfrm/IPsec compat layer, solving the 32bit user space on 64bit kernel problem. - Add TC actions for implementing MPLS L2 VPNs. - Improve nexthop code - e.g. handle various corner cases when nexthop objects are removed from groups better, skip unnecessary notifications and make it easier to offload nexthops into HW by converting to a blocking notifier. - Support adding and consuming TCP header options by BPF programs, opening the doors for easy experimental and deployment-specific TCP option use. - Reorganize TCP congestion control (CC) initialization to simplify life of TCP CC implemented in BPF. - Add support for shipping BPF programs with the kernel and loading them early on boot via the User Mode Driver mechanism, hence reusing all the user space infra we have. - Support sleepable BPF programs, initially targeting LSM and tracing. - Add bpf_d_path() helper for returning full path for given 'struct path'. - Make bpf_tail_call compatible with bpf-to-bpf calls. - Allow BPF programs to call map_update_elem on sockmaps. - Add BPF Type Format (BTF) support for type and enum discovery, as well as support for using BTF within the kernel itself (current use is for pretty printing structures). - Support listing and getting information about bpf_links via the bpf syscall. - Enhance kernel interfaces around NIC firmware update. Allow specifying overwrite mask to control if settings etc. are reset during update; report expected max time operation may take to users; support firmware activation without machine reboot incl. limits of how much impact reset may have (e.g. dropping link or not). - Extend ethtool configuration interface to report IEEE-standard counters, to limit the need for per-vendor logic in user space. - Adopt or extend devlink use for debug, monitoring, fw update in many drivers (dsa loop, ice, ionic, sja1105, qed, mlxsw, mv88e6xxx, dpaa2-eth). - In mlxsw expose critical and emergency SFP module temperature alarms. Refactor port buffer handling to make the defaults more suitable and support setting these values explicitly via the DCBNL interface. - Add XDP support for Intel's igb driver. - Support offloading TC flower classification and filtering rules to mscc_ocelot switches. - Add PTP support for Marvell Octeontx2 and PP2.2 hardware, as well as fixed interval period pulse generator and one-step timestamping in dpaa-eth. - Add support for various auth offloads in WiFi APs, e.g. SAE (WPA3) offload. - Add Lynx PHY/PCS MDIO module, and convert various drivers which have this HW to use it. Convert mvpp2 to split PCS. - Support Marvell Prestera 98DX3255 24-port switch ASICs, as well as 7-port Mediatek MT7531 IP. - Add initial support for QCA6390 and IPQ6018 in ath11k WiFi driver, and wcn3680 support in wcn36xx. - Improve performance for packets which don't require much offloads on recent Mellanox NICs by 20% by making multiple packets share a descriptor entry. - Move chelsio inline crypto drivers (for TLS and IPsec) from the crypto subtree to drivers/net. Move MDIO drivers out of the phy directory. - Clean up a lot of W=1 warnings, reportedly the actively developed subsections of networking drivers should now build W=1 warning free. - Make sure drivers don't use in_interrupt() to dynamically adapt their code. Convert tasklets to use new tasklet_setup API (sadly this conversion is not yet complete). * tag 'net-next-5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2583 commits) Revert "bpfilter: Fix build error with CONFIG_BPFILTER_UMH" net, sockmap: Don't call bpf_prog_put() on NULL pointer bpf, selftest: Fix flaky tcp_hdr_options test when adding addr to lo bpf, sockmap: Add locking annotations to iterator netfilter: nftables: allow re-computing sctp CRC-32C in 'payload' statements net: fix pos incrementment in ipv6_route_seq_next net/smc: fix invalid return code in smcd_new_buf_create() net/smc: fix valid DMBE buffer sizes net/smc: fix use-after-free of delayed events bpfilter: Fix build error with CONFIG_BPFILTER_UMH cxgb4/ch_ipsec: Replace the module name to ch_ipsec from chcr net: sched: Fix suspicious RCU usage while accessing tcf_tunnel_info bpf: Fix register equivalence tracking. rxrpc: Fix loss of final ack on shutdown rxrpc: Fix bundle counting for exclusive connections netfilter: restore NF_INET_NUMHOOKS ibmveth: Identify ingress large send packets. ibmveth: Switch order of ibmveth_helper calls. cxgb4: handle 4-tuple PEDIT to NAT mode translation selftests: Add VRF route leaking tests ...
Diffstat (limited to 'kernel/bpf/inode.c')
-rw-r--r--kernel/bpf/inode.c116
1 files changed, 113 insertions, 3 deletions
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 18f4969552ac..dd4b7fd60ee7 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -20,6 +20,7 @@
#include <linux/filter.h>
#include <linux/bpf.h>
#include <linux/bpf_trace.h>
+#include "preload/bpf_preload.h"
enum bpf_type {
BPF_TYPE_UNSPEC = 0,
@@ -371,9 +372,10 @@ static struct dentry *
bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags)
{
/* Dots in names (e.g. "/sys/fs/bpf/foo.bar") are reserved for future
- * extensions.
+ * extensions. That allows popoulate_bpffs() create special files.
*/
- if (strchr(dentry->d_name.name, '.'))
+ if ((dir->i_mode & S_IALLUGO) &&
+ strchr(dentry->d_name.name, '.'))
return ERR_PTR(-EPERM);
return simple_lookup(dir, dentry, flags);
@@ -411,6 +413,27 @@ static const struct inode_operations bpf_dir_iops = {
.unlink = simple_unlink,
};
+/* pin iterator link into bpffs */
+static int bpf_iter_link_pin_kernel(struct dentry *parent,
+ const char *name, struct bpf_link *link)
+{
+ umode_t mode = S_IFREG | S_IRUSR;
+ struct dentry *dentry;
+ int ret;
+
+ inode_lock(parent->d_inode);
+ dentry = lookup_one_len(name, parent, strlen(name));
+ if (IS_ERR(dentry)) {
+ inode_unlock(parent->d_inode);
+ return PTR_ERR(dentry);
+ }
+ ret = bpf_mkobj_ops(dentry, mode, link, &bpf_link_iops,
+ &bpf_iter_fops);
+ dput(dentry);
+ inode_unlock(parent->d_inode);
+ return ret;
+}
+
static int bpf_obj_do_pin(const char __user *pathname, void *raw,
enum bpf_type type)
{
@@ -640,6 +663,91 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param)
return 0;
}
+struct bpf_preload_ops *bpf_preload_ops;
+EXPORT_SYMBOL_GPL(bpf_preload_ops);
+
+static bool bpf_preload_mod_get(void)
+{
+ /* If bpf_preload.ko wasn't loaded earlier then load it now.
+ * When bpf_preload is built into vmlinux the module's __init
+ * function will populate it.
+ */
+ if (!bpf_preload_ops) {
+ request_module("bpf_preload");
+ if (!bpf_preload_ops)
+ return false;
+ }
+ /* And grab the reference, so the module doesn't disappear while the
+ * kernel is interacting with the kernel module and its UMD.
+ */
+ if (!try_module_get(bpf_preload_ops->owner)) {
+ pr_err("bpf_preload module get failed.\n");
+ return false;
+ }
+ return true;
+}
+
+static void bpf_preload_mod_put(void)
+{
+ if (bpf_preload_ops)
+ /* now user can "rmmod bpf_preload" if necessary */
+ module_put(bpf_preload_ops->owner);
+}
+
+static DEFINE_MUTEX(bpf_preload_lock);
+
+static int populate_bpffs(struct dentry *parent)
+{
+ struct bpf_preload_info objs[BPF_PRELOAD_LINKS] = {};
+ struct bpf_link *links[BPF_PRELOAD_LINKS] = {};
+ int err = 0, i;
+
+ /* grab the mutex to make sure the kernel interactions with bpf_preload
+ * UMD are serialized
+ */
+ mutex_lock(&bpf_preload_lock);
+
+ /* if bpf_preload.ko wasn't built into vmlinux then load it */
+ if (!bpf_preload_mod_get())
+ goto out;
+
+ if (!bpf_preload_ops->info.tgid) {
+ /* preload() will start UMD that will load BPF iterator programs */
+ err = bpf_preload_ops->preload(objs);
+ if (err)
+ goto out_put;
+ for (i = 0; i < BPF_PRELOAD_LINKS; i++) {
+ links[i] = bpf_link_by_id(objs[i].link_id);
+ if (IS_ERR(links[i])) {
+ err = PTR_ERR(links[i]);
+ goto out_put;
+ }
+ }
+ for (i = 0; i < BPF_PRELOAD_LINKS; i++) {
+ err = bpf_iter_link_pin_kernel(parent,
+ objs[i].link_name, links[i]);
+ if (err)
+ goto out_put;
+ /* do not unlink successfully pinned links even
+ * if later link fails to pin
+ */
+ links[i] = NULL;
+ }
+ /* finish() will tell UMD process to exit */
+ err = bpf_preload_ops->finish();
+ if (err)
+ goto out_put;
+ }
+out_put:
+ bpf_preload_mod_put();
+out:
+ mutex_unlock(&bpf_preload_lock);
+ for (i = 0; i < BPF_PRELOAD_LINKS && err; i++)
+ if (!IS_ERR_OR_NULL(links[i]))
+ bpf_link_put(links[i]);
+ return err;
+}
+
static int bpf_fill_super(struct super_block *sb, struct fs_context *fc)
{
static const struct tree_descr bpf_rfiles[] = { { "" } };
@@ -656,8 +764,8 @@ static int bpf_fill_super(struct super_block *sb, struct fs_context *fc)
inode = sb->s_root->d_inode;
inode->i_op = &bpf_dir_iops;
inode->i_mode &= ~S_IALLUGO;
+ populate_bpffs(sb->s_root);
inode->i_mode |= S_ISVTX | opts->mode;
-
return 0;
}
@@ -707,6 +815,8 @@ static int __init bpf_init(void)
{
int ret;
+ mutex_init(&bpf_preload_lock);
+
ret = sysfs_create_mount_point(fs_kobj, "bpf");
if (ret)
return ret;