aboutsummaryrefslogtreecommitdiff
path: root/security/keys/gc.c
diff options
context:
space:
mode:
authorLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
committerLibravatar Linus Torvalds <torvalds@linux-foundation.org>2023-02-21 18:24:12 -0800
commit5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 (patch)
treecc5c2d0a898769fd59549594fedb3ee6f84e59a0 /security/keys/gc.c
downloadlinux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.tar.gz
linux-5b7c4cabbb65f5c469464da6c5f614cbd7f730f2.zip
Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted
Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ...
Diffstat (limited to 'security/keys/gc.c')
-rw-r--r--security/keys/gc.c369
1 files changed, 369 insertions, 0 deletions
diff --git a/security/keys/gc.c b/security/keys/gc.c
new file mode 100644
index 000000000..3c9080747
--- /dev/null
+++ b/security/keys/gc.c
@@ -0,0 +1,369 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Key garbage collector
+ *
+ * Copyright (C) 2009-2011 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/slab.h>
+#include <linux/security.h>
+#include <keys/keyring-type.h>
+#include "internal.h"
+
+/*
+ * Delay between key revocation/expiry in seconds
+ */
+unsigned key_gc_delay = 5 * 60;
+
+/*
+ * Reaper for unused keys.
+ */
+static void key_garbage_collector(struct work_struct *work);
+DECLARE_WORK(key_gc_work, key_garbage_collector);
+
+/*
+ * Reaper for links from keyrings to dead keys.
+ */
+static void key_gc_timer_func(struct timer_list *);
+static DEFINE_TIMER(key_gc_timer, key_gc_timer_func);
+
+static time64_t key_gc_next_run = TIME64_MAX;
+static struct key_type *key_gc_dead_keytype;
+
+static unsigned long key_gc_flags;
+#define KEY_GC_KEY_EXPIRED 0 /* A key expired and needs unlinking */
+#define KEY_GC_REAP_KEYTYPE 1 /* A keytype is being unregistered */
+#define KEY_GC_REAPING_KEYTYPE 2 /* Cleared when keytype reaped */
+
+
+/*
+ * Any key whose type gets unregistered will be re-typed to this if it can't be
+ * immediately unlinked.
+ */
+struct key_type key_type_dead = {
+ .name = ".dead",
+};
+
+/*
+ * Schedule a garbage collection run.
+ * - time precision isn't particularly important
+ */
+void key_schedule_gc(time64_t gc_at)
+{
+ unsigned long expires;
+ time64_t now = ktime_get_real_seconds();
+
+ kenter("%lld", gc_at - now);
+
+ if (gc_at <= now || test_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags)) {
+ kdebug("IMMEDIATE");
+ schedule_work(&key_gc_work);
+ } else if (gc_at < key_gc_next_run) {
+ kdebug("DEFERRED");
+ key_gc_next_run = gc_at;
+ expires = jiffies + (gc_at - now) * HZ;
+ mod_timer(&key_gc_timer, expires);
+ }
+}
+
+/*
+ * Schedule a dead links collection run.
+ */
+void key_schedule_gc_links(void)
+{
+ set_bit(KEY_GC_KEY_EXPIRED, &key_gc_flags);
+ schedule_work(&key_gc_work);
+}
+
+/*
+ * Some key's cleanup time was met after it expired, so we need to get the
+ * reaper to go through a cycle finding expired keys.
+ */
+static void key_gc_timer_func(struct timer_list *unused)
+{
+ kenter("");
+ key_gc_next_run = TIME64_MAX;
+ key_schedule_gc_links();
+}
+
+/*
+ * Reap keys of dead type.
+ *
+ * We use three flags to make sure we see three complete cycles of the garbage
+ * collector: the first to mark keys of that type as being dead, the second to
+ * collect dead links and the third to clean up the dead keys. We have to be
+ * careful as there may already be a cycle in progress.
+ *
+ * The caller must be holding key_types_sem.
+ */
+void key_gc_keytype(struct key_type *ktype)
+{
+ kenter("%s", ktype->name);
+
+ key_gc_dead_keytype = ktype;
+ set_bit(KEY_GC_REAPING_KEYTYPE, &key_gc_flags);
+ smp_mb();
+ set_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags);
+
+ kdebug("schedule");
+ schedule_work(&key_gc_work);
+
+ kdebug("sleep");
+ wait_on_bit(&key_gc_flags, KEY_GC_REAPING_KEYTYPE,
+ TASK_UNINTERRUPTIBLE);
+
+ key_gc_dead_keytype = NULL;
+ kleave("");
+}
+
+/*
+ * Garbage collect a list of unreferenced, detached keys
+ */
+static noinline void key_gc_unused_keys(struct list_head *keys)
+{
+ while (!list_empty(keys)) {
+ struct key *key =
+ list_entry(keys->next, struct key, graveyard_link);
+ short state = key->state;
+
+ list_del(&key->graveyard_link);
+
+ kdebug("- %u", key->serial);
+ key_check(key);
+
+#ifdef CONFIG_KEY_NOTIFICATIONS
+ remove_watch_list(key->watchers, key->serial);
+ key->watchers = NULL;
+#endif
+
+ /* Throw away the key data if the key is instantiated */
+ if (state == KEY_IS_POSITIVE && key->type->destroy)
+ key->type->destroy(key);
+
+ security_key_free(key);
+
+ /* deal with the user's key tracking and quota */
+ if (test_bit(KEY_FLAG_IN_QUOTA, &key->flags)) {
+ spin_lock(&key->user->lock);
+ key->user->qnkeys--;
+ key->user->qnbytes -= key->quotalen;
+ spin_unlock(&key->user->lock);
+ }
+
+ atomic_dec(&key->user->nkeys);
+ if (state != KEY_IS_UNINSTANTIATED)
+ atomic_dec(&key->user->nikeys);
+
+ key_user_put(key->user);
+ key_put_tag(key->domain_tag);
+ kfree(key->description);
+
+ memzero_explicit(key, sizeof(*key));
+ kmem_cache_free(key_jar, key);
+ }
+}
+
+/*
+ * Garbage collector for unused keys.
+ *
+ * This is done in process context so that we don't have to disable interrupts
+ * all over the place. key_put() schedules this rather than trying to do the
+ * cleanup itself, which means key_put() doesn't have to sleep.
+ */
+static void key_garbage_collector(struct work_struct *work)
+{
+ static LIST_HEAD(graveyard);
+ static u8 gc_state; /* Internal persistent state */
+#define KEY_GC_REAP_AGAIN 0x01 /* - Need another cycle */
+#define KEY_GC_REAPING_LINKS 0x02 /* - We need to reap links */
+#define KEY_GC_SET_TIMER 0x04 /* - We need to restart the timer */
+#define KEY_GC_REAPING_DEAD_1 0x10 /* - We need to mark dead keys */
+#define KEY_GC_REAPING_DEAD_2 0x20 /* - We need to reap dead key links */
+#define KEY_GC_REAPING_DEAD_3 0x40 /* - We need to reap dead keys */
+#define KEY_GC_FOUND_DEAD_KEY 0x80 /* - We found at least one dead key */
+
+ struct rb_node *cursor;
+ struct key *key;
+ time64_t new_timer, limit;
+
+ kenter("[%lx,%x]", key_gc_flags, gc_state);
+
+ limit = ktime_get_real_seconds();
+ if (limit > key_gc_delay)
+ limit -= key_gc_delay;
+ else
+ limit = key_gc_delay;
+
+ /* Work out what we're going to be doing in this pass */
+ gc_state &= KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2;
+ gc_state <<= 1;
+ if (test_and_clear_bit(KEY_GC_KEY_EXPIRED, &key_gc_flags))
+ gc_state |= KEY_GC_REAPING_LINKS | KEY_GC_SET_TIMER;
+
+ if (test_and_clear_bit(KEY_GC_REAP_KEYTYPE, &key_gc_flags))
+ gc_state |= KEY_GC_REAPING_DEAD_1;
+ kdebug("new pass %x", gc_state);
+
+ new_timer = TIME64_MAX;
+
+ /* As only this function is permitted to remove things from the key
+ * serial tree, if cursor is non-NULL then it will always point to a
+ * valid node in the tree - even if lock got dropped.
+ */
+ spin_lock(&key_serial_lock);
+ cursor = rb_first(&key_serial_tree);
+
+continue_scanning:
+ while (cursor) {
+ key = rb_entry(cursor, struct key, serial_node);
+ cursor = rb_next(cursor);
+
+ if (refcount_read(&key->usage) == 0)
+ goto found_unreferenced_key;
+
+ if (unlikely(gc_state & KEY_GC_REAPING_DEAD_1)) {
+ if (key->type == key_gc_dead_keytype) {
+ gc_state |= KEY_GC_FOUND_DEAD_KEY;
+ set_bit(KEY_FLAG_DEAD, &key->flags);
+ key->perm = 0;
+ goto skip_dead_key;
+ } else if (key->type == &key_type_keyring &&
+ key->restrict_link) {
+ goto found_restricted_keyring;
+ }
+ }
+
+ if (gc_state & KEY_GC_SET_TIMER) {
+ if (key->expiry > limit && key->expiry < new_timer) {
+ kdebug("will expire %x in %lld",
+ key_serial(key), key->expiry - limit);
+ new_timer = key->expiry;
+ }
+ }
+
+ if (unlikely(gc_state & KEY_GC_REAPING_DEAD_2))
+ if (key->type == key_gc_dead_keytype)
+ gc_state |= KEY_GC_FOUND_DEAD_KEY;
+
+ if ((gc_state & KEY_GC_REAPING_LINKS) ||
+ unlikely(gc_state & KEY_GC_REAPING_DEAD_2)) {
+ if (key->type == &key_type_keyring)
+ goto found_keyring;
+ }
+
+ if (unlikely(gc_state & KEY_GC_REAPING_DEAD_3))
+ if (key->type == key_gc_dead_keytype)
+ goto destroy_dead_key;
+
+ skip_dead_key:
+ if (spin_is_contended(&key_serial_lock) || need_resched())
+ goto contended;
+ }
+
+contended:
+ spin_unlock(&key_serial_lock);
+
+maybe_resched:
+ if (cursor) {
+ cond_resched();
+ spin_lock(&key_serial_lock);
+ goto continue_scanning;
+ }
+
+ /* We've completed the pass. Set the timer if we need to and queue a
+ * new cycle if necessary. We keep executing cycles until we find one
+ * where we didn't reap any keys.
+ */
+ kdebug("pass complete");
+
+ if (gc_state & KEY_GC_SET_TIMER && new_timer != (time64_t)TIME64_MAX) {
+ new_timer += key_gc_delay;
+ key_schedule_gc(new_timer);
+ }
+
+ if (unlikely(gc_state & KEY_GC_REAPING_DEAD_2) ||
+ !list_empty(&graveyard)) {
+ /* Make sure that all pending keyring payload destructions are
+ * fulfilled and that people aren't now looking at dead or
+ * dying keys that they don't have a reference upon or a link
+ * to.
+ */
+ kdebug("gc sync");
+ synchronize_rcu();
+ }
+
+ if (!list_empty(&graveyard)) {
+ kdebug("gc keys");
+ key_gc_unused_keys(&graveyard);
+ }
+
+ if (unlikely(gc_state & (KEY_GC_REAPING_DEAD_1 |
+ KEY_GC_REAPING_DEAD_2))) {
+ if (!(gc_state & KEY_GC_FOUND_DEAD_KEY)) {
+ /* No remaining dead keys: short circuit the remaining
+ * keytype reap cycles.
+ */
+ kdebug("dead short");
+ gc_state &= ~(KEY_GC_REAPING_DEAD_1 | KEY_GC_REAPING_DEAD_2);
+ gc_state |= KEY_GC_REAPING_DEAD_3;
+ } else {
+ gc_state |= KEY_GC_REAP_AGAIN;
+ }
+ }
+
+ if (unlikely(gc_state & KEY_GC_REAPING_DEAD_3)) {
+ kdebug("dead wake");
+ smp_mb();
+ clear_bit(KEY_GC_REAPING_KEYTYPE, &key_gc_flags);
+ wake_up_bit(&key_gc_flags, KEY_GC_REAPING_KEYTYPE);
+ }
+
+ if (gc_state & KEY_GC_REAP_AGAIN)
+ schedule_work(&key_gc_work);
+ kleave(" [end %x]", gc_state);
+ return;
+
+ /* We found an unreferenced key - once we've removed it from the tree,
+ * we can safely drop the lock.
+ */
+found_unreferenced_key:
+ kdebug("unrefd key %d", key->serial);
+ rb_erase(&key->serial_node, &key_serial_tree);
+ spin_unlock(&key_serial_lock);
+
+ list_add_tail(&key->graveyard_link, &graveyard);
+ gc_state |= KEY_GC_REAP_AGAIN;
+ goto maybe_resched;
+
+ /* We found a restricted keyring and need to update the restriction if
+ * it is associated with the dead key type.
+ */
+found_restricted_keyring:
+ spin_unlock(&key_serial_lock);
+ keyring_restriction_gc(key, key_gc_dead_keytype);
+ goto maybe_resched;
+
+ /* We found a keyring and we need to check the payload for links to
+ * dead or expired keys. We don't flag another reap immediately as we
+ * have to wait for the old payload to be destroyed by RCU before we
+ * can reap the keys to which it refers.
+ */
+found_keyring:
+ spin_unlock(&key_serial_lock);
+ keyring_gc(key, limit);
+ goto maybe_resched;
+
+ /* We found a dead key that is still referenced. Reset its type and
+ * destroy its payload with its semaphore held.
+ */
+destroy_dead_key:
+ spin_unlock(&key_serial_lock);
+ kdebug("destroy key %d", key->serial);
+ down_write(&key->sem);
+ key->type = &key_type_dead;
+ if (key_gc_dead_keytype->destroy)
+ key_gc_dead_keytype->destroy(key);
+ memset(&key->payload, KEY_DESTROY, sizeof(key->payload));
+ up_write(&key->sem);
+ goto maybe_resched;
+}